Repository 'matchms'
hg clone https://toolshed.g2.bx.psu.edu/repos/recetox/matchms

Changeset 0:30e680e555d4 (2022-03-22)
Next changeset 1:f680068b7863 (2022-07-22)
Commit message:
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit 4d2ac914c951166e386a94d8ebb8cb1becfac122"
added:
macros.xml
matchms_similarity.xml
matchms_similarity_wrapper.py
test-data/filtering/clean_metadata.msp
test-data/filtering/default_filters.msp
test-data/filtering/input.msp
test-data/filtering/mz_range.msp
test-data/filtering/normalise_intensities.msp
test-data/filtering/relative_intensity.msp
test-data/formatter/test2_threshold_formatting.tsv
test-data/formatter/test2_topk_formatting.tsv
test-data/matches_test2_out.tsv
test-data/scores_test2_out.tsv
test-data/similarity/fill.mgf
test-data/similarity/fill.msp
test-data/similarity/fill2.msp
test-data/similarity/matches_test1_out.tsv
test-data/similarity/matches_test3_out.tsv
test-data/similarity/matches_test4_out.tsv
test-data/similarity/matches_test5_out.tsv
test-data/similarity/matches_test6_out.tsv
test-data/similarity/recetox_gc-ei_ms_20201028.msp
test-data/similarity/scores_test1_out.tsv
test-data/similarity/scores_test3_out.tsv
test-data/similarity/scores_test4_out.tsv
test-data/similarity/scores_test5_out.tsv
test-data/similarity/scores_test6_out.tsv
b
diff -r 000000000000 -r 30e680e555d4 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Tue Mar 22 16:07:32 2022 +0000
[
@@ -0,0 +1,70 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.14.0</token>
+
+    <xml name="creator">
+        <creator>
+            <person
+                givenName="Helge"
+                familyName="Hecht"
+                url="https://github.com/hechth"
+                identifier="0000-0001-6744-996X" />
+            <organization
+                url="https://www.recetox.muni.cz/"
+                email="GalaxyToolsDevelopmentandDeployment@space.muni.cz"
+                name="RECETOX MUNI" />
+        </creator>
+    </xml>
+
+    <token name="@HELP_matchms@">
+        <![CDATA[
+            Documentation
+                For documentation on the tool see https://github.com/matchms/matchms/blob/master/README.rst
+                and https://matchms.readthedocs.io/en/latest/.
+
+            Upstream Tools
+                +-----------+---------------+--------+-----------+
+                | Name      | Output File   | Format | Parameter |
+                +===========+===============+========+===========+
+                | RAMClustR | Mass spectra  | msp    | references|
+                +-----------+---------------+--------+-----------+
+                | RAMClustR | Mass spectra  | msp    | queries   |
+                +-----------+---------------+--------+-----------+
+
+            Downstream Tools
+                The outputs are two tsv datasets. One containing the similarity scores and the other number of matched peaks.
+        ]]>
+    </token>
+
+    <token name="@HELP_formatter@">
+        <![CDATA[
+            Usage
+                This tool creates user friendly tables from the data matrices produces by matchms.
+                The tool can be operated on two modes based on (i) thresholds or (ii) top k matches.
+
+            Input Table Format
+                The tool expects two data matrices with the format as depicted below.
+                The tool assumes the reference compound labels as row labels and the query labels as column labels (as naturally outputted by matchms).
+
+                +----------+------+------+-----+
+                |          | C001 | C002 | ... |
+                +==========+======+======+=====+
+                | Perylene | 0.1  | 0.0  | ... |
+                +----------+------+------+-----+
+                | Glycine  | 0.5  | 0.34 | ... |
+                +----------+------+------+-----+
+                |   ...    | ...  | ...  | ... |
+                +----------+------+------+-----+
+
+            Output Table Format
+                +----------+-----------+---------+--------+
+                | query    | reference | matches | scores |
+                +==========+===========+=========+========+
+                | C001     | Glycine   |      6  | 0.5    |
+                +----------+-----------+---------+--------+
+                | C002     | Glycine   |     3   | 0.34   |
+                +----------+-----------+---------+--------+
+                |   ...    | ...       | ...     | ...    |
+                +----------+-----------+---------+--------+
+        ]]>
+    </token>
+</macros>
b
diff -r 000000000000 -r 30e680e555d4 matchms_similarity.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/matchms_similarity.xml Tue Mar 22 16:07:32 2022 +0000
[
@@ -0,0 +1,151 @@
+<tool id="matchms" name="matchMS similarity" version="@TOOL_VERSION@+galaxy1" python_template_version="3.8">
+    <description>calculate the similarity score and matched peaks</description>
+
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+
+    <requirements>
+        <requirement type="package" version="1.1.4">pandas</requirement>
+        <requirement type="package" version="0.55.1">numba</requirement>
+        <requirement type="package" version="@TOOL_VERSION@">matchms</requirement>
+    </requirements>
+
+    <environment_variables>
+        <environment_variable name="MPLCONFIGDIR">/tmp</environment_variable>
+    </environment_variables>
+
+    <command detect_errors="exit_code"><![CDATA[
+        sh ${matchms_python_cli}
+    ]]> </command>
+
+    <configfiles>
+        <configfile name="matchms_python_cli">
+            python3 ${__tool_directory__}/matchms_similarity_wrapper.py \
+            #if $ri_filtering.is_true
+            -r $ri_filtering.tolerance \
+            #end if
+            #if $symmetric.is_symmetric
+            -s \
+            #else
+            --ref "$references" \
+            --ref_format "$references.ext" \
+            #end if
+            "$queries" \
+            "$queries.ext" \
+            "$similarity_metric" \
+            "$algorithm.tolerance" \
+            "$algorithm.mz_power" \
+            "$algorithm.intensity_power" \
+            "$similarity_scores" \
+            "$similarity_matches"
+        </configfile>
+    </configfiles>
+
+    <inputs>
+        <param label="Queries spectra" name="queries" type="data" format="msp,mgf"
+               help="Query mass spectra to match against references."/>
+        <conditional name="symmetric">
+            <param name="is_symmetric" label="Symmetric" type="boolean" truevalue="TRUE" falsevalue="FALSE"
+                   checked="false"/>
+            <when value="FALSE">
+                <param label="Reference spectra" name="references" type="data" format="msp,mgf"
+                       help="Reference mass spectra to match against as library."/>
+            </when>
+        </conditional>
+        <param label="Similarity metric" name="similarity_metric" type="select" display="radio"
+               help="Similarity metric to use for score computation.">
+            <option value="CosineGreedy" selected="true">CosineGreedy</option>
+            <option value="CosineHungarian">CosineHungarian</option>
+            <option value="ModifiedCosine">ModifiedCosine</option>
+        </param>
+
+        <section name="algorithm" title="Algorithm Parameters" expanded="true">
+            <param label="tolerance" name="tolerance" type="float" value="0.1"
+                   help="Peaks will be considered a match when less than tolerance apart. Absolute m/z value, not in ppm."/>
+            <param label="mz_power" name="mz_power" type="float" value="0.0"
+                   help="The power to raise mz to in the cosine function."/>
+            <param label="intensity_power" name="intensity_power" type="float" value="1.0"
+                   help="The power to raise intensity to in the cosine function."/>
+        </section>
+
+        <conditional name="ri_filtering">
+            <param name="is_true" label="Apply RI filtering" type="boolean" truevalue="TRUE" falsevalue="FALSE"
+                   checked="false"/>
+            <when value="TRUE">
+            <param label="tolerance" name="tolerance" type="float" value="60"
+                   help="Peaks will be considered a match when less than tolerance apart."/>
+            </when>
+        </conditional>
+    </inputs>
+
+    <outputs>
+        <data label="$similarity_metric scores of ${on_string}" name="similarity_scores" format="tsv"/>
+        <data label="$similarity_metric matches of ${on_string}" name="similarity_matches" format="tsv"/>
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="references" value="similarity/fill.mgf" ftype="mgf"/>
+            <param name="queries" value="similarity/fill.msp" ftype="msp"/>
+            <param name="similarity_metric" value="CosineGreedy"/>
+            <output name="similarity_scores" file="similarity/scores_test1_out.tsv" ftype="tsv"
+                    checksum="md5$1aff8d0777e2f4e565be2b1b393547ef"/>
+            <output name="similarity_matches" file="similarity/matches_test1_out.tsv" ftype="tsv"
+                    checksum="md5$aab26ef4a0e80a53699832db72c06340"/>
+        </test>
+        <test>
+            <param name="references" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/>
+            <param name="queries" value="similarity/fill.msp" ftype="msp"/>
+            <param name="similarity_metric" value="CosineGreedy"/>
+            <output name="similarity_scores" file="scores_test2_out.tsv" ftype="tsv"
+                    checksum="md5$d2a5a01d9980636ce6a246d68834b84e"/>
+            <output name="similarity_matches" file="matches_test2_out.tsv" ftype="tsv"
+                    checksum="md5$28dc16ce45105234437e53d59e240046"/>
+        </test>
+        <test>
+            <param name="references" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/>
+            <param name="queries" value="similarity/fill.msp" ftype="msp"/>
+            <param name="similarity_metric" value="CosineHungarian"/>
+            <output name="similarity_scores" file="similarity/scores_test3_out.tsv" ftype="tsv"
+                    checksum="md5$1341369778036e0a267ff723f8cfca9c"/>
+            <output name="similarity_matches" file="similarity/matches_test3_out.tsv" ftype="tsv"
+                    checksum="md5$28dc16ce45105234437e53d59e240046"/>
+        </test>
+        <test>
+            <param name="references" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/>
+            <param name="queries" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/>
+            <param name="similarity_metric" value="ModifiedCosine"/>
+            <output name="similarity_scores" file="similarity/scores_test4_out.tsv" ftype="tsv"/>
+            <output name="similarity_matches" file="similarity/matches_test4_out.tsv" ftype="tsv"/>
+        </test>
+        <test>
+            <param name="queries" value="similarity/fill.msp" ftype="msp"/>
+            <param name="similarity_metric" value="CosineHungarian"/>
+            <param name="is_symmetric" value="TRUE"/>
+            <output name="similarity_scores" file="similarity/scores_test5_out.tsv" ftype="tsv"/>
+            <output name="similarity_matches" file="similarity/matches_test5_out.tsv" ftype="tsv"/>
+        </test>
+        <test>
+            <param name="references" value="similarity/recetox_gc-ei_ms_20201028.msp" ftype="msp"/>
+            <param name="queries" value="similarity/fill2.msp" ftype="msp"/>
+            <param name="ri_filtering.is_true" value="TRUE" />
+            <param name="ri_filtering.tolerance" value="60.0" />
+            <param name="similarity_metric" value="CosineGreedy"/>
+            <output name="similarity_scores" file="similarity/scores_test6_out.tsv" ftype="tsv"/>
+            <output name="similarity_matches" file="similarity/matches_test6_out.tsv" ftype="tsv"/>
+        </test>
+    </tests>
+
+    <help>
+        <![CDATA[
+            @HELP_matchms@
+        ]]>
+    </help>
+
+    <citations>
+        <citation type="doi">10.5281/zenodo.4589154</citation>
+        <citation type="doi">10.21105/joss.02411</citation>
+    </citations>
+</tool>
b
diff -r 000000000000 -r 30e680e555d4 matchms_similarity_wrapper.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/matchms_similarity_wrapper.py Tue Mar 22 16:07:32 2022 +0000
[
@@ -0,0 +1,103 @@
+import argparse
+import sys
+
+import numpy as np
+from matchms import calculate_scores
+from matchms.importing import load_from_mgf, load_from_msp
+from matchms.similarity import CosineGreedy, CosineHungarian, MetadataMatch, ModifiedCosine
+from pandas import DataFrame
+
+
+def convert_precursor_mz(spectrum):
+    """
+    Check the presence of precursor m/z since it is needed for ModifiedCosine similarity metric. Convert to float if
+    needed, raise error if missing.
+    """
+
+    if "precursor_mz" in spectrum.metadata:
+        metadata = spectrum.metadata
+        metadata["precursor_mz"] = float(metadata["precursor_mz"])
+        spectrum.metadata = metadata
+        return spectrum
+    else:
+        raise ValueError("Precursor_mz missing. Apply 'add_precursor_mz' filter first.")
+
+
+def main(argv):
+    parser = argparse.ArgumentParser(description="Compute MSP similarity scores")
+    parser.add_argument("-r", dest="ri_tolerance", type=float, help="Use RI filtering with given tolerance.")
+    parser.add_argument("-s", dest="symmetric", action='store_true', help="Computation is symmetric.")
+    parser.add_argument("--ref", dest="references_filename", type=str, help="Path to reference spectra library.")
+    parser.add_argument("--ref_format", dest="references_format", type=str, help="Reference spectra library file format.")
+    parser.add_argument("queries_filename", type=str, help="Path to query spectra.")
+    parser.add_argument("queries_format", type=str, help="Query spectra file format.")
+    parser.add_argument("similarity_metric", type=str, help='Metric to use for matching.')
+    parser.add_argument("tolerance", type=float, help="Tolerance to use for peak matching.")
+    parser.add_argument("mz_power", type=float, help="The power to raise mz to in the cosine function.")
+    parser.add_argument("intensity_power", type=float, help="The power to raise intensity to in the cosine function.")
+    parser.add_argument("output_filename_scores", type=str, help="Path where to store the output .tsv scores.")
+    parser.add_argument("output_filename_matches", type=str, help="Path where to store the output .tsv matches.")
+    args = parser.parse_args()
+
+    if args.queries_format == 'msp':
+        queries_spectra = list(load_from_msp(args.queries_filename))
+    elif args.queries_format == 'mgf':
+        queries_spectra = list(load_from_mgf(args.queries_filename))
+    else:
+        raise ValueError(f'File format {args.queries_format} not supported for query spectra.')
+
+    if args.symmetric:
+        reference_spectra = []
+    else:
+        if args.references_format == 'msp':
+            reference_spectra = list(load_from_msp(args.references_filename))
+        elif args.references_format == 'mgf':
+            reference_spectra = list(load_from_mgf(args.references_filename))
+        else:
+            raise ValueError(f'File format {args.references_format} not supported for reference spectra library.')
+
+    if args.similarity_metric == 'CosineGreedy':
+        similarity_metric = CosineGreedy(args.tolerance, args.mz_power, args.intensity_power)
+    elif args.similarity_metric == 'CosineHungarian':
+        similarity_metric = CosineHungarian(args.tolerance, args.mz_power, args.intensity_power)
+    elif args.similarity_metric == 'ModifiedCosine':
+        similarity_metric = ModifiedCosine(args.tolerance, args.mz_power, args.intensity_power)
+        reference_spectra = list(map(convert_precursor_mz, reference_spectra))
+        queries_spectra = list(map(convert_precursor_mz, queries_spectra))
+    else:
+        return -1
+
+    print("Calculating scores...")
+    scores = calculate_scores(
+        references=queries_spectra if args.symmetric else reference_spectra,
+        queries=queries_spectra,
+        similarity_function=similarity_metric,
+        is_symmetric=args.symmetric
+    )
+
+    if args.ri_tolerance is not None:
+        print("RI filtering with tolerance ", args.ri_tolerance)
+        ri_matches = calculate_scores(reference_spectra, queries_spectra, MetadataMatch("retention_index", "difference", args.ri_tolerance)).scores
+        scores.scores["score"] = np.where(ri_matches, scores.scores["score"], 0.0)
+
+    write_outputs(args, scores)
+    return 0
+
+
+def write_outputs(args, scores):
+    print("Storing outputs...")
+    query_names = [spectra.metadata['compound_name'] for spectra in scores.queries]
+    reference_names = [spectra.metadata['compound_name'] for spectra in scores.references]
+
+    # Write scores to dataframe
+    dataframe_scores = DataFrame(data=[entry["score"] for entry in scores.scores], index=reference_names, columns=query_names)
+    dataframe_scores.to_csv(args.output_filename_scores, sep='\t')
+
+    # Write number of matches to dataframe
+    dataframe_matches = DataFrame(data=[entry["matches"] for entry in scores.scores], index=reference_names, columns=query_names)
+    dataframe_matches.to_csv(args.output_filename_matches, sep='\t')
+
+
+if __name__ == "__main__":
+    main(argv=sys.argv[1:])
+    pass
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/clean_metadata.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/clean_metadata.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,197 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+NUM PEAKS: 57
+138.9121    10186226.0
+148.9337    1008656.0
+175.0641    26780143.0
+186.1095    2675456.0
+196.8658    21390430.0
+198.8647    21688594.0
+200.8848    7742528.0
+206.9034    26130980.0
+216.9205    32607700.0
+234.0134    2550129.0
+254.8252    23747536.0
+256.8215    31377637.0
+258.8237    15532799.0
+266.8652    9805546.0
+268.8537    3090354.0
+306.9914    3169316.0
+312.7841    10051801.0
+316.7777    10734168.0
+322.8157    6317648.0
+324.9549    8619910.0
+334.849     4178412.0
+342.8093    3285552.0
+349.9455    2050695.0
+350.9875    6150799.0
+351.941     1965882.0
+366.8281    3253770.0
+370.7418    9765463.0
+372.7383    19374863.0
+382.8218    12815572.0
+384.8177    8311500.0
+392.7685    10913351.0
+413.2664    3965867.0
+426.7772    5431633.0
+428.7834    8554675.0
+434.7287    9943329.0
+436.8161    3705247.0
+440.7322    10603010.0
+442.7401    8271752.0
+450.7016    8762673.0
+460.7076    4528973.0
+462.7862    2123666.0
+484.7242    4273989.0
+486.7743    4886062.0
+488.6825    12267966.0
+492.744     7662344.0
+494.8953    7188793.0
+498.8794    6811405.0
+500.8484    6520691.0
+502.7832    3567833.0
+510.763     4989757.0
+518.7415    4243468.0
+546.6093    7177067.0
+550.6949    6104789.0
+566.5977    5171811.0
+612.6927    2005587.0
+676.6436    1982714.0
+800.4451    2792137.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+NUM PEAKS: 35
+131.1733    1971789.0
+267.2688    6103973.0
+279.0196    1946255.0
+289.6491    46498377.0
+301.1565    15185412.0
+309.1649    18045974.0
+310.1623    295359836.0
+311.1658    13124727.0
+312.0296    38757284.0
+330.6757    12666597.0
+525.375     1073323842.0
+526.3783    181668883.0
+527.3812    23642795.0
+551.3321    111616808.0
+552.3348    28340614.0
+553.3314    2609936.0
+562.3269    7538206.0
+578.2905    7578406.0
+619.3008    4742103.0
+624.296     11790213.0
+813.5403    25060147.0
+814.5336    5865975.0
+955.1171    2322927.0
+1047.7378   150394804.0
+1048.7399   90978863.0
+1049.7432   29946438.0
+1050.7453   6807767.0
+1069.7158   5074652.0
+1074.1979   3402288.0
+1075.1968   33352763.0
+1076.2004   10417953.0
+1101.6535   2023916.0
+1206.3127   3738816.0
+1216.8041   4439324.0
+1217.807    3565334.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+RETENTION_INDEX: None
+NUM PEAKS: 26
+265.2529    11366224.0
+266.2564    1420444.0
+279.6362    29849749.0
+280.6546    8848921.0
+288.6414    202172046.0
+378.2093    15309961.0
+379.1966    2902366.0
+522.3565    4089569222.0
+523.354     1201714423.0
+549.3267    63300808.0
+576.2749    7386007.0
+577.3074    2354251.0
+617.2778    2323470.0
+625.4543    4040374.0
+796.9808    13576738.0
+797.9841    6368973.0
+809.9883    12596682.0
+810.9916    6601055.0
+1043.7028   144351468.0
+1044.7068   83271854.0
+1045.706    27998321.0
+1046.7131   6505178.0
+1058.1594   20718345.0
+1059.1626   6608764.0
+1071.1639   15461047.0
+1072.1671   5096642.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+RETENTION_INDEX: None
+NUM PEAKS: 24
+124.1405    6517662.0
+170.2437    1237313.0
+275.6336    28001849.0
+296.147     190395687.0
+482.3247    145772322.0
+483.3283    36245876.0
+496.34      12577588056.0
+497.3442    3337125302.0
+498.3462    532285213.0
+499.3493    68176083.0
+770.964     49250157.0
+771.9675    22666873.0
+783.9721    9839299.0
+784.9749    3622908.0
+949.6233    8009033.0
+950.6274    3674694.0
+991.6726    1420557258.0
+992.6749    763118028.0
+993.6787    239161906.0
+994.6801    53549573.0
+1017.6897   168186952.0
+1018.6656   120599518.0
+1019.6555   57647644.0
+1020.6591   12469103.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+RETENTION_INDEX: None
+NUM PEAKS: 20
+218.1386    14009249.0
+337.0623    88672453.0
+338.0654    8770055.0
+353.0361    37061354.0
+359.0443    48435582.0
+360.0459    5025128.0
+375.018     29159485.0
+376.0216    2740193.0
+381.0261    13522755.0
+396.9999    10317665.0
+417.0027    13822994.0
+418.9966    4386311.0
+432.9764    9779399.0
+438.9851    11307111.0
+440.9796    3364168.0
+454.9592    9820452.0
+456.9603    3774845.0
+470.9263    3632486.0
+512.8989    4072570.0
+572.871     3485486.0
+
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/default_filters.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/default_filters.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,199 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+CHARGE: -1
+NUM PEAKS: 57
+138.9121    10186226.0
+148.9337    1008656.0
+175.0641    26780143.0
+186.1095    2675456.0
+196.8658    21390430.0
+198.8647    21688594.0
+200.8848    7742528.0
+206.9034    26130980.0
+216.9205    32607700.0
+234.0134    2550129.0
+254.8252    23747536.0
+256.8215    31377637.0
+258.8237    15532799.0
+266.8652    9805546.0
+268.8537    3090354.0
+306.9914    3169316.0
+312.7841    10051801.0
+316.7777    10734168.0
+322.8157    6317648.0
+324.9549    8619910.0
+334.849     4178412.0
+342.8093    3285552.0
+349.9455    2050695.0
+350.9875    6150799.0
+351.941     1965882.0
+366.8281    3253770.0
+370.7418    9765463.0
+372.7383    19374863.0
+382.8218    12815572.0
+384.8177    8311500.0
+392.7685    10913351.0
+413.2664    3965867.0
+426.7772    5431633.0
+428.7834    8554675.0
+434.7287    9943329.0
+436.8161    3705247.0
+440.7322    10603010.0
+442.7401    8271752.0
+450.7016    8762673.0
+460.7076    4528973.0
+462.7862    2123666.0
+484.7242    4273989.0
+486.7743    4886062.0
+488.6825    12267966.0
+492.744     7662344.0
+494.8953    7188793.0
+498.8794    6811405.0
+500.8484    6520691.0
+502.7832    3567833.0
+510.763     4989757.0
+518.7415    4243468.0
+546.6093    7177067.0
+550.6949    6104789.0
+566.5977    5171811.0
+612.6927    2005587.0
+676.6436    1982714.0
+800.4451    2792137.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+CHARGE: -1
+NUM PEAKS: 35
+131.1733    1971789.0
+267.2688    6103973.0
+279.0196    1946255.0
+289.6491    46498377.0
+301.1565    15185412.0
+309.1649    18045974.0
+310.1623    295359836.0
+311.1658    13124727.0
+312.0296    38757284.0
+330.6757    12666597.0
+525.375     1073323842.0
+526.3783    181668883.0
+527.3812    23642795.0
+551.3321    111616808.0
+552.3348    28340614.0
+553.3314    2609936.0
+562.3269    7538206.0
+578.2905    7578406.0
+619.3008    4742103.0
+624.296     11790213.0
+813.5403    25060147.0
+814.5336    5865975.0
+955.1171    2322927.0
+1047.7378   150394804.0
+1048.7399   90978863.0
+1049.7432   29946438.0
+1050.7453   6807767.0
+1069.7158   5074652.0
+1074.1979   3402288.0
+1075.1968   33352763.0
+1076.2004   10417953.0
+1101.6535   2023916.0
+1206.3127   3738816.0
+1216.8041   4439324.0
+1217.807    3565334.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+CHARGE: -1
+NUM PEAKS: 26
+265.2529    11366224.0
+266.2564    1420444.0
+279.6362    29849749.0
+280.6546    8848921.0
+288.6414    202172046.0
+378.2093    15309961.0
+379.1966    2902366.0
+522.3565    4089569222.0
+523.354     1201714423.0
+549.3267    63300808.0
+576.2749    7386007.0
+577.3074    2354251.0
+617.2778    2323470.0
+625.4543    4040374.0
+796.9808    13576738.0
+797.9841    6368973.0
+809.9883    12596682.0
+810.9916    6601055.0
+1043.7028   144351468.0
+1044.7068   83271854.0
+1045.706    27998321.0
+1046.7131   6505178.0
+1058.1594   20718345.0
+1059.1626   6608764.0
+1071.1639   15461047.0
+1072.1671   5096642.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+CHARGE: -1
+NUM PEAKS: 24
+124.1405    6517662.0
+170.2437    1237313.0
+275.6336    28001849.0
+296.147     190395687.0
+482.3247    145772322.0
+483.3283    36245876.0
+496.34      12577588056.0
+497.3442    3337125302.0
+498.3462    532285213.0
+499.3493    68176083.0
+770.964     49250157.0
+771.9675    22666873.0
+783.9721    9839299.0
+784.9749    3622908.0
+949.6233    8009033.0
+950.6274    3674694.0
+991.6726    1420557258.0
+992.6749    763118028.0
+993.6787    239161906.0
+994.6801    53549573.0
+1017.6897   168186952.0
+1018.6656   120599518.0
+1019.6555   57647644.0
+1020.6591   12469103.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+CHARGE: -1
+NUM PEAKS: 20
+218.1386    14009249.0
+337.0623    88672453.0
+338.0654    8770055.0
+353.0361    37061354.0
+359.0443    48435582.0
+360.0459    5025128.0
+375.018     29159485.0
+376.0216    2740193.0
+381.0261    13522755.0
+396.9999    10317665.0
+417.0027    13822994.0
+418.9966    4386311.0
+432.9764    9779399.0
+438.9851    11307111.0
+440.9796    3364168.0
+454.9592    9820452.0
+456.9603    3774845.0
+470.9263    3632486.0
+512.8989    4072570.0
+572.871     3485486.0
+
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/input.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/input.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,193 @@
+NAME:C001
+IONMODE:Negative
+RETENTIONTIME:38.74
+RETENTIONINDEX: -1
+SPECTRUMTYPE:Centroid
+Num Peaks:57
+216.9205 32607700
+256.8215 31377637
+175.0641 26780143
+206.9034 26130980
+254.8252 23747536
+198.8647 21688594
+196.8658 21390430
+372.7383 19374863
+258.8237 15532799
+382.8218 12815572
+488.6825 12267966
+392.7685 10913351
+316.7777 10734168
+440.7322 10603010
+138.9121 10186226
+312.7841 10051801
+434.7287 9943329
+266.8652 9805546
+370.7418 9765463
+450.7016 8762673
+324.9549 8619910
+428.7834 8554675
+384.8177 8311500
+442.7401 8271752
+200.8848 7742528
+492.744 7662344
+494.8953 7188793
+546.6093 7177067
+498.8794 6811405
+500.8484 6520691
+322.8157 6317648
+350.9875 6150799
+550.6949 6104789
+426.7772 5431633
+566.5977 5171811
+510.763 4989757
+486.7743 4886062
+460.7076 4528973
+484.7242 4273989
+518.7415 4243468
+334.849 4178412
+413.2664 3965867
+436.8161 3705247
+502.7832 3567833
+342.8093 3285552
+366.8281 3253770
+306.9914 3169316
+268.8537 3090354
+800.4451 2792137
+186.1095 2675456
+234.0134 2550129
+462.7862 2123666
+349.9455 2050695
+612.6927 2005587
+676.6436 1982714
+351.941 1965882
+148.9337 1008656
+
+NAME:C002
+IONMODE:Negative
+RETENTIONTIME:520.25
+RETENTIONINDEX: 1234.5
+SPECTRUMTYPE:Centroid
+Num Peaks:35
+525.375 1073323842
+310.1623 295359836
+526.3783 181668883
+1047.7378 150394804
+551.3321 111616808
+1048.7399 90978863
+289.6491 46498377
+312.0296 38757284
+1075.1968 33352763
+1049.7432 29946438
+552.3348 28340614
+813.5403 25060147
+527.3812 23642795
+309.1649 18045974
+301.1565 15185412
+311.1658 13124727
+330.6757 12666597
+624.296 11790213
+1076.2004 10417953
+578.2905 7578406
+562.3269 7538206
+1050.7453 6807767
+267.2688 6103973
+814.5336 5865975
+1069.7158 5074652
+619.3008 4742103
+1216.8041 4439324
+1206.3127 3738816
+1217.807 3565334
+1074.1979 3402288
+553.3314 2609936
+955.1171 2322927
+1101.6535 2023916
+131.1733 1971789
+279.0196 1946255
+
+NAME:C003
+IONMODE:Negative
+RETENTIONTIME:483.67
+SPECTRUMTYPE:Centroid
+Num Peaks:26
+522.3565 4089569222
+523.354 1201714423
+288.6414 202172046
+1043.7028 144351468
+1044.7068 83271854
+549.3267 63300808
+279.6362 29849749
+1045.706 27998321
+1058.1594 20718345
+1071.1639 15461047
+378.2093 15309961
+796.9808 13576738
+809.9883 12596682
+265.2529 11366224
+280.6546 8848921
+576.2749 7386007
+1059.1626 6608764
+810.9916 6601055
+1046.7131 6505178
+797.9841 6368973
+1072.1671 5096642
+625.4543 4040374
+379.1966 2902366
+577.3074 2354251
+617.2778 2323470
+266.2564 1420444
+
+NAME:C004
+IONMODE:Negative
+RETENTIONTIME:473.48
+SPECTRUMTYPE:Centroid
+Num Peaks:24
+496.34 12577588056
+497.3442 3337125302
+991.6726 1420557258
+992.6749 763118028
+498.3462 532285213
+993.6787 239161906
+296.147 190395687
+1017.6897 168186952
+482.3247 145772322
+1018.6656 120599518
+499.3493 68176083
+1019.6555 57647644
+994.6801 53549573
+770.964 49250157
+483.3283 36245876
+275.6336 28001849
+771.9675 22666873
+1020.6591 12469103
+783.9721 9839299
+949.6233 8009033
+124.1405 6517662
+950.6274 3674694
+784.9749 3622908
+170.2437 1237313
+
+NAME:C005
+IONMODE:Negative
+RETENTIONTIME:41.72
+SPECTRUMTYPE:Centroid
+Num Peaks:20
+337.0623 88672453
+359.0443 48435582
+353.0361 37061354
+375.018 29159485
+218.1386 14009249
+417.0027 13822994
+381.0261 13522755
+438.9851 11307111
+396.9999 10317665
+454.9592 9820452
+432.9764 9779399
+338.0654 8770055
+360.0459 5025128
+418.9966 4386311
+512.8989 4072570
+456.9603 3774845
+470.9263 3632486
+572.871 3485486
+440.9796 3364168
+376.0216 2740193
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/mz_range.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/mz_range.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,129 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+NUM PEAKS: 41
+306.9914    3169316.0
+312.7841    10051801.0
+316.7777    10734168.0
+322.8157    6317648.0
+324.9549    8619910.0
+334.849     4178412.0
+342.8093    3285552.0
+349.9455    2050695.0
+350.9875    6150799.0
+351.941     1965882.0
+366.8281    3253770.0
+370.7418    9765463.0
+372.7383    19374863.0
+382.8218    12815572.0
+384.8177    8311500.0
+392.7685    10913351.0
+413.2664    3965867.0
+426.7772    5431633.0
+428.7834    8554675.0
+434.7287    9943329.0
+436.8161    3705247.0
+440.7322    10603010.0
+442.7401    8271752.0
+450.7016    8762673.0
+460.7076    4528973.0
+462.7862    2123666.0
+484.7242    4273989.0
+486.7743    4886062.0
+488.6825    12267966.0
+492.744     7662344.0
+494.8953    7188793.0
+498.8794    6811405.0
+500.8484    6520691.0
+502.7832    3567833.0
+510.763     4989757.0
+518.7415    4243468.0
+546.6093    7177067.0
+550.6949    6104789.0
+566.5977    5171811.0
+612.6927    2005587.0
+676.6436    1982714.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+NUM PEAKS: 16
+301.1565    15185412.0
+309.1649    18045974.0
+310.1623    295359836.0
+311.1658    13124727.0
+312.0296    38757284.0
+330.6757    12666597.0
+525.375     1073323842.0
+526.3783    181668883.0
+527.3812    23642795.0
+551.3321    111616808.0
+552.3348    28340614.0
+553.3314    2609936.0
+562.3269    7538206.0
+578.2905    7578406.0
+619.3008    4742103.0
+624.296     11790213.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+NUM PEAKS: 11
+378.2093    15309961.0
+379.1966    2902366.0
+522.3565    4089569222.0
+523.354     1201714423.0
+549.3267    63300808.0
+576.2749    7386007.0
+577.3074    2354251.0
+617.2778    2323470.0
+625.4543    4040374.0
+796.9808    13576738.0
+797.9841    6368973.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+NUM PEAKS: 10
+482.3247    145772322.0
+483.3283    36245876.0
+496.34      12577588056.0
+497.3442    3337125302.0
+498.3462    532285213.0
+499.3493    68176083.0
+770.964     49250157.0
+771.9675    22666873.0
+783.9721    9839299.0
+784.9749    3622908.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+NUM PEAKS: 19
+337.0623    88672453.0
+338.0654    8770055.0
+353.0361    37061354.0
+359.0443    48435582.0
+360.0459    5025128.0
+375.018     29159485.0
+376.0216    2740193.0
+381.0261    13522755.0
+396.9999    10317665.0
+417.0027    13822994.0
+418.9966    4386311.0
+432.9764    9779399.0
+438.9851    11307111.0
+440.9796    3364168.0
+454.9592    9820452.0
+456.9603    3774845.0
+470.9263    3632486.0
+512.8989    4072570.0
+572.871     3485486.0
+
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/normalise_intensities.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/normalise_intensities.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,194 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+NUM PEAKS: 57
+138.9121    0.31238713555387226
+148.9337    0.03093306182282099
+175.0641    0.8212827951680125
+186.1095    0.08204982258791635
+196.8658    0.6559932163262051
+198.8647    0.6651371915222478
+200.8848    0.23744477531380626
+206.9034    0.8013745219687375
+216.9205    1.0
+234.0134    0.0782063439003671
+254.8252    0.7282800074828951
+256.8215    0.9622769161885076
+258.8237    0.4763537140000675
+266.8652    0.30071259242448867
+268.8537    0.09477374975849262
+306.9914    0.09719532503059093
+312.7841    0.30826464301376666
+316.7777    0.3291912033047409
+322.8157    0.1937471210787636
+324.9549    0.2643519782137348
+334.849     0.12814188059875428
+342.8093    0.10076000453880525
+349.9455    0.06288990023828728
+350.9875    0.18863026217733847
+351.941     0.06028888882073866
+366.8281    0.09978532677864431
+370.7418    0.29948334289140294
+372.7383    0.5941806076478868
+382.8218    0.3930228749651156
+384.8177    0.2548937827568335
+392.7685    0.33468631642219476
+413.2664    0.1216236349083192
+426.7772    0.1665751647616974
+428.7834    0.262351377128715
+434.7287    0.3049380667756389
+436.8161    0.11363104420121628
+440.7322    0.32516890182380237
+442.7401    0.25367480687076976
+450.7016    0.268730177228078
+460.7076    0.13889274619185038
+462.7862    0.06512774590050817
+484.7242    0.13107299809554185
+486.7743    0.14984380989766222
+488.6825    0.376229111528872
+492.744     0.23498572423077985
+494.8953    0.22046305013846423
+498.8794    0.20888946475832396
+500.8484    0.19997396320500985
+502.7832    0.10941688619559184
+510.763     0.15302388699601627
+518.7415    0.13013699218282798
+546.6093    0.2201034418250904
+550.6949    0.18721924576097057
+566.5977    0.15860704680182902
+612.6927    0.061506545999871196
+676.6436    0.06080508591528995
+800.4451    0.08562814917948829
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+NUM PEAKS: 35
+131.1733    0.0018370867419900284
+267.2688    0.005686981655625982
+279.0196    0.0018132970906277511
+289.6491    0.04332185234360982
+301.1565    0.014148024487841387
+309.1649    0.01681316793110052
+310.1623    0.2751824048272655
+311.1658    0.012228114653210135
+312.0296    0.03610959011940033
+330.6757    0.011801281686240601
+525.375     1.0
+526.3783    0.16925822001818533
+527.3812    0.022027643545069038
+551.3321    0.10399173449088443
+552.3348    0.026404532249270578
+553.3314    0.00243163889393971
+562.3269    0.0070232353973927655
+578.2905    0.007060689144739971
+619.3008    0.004418147454139941
+624.296     0.010984767633625341
+813.5403    0.023348169508005768
+814.5336    0.005465242427736922
+955.1171    0.0021642368399005527
+1047.7378   0.1401206216753359
+1048.7399   0.08476366539149328
+1049.7432   0.027900654796038715
+1050.7453   0.006342696149667753
+1069.7158   0.004727978454800783
+1074.1979   0.0031698615710057058
+1075.1968   0.03107427758042852
+1076.2004   0.009706253222314986
+1101.6535   0.0018856526994021623
+1206.3127   0.003483399747305716
+1216.8041   0.004136052723591693
+1217.807    0.0033217691254826334
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+NUM PEAKS: 26
+265.2529    0.0027793206039538215
+266.2564    0.00034733340430054716
+279.6362    0.0072989959038771346
+280.6546    0.002163778266032735
+288.6414    0.049436024927126176
+378.2093    0.0037436610481220017
+379.1966    0.0007096996877780199
+522.3565    1.0
+523.354     0.29384865685493955
+549.3267    0.015478600450010918
+576.2749    0.0018060599048590942
+577.3074    0.0005756721239330571
+617.2778    0.0005681454143142512
+625.4543    0.0009879705613649104
+796.9808    0.0033198455052339984
+797.9841    0.0015573701420036753
+809.9883    0.0030801977705220513
+810.9916    0.0016141198844341264
+1043.7028   0.035297475152995465
+1044.7068   0.020362011126266247
+1045.706    0.0068462763386867055
+1046.7131   0.0015906756058816994
+1058.1594   0.00506614361447774
+1059.1626   0.0016160049240511426
+1071.1639   0.0037806052815603864
+1072.1671   0.0012462539997079428
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+NUM PEAKS: 24
+124.1405    0.0005181964913289414
+170.2437    9.837442556482469e-05
+275.6336    0.002226328996889195
+296.147     0.015137694616192635
+482.3247    0.011589847063758851
+483.3283    0.00288178272643532
+496.34      1.0
+497.3442    0.2653231515567137
+498.3462    0.04232013408533278
+499.3493    0.005420441717160338
+770.964     0.003915707588825487
+771.9675    0.0018021637295703144
+783.9721    0.0007822882222085712
+784.9749    0.0002880447335267696
+949.6233    0.0006367701791743273
+950.6274    0.00029216205711611197
+991.6726    0.11294353509394345
+992.6749    0.06067284320350776
+993.6787    0.01901492598860482
+994.6801    0.004257539105397458
+1017.6897   0.013371955835345416
+1018.6656   0.00958844553208827
+1019.6555   0.004583362385803359
+1020.6591   0.0009913747329363162
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+NUM PEAKS: 20
+218.1386    0.15798873862212878
+337.0623    1.0
+338.0654    0.09890394032518758
+353.0361    0.4179579198062785
+359.0443    0.5462303157441691
+360.0459    0.0566706776455141
+375.018     0.3288449119592981
+376.0216    0.03090241565776916
+381.0261    0.15250232222627247
+396.9999    0.1163570494660839
+417.0027    0.1558882553976487
+418.9966    0.049466444781898614
+432.9764    0.11028677643551825
+438.9851    0.12751548668671656
+440.9796    0.037939268467062706
+454.9592    0.11074974998154162
+456.9603    0.042570661713847026
+470.9263    0.04096521385282981
+512.8989    0.04592824335196862
+572.871     0.03930742730214083
+
b
diff -r 000000000000 -r 30e680e555d4 test-data/filtering/relative_intensity.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/filtering/relative_intensity.msp Tue Mar 22 16:07:32 2022 +0000
b
@@ -0,0 +1,51 @@
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C001
+RETENTION_TIME: 38.74
+RETENTION_INDEX: None
+NUM PEAKS: 16
+138.9121    10186226.0
+175.0641    26780143.0
+196.8658    21390430.0
+198.8647    21688594.0
+206.9034    26130980.0
+254.8252    23747536.0
+258.8237    15532799.0
+266.8652    9805546.0
+312.7841    10051801.0
+316.7777    10734168.0
+372.7383    19374863.0
+382.8218    12815572.0
+392.7685    10913351.0
+434.7287    9943329.0
+440.7322    10603010.0
+488.6825    12267966.0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C002
+RETENTION_TIME: 520.25
+RETENTION_INDEX: 1234.5
+NUM PEAKS: 0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C003
+RETENTION_TIME: 483.67
+NUM PEAKS: 0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C004
+RETENTION_TIME: 473.48
+NUM PEAKS: 0
+
+IONMODE: negative
+SPECTRUMTYPE: Centroid
+COMPOUND_NAME: C005
+RETENTION_TIME: 41.72
+NUM PEAKS: 3
+353.0361    37061354.0
+359.0443    48435582.0
+375.018     29159485.0
+
b
diff -r 000000000000 -r 30e680e555d4 test-data/formatter/test2_threshold_formatting.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/formatter/test2_threshold_formatting.tsv Tue Mar 22 16:07:32 2022 +0000
[
@@ -0,0 +1,19 @@
+query reference matches score
+C007 Benzo[b]naphtho[2,1-d]thiophene 3 0.4302304171927885
+C023 Butylated hydroxytoluene 3 0.4899347755610658
+C016 Drometrizole 3 0.5535081364244014
+C040 Deltamethrin 4 0.5995685829585914
+C040 cis-Cypermethrin_isomer1 3 0.7514936043388737
+C040 cis-Cypermethrin_isomer2 3 0.6205879323732599
+C043 Carbofuran phenol 3 0.5173781620618291
+C023 Alachlor 4 0.4289634841639738
+C012 Chlorpyrifos 3 0.43976068904478827
+C016 Atrazine 5 0.4399647084473271
+C029 Metolachlor 3 0.8624580271763471
+C073 Praziquantel 3 0.6840766738581763
+C034 Carbaryl 3 0.4781026376526427
+C043 Carbofuran 3 0.5212598550187718
+C013 Indoxacarb 5 0.4827488304818007
+C073 Oxadixyl 4 0.7910256109540179
+C073 Amitraz 4 0.5270236660009217
+C008 Spirotetramat 5 0.40641914075077024
b
diff -r 000000000000 -r 30e680e555d4 test-data/formatter/test2_topk_formatting.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/formatter/test2_topk_formatting.tsv Tue Mar 22 16:07:32 2022 +0000
[
b"@@ -0,0 +1,523 @@\n+query\treference\tmatches\tscore\n+C001\tChlorpyrifos\t7\t0.2439698460078672\n+C001\ttrans-Chlordane\t10\t0.1709889053423956\n+C001\tcis-Chlordane\t10\t0.16934374734008048\n+C002\tCarfentrazone-ethyl\t1\t0.023438813553203555\n+C002\t2,2',3,3',4,5',6,6'-Octachlorobiphenyl\t2\t0.012935401162453864\n+C002\tPyridaben\t4\t0.011168624908917228\n+C003\tPerylene_2H12\t2\t0.0005256270959446041\n+C003\tMetalaxyl\t1\t1.7567415612900304e-06\n+C003\tPerylene\t0\t0.0\n+C004\t17-alpha-Ethynylestradiol\t2\t0.002716713573623163\n+C004\tCoronene\t1\t0.0009680981940665212\n+C004\tProgesterone\t2\t0.0007924296222333303\n+C005\tTetraconazole\t3\t0.12154746411094572\n+C005\tSulfentrazone\t1\t0.05393598836706972\n+C005\tIndoxacarb\t1\t0.0441412960627566\n+C006\tTris(4-tert-butylphenyl) phosphate\t2\t0.12426514943875827\n+C006\tPerylene_2H12\t0\t0.0\n+C006\tPerylene\t0\t0.0\n+C007\tBenzo[b]naphtho[2,1-d]thiophene\t3\t0.4302304171927885\n+C007\t2-Chlorobiphenyl\t2\t0.30327152545734354\n+C007\tRetene\t3\t0.16318259462298138\n+C008\tSpirotetramat\t5\t0.40641914075077024\n+C008\tEthofumesate\t4\t0.17576877383827938\n+C008\t2,4-Di-tert-butyl-6-(5-chloro-2H-benzotriazol-2-yl)phenol\t3\t0.1419543758042326\n+C009\tPicoxystrobin\t1\t0.0006870380110630028\n+C009\tTris(isopropylphenyl)phosphate\t1\t0.00023550942343171069\n+C009\tTebufenpyrad\t1\t0.00017257075992195458\n+C010\tcis-Permethrin\t1\t0.008724226797557697\n+C010\ttrans-Permethrin\t1\t0.008418860878033153\n+C010\tcis-Phenothrin\t1\t0.005882714253167312\n+C011\tFuberidazole\t1\t0.2308319926807784\n+C011\tPrometryn\t2\t0.1773186209832549\n+C011\tBenzoximate\t1\t0.07676637011355666\n+C012\tChlorpyrifos\t3\t0.43976068904478827\n+C012\tTerbufos\t1\t0.4006683041096004\n+C012\t2,6-Dichloro-4-nitroaniline\t1\t0.20998341159494333\n+C013\tIndoxacarb\t5\t0.4827488304818007\n+C013\tTemephos\t2\t0.32810153796559577\n+C013\tNuarimol\t2\t0.2936210041931014\n+C014\tChlorferone\t1\t0.5119124308782732\n+C014\tPiperonyl butoxide\t1\t0.4857177881241794\n+C014\t2,6-Dichloro-4-nitroaniline\t2\t0.33898957004708385\n+C015\tMetazachlor\t1\t0.0011434403294572687\n+C015\talpha-Amylcinnamyl alcohol\t1\t0.0005805859933790689\n+C015\tPendimethalin\t1\t0.0005015386924657569\n+C016\tDrometrizole\t3\t0.5535081364244014\n+C016\tAcenaphthylene\t2\t0.540073031173669\n+C016\tAtrazine\t5\t0.4399647084473271\n+C017\t4-tert-Octylphenol\t1\t0.9088788152148044\n+C017\tPropargite_isomer2\t1\t0.8953233485170952\n+C017\tPropargite_isomer1\t1\t0.8942159049307404\n+C018\tTris(4-tert-butylphenyl) phosphate\t1\t0.189695375366971\n+C018\tPerylene_2H12\t0\t0.0\n+C018\tPerylene\t0\t0.0\n+C019\tTriclosan\t1\t0.13434903881343435\n+C019\tTerbufos\t1\t0.08080384965580391\n+C019\tEpoxiconazole\t2\t0.07313225916488224\n+C020\tTris(isopropylphenyl)phosphate\t2\t0.2520159660977677\n+C020\tAmitraz\t2\t0.1245102870796828\n+C020\tMetribuzin\t1\t0.05224979683560159\n+C021\tTebuthiuron\t2\t0.9340205348244696\n+C021\t1,5-Dimethylnaphthalene\t1\t0.6803608761410861\n+C021\t2,6-Dimethylnaphthalene\t1\t0.6264160291669295\n+C022\t2-Bromoallyl(2,4,6-tribromophenyl) ether\t1\t0.11311229152083695\n+C022\t2,3,4,5,6-Pentabromobenzyl alcohol\t2\t0.07003350703850979\n+C022\tAllyl 2,4,6-tribromophenyl ether\t1\t0.06571493640420596\n+C023\tPhenanthrene_2H10\t1\t0.7408591267092633\n+C023\t2-Chlorobiphenyl\t1\t0.6159214014775711\n+C023\tButylated hydroxytoluene\t3\t0.4899347755610658\n+C024\tMepronil\t2\t0.18000248105004787\n+C024\tSpirotetramat\t8\t0.17523909122675907\n+C024\tEstrone\t7\t0.17146514923780354\n+C025\tTris(4-tert-butylphenyl) phosphate\t2\t0.2957673370199089\n+C025\tPerylene_2H12\t0\t0.0\n+C025\tPerylene\t0\t0.0\n+C026\tIsodecyl diphenyl phosphate\t2\t0.4122773057565717\n+C026\tDicofol\t1\t0.32235849897575225\n+C026\tTris(isopropylphenyl)phosphate\t2\t0.18207675907106227\n+C027\tFenobucarb\t1\t0.058048257187677615\n+C027\tIsoprocarb\t1\t0.056638368345330564\n+C027\tDioxacarb\t1\t0.041723437047250914\n+C028\tPhosmet\t1\t0.7848313885767587\n+C028\tAlachlor\t1\t0.5400260886224933\n+C028\tButafenacil\t2\t0.5287006460619553\n+C029\tMetolachlor\t3\t0.8624580271763471\n+C029\tSafrole\t2\t0.591167446764124\n+C029\tAmitraz\t2\t0.4100617029164697\n+C030\tEthofumesate\t2\t0.1283368182166788\n+C030\tIprovalicarb isomer 1\t1\t0.1278518291141877\n+C030\tAcephate\t4\t0.12723099231343524\n+C031\tProgesterone\t1\t1.642699424"..b"\n+C138\tPhenanthrene_2H10\t0\t0.0\n+C139\tPerylene_2H12\t0\t0.0\n+C139\tPerylene\t0\t0.0\n+C139\tPhenanthrene_2H10\t0\t0.0\n+C140\tRotenone\t1\t0.0015990284859575886\n+C140\tPerylene_2H12\t0\t0.0\n+C140\tPerylene\t0\t0.0\n+C141\tTebufenpyrad\t2\t0.2938100129854653\n+C141\tTris(isopropylphenyl)phosphate\t2\t0.020202034111700597\n+C141\tIpconazole\t1\t0.017041584156450424\n+C142\tPerylene_2H12\t0\t0.0\n+C142\tPerylene\t0\t0.0\n+C142\tPhenanthrene_2H10\t0\t0.0\n+C143\tDimethomorph_isomer2\t1\t0.16685279162562694\n+C143\tDimethomorph _isomer1\t1\t0.16482807037456434\n+C143\t2,3,4,5,6-Pentabromotoluene\t1\t0.032682863992618404\n+C144\tEtoxazole\t2\t0.1027909809180103\n+C144\t2,4-Di-tert-butyl-6-(5-chloro-2H-benzotriazol-2-yl)phenol\t2\t0.04732776045289416\n+C144\tAzoxystrobin\t2\t0.035630773587232864\n+C145\tPerylene_2H12\t0\t0.0\n+C145\tPerylene\t0\t0.0\n+C145\tPhenanthrene_2H10\t0\t0.0\n+C146\tPropargite_isomer1\t1\t0.0633083562823998\n+C146\tPropargite_isomer2\t1\t0.05654738208679003\n+C146\t2,2',3,3',4,5',6,6'-Octachlorobiphenyl\t1\t0.035712333462604294\n+C147\t2,2',3,4,4',5',6-Heptabromodiphenyl ether\t1\t0.03047378825096018\n+C147\tChlorferone\t1\t0.01855122445019196\n+C147\tProgesterone\t2\t0.007867919703105094\n+C148\tBuprofezin\t1\t0.01875857752389424\n+C148\tPerylene_2H12\t0\t0.0\n+C148\tPerylene\t0\t0.0\n+C149\tMetalaxyl\t2\t0.29742589743178666\n+C149\t1,4-Naphthoquinone\t1\t0.2740480911849054\n+C149\tPraziquantel\t1\t0.260732240603901\n+C150\ttrans-Prallethrin\t1\t0.00633664692361121\n+C150\tPerylene_2H12\t0\t0.0\n+C150\tPerylene\t0\t0.0\n+C151\tSpirotetramat\t1\t0.011452966094891676\n+C151\tPerylene_2H12\t0\t0.0\n+C151\tPerylene\t0\t0.0\n+C152\tTris(3,5-xylenyl)phosphate\t1\t0.05756111981021594\n+C152\tTris(isopropylphenyl)phosphate\t1\t0.0449470954588726\n+C152\tPerylene_2H12\t0\t0.0\n+C153\tEthiofencarb\t1\t0.8284613374855048\n+C153\t1,1-Dibromo-2,3,3,4,4,5-hexachloro-2-cyclopenta-2,4-dien-1-ylcyclooctane\t1\t0.4257874890609336\n+C153\tIsomethyl-alpha-ionone\t1\t0.36103138237616267\n+C154\t7,12-Dimethylbenz[a]anthracene\t1\t0.29226381053937395\n+C154\tEnzacamene\t1\t0.14396940230197552\n+C154\tTriflumizole\t1\t0.10858411907186044\n+C155\tPerylene_2H12\t0\t0.0\n+C155\tPerylene\t0\t0.0\n+C155\tPhenanthrene_2H10\t0\t0.0\n+C156\t7,12-Dimethylbenz[a]anthracene\t1\t0.08248293081186396\n+C156\tMethoprotryne\t1\t0.0432082364937662\n+C156\tProgesterone\t1\t0.02316539180928352\n+C157\tPerylene_2H12\t0\t0.0\n+C157\tPerylene\t0\t0.0\n+C157\tPhenanthrene_2H10\t0\t0.0\n+C158\tTris(4-tert-butylphenyl) phosphate\t1\t0.012341356867974116\n+C158\tPerylene_2H12\t0\t0.0\n+C158\tPerylene\t0\t0.0\n+C159\tTrifluralin\t1\t0.1883562158254524\n+C159\tFenpropathrin\t1\t0.015975881134824614\n+C159\tEthiprole\t1\t0.007596489095240584\n+C160\tBumetrizole\t1\t0.04337092323628775\n+C160\ttrans-Cypermethrin_isomer2\t1\t0.030241071137562938\n+C160\tPerylene_2H12\t1\t0.029465908012253836\n+C161\tPerylene_2H12\t0\t0.0\n+C161\tPerylene\t0\t0.0\n+C161\tPhenanthrene_2H10\t0\t0.0\n+C162\tPerylene_2H12\t0\t0.0\n+C162\tPerylene\t0\t0.0\n+C162\tPhenanthrene_2H10\t0\t0.0\n+C163\tPerylene_2H12\t0\t0.0\n+C163\tPerylene\t0\t0.0\n+C163\tPhenanthrene_2H10\t0\t0.0\n+C164\t7,12-Dimethylbenz[a]anthracene\t1\t0.2284760273276565\n+C164\tEnzacamene\t1\t0.112547485896346\n+C164\tFenamidone\t1\t0.0486288864876461\n+C165\tBoscalid\t1\t0.08498662209290331\n+C165\tBuprofezin\t1\t0.08205704595848827\n+C165\tIpconazole\t1\t0.08152620214218925\n+C166\tTris(2-butoxyethyl) phosphate\t1\t0.008342150525801997\n+C166\tRotenone\t1\t0.0015006556689027325\n+C166\tPerylene_2H12\t0\t0.0\n+C167\tPerylene_2H12\t0\t0.0\n+C167\tPerylene\t0\t0.0\n+C167\tPhenanthrene_2H10\t0\t0.0\n+C168\tPerylene_2H12\t0\t0.0\n+C168\tPerylene\t0\t0.0\n+C168\tPhenanthrene_2H10\t0\t0.0\n+C169\tPerylene_2H12\t0\t0.0\n+C169\tPerylene\t0\t0.0\n+C169\tPhenanthrene_2H10\t0\t0.0\n+C170\tPerylene_2H12\t0\t0.0\n+C170\tPerylene\t0\t0.0\n+C170\tPhenanthrene_2H10\t0\t0.0\n+C171\t2,4-D butyl ester\t1\t0.6610587362108564\n+C171\tTerbutryn\t1\t0.6012657870951452\n+C171\tEstrone\t2\t0.31623371975319553\n+C172\tPerylene_2H12\t1\t0.06765194944236241\n+C172\t17-alpha-Ethynylestradiol\t1\t0.01884162876915315\n+C172\tProgesterone\t1\t0.01306130902820296\n+C173\tSpiromesifen\t1\t0.016586079079264453\n+C173\tRotenone\t1\t0.0025109428261963678\n+C173\tPerylene_2H12\t0\t0.0\n+C174\tPerylene_2H12\t0\t0.0\n+C174\tPerylene\t0\t0.0\n+C174\tPhenanthrene_2H10\t0\t0.0\n"
b
diff -r 000000000000 -r 30e680e555d4 test-data/matches_test2_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/matches_test2_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,387 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+Perylene_2H12\t0\t0\t2\t0\t1\t0\t0\t1\t0\t0\t0\t0\t2\t0\t0\t3\t0\t0\t0\t1\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\n+Perylene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t0\t1\t1\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Phenanthrene_2H10\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t2\t0\t1\t0\t0\t0\t0\t1\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\n+Phenanthrene\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Anthracene\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t2\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Acenaphthylene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Acenaphthene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t3\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Fluoranthene\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t0\t2\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Pyrene\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0'..b'ph_isomer2\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Spirodiclofen\t3\t2\t0\t0\t0\t0\t4\t1\t0\t0\t1\t1\t4\t0\t0\t4\t3\t0\t1\t2\t4\t0\t2\t0\t0\t1\t0\t0\t2\t1\t0\t0\t3\t1\t0\t0\t1\t1\t1\t1\t0\t0\t2\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t3\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t1\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Spiromesifen\t1\t1\t0\t1\t0\t0\t2\t2\t0\t1\t1\t0\t2\t1\t0\t5\t0\t0\t0\t1\t3\t0\t3\t4\t0\t1\t2\t1\t2\t1\t0\t0\t1\t7\t0\t0\t2\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t3\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t2\t0\t1\t0\t0\t0\t0\t1\t2\t0\t1\t0\t0\t0\t0\t0\t2\t0\t0\t3\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\n+Spirotetramat\t2\t2\t0\t1\t0\t0\t2\t5\t0\t2\t1\t0\t6\t1\t0\t7\t1\t0\t1\t2\t4\t0\t4\t8\t0\t3\t2\t1\t2\t1\t0\t0\t3\t7\t0\t0\t3\t0\t0\t4\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t3\t0\t0\t3\t0\t0\t3\t0\t0\t1\t0\t0\t1\t0\t0\t3\t1\t3\t0\t0\t0\t0\t0\t2\t2\t3\t0\t1\t0\t0\t1\t0\t0\t3\t0\t2\t3\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t2\t1\t0\t1\t1\t0\t0\t1\t2\t0\t1\t0\t2\t0\t0\t1\t1\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t1\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\n+17-alpha-Ethynylestradiol\t1\t0\t0\t2\t0\t0\t2\t2\t0\t1\t1\t0\t4\t1\t1\t5\t1\t0\t0\t1\t2\t0\t3\t4\t0\t2\t2\t1\t2\t1\t0\t0\t3\t7\t0\t0\t1\t1\t0\t4\t0\t0\t2\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t2\t0\t1\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t2\t1\t0\t3\t1\t0\t0\t0\t0\t0\t1\t0\t0\t2\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t2\t1\t0\t0\n+Bisphenol A\t0\t0\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t1\t0\t0\t3\t1\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t3\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+4-tert-Octylphenol\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Estrone\t1\t0\t0\t0\t0\t0\t1\t1\t0\t1\t1\t0\t3\t1\t1\t6\t0\t0\t0\t2\t1\t0\t2\t7\t0\t1\t3\t1\t2\t1\t0\t0\t3\t7\t0\t0\t0\t1\t0\t3\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t3\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t1\t0\t1\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n+17-beta-Estradiol\t2\t0\t0\t0\t0\t0\t4\t2\t0\t1\t1\t0\t2\t0\t1\t4\t0\t0\t0\t0\t1\t0\t4\t4\t0\t0\t0\t1\t1\t0\t1\t0\t1\t6\t0\t0\t1\t1\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t2\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Progesterone\t2\t3\t0\t2\t0\t0\t3\t3\t0\t2\t2\t0\t4\t2\t1\t6\t1\t0\t0\t2\t2\t0\t4\t9\t0\t4\t3\t1\t5\t2\t1\t0\t3\t6\t0\t0\t3\t0\t2\t4\t0\t0\t2\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t1\t1\t1\t1\t1\t2\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t2\t1\t4\t0\t1\t0\t0\t1\t2\t2\t2\t0\t1\t0\t0\t2\t0\t0\t2\t2\t3\t3\t2\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t2\t1\t0\t0\t1\t0\t1\t0\t2\t0\t1\t0\t1\t0\t0\t1\t2\t2\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t2\t0\t0\t0\t2\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t2\t1\t0\t0\n+Testosterone\t1\t1\t0\t1\t1\t0\t0\t2\t0\t1\t1\t0\t4\t1\t1\t5\t0\t0\t0\t1\t2\t0\t3\t7\t0\t2\t2\t1\t4\t1\t0\t0\t3\t3\t0\t0\t1\t0\t1\t2\t0\t0\t3\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t1\t1\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t4\t0\t1\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t2\t0\t0\t2\t2\t3\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t1\t0\t2\t0\t2\t0\t1\t0\t0\t0\t0\t1\t1\t2\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t2\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/scores_test2_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/scores_test2_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,387 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+Perylene_2H12\t0.0\t0.0\t0.0005256270959446041\t0.0\t0.03073097535576865\t0.0\t0.0\t6.24557070442715e-05\t0.0\t0.0\t0.0\t0.0\t0.004564716964324221\t0.0\t0.0\t0.01320306660370882\t0.0\t0.0\t0.0\t0.00039214513461787934\t0.0\t0.0\t0.0007918167287744313\t0.0\t0.0\t0.0004447561432835879\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.01405301901669034\t0.0\t0.0\t0.0\t0.0\t0.0\t0.010864712316628123\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.1457986453664692\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07136533213674005\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008502864326957613\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008332485011325066\t0.06707997408159612\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.014331972335452477\t0.0\t0.00279044697331512\t0.0\t0.0\t0.0\t0.0\t0.08644538826313945\t0.0\t0.0230223502665467\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.051946183665058966\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07451431952403162\t0.0\t0.0\t0.0\t0.0\t0.008606424963572753\t0.0\t0.0\t0.0\t0.0\t0.0\t0.029465908012253836\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.06765194944236241\t0.0\t0.0\n+Perylene\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0032741303817077233\t0.0\t0.01059895859620056\t0.0\t0.0\t0.011988179251417755\t0.00444506750394149\t0.0\t0.0\t0.0\t0.0\t0.0\t0.010205422020394999\t0.0\t0.0\t0.07094451588225481\t0.0\t0.0\t0.0012435925952213776\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0028113782310797255\t0.0\t0.0\t0.0015057844692663738\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.015722861787553524\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.04875136828344371\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.02339585450305575\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07014255094522089\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+Phenanthrene_2H10\t0.0024478437470211957\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.04458305878768819\t0.0\t0.0\t0.010556784103056164\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.053243824199748255\t0.0\t0.7408591267092633\t0.0\t0.0\t0.0\t0.0\t0.12202560685242984\t0.04568269717012136\t0.004157278401108382\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.028649962860904238\t0.0\t0.0391645806143903\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008485163950429123\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.004892255878207329\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.027071584755955534\t0.0\t0.0\t0.0\n+Phenanthrene\t0.00561720665430217\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0014924956391185538\t0.12453944133920958\t0.0\t0.08707842241811789'..b'99\t0.0\t0.0\t0.0\t0.05477359359289294\t0.014982137997848576\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.011712224528606202\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+Progesterone\t0.009204773873174418\t0.00034332000251610846\t0.0\t0.0007924296222333303\t0.0\t0.0\t0.009441153443328694\t0.005947519671344408\t0.0\t0.0005356814581771544\t0.0062158573429365515\t0.0\t0.009417667003961789\t0.009918679539108183\t0.00023339501999512072\t0.02671768716952186\t0.00030790986345821436\t0.0\t0.0\t0.0013743163821902838\t0.01723317359032806\t0.0\t0.031565466787107484\t0.012448459343477094\t0.0\t0.007750527312298496\t0.0070234525583043545\t0.020597611603217006\t0.023913761352649474\t0.011281962106545012\t1.6426994248357484e-05\t0.0\t0.036975166579308195\t0.033662224880288756\t0.0\t0.0\t0.023540677910418212\t0.0\t0.036138976947232074\t0.025424940901129827\t0.0\t0.0\t0.011503400057545196\t0.0\t0.00020822196303031898\t0.0\t0.0\t0.0\t0.0\t0.0014763317286047445\t0.0\t0.0012583838846539634\t0.0\t0.003999037208194656\t0.013710430439412244\t0.001352473025884712\t0.007867754340786993\t0.04052738458771679\t0.010996257146538806\t0.0\t0.0\t0.06835446607134321\t0.0\t0.0\t0.008591363167784043\t0.0\t0.0\t0.0\t0.0\t0.0\t0.007090284250167511\t0.008465564938609326\t0.08040814196887736\t0.0\t0.028294996723359764\t0.0\t0.0\t0.0038398141926578064\t0.16023981186600048\t0.04805946943116568\t0.037035561711554706\t0.0\t0.0005120942309216829\t0.0\t0.0\t0.034941826561919985\t0.0\t0.0\t0.027888357150312005\t0.01258535522221259\t0.03740123828771992\t0.008517825868349588\t0.00913703375472102\t0.0\t0.0\t0.0\t0.0\t0.0\t0.029300775267851735\t0.0\t0.0\t0.0\t0.01295087988307018\t0.0005955124138932553\t0.0\t0.0\t0.0\t0.005304965226057589\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.039134050766579234\t0.27148697274385963\t0.0035271606926311825\t0.0\t0.0\t0.020497841819279862\t0.0\t0.0025113292870849223\t0.0\t0.35008458730475683\t0.0\t0.002239902702309837\t0.0\t0.0054911380358033625\t0.0\t0.0\t0.011672805021412769\t0.025682900399847084\t0.07006608189710377\t0.018632962351792192\t0.0\t0.04153373284622605\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.007867919703105093\t0.0\t0.047481418502903334\t0.0\t0.0\t0.0\t0.10974594417370813\t0.03429165867240808\t0.0\t0.023165391809283516\t0.0\t0.0\t0.0\t0.0002833417563650782\t0.0\t0.0\t0.0\t0.026807362599866824\t0.003975994609085822\t0.0\t0.0\t0.0\t0.0\t0.0\t0.06458445415629567\t0.013061309028202961\t0.0\t0.0\n+Testosterone\t0.009633211930500658\t0.0002486431572929\t0.0\t0.00023222574210458814\t0.0009261428396286391\t0.0\t0.0\t0.00040034384039336243\t0.0\t6.734322542065856e-05\t0.0016889974488375876\t0.0\t0.1780813812315969\t0.007271975837211051\t0.00015349402653421548\t0.027912903539727696\t0.0\t0.0\t0.0\t0.0005797401705402813\t0.01109882605223559\t0.0\t0.024485309434567656\t0.020836980610370613\t0.0\t0.004730656796420955\t0.009055625850088012\t0.017644857519378446\t0.03429748760686159\t0.0031719104702998637\t0.0\t0.0\t0.039580956813763224\t0.008699485073663131\t0.0\t0.0\t0.027921629937492445\t0.0\t0.011883152521337896\t0.004739553677117161\t0.0\t0.0\t0.06041370798509162\t0.0\t0.042697154051077546\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.002871402290315483\t0.02141815638649301\t0.0015186515255164064\t0.006270179831850896\t0.029915893967898583\t0.00688460931497788\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001333543171051696\t0.0\t0.08702752210600659\t0.0\t0.03171198034450119\t0.0\t0.0\t0.0\t0.0\t0.000766019375887316\t0.010813507002141582\t0.0\t0.0\t0.0\t0.0\t0.004200894168035819\t0.0\t0.0\t0.02349484368553467\t0.01816654272894712\t0.0633986728469274\t0.00859117181156952\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.11646566920503162\t0.0\t0.0\t0.0\t0.0\t0.0031342530947578136\t0.0\t0.15489171142643712\t0.0\t0.013048242174815912\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001658310433454475\t0.03949452321180806\t0.0\t0.0\t0.0\t0.021990926351807643\t0.0\t0.13014922112429483\t0.0\t0.18331721895001493\t0.0\t0.0014411200837741657\t0.0\t0.0\t0.0\t0.0\t0.01092105341354284\t0.009432436710872112\t0.06421886680272976\t0.025882956568067213\t0.0\t0.03618383380922253\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0006655628265325035\t0.0\t0.026485058850513152\t0.0\t0.0\t0.0\t0.10783284756046711\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.12344754627650135\t0.0\t0.0\t0.0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/fill.mgf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/fill.mgf Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,2513 @@\n+BEGIN IONS\n+NAME=C001\n+IONMODE=Negative\n+RETENTIONTIME=38.74\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=57\n+138.9121 10186226.0 \n+148.9337 1008656.0 \n+175.0641 26780143.0 \n+186.1095 2675456.0 \n+196.8658 21390430.0 \n+198.8647 21688594.0 \n+200.8848 7742528.0 \n+206.9034 26130980.0 \n+216.9205 32607700.0 \n+234.0134 2550129.0 \n+254.8252 23747536.0 \n+256.8215 31377637.0 \n+258.8237 15532799.0 \n+266.8652 9805546.0 \n+268.8537 3090354.0 \n+306.9914 3169316.0 \n+312.7841 10051801.0 \n+316.7777 10734168.0 \n+322.8157 6317648.0 \n+324.9549 8619910.0 \n+334.849 4178412.0 \n+342.8093 3285552.0 \n+349.9455 2050695.0 \n+350.9875 6150799.0 \n+351.941 1965882.0 \n+366.8281 3253770.0 \n+370.7418 9765463.0 \n+372.7383 19374863.0 \n+382.8218 12815572.0 \n+384.8177 8311500.0 \n+392.7685 10913351.0 \n+413.2664 3965867.0 \n+426.7772 5431633.0 \n+428.7834 8554675.0 \n+434.7287 9943329.0 \n+436.8161 3705247.0 \n+440.7322 10603010.0 \n+442.7401 8271752.0 \n+450.7016 8762673.0 \n+460.7076 4528973.0 \n+462.7862 2123666.0 \n+484.7242 4273989.0 \n+486.7743 4886062.0 \n+488.6825 12267966.0 \n+492.744 7662344.0 \n+494.8953 7188793.0 \n+498.8794 6811405.0 \n+500.8484 6520691.0 \n+502.7832 3567833.0 \n+510.763 4989757.0 \n+518.7415 4243468.0 \n+546.6093 7177067.0 \n+550.6949 6104789.0 \n+566.5977 5171811.0 \n+612.6927 2005587.0 \n+676.6436 1982714.0 \n+800.4451 2792137.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C002\n+IONMODE=Negative\n+RETENTIONTIME=520.25\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=35\n+131.1733 1971789.0 \n+267.2688 6103973.0 \n+279.0196 1946255.0 \n+289.6491 46498377.0 \n+301.1565 15185412.0 \n+309.1649 18045974.0 \n+310.1623 295359836.0 \n+311.1658 13124727.0 \n+312.0296 38757284.0 \n+330.6757 12666597.0 \n+525.375 1073323842.0 \n+526.3783 181668883.0 \n+527.3812 23642795.0 \n+551.3321 111616808.0 \n+552.3348 28340614.0 \n+553.3314 2609936.0 \n+562.3269 7538206.0 \n+578.2905 7578406.0 \n+619.3008 4742103.0 \n+624.296 11790213.0 \n+813.5403 25060147.0 \n+814.5336 5865975.0 \n+955.1171 2322927.0 \n+1047.7378 150394804.0 \n+1048.7399 90978863.0 \n+1049.7432 29946438.0 \n+1050.7453 6807767.0 \n+1069.7158 5074652.0 \n+1074.1979 3402288.0 \n+1075.1968 33352763.0 \n+1076.2004 10417953.0 \n+1101.6535 2023916.0 \n+1206.3127 3738816.0 \n+1216.8041 4439324.0 \n+1217.807 3565334.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C003\n+IONMODE=Negative\n+RETENTIONTIME=483.67\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=26\n+265.2529 11366224.0 \n+266.2564 1420444.0 \n+279.6362 29849749.0 \n+280.6546 8848921.0 \n+288.6414 202172046.0 \n+378.2093 15309961.0 \n+379.1966 2902366.0 \n+522.3565 4089569222.0 \n+523.354 1201714423.0 \n+549.3267 63300808.0 \n+576.2749 7386007.0 \n+577.3074 2354251.0 \n+617.2778 2323470.0 \n+625.4543 4040374.0 \n+796.9808 13576738.0 \n+797.9841 6368973.0 \n+809.9883 12596682.0 \n+810.9916 6601055.0 \n+1043.7028 144351468.0 \n+1044.7068 83271854.0 \n+1045.706 27998321.0 \n+1046.7131 6505178.0 \n+1058.1594 20718345.0 \n+1059.1626 6608764.0 \n+1071.1639 15461047.0 \n+1072.1671 5096642.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C004\n+IONMODE=Negative\n+RETENTIONTIME=473.48\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=24\n+124.1405 6517662.0 \n+170.2437 1237313.0 \n+275.6336 28001849.0 \n+296.147 190395687.0 \n+482.3247 145772322.0 \n+483.3283 36245876.0 \n+496.34 12577588056.0 \n+497.3442 3337125302.0 \n+498.3462 532285213.0 \n+499.3493 68176083.0 \n+770.964 49250157.0 \n+771.9675 22666873.0 \n+783.9721 9839299.0 \n+784.9749 3622908.0 \n+949.6233 8009033.0 \n+950.6274 3674694.0 \n+991.6726 1420557258.0 \n+992.6749 763118028.0 \n+993.6787 239161906.0 \n+994.6801 53549573.0 \n+1017.6897 168186952.0 \n+1018.6656 120599518.0 \n+1019.6555 57647644.0 \n+1020.6591 12469103.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C005\n+IONMODE=Negative\n+RETENTIONTIME=41.72\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=20\n+218.1386 14009249.0 \n+337.0623 88672453.0 \n+338.0654 8770055.0 \n+353.0361 37061354.0 \n+359.0443 48435582.0 \n+360.0459 5025128.0 \n+375.018 29159485.0 \n+376.0216 2740193.0 \n+381.0261 13522755.0 \n+396.9999 10317665.0 \n+417.0027 13822994.0 \n+418.9966 4386311.0 \n+432'..b'TRUMTYPE=Centroid\n+NUM PEAKS=2\n+328.2481 11119434.0 \n+329.2519 2068394.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C152\n+IONMODE=Negative\n+RETENTIONTIME=385.78\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+409.1497 1369551.0 \n+427.1607 2275086.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C153\n+IONMODE=Negative\n+RETENTIONTIME=401.39\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+107.0557 2271180.0 \n+197.1612 1286942.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C154\n+IONMODE=Negative\n+RETENTIONTIME=388.72\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+239.1276 1743749.0 \n+286.9585 1645545.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C155\n+IONMODE=Negative\n+RETENTIONTIME=373.67\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+507.1617 6285930.0 \n+508.1657 1535734.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C156\n+IONMODE=Negative\n+RETENTIONTIME=378.37\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+257.2254 3302868.0 \n+777.6928 4522421.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C157\n+IONMODE=Negative\n+RETENTIONTIME=473.08\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+267.6425 11780168.0 \n+534.2949 13399261.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C158\n+IONMODE=Negative\n+RETENTIONTIME=508.15\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+380.2992 5790633.0 \n+423.2518 1386850.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C159\n+IONMODE=Negative\n+RETENTIONTIME=471.89\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+304.2357 21716257.0 \n+306.1523 8327492.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C160\n+IONMODE=Negative\n+RETENTIONTIME=465.45\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+193.1239 1274413.0 \n+295.1974 20379534.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C161\n+IONMODE=Negative\n+RETENTIONTIME=488.7\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+667.4214 3075774.0 \n+1189.7766 2040172.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C162\n+IONMODE=Negative\n+RETENTIONTIME=471.97\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+316.6601 7221684.0 \n+393.2201 8389493.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C163\n+IONMODE=Negative\n+RETENTIONTIME=465.16\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+422.3267 4962906.0 \n+431.3157 12163271.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C164\n+IONMODE=Negative\n+RETENTIONTIME=474.29\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+239.1779 8236995.0 \n+398.3268 11918127.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C165\n+IONMODE=Negative\n+RETENTIONTIME=477.74\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+249.1858 1576729.0 \n+307.15 1941191.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C166\n+IONMODE=Negative\n+RETENTIONTIME=494.51\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+355.2846 54372680.0 \n+373.2951 6108864.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C167\n+IONMODE=Negative\n+RETENTIONTIME=497.67\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+474.3486 2732000.0 \n+649.4483 2434649.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C168\n+IONMODE=Negative\n+RETENTIONTIME=498.02\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+459.2569 3550909.0 \n+539.4163 5285541.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C169\n+IONMODE=Negative\n+RETENTIONTIME=492.45\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+732.5452 4526953.0 \n+733.5465 1043642.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C170\n+IONMODE=Negative\n+RETENTIONTIME=497.3\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+450.3586 4210116.0 \n+451.3631 6446370.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C171\n+IONMODE=Negative\n+RETENTIONTIME=467.81\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+185.0776 5067455.0 \n+200.203 1398415.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C172\n+IONMODE=Negative\n+RETENTIONTIME=457.02\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+263.2347 3933284.0 \n+615.2633 1132491.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C173\n+IONMODE=Negative\n+RETENTIONTIME=443.89\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+370.2956 41596161.0 \n+371.304 9966707.0 \n+END IONS\n+\n+BEGIN IONS\n+NAME=C174\n+IONMODE=Negative\n+RETENTIONTIME=438.81\n+RETENTIONINDEX=\n+SPECTRUMTYPE=Centroid\n+NUM PEAKS=2\n+330.2563 5274387.0 \n+579.2938 6044865.0 \n+END IONS\n+\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/fill.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/fill.msp Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,2165 @@\n+NAME:C001\n+IONMODE:Negative\n+RETENTIONTIME:38.74\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:57\n+216.9205 32607700\n+256.8215 31377637\n+175.0641 26780143\n+206.9034 26130980\n+254.8252 23747536\n+198.8647 21688594\n+196.8658 21390430\n+372.7383 19374863\n+258.8237 15532799\n+382.8218 12815572\n+488.6825 12267966\n+392.7685 10913351\n+316.7777 10734168\n+440.7322 10603010\n+138.9121 10186226\n+312.7841 10051801\n+434.7287 9943329\n+266.8652 9805546\n+370.7418 9765463\n+450.7016 8762673\n+324.9549 8619910\n+428.7834 8554675\n+384.8177 8311500\n+442.7401 8271752\n+200.8848 7742528\n+492.744 7662344\n+494.8953 7188793\n+546.6093 7177067\n+498.8794 6811405\n+500.8484 6520691\n+322.8157 6317648\n+350.9875 6150799\n+550.6949 6104789\n+426.7772 5431633\n+566.5977 5171811\n+510.763 4989757\n+486.7743 4886062\n+460.7076 4528973\n+484.7242 4273989\n+518.7415 4243468\n+334.849 4178412\n+413.2664 3965867\n+436.8161 3705247\n+502.7832 3567833\n+342.8093 3285552\n+366.8281 3253770\n+306.9914 3169316\n+268.8537 3090354\n+800.4451 2792137\n+186.1095 2675456\n+234.0134 2550129\n+462.7862 2123666\n+349.9455 2050695\n+612.6927 2005587\n+676.6436 1982714\n+351.941 1965882\n+148.9337 1008656\n+\n+NAME:C002\n+IONMODE:Negative\n+RETENTIONTIME:520.25\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:35\n+525.375 1073323842\n+310.1623 295359836\n+526.3783 181668883\n+1047.7378 150394804\n+551.3321 111616808\n+1048.7399 90978863\n+289.6491 46498377\n+312.0296 38757284\n+1075.1968 33352763\n+1049.7432 29946438\n+552.3348 28340614\n+813.5403 25060147\n+527.3812 23642795\n+309.1649 18045974\n+301.1565 15185412\n+311.1658 13124727\n+330.6757 12666597\n+624.296 11790213\n+1076.2004 10417953\n+578.2905 7578406\n+562.3269 7538206\n+1050.7453 6807767\n+267.2688 6103973\n+814.5336 5865975\n+1069.7158 5074652\n+619.3008 4742103\n+1216.8041 4439324\n+1206.3127 3738816\n+1217.807 3565334\n+1074.1979 3402288\n+553.3314 2609936\n+955.1171 2322927\n+1101.6535 2023916\n+131.1733 1971789\n+279.0196 1946255\n+\n+NAME:C003\n+IONMODE:Negative\n+RETENTIONTIME:483.67\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:26\n+522.3565 4089569222\n+523.354 1201714423\n+288.6414 202172046\n+1043.7028 144351468\n+1044.7068 83271854\n+549.3267 63300808\n+279.6362 29849749\n+1045.706 27998321\n+1058.1594 20718345\n+1071.1639 15461047\n+378.2093 15309961\n+796.9808 13576738\n+809.9883 12596682\n+265.2529 11366224\n+280.6546 8848921\n+576.2749 7386007\n+1059.1626 6608764\n+810.9916 6601055\n+1046.7131 6505178\n+797.9841 6368973\n+1072.1671 5096642\n+625.4543 4040374\n+379.1966 2902366\n+577.3074 2354251\n+617.2778 2323470\n+266.2564 1420444\n+\n+NAME:C004\n+IONMODE:Negative\n+RETENTIONTIME:473.48\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:24\n+496.34 12577588056\n+497.3442 3337125302\n+991.6726 1420557258\n+992.6749 763118028\n+498.3462 532285213\n+993.6787 239161906\n+296.147 190395687\n+1017.6897 168186952\n+482.3247 145772322\n+1018.6656 120599518\n+499.3493 68176083\n+1019.6555 57647644\n+994.6801 53549573\n+770.964 49250157\n+483.3283 36245876\n+275.6336 28001849\n+771.9675 22666873\n+1020.6591 12469103\n+783.9721 9839299\n+949.6233 8009033\n+124.1405 6517662\n+950.6274 3674694\n+784.9749 3622908\n+170.2437 1237313\n+\n+NAME:C005\n+IONMODE:Negative\n+RETENTIONTIME:41.72\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:20\n+337.0623 88672453\n+359.0443 48435582\n+353.0361 37061354\n+375.018 29159485\n+218.1386 14009249\n+417.0027 13822994\n+381.0261 13522755\n+438.9851 11307111\n+396.9999 10317665\n+454.9592 9820452\n+432.9764 9779399\n+338.0654 8770055\n+360.0459 5025128\n+418.9966 4386311\n+512.8989 4072570\n+456.9603 3774845\n+470.9263 3632486\n+572.871 3485486\n+440.9796 3364168\n+376.0216 2740193\n+\n+NAME:C006\n+IONMODE:Negative\n+RETENTIONTIME:452.08\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:19\n+494.3249 803829845\n+495.3278 207959661\n+542.3239 193323900\n+543.3276 55501736\n+1087.6715 34676828\n+516.3076 24092471\n+274.6257 21694276\n+1088.6773 21466528\n+1001.658 11852076\n+1089.682 9948820\n+290.6256 9704443\n+1061.6562 9417442\n+987.6411 7453650\n+1037.6578 7076912\n+1062.6592 5657208\n+484.3311 5283943\n+265.6196 '..b'5.2288 1932289\n+\n+NAME:C147\n+IONMODE:Negative\n+RETENTIONTIME:563.22\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+282.2792 241362345\n+256.2615 19433189\n+\n+NAME:C148\n+IONMODE:Negative\n+RETENTIONTIME:548.47\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+305.2468 9633582\n+329.249 5814756\n+\n+NAME:C149\n+IONMODE:Negative\n+RETENTIONTIME:350.93\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+130.0643 7419216\n+190.0865 4433780\n+\n+NAME:C150\n+IONMODE:Negative\n+RETENTIONTIME:365.37\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+490.2083 5275418\n+465.1226 1763287\n+\n+NAME:C151\n+IONMODE:Negative\n+RETENTIONTIME:394.87\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+328.2481 11119434\n+329.2519 2068394\n+\n+NAME:C152\n+IONMODE:Negative\n+RETENTIONTIME:385.78\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+427.1607 2275086\n+409.1497 1369551\n+\n+NAME:C153\n+IONMODE:Negative\n+RETENTIONTIME:401.39\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+107.0557 2271180\n+197.1612 1286942\n+\n+NAME:C154\n+IONMODE:Negative\n+RETENTIONTIME:388.72\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+239.1276 1743749\n+286.9585 1645545\n+\n+NAME:C155\n+IONMODE:Negative\n+RETENTIONTIME:373.67\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+507.1617 6285930\n+508.1657 1535734\n+\n+NAME:C156\n+IONMODE:Negative\n+RETENTIONTIME:378.37\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+777.6928 4522421\n+257.2254 3302868\n+\n+NAME:C157\n+IONMODE:Negative\n+RETENTIONTIME:473.08\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+534.2949 13399261\n+267.6425 11780168\n+\n+NAME:C158\n+IONMODE:Negative\n+RETENTIONTIME:508.15\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+380.2992 5790633\n+423.2518 1386850\n+\n+NAME:C159\n+IONMODE:Negative\n+RETENTIONTIME:471.89\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+304.2357 21716257\n+306.1523 8327492\n+\n+NAME:C160\n+IONMODE:Negative\n+RETENTIONTIME:465.45\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+295.1974 20379534\n+193.1239 1274413\n+\n+NAME:C161\n+IONMODE:Negative\n+RETENTIONTIME:488.7\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+667.4214 3075774\n+1189.7766 2040172\n+\n+NAME:C162\n+IONMODE:Negative\n+RETENTIONTIME:471.97\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+393.2201 8389493\n+316.6601 7221684\n+\n+NAME:C163\n+IONMODE:Negative\n+RETENTIONTIME:465.16\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+431.3157 12163271\n+422.3267 4962906\n+\n+NAME:C164\n+IONMODE:Negative\n+RETENTIONTIME:474.29\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+398.3268 11918127\n+239.1779 8236995\n+\n+NAME:C165\n+IONMODE:Negative\n+RETENTIONTIME:477.74\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+307.15 1941191\n+249.1858 1576729\n+\n+NAME:C166\n+IONMODE:Negative\n+RETENTIONTIME:494.51\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+355.2846 54372680\n+373.2951 6108864\n+\n+NAME:C167\n+IONMODE:Negative\n+RETENTIONTIME:497.67\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+474.3486 2732000\n+649.4483 2434649\n+\n+NAME:C168\n+IONMODE:Negative\n+RETENTIONTIME:498.02\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+539.4163 5285541\n+459.2569 3550909\n+\n+NAME:C169\n+IONMODE:Negative\n+RETENTIONTIME:492.45\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+732.5452 4526953\n+733.5465 1043642\n+\n+NAME:C170\n+IONMODE:Negative\n+RETENTIONTIME:497.3\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+451.3631 6446370\n+450.3586 4210116\n+\n+NAME:C171\n+IONMODE:Negative\n+RETENTIONTIME:467.81\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+185.0776 5067455\n+200.203 1398415\n+\n+NAME:C172\n+IONMODE:Negative\n+RETENTIONTIME:457.02\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+263.2347 3933284\n+615.2633 1132491\n+\n+NAME:C173\n+IONMODE:Negative\n+RETENTIONTIME:443.89\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+370.2956 41596161\n+371.304 9966707\n+\n+NAME:C174\n+IONMODE:Negative\n+RETENTIONTIME:438.81\n+RETENTIONINDEX:\n+SPECTRUMTYPE:Centroid\n+Num Peaks:2\n+579.2938 6044865\n+330.2563 5274387\n+\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/fill2.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/fill2.msp Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,5150 @@\n+NAME: C041\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 122.44\n+RETENTIONINDEX: 1079.198718\n+NUM PEAKS: 32\n+73.0841293753643        962537.0\n+92.9922681974622        25809589.0\n+93.5236243719193        7832508.0\n+93.9918503397022        4037554.0\n+94.9892593290089        9273560.0\n+102.528897846033        5258508.0\n+103.032878700634        5618676.0\n+106.048287181011        17919228.0\n+116.082937025519        19358163.0\n+116.088997408008        2749072817.0\n+116.093789141941        21174548.0\n+117.085953932526        5958559.0\n+117.088526521735        137197201.0\n+117.09226575013         144026411.0\n+117.095343138483        3078493.0\n+118.085738968471        93658275.0\n+118.091857064635        7792967.0\n+118.095506285782        3082221.0\n+120.088840757968        158124.0\n+129.052817882804        2757896.0\n+144.047597981883        6935455.0\n+154.03180616847         40749504.0\n+155.035134922158        4354801.0\n+156.011148185837        2560241.0\n+172.042203916163        16922092.0\n+178.047197818956        372134.0\n+190.107642341182        143044792.0\n+191.109992585577        20336483.0\n+192.104283767627        9359612.0\n+204.050979060253        4818700.0\n+205.059630310281        24572956.0\n+244.042971889438        1521120.0\n+\n+NAME: C078\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 123.01\n+RETENTIONINDEX: 1084.222756\n+NUM PEAKS: 19\n+75.010394066048         41579966.0\n+76.0137882041242        2876047.0\n+76.0181929768627        28340717.0\n+77.0259504577085        2087987.0\n+78.0338979909698        183026502.0\n+78.5690293876576        1621521.0\n+78.8681599478139        1487893.0\n+79.0376938452989        30093264.0\n+79.0416552579741        2825081311.0\n+79.0447459388332        28320503.0\n+79.0501993561375        4270687.0\n+79.2157179170819        1455165.0\n+79.5185598181509        1593839.0\n+80.0386557190469        10075569.0\n+80.0450063493877        149614748.0\n+81.0483295726077        3268158.0\n+89.9974943554148        1961794.0\n+95.0365701495921        4214292.0\n+96.0443688524812        20830699.0\n+\n+NAME: C115\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 123.7\n+RETENTIONINDEX: 1090.304487\n+NUM PEAKS: 12\n+77.9912808985361        1430046.0\n+78.0150262817737        37531039.0\n+84.0934034839136        3045143.0\n+85.1012069274801        7651144.0\n+86.1044999837715        502049.0\n+127.023946499139        21672536.0\n+155.015395274682        50181759.0\n+173.025818014551        19321056.0\n+225.059247121035        54449419.0\n+240.031884101672        47027617.0\n+278.105692656594        44448528.0\n+332.077037506685        36734393.0\n+\n+NAME: C072\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 126.02\n+RETENTIONINDEX: 1105.809524\n+NUM PEAKS: 20\n+75.026123979198         434239353.0\n+76.0294479264598        10769681.0\n+79.0184721827801        4406598.0\n+79.0228409649542        3040911.0\n+86.0420715774215        69402087.0\n+93.9412902191997        4117357.0\n+95.0446916434486        4401744.0\n+95.9392474302401        3764925.0\n+120.033807681496        1445863.0\n+122.943972830176        4871174.0\n+131.088643222278        12343251.0\n+134.108939486662        1310131.0\n+137.026000929413        1710939.0\n+168.950062688366        1235026.0\n+176.091958662459        68901069.0\n+177.09146256329         9695519.0\n+184.040024671153        13159137.0\n+206.084125728074        4028572.0\n+249.138642058545        13543889.0\n+251.137167813194        1490829.0\n+\n+NAME: C050\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 128.53\n+RETENTIONINDEX: 1117.761905\n+NUM PEAKS: 26\n+72.0264235348245        4721310.0\n+75.0234110401587        7374271.0\n+75.0288404069534        9420937.0\n+86.9717728755449        9553539.0\n+88.9509947069327        6380434.0\n+97.088645546243         920854.0\n+100.00330732202         18214503.0\n+102.073359041231        484549126.0\n+103.002973695426        21838182.0\n+105.0182950443          11385761.0\n+108.947110640446        3717342.0\n+111.104289675305        3'..b'        50206470.0\n+209.047732156056        2402702.0\n+224.063049376575        5028073.0\n+237.079282533047        3254126.0\n+249.987809880519        7068049.0\n+250.967699771612        4666725.0\n+250.985590439413        4155732.0\n+251.00396611366         4712547.0\n+252.983678728064        24136227.0\n+267.016209949758        5864415.0\n+283.063228005498        1245664.0\n+285.04434812945         5580645.0\n+285.079068565003        8168809.0\n+323.006809434282        4228442.0\n+342.088126205946        12649128.0\n+343.014343300482        13057700.0\n+343.066328014548        11668807.0\n+344.014693258176        2143320.0\n+400.005631091464        1275209.0\n+\n+NAME: C020\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 687.99\n+RETENTIONINDEX: 4135.089286\n+NUM PEAKS: 43\n+109.052235628516        1922885.0\n+111.044058476785        1730416.0\n+133.064909307365        1579533.0\n+137.041722086745        2474039.0\n+194.053642118165        5252308.0\n+212.061782732582        10437319.0\n+267.034768010352        4429084.0\n+267.068824022318        27744081.0\n+268.069192256745        2367920.0\n+310.970568727813        3126083.0\n+311.004219192148        2666091.0\n+325.055731606087        7634729.0\n+327.965549188207        5442532.0\n+328.962716535303        2722019.0\n+339.03821058645         6627839.0\n+341.051986399316        1671451.0\n+342.996634492902        3939816.0\n+345.115297423962        3938049.0\n+358.067243216398        3526875.0\n+361.025211906011        6516476.0\n+388.003000430725        3422825.0\n+388.073272089579        4224454.0\n+399.005054559559        4141766.0\n+401.984326631505        5585170.0\n+402.98179623463         3562508.0\n+416.036473280551        7221552.0\n+417.033665098569        4129234.0\n+417.087073648909        1945166.0\n+418.994970709551        2648178.0\n+430.088321970134        10765018.0\n+431.085366629672        6887942.0\n+473.09370665615         2502410.0\n+475.002854889036        2969642.0\n+475.14184210128         30625723.0\n+477.070907310139        2271450.0\n+489.055479984185        1973511.0\n+503.107930410573        2407435.0\n+549.092119293556        2513579.0\n+552.160354111203        1673065.0\n+565.143723544965        3485979.0\n+610.132183060405        1997085.0\n+625.181479977537        3872339.0\n+697.202597429349        2820429.0\n+\n+NAME: C019\n+IONMODE: Negative\n+SPECTRUMTYPE: Centroid\n+RETENTIONTIME: 688.11\n+RETENTIONINDEX: 4135.446429\n+NUM PEAKS: 45\n+70.261357375322         1769331.0\n+82.0777101637279        1721684.0\n+92.0256956423549        1063403.0\n+104.057597689888        2564581.0\n+106.07773010104         1697865.0\n+118.073139793174        3070732.0\n+135.080430341161        1465718.0\n+144.946939559008        1208427.0\n+145.046705119092        2856482.0\n+164.985419247789        16217649.0\n+179.033979756352        10865004.0\n+180.980322946522        4830502.0\n+191.070496682473        3188459.0\n+192.078428243192        3993484.0\n+194.04893073403         5942766.0\n+195.046783458568        4544081.0\n+211.026857856803        2083491.0\n+213.039588698474        3950087.0\n+213.998834302427        1664182.0\n+248.988380501455        23053112.0\n+251.037178293           10860752.0\n+265.054817014529        3722747.0\n+265.089588392487        3283162.0\n+283.099929585291        13668779.0\n+313.053040045895        8388200.0\n+329.031653006854        6682061.0\n+341.157248840923        18181095.0\n+385.022947628725        6484159.0\n+399.075287615392        4270821.0\n+401.053681557414        30562249.0\n+401.124275228471        4559258.0\n+403.051400482668        5874830.0\n+415.106669687654        54985895.0\n+416.107049345269        18386437.0\n+417.104122333661        8837789.0\n+476.073864807294        4515967.0\n+489.124198650628        43332063.0\n+535.10922525834         9870959.0\n+536.110887614382        4207959.0\n+550.163296442538        12203065.0\n+551.161445828019        6205283.0\n+564.146181690587        6031009.0\n+609.130287444605        3608658.0\n+623.183150220198        13681871.0\n+638.166995588673        2404616.0\n+\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/matches_test1_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/matches_test1_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,175 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+C001\t57\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C002\t0\t35\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C003\t0\t0\t26\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C004\t0\t0\t0\t24\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C005\t0\t0\t0\t0\t20\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C006\t0\t0\t0\t0\t0\t19\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C007\t0\t0\t0\t0\t0\t0\t15\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C008\t0\t1\t0\t0\t0\t0\t0\t15\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C009\t0\t0\t0\t0\t0\t0\t0\t0\t14\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t'..b'\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C164\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C165\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C166\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\n+C167\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\n+C168\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\n+C169\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\n+C170\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\n+C171\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n+C172\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\n+C173\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\n+C174\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/matches_test3_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/matches_test3_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,387 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+Perylene_2H12\t0\t0\t2\t0\t1\t0\t0\t1\t0\t0\t0\t0\t2\t0\t0\t3\t0\t0\t0\t1\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\n+Perylene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t0\t1\t1\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Phenanthrene_2H10\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t2\t0\t1\t0\t0\t0\t0\t1\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\n+Phenanthrene\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Anthracene\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t2\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Acenaphthylene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Acenaphthene\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t3\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Fluoranthene\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t0\t2\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Pyrene\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0'..b'ph_isomer2\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Spirodiclofen\t3\t2\t0\t0\t0\t0\t4\t1\t0\t0\t1\t1\t4\t0\t0\t4\t3\t0\t1\t2\t4\t0\t2\t0\t0\t1\t0\t0\t2\t1\t0\t0\t3\t1\t0\t0\t1\t1\t1\t1\t0\t0\t2\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t3\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t1\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Spiromesifen\t1\t1\t0\t1\t0\t0\t2\t2\t0\t1\t1\t0\t2\t1\t0\t5\t0\t0\t0\t1\t3\t0\t3\t4\t0\t1\t2\t1\t2\t1\t0\t0\t1\t7\t0\t0\t2\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t3\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t2\t0\t1\t0\t0\t0\t0\t1\t2\t0\t1\t0\t0\t0\t0\t0\t2\t0\t0\t3\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\n+Spirotetramat\t2\t2\t0\t1\t0\t0\t2\t5\t0\t2\t1\t0\t6\t1\t0\t7\t1\t0\t1\t2\t4\t0\t4\t8\t0\t3\t2\t1\t2\t1\t0\t0\t3\t7\t0\t0\t3\t0\t0\t4\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t3\t0\t0\t3\t0\t0\t3\t0\t0\t1\t0\t0\t1\t0\t0\t3\t1\t3\t0\t0\t0\t0\t0\t2\t2\t3\t0\t1\t0\t0\t1\t0\t0\t3\t0\t2\t3\t2\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t2\t1\t0\t1\t1\t0\t0\t1\t2\t0\t1\t0\t2\t0\t0\t1\t1\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t1\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\n+17-alpha-Ethynylestradiol\t1\t0\t0\t2\t0\t0\t2\t2\t0\t1\t1\t0\t4\t1\t1\t5\t1\t0\t0\t1\t2\t0\t3\t4\t0\t2\t2\t1\t2\t1\t0\t0\t3\t7\t0\t0\t1\t1\t0\t4\t0\t0\t2\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t2\t0\t1\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t2\t1\t0\t3\t1\t0\t0\t0\t0\t0\t1\t0\t0\t2\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t2\t1\t0\t0\n+Bisphenol A\t0\t0\t0\t0\t0\t0\t1\t1\t0\t1\t0\t0\t1\t0\t0\t3\t1\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t3\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+4-tert-Octylphenol\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Estrone\t1\t0\t0\t0\t0\t0\t1\t1\t0\t1\t1\t0\t3\t1\t1\t6\t0\t0\t0\t2\t1\t0\t2\t7\t0\t1\t3\t1\t2\t1\t0\t0\t3\t7\t0\t0\t0\t1\t0\t3\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t3\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t1\t0\t1\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n+17-beta-Estradiol\t2\t0\t0\t0\t0\t0\t4\t2\t0\t1\t1\t0\t2\t0\t1\t4\t0\t0\t0\t0\t1\t0\t4\t4\t0\t0\t0\t1\t1\t0\t1\t0\t1\t6\t0\t0\t1\t1\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t3\t0\t1\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t2\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+Progesterone\t2\t3\t0\t2\t0\t0\t3\t3\t0\t2\t2\t0\t4\t2\t1\t6\t1\t0\t0\t2\t2\t0\t4\t9\t0\t4\t3\t1\t5\t2\t1\t0\t3\t6\t0\t0\t3\t0\t2\t4\t0\t0\t2\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t1\t1\t1\t1\t1\t2\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t2\t1\t4\t0\t1\t0\t0\t1\t2\t2\t2\t0\t1\t0\t0\t2\t0\t0\t2\t2\t3\t3\t2\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t1\t2\t1\t0\t0\t1\t0\t1\t0\t2\t0\t1\t0\t1\t0\t0\t1\t2\t2\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t2\t0\t0\t0\t2\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t2\t1\t0\t0\n+Testosterone\t1\t1\t0\t1\t1\t0\t0\t2\t0\t1\t1\t0\t4\t1\t1\t5\t0\t0\t0\t1\t2\t0\t3\t7\t0\t2\t2\t1\t4\t1\t0\t0\t3\t3\t0\t0\t1\t0\t1\t2\t0\t0\t3\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t1\t1\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t4\t0\t1\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t2\t0\t0\t2\t2\t3\t1\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t1\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t1\t0\t2\t0\t2\t0\t1\t0\t0\t0\t0\t1\t1\t2\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t2\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/matches_test4_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/matches_test4_out.tsv Tue Mar 22 16:07:32 2022 +0000
[
b"@@ -0,0 +1,387 @@\n+\tPerylene_2H12\tPerylene\tPhenanthrene_2H10\tPhenanthrene\tAnthracene\tAcenaphthylene\tAcenaphthene\tFluoranthene\tPyrene\tpara-Terphenyl\tRetene\tBenzo[b]naphtho[2,1-d]thiophene\t2,3-Benzofluorene\tBenzo[ghi]fluoranthene\tTriphenylene\tBenzanthracene/Benzophenanthrene\tBenzofluoranthene\tBenzo(k)fluoranthene\tBenzo[e]pyrene\tBenzo(a)pyrene\tIndeno[1,2,3-cd]pyrene\tBenzo(g,h,i)perylene\tAnthanthrene\tDibenzanthracene\tCoronene\tDicofol\tBenzophenone\t2-tert-Butyl-4-methoxyphenol\tButylated hydroxytoluene\tBumetrizole\t4-Methylbenzophenone\t2,4,6-Tribromophenol\t2,6-Dichloro-4-nitroaniline\t1-Methylphenanthrene\tTriclosan\tDrometrizole\tEnzacamene\t2,4-Di-tert-butyl-6-(5-chloro-2H-benzotriazol-2-yl)phenol\tOctrizole\t1,2,7,9-Tetrachlorodibenzofuran\t2,2',3,4,5,5',6-Heptachlorobiphenyl\t2,4,6-Trichlorobiphenyl\t2,2',3,3',4,5',6,6'-Octachlorobiphenyl\tMirex\tbeta-Hexachlorocyclohexane\talpha-1,2,3,4,5,6-Hexachlorocyclohexane\tLindane\tdelta-Hexachlorocyclohexane\tepsilon-Hexachlorocyclohexane\tPentachlorobenzene\tHexachlorobenzene\t2,4'-Dichlorodiphenyldichloroethylene\t2,4'-Dichlorodiphenyldichloroethane\t2,4'-Dichlorodiphenyltrichloroethane\t1,2,7,9-Tetrachlorodibenzo-p-dioxin\t2,4,4'-Trichlorobiphenyl\t2,2',4,5,5'-Pentachlorobiphenyl\t2,3',4,4',5-Pentachlorobiphenyl\t2,2',3,4,4',5'-Hexachlorobiphenyl\t2,2',4,4',5,5'-Hexachlorobiphenyl\t2,2',3,4,4',5,5'-Heptachlorobiphenyl\t2,2',5,5'-Tetrachlorobiphenyl\t2,3',4,6-Tetrachlorobiphenyl\t2,3',5',6-Tetrachlorobiphenyl\t2,2',3,4',5-Pentachlorobiphenyl\t2,3,3',4,5-Pentachlorobiphenyl\t3,3',4,5,5'-Pentachlorobiphenyl\t2,3',4,4',5',6-Hexachlorobiphenyl\t2,3,3',4,5,6-Hexachlorobiphenyl\t2,3,3',4',5',6-Hexachlorobiphenyl\t2,3,3',4',5,6-Hexachlorobiphenyl\t2,3,3',4',5,5',6-Heptachlorobiphenyl\tcis-Prallethrin\ttrans-Prallethrin\tcis-Resmethrin\ttrans-Resmethrin\tcis-Tetramethrin\ttrans-Tetramethrin\tBifenthrin\tFenpropathrin\tcis-Phenothrin\ttrans-Phenothrin\tcis-Cyphenothrin\ttrans-Cyphenothrin\tFlucythrinate_isomer1\tFlucythrinate_isomer2\tcis-Fenvalerate\ttrans-Fenvalerate\tDeltamethrin\tChlorpyrifos oxon\tlambda-Cyhalothrin\tTefluthrin\tTransfluthrin\tcis-Permethrin\ttrans-Permethrin\tcis-Allethrin\ttrans-Allethrin\tcis-Cypermethrin_isomer1\ttrans-Cypermethrin_isomer1\tcis-Cypermethrin_isomer2\ttrans-Cypermethrin_isomer2\tcis-Cyfluthrin_isomer1\ttrans-Cyfluthrin_isomer1\tcis-Cyfluthrin_isomer2\ttrans-Cyfluthrin_Isomer2\t1,2,3,4,7,8-Hexachlorodibenzo-p-dioxin\t1,2,3,4,6,7,8-Heptachlorodibenzo-p-dioxin\tOctachlorodibenzo-p-dioxin\tOctachlorodibenzofuran\t1,2,3,7,8-Pentachlorodibenzofuran\t1,2,3,4,7,8-Hexachlorodibenzofuran\t1,2,3,4,6,7,8-Heptachlorodibenzofuran\t2,3,7,8-Tetrachlorodibenzofuran\t2,3,7,8-Tetrachlorodibenzo-p-dioxin\t1,2,3,7,8-Pentachlorodibenzo-p-dioxin\t2,3,4,5-Tetrabromo-6-chlorotoluene\t2,3,4,5,6-Pentabromotoluene\t2,3,4,5,6-Pentabromoethylbenzene\t2,3,5,6-Tetrabromo-p-xylene\tAllyl 2,4,6-tribromophenyl ether\t2-Bromoallyl(2,4,6-tribromophenyl) ether\tPentabromobenzene\tHexabromobenzene\t2,3,4,5,6-Pentabromobenzyl alcohol\t2-Ethylhexyl 2,3,4,5-Tetrabromobenzoate\tsyn-Dechlorane plus\tanti-Dechlorane plus\talpha-1,2-Dibromo-4-(1,2-dibromoethyl)cyclohexane\tbeta-1,2-Dibromo-4-(1,2-dibromoethyl)cyclohexane\t1,2,5,6-Tetrabromocyclooctane\t1,1-Dibromo-2,3,3,4,4,5-hexachloro-2-cyclopenta-2,4-dien-1-ylcyclooctane\talpha-Amylcinnamaldehyde\ttrans-Cinnamaldehyde\tCitral (Geranial)\t1-Fluronaphthalene\talpha-Hexylcinnamaldehyde\tLilial\talpha-Amylcinnamyl alcohol\tEugenol\tIsoeugenol\t4-Methoxybenzyl alcohol\tMethyleugenol\tCinnamyl alcohol\tBenzyl alcohol\tEstragole\tBenzyl benzoate\tBenzyl cinnamate\tBenzyl salicylate\tCamphor\tEucalyptol\tCoumarin\tLimonene\tIsomethyl-alpha-ionone\tdelta-Iraldeine\tSafrole\tCashmeran\tCelestolide\tPhantolide\tTonalide\tTraseolide\tGalaxolide\tAldrin\tEndosulfan\tHeptachlor\tcis-Heptachlor epoxide\tEndosulfan sulphate\tEndrin ketone\ttrans-Chlordane\tcis-Chlordane\tEndrin aldehyde\tEndrin\t4,4'-Dichlorodiphenyldichloroethylene\tMethoxychlor\t4,4'-Dichlorodiphenyldichloroethane\t4,4'-Dichlorodiphenyltrichloroethane\tTris(4-tert-butylphenyl) phosphate\tTri-n-butyl-phosphate\tTris(1,3-dichloro-2-propy"..b'39\t11\t10\t27\t32\t19\t34\t20\t25\t21\t47\t11\t36\t46\t25\t47\t36\t44\t37\t31\t33\t34\t39\t61\t9\t23\t30\t44\t15\t19\t21\t18\t18\t22\t14\t18\t22\t21\t24\t17\t16\t24\t29\t34\t31\t22\t45\t37\t26\t34\t36\t12\t12\t17\t49\t22\t30\t29\t13\t22\t57\t14\t33\t16\t17\t18\t22\t12\t6\t8\t17\t10\t55\t34\t40\t15\t9\t13\t49\t34\t22\t35\t7\t10\t19\t18\t26\t45\t23\t47\t38\t22\t19\t20\t7\t13\t37\t23\t7\t30\t22\t7\t12\t55\t52\t41\t39\t26\t37\t8\t12\t18\t16\t36\t32\t19\t31\t17\t2\t6\t35\t40\t19\t35\t29\t20\t16\t35\t47\t16\t31\t35\t18\t20\t19\t38\t24\t42\t27\t28\t17\t25\t60\t19\t20\t20\t34\t28\t36\t11\t16\t19\t14\t27\t21\t20\t13\t17\t30\t46\t75\t36\t3\t29\t10\t23\t45\t31\t21\t35\t18\t34\t10\t28\t51\t61\t56\t48\t62\t16\t8\t11\t44\t68\t80\t78\t26\t13\t88\t56\t85\t72\n+17-beta-Estradiol\t11\t11\t7\t12\t13\t9\t7\t13\t12\t16\t17\t15\t12\t12\t13\t14\t11\t12\t12\t12\t9\t9\t24\t12\t15\t16\t14\t28\t34\t34\t16\t18\t24\t13\t26\t21\t53\t22\t13\t13\t18\t13\t38\t1\t19\t19\t18\t20\t21\t4\t6\t11\t13\t10\t22\t12\t15\t12\t18\t18\t17\t13\t13\t12\t17\t13\t11\t15\t14\t15\t11\t17\t18\t22\t30\t27\t16\t7\t12\t30\t27\t25\t21\t19\t37\t28\t26\t27\t34\t18\t19\t12\t18\t19\t20\t13\t11\t31\t24\t26\t40\t23\t31\t28\t33\t9\t8\t8\t9\t13\t11\t12\t11\t13\t11\t6\t6\t10\t7\t31\t14\t9\t6\t21\t12\t16\t13\t7\t10\t5\t27\t38\t10\t23\t10\t25\t30\t31\t24\t27\t13\t29\t19\t10\t19\t17\t22\t6\t13\t21\t7\t13\t24\t19\t20\t42\t32\t29\t35\t13\t42\t21\t22\t16\t12\t9\t26\t7\t10\t48\t37\t11\t18\t12\t11\t20\t9\t6\t26\t27\t24\t12\t29\t20\t16\t18\t14\t1\t18\t14\t37\t17\t35\t14\t30\t8\t7\t21\t25\t15\t26\t17\t19\t25\t28\t11\t26\t30\t19\t39\t24\t35\t30\t23\t22\t28\t23\t50\t6\t14\t27\t37\t9\t20\t16\t14\t14\t15\t9\t14\t18\t16\t15\t11\t13\t18\t21\t25\t24\t16\t34\t31\t22\t23\t28\t11\t8\t13\t38\t14\t26\t26\t11\t18\t44\t9\t22\t10\t14\t13\t14\t10\t4\t4\t17\t7\t39\t31\t34\t15\t8\t11\t34\t27\t18\t30\t5\t9\t14\t16\t20\t35\t15\t37\t34\t17\t15\t13\t6\t14\t24\t13\t5\t28\t16\t6\t9\t46\t27\t31\t31\t18\t34\t6\t8\t15\t11\t27\t22\t12\t27\t15\t2\t6\t27\t28\t11\t34\t20\t11\t11\t20\t34\t13\t19\t26\t11\t14\t10\t31\t19\t35\t21\t20\t10\t16\t42\t17\t15\t16\t33\t17\t33\t12\t13\t14\t7\t17\t21\t13\t8\t13\t17\t30\t58\t28\t1\t17\t11\t23\t33\t28\t20\t24\t17\t28\t6\t26\t38\t47\t46\t41\t47\t12\t7\t11\t32\t50\t63\t63\t24\t9\t56\t67\t62\t60\n+Progesterone\t18\t10\t17\t16\t18\t13\t10\t14\t12\t23\t35\t19\t16\t13\t18\t17\t12\t13\t14\t13\t11\t10\t31\t14\t24\t28\t21\t46\t42\t64\t23\t38\t56\t21\t50\t27\t103\t32\t16\t21\t19\t28\t71\t2\t45\t42\t44\t42\t43\t12\t10\t24\t26\t24\t35\t20\t25\t19\t19\t22\t20\t25\t24\t21\t26\t18\t20\t21\t20\t20\t13\t18\t40\t51\t55\t48\t34\t21\t15\t59\t47\t45\t54\t47\t59\t48\t43\t55\t63\t38\t28\t21\t31\t24\t30\t47\t39\t52\t47\t51\t74\t42\t53\t52\t67\t20\t18\t14\t15\t16\t17\t20\t20\t17\t16\t13\t9\t18\t11\t61\t23\t13\t8\t51\t31\t22\t22\t15\t21\t15\t40\t48\t14\t43\t13\t40\t38\t39\t38\t39\t24\t43\t28\t16\t27\t19\t33\t8\t21\t33\t9\t24\t31\t31\t28\t65\t42\t40\t45\t16\t57\t50\t68\t27\t29\t21\t55\t17\t22\t112\t78\t29\t29\t23\t24\t30\t10\t15\t50\t41\t41\t17\t57\t44\t32\t32\t21\t5\t26\t37\t84\t30\t44\t22\t44\t11\t9\t29\t38\t20\t34\t23\t26\t42\t56\t15\t45\t68\t29\t62\t46\t58\t61\t34\t42\t41\t57\t81\t10\t30\t39\t56\t27\t24\t26\t28\t26\t28\t24\t21\t21\t22\t26\t20\t20\t21\t39\t45\t40\t22\t55\t39\t29\t43\t51\t12\t15\t25\t68\t25\t43\t42\t18\t20\t77\t14\t47\t24\t20\t18\t26\t14\t7\t9\t22\t14\t80\t44\t49\t19\t13\t10\t54\t34\t20\t43\t10\t14\t28\t20\t35\t59\t27\t58\t49\t31\t10\t24\t6\t15\t43\t34\t11\t40\t29\t9\t14\t83\t52\t50\t44\t35\t44\t9\t13\t21\t23\t44\t37\t27\t35\t19\t7\t16\t42\t52\t15\t46\t49\t34\t21\t52\t69\t18\t47\t44\t16\t37\t29\t51\t33\t52\t40\t38\t21\t30\t91\t23\t22\t29\t46\t36\t44\t14\t22\t31\t27\t32\t32\t28\t20\t28\t44\t59\t103\t43\t9\t33\t24\t44\t63\t43\t34\t55\t36\t52\t15\t43\t80\t101\t84\t86\t100\t16\t9\t14\t80\t81\t125\t95\t29\t13\t85\t62\t168\t125\n+Testosterone\t14\t8\t13\t13\t15\t12\t10\t14\t12\t24\t36\t18\t16\t10\t17\t16\t9\t9\t10\t9\t10\t9\t28\t12\t22\t25\t19\t44\t39\t48\t22\t35\t46\t19\t38\t25\t101\t27\t15\t18\t17\t26\t51\t2\t38\t36\t39\t37\t37\t8\t6\t20\t22\t21\t25\t18\t21\t16\t17\t15\t18\t23\t24\t19\t21\t15\t15\t16\t16\t16\t9\t15\t39\t46\t43\t44\t29\t20\t10\t46\t37\t36\t40\t34\t43\t36\t30\t41\t51\t33\t19\t20\t24\t17\t22\t41\t35\t38\t33\t36\t65\t34\t39\t36\t52\t13\t12\t10\t11\t11\t11\t13\t14\t14\t11\t7\t3\t10\t5\t51\t19\t7\t3\t41\t25\t19\t16\t11\t17\t14\t35\t48\t14\t41\t15\t35\t37\t37\t38\t37\t22\t44\t26\t15\t29\t16\t29\t8\t21\t32\t10\t24\t32\t30\t28\t63\t38\t34\t42\t16\t49\t41\t46\t19\t20\t15\t44\t13\t16\t91\t63\t24\t21\t19\t20\t27\t10\t13\t32\t27\t27\t15\t51\t30\t21\t27\t19\t3\t23\t35\t72\t29\t44\t18\t37\t8\t8\t26\t33\t17\t31\t21\t23\t32\t47\t13\t44\t56\t28\t60\t39\t52\t60\t37\t39\t38\t48\t78\t10\t26\t40\t49\t24\t22\t22\t24\t21\t24\t18\t15\t17\t18\t21\t15\t17\t17\t33\t39\t35\t18\t48\t38\t29\t39\t42\t12\t14\t18\t60\t23\t36\t36\t16\t16\t61\t13\t42\t21\t19\t16\t26\t14\t7\t8\t19\t14\t64\t41\t42\t19\t12\t11\t46\t34\t19\t40\t7\t15\t27\t20\t29\t49\t27\t55\t41\t30\t10\t21\t6\t15\t38\t28\t12\t37\t28\t7\t14\t75\t37\t43\t43\t33\t43\t9\t12\t20\t14\t39\t33\t21\t33\t18\t5\t13\t41\t45\t10\t44\t44\t28\t20\t43\t57\t15\t41\t38\t15\t30\t27\t46\t30\t49\t39\t36\t20\t27\t70\t22\t20\t25\t44\t27\t45\t13\t18\t26\t18\t26\t30\t21\t18\t25\t34\t45\t86\t38\t7\t24\t22\t32\t50\t37\t25\t48\t34\t47\t14\t37\t66\t81\t71\t74\t84\t15\t8\t12\t68\t60\t96\t82\t27\t13\t72\t60\t125\t130\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/matches_test5_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/matches_test5_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,175 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+C001\t57\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C002\t0\t35\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C003\t0\t0\t26\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C004\t0\t0\t0\t24\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C005\t0\t0\t0\t0\t20\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C006\t0\t0\t0\t0\t0\t19\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C007\t0\t0\t0\t0\t0\t0\t15\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C008\t0\t1\t0\t0\t0\t0\t0\t15\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C009\t0\t0\t0\t0\t0\t0\t0\t0\t14\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t'..b'\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C164\t0\t0\t0\t0\t0\t0\t1\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C165\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\n+C166\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\n+C167\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\n+C168\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\n+C169\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\n+C170\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\n+C171\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\t0\n+C172\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\t0\n+C173\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\t0\n+C174\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t2\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/matches_test6_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/matches_test6_out.tsv Tue Mar 22 16:07:32 2022 +0000
[
b'@@ -0,0 +1,387 @@\n+\tC041\tC078\tC115\tC072\tC050\tC069\tC108\tC121\tC085\tC122\tC114\tC084\tC014\tC029\tC006\tC113\tC107\tC129\tC037\tC092\tC021\tC016\tC109\tC079\tC116\tC123\tC135\tC134\tC070\tC056\tC062\tC082\tC061\tC133\tC087\tC025\tC096\tC009\tC075\tC052\tC130\tC015\tC060\tC131\tC132\tC073\tC090\tC091\tC007\tC074\tC104\tC102\tC103\tC001\tC042\tC010\tC127\tC101\tC004\tC110\tC086\tC051\tC002\tC032\tC039\tC057\tC105\tC095\tC033\tC137\tC138\tC066\tC003\tC040\tC011\tC043\tC106\tC048\tC128\tC058\tC088\tC031\tC100\tC053\tC081\tC023\tC099\tC049\tC044\tC017\tC064\tC098\tC008\tC077\tC119\tC094\tC093\tC124\tC083\tC063\tC035\tC047\tC024\tC022\tC097\tC076\tC030\tC118\tC126\tC038\tC080\tC136\tC117\tC125\tC112\tC026\tC005\tC013\tC034\tC046\tC055\tC071\tC036\tC027\tC067\tC120\tC111\tC068\tC089\tC028\tC045\tC059\tC054\tC018\tC012\tC065\tC020\tC019\n+Perylene_2H12\t2\t0\t1\t0\t0\t1\t0\t3\t0\t1\t1\t0\t1\t3\t5\t1\t2\t0\t1\t0\t5\t6\t1\t4\t2\t0\t0\t1\t2\t2\t2\t2\t2\t1\t2\t6\t1\t8\t0\t1\t1\t6\t3\t0\t1\t1\t0\t0\t7\t2\t1\t3\t4\t8\t4\t2\t3\t0\t8\t0\t1\t2\t9\t4\t3\t0\t0\t0\t5\t0\t0\t2\t5\t6\t5\t0\t1\t2\t1\t0\t0\t1\t1\t0\t0\t4\t3\t2\t1\t6\t1\t2\t11\t2\t1\t1\t0\t1\t2\t1\t3\t3\t1\t3\t0\t1\t1\t0\t0\t3\t1\t0\t0\t0\t0\t3\t2\t5\t2\t0\t2\t1\t1\t2\t2\t0\t2\t1\t1\t5\t0\t0\t5\t4\t2\t1\t0\t5\n+Perylene\t0\t0\t0\t2\t2\t0\t2\t0\t1\t0\t0\t0\t2\t1\t1\t0\t0\t0\t6\t2\t0\t2\t1\t2\t1\t0\t1\t0\t3\t0\t1\t1\t2\t1\t2\t1\t0\t5\t1\t1\t0\t2\t2\t0\t1\t1\t3\t0\t1\t1\t0\t1\t1\t3\t0\t1\t0\t1\t3\t0\t1\t2\t7\t2\t0\t3\t1\t2\t1\t0\t1\t1\t4\t0\t2\t0\t1\t1\t0\t0\t0\t0\t0\t0\t1\t6\t0\t3\t1\t4\t3\t0\t7\t1\t1\t1\t0\t0\t0\t0\t2\t1\t2\t0\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t0\t4\t0\t3\t2\t1\t2\t1\t1\t0\t0\t1\t0\t0\t0\t1\t0\t1\t1\t3\t0\t2\n+Phenanthrene_2H10\t3\t4\t1\t3\t0\t2\t0\t0\t1\t0\t1\t0\t4\t4\t1\t3\t1\t0\t4\t1\t3\t4\t1\t2\t1\t0\t0\t1\t1\t4\t1\t1\t1\t1\t1\t2\t1\t5\t3\t0\t0\t3\t1\t0\t1\t0\t1\t0\t0\t0\t1\t0\t0\t4\t1\t5\t0\t0\t6\t1\t2\t1\t9\t3\t0\t0\t2\t0\t1\t0\t0\t1\t6\t2\t1\t1\t0\t0\t0\t0\t0\t2\t0\t1\t2\t0\t0\t0\t0\t3\t1\t0\t4\t1\t0\t0\t0\t0\t0\t0\t1\t1\t2\t4\t0\t0\t0\t1\t0\t1\t0\t0\t1\t0\t0\t0\t10\t5\t2\t0\t2\t0\t0\t1\t0\t0\t0\t0\t0\t4\t0\t1\t0\t2\t1\t0\t0\t1\n+Phenanthrene\t1\t2\t0\t4\t4\t1\t1\t0\t1\t0\t0\t0\t7\t3\t9\t0\t1\t0\t8\t1\t3\t4\t0\t0\t2\t0\t1\t0\t1\t2\t0\t2\t0\t0\t0\t2\t0\t5\t1\t3\t0\t2\t0\t0\t1\t0\t0\t0\t2\t1\t0\t0\t0\t7\t0\t5\t0\t2\t5\t1\t1\t1\t9\t5\t2\t0\t0\t0\t0\t1\t0\t0\t9\t2\t2\t1\t0\t0\t1\t3\t0\t0\t2\t0\t1\t0\t1\t1\t0\t2\t1\t1\t3\t0\t1\t3\t0\t0\t0\t0\t0\t2\t3\t1\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t9\t2\t0\t1\t0\t1\t1\t1\t0\t3\t2\t2\t0\t3\t2\t1\t2\t0\t0\t1\t0\t1\n+Anthracene\t1\t2\t0\t4\t5\t1\t3\t0\t1\t0\t0\t0\t7\t3\t9\t0\t1\t0\t8\t2\t3\t4\t1\t0\t1\t0\t1\t0\t1\t2\t1\t2\t0\t1\t0\t1\t0\t4\t2\t4\t0\t2\t0\t0\t1\t0\t0\t0\t2\t2\t0\t0\t0\t8\t0\t6\t0\t2\t7\t1\t1\t1\t9\t5\t3\t0\t0\t0\t0\t1\t0\t0\t11\t2\t2\t1\t1\t0\t1\t3\t0\t0\t2\t0\t1\t0\t0\t1\t0\t2\t2\t1\t4\t0\t1\t3\t0\t0\t0\t0\t0\t1\t3\t1\t0\t1\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t11\t1\t0\t1\t0\t1\t1\t1\t0\t3\t2\t2\t1\t3\t2\t1\t2\t0\t0\t2\t0\t1\n+Acenaphthylene\t1\t3\t1\t3\t4\t2\t3\t0\t3\t0\t0\t0\t5\t2\t5\t0\t0\t0\t2\t2\t1\t4\t1\t0\t3\t0\t1\t0\t1\t0\t2\t0\t1\t1\t0\t4\t0\t5\t3\t2\t0\t1\t0\t0\t2\t0\t0\t0\t3\t2\t1\t0\t0\t9\t1\t5\t0\t2\t5\t1\t0\t1\t9\t3\t2\t1\t1\t1\t1\t1\t0\t1\t9\t3\t1\t0\t1\t0\t1\t2\t0\t0\t2\t0\t0\t0\t1\t1\t0\t1\t2\t1\t5\t0\t1\t2\t0\t0\t0\t1\t0\t2\t1\t1\t0\t1\t0\t0\t1\t2\t0\t0\t0\t0\t0\t0\t7\t3\t1\t1\t1\t1\t1\t1\t1\t4\t1\t2\t2\t4\t0\t0\t0\t2\t0\t2\t0\t2\n+Acenaphthene\t2\t2\t2\t3\t6\t2\t2\t0\t2\t0\t0\t0\t5\t2\t8\t1\t0\t0\t2\t3\t1\t3\t0\t0\t2\t0\t1\t0\t1\t0\t3\t0\t0\t0\t0\t4\t0\t5\t1\t0\t0\t1\t0\t0\t1\t0\t1\t0\t4\t3\t0\t0\t0\t9\t0\t3\t0\t2\t4\t1\t1\t1\t11\t2\t2\t2\t1\t0\t0\t1\t0\t0\t9\t4\t2\t0\t1\t0\t1\t2\t0\t0\t2\t0\t0\t0\t2\t2\t1\t1\t3\t1\t4\t0\t1\t2\t0\t0\t0\t0\t0\t2\t2\t2\t0\t0\t0\t0\t0\t2\t0\t0\t0\t0\t0\t1\t4\t3\t1\t1\t0\t1\t1\t2\t0\t5\t2\t3\t0\t3\t0\t1\t0\t1\t0\t1\t0\t2\n+Fluoranthene\t1\t1\t0\t2\t4\t2\t0\t0\t2\t2\t1\t1\t8\t3\t5\t0\t1\t0\t5\t0\t5\t8\t0\t0\t0\t0\t0\t0\t3\t2\t1\t1\t1\t0\t1\t2\t0\t3\t0\t1\t2\t4\t0\t0\t1\t0\t2\t0\t3\t0\t1\t1\t0\t5\t0\t1\t0\t1\t9\t2\t0\t2\t10\t2\t1\t0\t2\t1\t0\t0\t1\t2\t5\t2\t3\t1\t0\t0\t0\t0\t0\t6\t0\t0\t0\t1\t0\t2\t0\t2\t2\t1\t6\t0\t0\t1\t0\t0\t0\t1\t3\t4\t4\t3\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t9\t0\t0\t0\t0\t1\t0\t0\t2\t1\t0\t0\t1\t0\t2\t0\t0\t1\t1\t0\t0\t0\n+Pyrene\t1\t0\t0\t0\t3\t2\t0\t0\t2\t2\t1\t1\t8\t3\t3\t0\t1\t0\t4\t0\t5\t7\t0\t0\t0\t0\t0\t0\t3\t1\t1\t1\t1\t0\t1\t2\t0\t2\t0\t1\t2\t4\t0\t0\t1\t0\t2\t0\t2\t0\t1\t1\t0\t5\t0\t1\t0\t0\t8\t2\t0\t2\t9\t1\t1\t0\t2\t1\t0\t0\t1\t2\t5\t2\t3\t1\t0\t0\t0\t0\t0\t6\t0\t0\t0\t1\t0\t2\t0\t2\t2\t1\t6\t0\t0\t1\t0\t0\t0\t1\t3\t4\t3\t3\t0\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t0\t8\t0\t0\t0\t0\t1\t0\t0\t2\t0\t0\t0\t1\t0\t2\t0\t0\t1\t1\t0\t0\t0\n+para-Terphenyl\t0\t0\t0\t1\t1\t1\t2\t0\t1\t2\t4\t1\t4\t3\t10\t0\t2\t1\t4\t1\t7\t7\t0\t3\t0\t0\t2\t2\t6\t3\t1\t1\t3\t0\t3\t6\t2\t9\t2\t0\t0\t5\t3\t0\t2\t3\t1\t1\t8\t3\t0\t1\t1\t8\t0\t2\t1\t1\t13\t1\t0\t3\t18\t2\t2\t1\t1\t1\t0\t2\t0\t4\t5\t4\t5\t2\t0\t0\t1\t3\t1\t5\t2\t0\t2\t1\t1\t2\t0\t4\t2\t1\t10\t2\t1\t1\t0\t0\t2\t0\t2\t4\t4\t4\t0\t1\t1\t1\t1\t2\t0\t0\t1\t0\t0\t1\t15\t2\t2\t1\t0\t0\t1\t1\t1\t2\t1\t0\t2\t5\t3\t0\t0\t4\t1\t1\t0\t1\n+Retene\t7\t1\t0\t3\t4\t9\t1\t0\t1\t2\t2\t3\t9\t6\t14\t1\t3\t2\t7\t2\t13\t14\t1\t1\t0\t0\t0\t2\t4\t10\t4\t3\t2\t1\t2\t3\t2\t6\t9\t8\t0\t4\t1\t0\t2\t3\t1\t0\t4\t3\t0\t0\t1\t15\t1\t7\t0\t2\t19\t3\t2\t5\t11\t6\t5\t0\t2\t1\t1\t1\t0\t2\t11\t5\t12\t2\t1\t0\t1\t0\t0\t7\t2\t1\t2\t0\t0\t0\t1\t6\t1\t1\t7\t3\t0\t2\t0\t0\t1\t0\t5\t3\t2\t4\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t4\t30\t1\t0\t0\t1\t1\t1\t1\t2\t2\t0\t3\t3\t3\t3\t2\t3\t1\t3\t2\t0\t5\n+Benzo[b]naphtho[2,1-d]thiophene\t4\t0\t0\t0\t2\t5\t1\t0\t2\t1\t1\t0\t4\t2\t6\t0\t2\t0\t3\t1\t5\t6\t1\t3\t0\t0\t0'..b'1\t0\t1\t0\t4\t1\t0\t0\t0\t7\t3\t6\t0\t1\t8\t2\t3\t1\t9\t3\t3\t1\t0\t0\t1\t0\t0\t0\t8\t2\t1\t1\t0\t0\t0\t0\t0\t3\t0\t0\t1\t0\t2\t0\t1\t1\t1\t0\t6\t0\t0\t0\t0\t0\t0\t1\t0\t3\t1\t4\t0\t0\t0\t0\t1\t2\t1\t0\t0\t0\t0\t0\t7\t5\t1\t0\t1\t0\t0\t1\t0\t2\t2\t1\t1\t7\t0\t0\t0\t2\t1\t0\t0\t2\n+Fenpropimorph_isomer1\t1\t0\t1\t2\t2\t2\t2\t0\t2\t1\t1\t1\t1\t1\t0\t0\t0\t0\t0\t1\t0\t3\t1\t0\t0\t0\t1\t2\t3\t0\t2\t0\t0\t1\t0\t2\t1\t4\t1\t1\t0\t0\t1\t0\t1\t0\t0\t1\t0\t1\t0\t1\t0\t2\t0\t1\t0\t0\t2\t0\t0\t0\t7\t0\t2\t1\t0\t0\t0\t0\t0\t0\t6\t2\t0\t0\t1\t0\t0\t0\t0\t2\t0\t0\t1\t0\t1\t0\t0\t0\t2\t0\t2\t0\t0\t0\t0\t0\t0\t1\t0\t0\t1\t4\t0\t0\t0\t1\t1\t1\t0\t0\t0\t0\t0\t0\t3\t1\t3\t0\t0\t0\t0\t1\t0\t1\t0\t1\t1\t1\t0\t0\t0\t1\t0\t0\t0\t0\n+Fenpropimorph_isomer2\t2\t0\t2\t2\t1\t1\t0\t0\t3\t2\t1\t2\t2\t2\t2\t0\t1\t0\t1\t0\t2\t4\t1\t0\t0\t0\t1\t2\t3\t1\t2\t0\t2\t1\t1\t2\t2\t7\t1\t2\t0\t1\t1\t2\t1\t0\t1\t1\t1\t1\t0\t1\t0\t4\t1\t1\t0\t0\t7\t0\t0\t1\t5\t1\t3\t2\t0\t0\t0\t0\t0\t1\t8\t3\t0\t0\t0\t0\t0\t0\t0\t4\t0\t0\t1\t0\t2\t0\t0\t0\t1\t0\t2\t1\t0\t0\t0\t0\t0\t2\t0\t1\t1\t7\t0\t0\t0\t1\t2\t2\t0\t0\t0\t0\t0\t0\t4\t2\t6\t0\t0\t0\t1\t2\t0\t3\t0\t0\t1\t3\t0\t0\t1\t0\t0\t0\t0\t1\n+Spirodiclofen\t3\t3\t4\t5\t5\t6\t3\t4\t6\t3\t4\t1\t15\t5\t29\t1\t3\t0\t11\t0\t9\t7\t4\t3\t3\t0\t3\t1\t4\t5\t4\t4\t4\t3\t4\t8\t2\t12\t5\t3\t1\t8\t3\t0\t5\t2\t2\t1\t20\t4\t4\t1\t5\t33\t3\t6\t3\t2\t17\t1\t1\t4\t18\t8\t7\t8\t5\t6\t6\t3\t0\t3\t18\t10\t13\t2\t0\t2\t2\t3\t1\t3\t4\t3\t1\t9\t4\t2\t3\t10\t7\t2\t20\t3\t2\t4\t1\t0\t5\t4\t5\t4\t3\t5\t3\t1\t3\t1\t2\t3\t3\t1\t1\t0\t0\t6\t6\t5\t5\t3\t3\t4\t2\t5\t8\t3\t2\t6\t5\t9\t15\t3\t3\t9\t10\t7\t2\t9\n+Spiromesifen\t11\t2\t4\t3\t6\t6\t3\t1\t5\t5\t3\t3\t19\t8\t19\t7\t7\t5\t7\t9\t9\t15\t8\t8\t5\t0\t5\t3\t10\t4\t5\t7\t9\t6\t6\t19\t6\t23\t4\t7\t4\t17\t6\t4\t4\t6\t7\t5\t13\t9\t3\t2\t3\t39\t16\t6\t4\t1\t30\t4\t10\t6\t44\t11\t8\t5\t5\t4\t5\t2\t1\t4\t50\t14\t11\t5\t1\t2\t2\t4\t0\t10\t3\t0\t5\t11\t5\t9\t3\t12\t8\t3\t31\t8\t2\t2\t3\t0\t2\t3\t9\t9\t9\t19\t1\t1\t2\t1\t2\t14\t4\t1\t2\t0\t1\t7\t27\t12\t14\t4\t8\t5\t5\t4\t4\t7\t3\t3\t5\t16\t2\t3\t5\t3\t5\t4\t2\t8\n+Spirotetramat\t19\t5\t5\t7\t10\t10\t5\t5\t9\t8\t7\t6\t26\t13\t34\t6\t8\t6\t11\t11\t17\t19\t10\t10\t6\t0\t4\t4\t17\t5\t6\t10\t13\t6\t10\t23\t7\t28\t9\t14\t7\t24\t10\t4\t4\t10\t9\t6\t29\t13\t5\t7\t7\t54\t22\t19\t5\t8\t52\t8\t11\t12\t65\t18\t16\t11\t6\t7\t10\t2\t5\t11\t66\t20\t23\t6\t2\t5\t4\t7\t2\t16\t8\t5\t12\t16\t6\t11\t7\t25\t9\t5\t49\t15\t2\t5\t4\t2\t3\t5\t14\t16\t14\t27\t1\t5\t3\t5\t5\t15\t5\t1\t3\t0\t2\t13\t50\t28\t20\t8\t10\t11\t10\t8\t5\t7\t5\t6\t8\t22\t8\t5\t9\t15\t9\t7\t5\t15\n+17-alpha-Ethynylestradiol\t12\t5\t6\t9\t8\t9\t5\t3\t7\t4\t6\t6\t17\t12\t23\t7\t6\t3\t8\t9\t12\t14\t6\t6\t4\t0\t3\t4\t10\t2\t5\t7\t8\t5\t10\t14\t7\t17\t7\t10\t4\t15\t3\t4\t3\t5\t6\t6\t12\t8\t1\t3\t5\t34\t15\t19\t5\t5\t35\t4\t9\t7\t37\t13\t13\t7\t5\t3\t6\t1\t1\t4\t47\t15\t13\t2\t3\t3\t1\t2\t0\t9\t3\t1\t8\t15\t5\t11\t5\t15\t8\t1\t27\t7\t3\t3\t4\t2\t2\t2\t9\t6\t9\t22\t2\t2\t1\t2\t6\t11\t5\t1\t2\t0\t2\t7\t30\t19\t18\t5\t8\t5\t6\t4\t8\t9\t5\t6\t4\t21\t2\t3\t6\t8\t9\t5\t5\t10\n+Bisphenol A\t1\t1\t0\t2\t5\t0\t1\t0\t2\t2\t3\t1\t5\t2\t12\t0\t3\t0\t2\t4\t4\t3\t4\t0\t2\t0\t3\t1\t3\t1\t3\t1\t2\t2\t5\t5\t4\t6\t2\t5\t1\t2\t2\t0\t0\t3\t1\t1\t9\t6\t0\t2\t2\t17\t6\t7\t0\t1\t9\t1\t4\t3\t14\t5\t6\t1\t2\t0\t0\t1\t0\t1\t14\t1\t5\t2\t1\t0\t1\t3\t2\t3\t1\t0\t3\t5\t3\t4\t1\t3\t3\t1\t10\t1\t0\t1\t1\t0\t2\t1\t1\t5\t3\t2\t1\t0\t0\t1\t1\t3\t1\t1\t0\t0\t0\t2\t11\t3\t6\t2\t1\t1\t2\t1\t1\t4\t2\t3\t3\t10\t4\t3\t3\t1\t2\t0\t0\t6\n+4-tert-Octylphenol\t1\t3\t0\t3\t3\t1\t2\t0\t1\t0\t2\t0\t3\t2\t5\t0\t0\t0\t1\t0\t1\t1\t1\t0\t0\t0\t0\t1\t0\t1\t0\t1\t2\t1\t1\t0\t0\t1\t1\t2\t0\t2\t0\t0\t0\t1\t1\t1\t2\t0\t0\t0\t1\t3\t3\t5\t1\t1\t5\t0\t0\t0\t0\t4\t3\t0\t0\t0\t0\t0\t0\t0\t3\t1\t0\t0\t2\t0\t0\t0\t0\t1\t0\t0\t0\t0\t2\t1\t0\t0\t0\t0\t2\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t1\t0\t0\t0\t0\t1\t0\t0\t0\t0\t0\t1\t1\t6\t1\t6\t0\t1\t0\t2\t0\t2\t1\t2\t3\t2\t4\t0\t1\t1\t0\t2\t0\t1\t1\n+Estrone\t12\t5\t4\t6\t11\t8\t5\t4\t7\t6\t3\t5\t20\t12\t23\t7\t6\t3\t5\t10\t7\t12\t8\t8\t4\t0\t4\t4\t9\t2\t4\t6\t11\t4\t6\t14\t6\t19\t5\t6\t4\t17\t5\t4\t2\t5\t6\t5\t14\t8\t1\t2\t3\t36\t14\t16\t3\t2\t31\t5\t9\t5\t38\t11\t11\t6\t6\t2\t3\t2\t2\t3\t49\t15\t9\t3\t2\t2\t1\t5\t1\t10\t7\t0\t5\t8\t5\t8\t4\t11\t7\t1\t27\t7\t2\t1\t2\t1\t3\t3\t6\t6\t11\t23\t2\t2\t2\t2\t6\t11\t5\t1\t2\t0\t2\t7\t32\t14\t21\t4\t4\t5\t7\t3\t6\t9\t4\t8\t4\t20\t2\t4\t4\t9\t7\t3\t2\t8\n+17-beta-Estradiol\t7\t2\t4\t4\t4\t3\t4\t1\t8\t3\t4\t6\t18\t7\t14\t5\t6\t3\t5\t8\t10\t10\t7\t5\t5\t0\t4\t4\t10\t4\t4\t3\t7\t4\t5\t12\t8\t16\t3\t3\t3\t12\t3\t2\t2\t3\t6\t3\t9\t8\t2\t2\t3\t33\t10\t9\t5\t2\t25\t5\t8\t6\t36\t8\t9\t5\t3\t3\t0\t1\t1\t4\t40\t8\t7\t1\t1\t1\t0\t2\t0\t6\t2\t0\t5\t8\t3\t9\t2\t9\t5\t1\t23\t7\t2\t2\t1\t1\t3\t1\t4\t6\t7\t17\t1\t2\t0\t2\t5\t9\t4\t1\t2\t0\t1\t4\t26\t9\t13\t4\t4\t4\t4\t1\t2\t6\t4\t3\t3\t12\t0\t1\t3\t4\t5\t1\t2\t5\n+Progesterone\t19\t7\t5\t11\t15\t11\t8\t1\t9\t6\t9\t7\t30\t15\t19\t7\t9\t5\t16\t11\t17\t21\t6\t10\t7\t0\t4\t7\t14\t10\t6\t10\t15\t5\t11\t15\t9\t40\t12\t11\t5\t23\t6\t4\t3\t6\t8\t7\t5\t11\t3\t3\t5\t51\t21\t30\t8\t7\t50\t8\t11\t11\t74\t17\t15\t8\t8\t7\t6\t3\t5\t11\t69\t20\t23\t7\t4\t3\t2\t3\t0\t18\t7\t3\t6\t10\t7\t12\t5\t15\t10\t3\t46\t12\t3\t8\t3\t3\t5\t6\t11\t16\t19\t32\t2\t1\t2\t5\t9\t17\t7\t1\t2\t0\t1\t10\t73\t29\t28\t4\t9\t5\t11\t15\t9\t9\t8\t9\t5\t20\t1\t5\t7\t6\t8\t3\t5\t11\n+Testosterone\t16\t7\t2\t9\t14\t10\t6\t0\t8\t6\t7\t8\t24\t12\t13\t7\t6\t5\t12\t12\t19\t19\t2\t11\t4\t0\t3\t6\t10\t11\t7\t7\t13\t3\t9\t9\t11\t34\t10\t8\t4\t23\t4\t4\t2\t4\t7\t4\t3\t9\t3\t2\t3\t42\t11\t27\t4\t4\t41\t5\t11\t10\t55\t12\t14\t6\t7\t3\t3\t2\t2\t8\t47\t17\t17\t4\t2\t1\t1\t4\t0\t13\t7\t2\t6\t7\t4\t9\t2\t11\t5\t1\t33\t7\t3\t6\t1\t2\t7\t4\t10\t10\t16\t26\t1\t2\t3\t4\t9\t13\t6\t1\t4\t0\t1\t6\t69\t21\t25\t3\t6\t4\t6\t11\t4\t9\t7\t7\t3\t16\t1\t3\t3\t5\t6\t3\t5\t8\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/recetox_gc-ei_ms_20201028.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/recetox_gc-ei_ms_20201028.msp Tue Mar 22 16:07:32 2022 +0000
[
b'@@ -0,0 +1,31986 @@\n+NAME: Perylene_2H12\r\n+SCANNUMBER: -1\r\n+RETENTIONTIME: -1\r\n+RETENTIONINDEX: 2876\r\n+PRECURSORMZ: 264.16858\r\n+PRECURSORTYPE: [M]+\r\n+IONMODE: Positive\r\n+SPECTRUMTYPE: Centroid\r\n+FORMULA: C20H12\r\n+INCHIKEY: CSHWQDPOILHKBI-AQZSQYOVSA-N\r\n+INCHI: \r\n+SMILES: [2H]C1=C(C2=C3C(=C1[2H])C4=C(C(=C(C5=C4C(=C(C(=C5[2H])[2H])[2H])C3=C(C(=C2[2H])[2H])[2H])[2H])[2H])[2H])[2H]\r\n+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)\r\n+COLLISIONENERGY: 70eV\r\n+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS\r\n+INSTRUMENTTYPE: GC-EI-Orbitrap\r\n+IONIZATION: EI+\r\n+LICENSE: CC BY-NC\r\n+COMMENT: \r\n+Num Peaks: 33\r\n+116.05576\t29277\r\n+118.06992\t49651\r\n+128.0558\t37001\r\n+130.06996\t78584\r\n+130.57159\t17533\r\n+132.08408\t65686\r\n+132.5858\t12593\r\n+207.0322\t39569\r\n+222.08282\t13141\r\n+223.06346\t20762\r\n+225.04277\t18058\r\n+227.02202\t26370\r\n+232.11204\t30354\r\n+236.1405\t22796\r\n+252.09322\t8564\r\n+256.11212\t41765\r\n+257.11557\t8688\r\n+258.12622\t21742\r\n+259.13446\t11564\r\n+260.14041\t248997\r\n+261.14358\t51721\r\n+262.15466\t33597\r\n+263.16254\t63732\r\n+264.16858\t829577\r\n+265.01968\t18286\r\n+265.17191\t176460\r\n+266.17523\t18876\r\n+283.03036\t10261\r\n+287.00632\t11352\r\n+295.10288\t26727\r\n+299.06152\t33379\r\n+359.0282\t67046\r\n+400.98447\t17406\r\n+\r\n+NAME: Perylene\r\n+SCANNUMBER: -1\r\n+RETENTIONTIME: -1\r\n+RETENTIONINDEX: 2886.9\r\n+PRECURSORMZ: 252.09323\r\n+PRECURSORTYPE: [M]+\r\n+IONMODE: Positive\r\n+SPECTRUMTYPE: Centroid\r\n+FORMULA: C20H12\r\n+INCHIKEY: CSHWQDPOILHKBI-UHFFFAOYSA-N\r\n+INCHI: \r\n+SMILES: C1=CC2=C3C(=C1)C1=CC=CC4=C1C(=CC=C4)C3=CC=C2\r\n+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)\r\n+COLLISIONENERGY: 70eV\r\n+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS\r\n+INSTRUMENTTYPE: GC-EI-Orbitrap\r\n+IONIZATION: EI+\r\n+LICENSE: CC BY-NC\r\n+COMMENT: \r\n+Num Peaks: 19\r\n+112.03071\t49892\r\n+113.03854\t87510\t"Theoretical m/z 113.039125, Mass diff 0 (0 ppm), Formula C9H5"\r\n+124.03076\t100146\r\n+124.53242\t24923\r\n+125.03855\t179254\t"Theoretical m/z 125.039125, Mass diff 0 (0 ppm), Formula C10H5"\r\n+125.54019\t49039\r\n+126.04636\t131679\r\n+126.54804\t36313\r\n+222.04645\t28905\r\n+224.06192\t55632\r\n+226.04175\t37413\r\n+246.04646\t23286\r\n+248.06204\t140007\r\n+249.07072\t62236\t"Theoretical m/z 249.070425, Mass diff -0.001 (0 ppm), Formula C20H9"\r\n+250.07765\t641789\r\n+251.07967\t137600\r\n+252.09323\t1955166\t"Theoretical m/z 252.093354, Mass diff 0 (0.49 ppm), SMILES C1=CC=2C=CC=C3C4=CC=CC5=CC=CC(C(=C1)C23)=C54, Annotation [C20H12]+, Rule of HR False"\r\n+253.09656\t402252\r\n+254.09985\t39987\r\n+\r\n+NAME: Phenanthrene_2H10\r\n+SCANNUMBER: -1\r\n+RETENTIONTIME: -1\r\n+RETENTIONINDEX: 1827.1\r\n+PRECURSORMZ: 188.14029\r\n+PRECURSORTYPE: [M]+\r\n+IONMODE: Positive\r\n+SPECTRUMTYPE: Centroid\r\n+FORMULA: C14H10\r\n+INCHIKEY: YNPNZTXNASCQKK-LHNTUAQVSA-N\r\n+INCHI: \r\n+SMILES: [2H]C1=C(C(=C2C(=C1[2H])C(=C(C3=C(C(=C(C(=C32)[2H])[2H])[2H])[2H])[2H])[2H])[2H])[2H]\r\n+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)\r\n+COLLISIONENERGY: 70eV\r\n+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS\r\n+INSTRUMENTTYPE: GC-EI-Orbitrap\r\n+IONIZATION: EI+\r\n+LICENSE: CC BY-NC\r\n+COMMENT: \r\n+Num Peaks: 17\r\n+76.02767\t185421\r\n+78.0418\t256858\r\n+80.05586\t881271\r\n+90.04181\t200162\r\n+92.06206\t537968\r\n+94.06999\t628791\r\n+156.08402\t836513\r\n+158.09808\t477819\r\n+160.11218\t2421148\r\n+161.11554\t310248\r\n+176.10866\t308983\r\n+184.11224\t2784543\r\n+185.11562\t445833\r\n+186.12637\t1283282\r\n+188.14029\t15115275\r\n+189.1436\t2312386\r\n+190.14688\t151400\r\n+\r\n+NAME: Phenanthrene\r\n+SCANNUMBER: -1\r\n+RETENTIONTIME: -1\r\n+RETENTIONINDEX: 1832.9\r\n+PRECURSORMZ: 178.0775\r\n+PRECURSORTYPE: [M]+\r\n+IONMODE: Positive\r\n+SPECTRUMTYPE: Centroid\r\n+FORMULA: C14H10\r\n+INCHIKEY: YNPNZTXNASCQKK-UHFFFAOYSA-N\r\n+INCHI: \r\n+SMILES: C1=CC2=C(C=C1)C1=C(C=CC=C1)C=C2\r\n+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)\r\n+COLLISIONENERGY: 70eV\r\n+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS\r\n+INSTRUMENTTYPE: GC-EI-Orbitrap\r\n+IONIZATION: EI+\r\n+LICENSE: CC BY-NC\r\n+COMMENT: \r\n+Num Peaks: 19\r\n+74.01508\t137808\t"Theoretical m/z 74.01565, Mass diff 0 (0 ppm), Formula C6H2"\r\n+75.02295\t278714\t"Theoretical m/z 75.023475, Mass diff 0 (0 ppm), Formula C6H3"\r\n+76.03075\t6'..b'pm), SMILES C=C2CCC1CC(C)CCC1C2(C)C, Annotation [C14H24-7H]+, Rule of HR True"\r\n+187.14806\t422332\t"Theoretical m/z 187.148122, Mass diff 0 (0.33 ppm), SMILES CC2CCC1C(CCCC1(C)(C))C2(C), Annotation [C14H26-7H]+, Rule of HR True"\r\n+188.1559\t151252\t"Theoretical m/z 188.155947, Mass diff 0 (0.25 ppm), SMILES CC2CCC1C(CCCC1(C)(C))C2(C), Annotation [C14H26-6H]+, Rule of HR False"\r\n+189.12735\t68862\t"Theoretical m/z 189.127389, Mass diff 0 (0.21 ppm), SMILES O=C2C=C1CCCC(CC)C1(C)CC2, Annotation [C13H20O-3H]+, Rule of HR True"\r\n+189.16364\t163919\t"Theoretical m/z 189.163772, Mass diff 0 (0.7 ppm), SMILES CC2CCC1C(CCCC1(C)(C))C2(C), Annotation [C14H26-5H]+, Rule of HR True"\r\n+190.13504\t97146\r\n+195.11685\t57370\t"Theoretical m/z 195.117375, Mass diff 0 (0 ppm), Formula C15H15"\r\n+197.13249\t50230\t"Theoretical m/z 197.132481, Mass diff 0 (0.04 ppm), SMILES C=C3CCC2C(CCC1CCCC12)C3C, Annotation [C15H24-7H]+, Rule of HR True"\r\n+199.14803\t221936\t"Theoretical m/z 199.148122, Mass diff 0 (0.46 ppm), SMILES C=C2CCC1C(C)C(C)CCC1C2(C)C, Annotation [C15H26-7H]+, Rule of HR True"\r\n+200.15579\t108028\r\n+201.16364\t216321\t"Theoretical m/z 201.163772, Mass diff 0 (0.65 ppm), SMILES C=C2CCC1C(C)C(C)CCC1C2(C)C, Annotation [C15H26-5H]+, Rule of HR True"\r\n+202.17162\t208618\r\n+203.14304\t1200123\t"Theoretical m/z 203.143035, Mass diff 0 (0.02 ppm), SMILES OC3CCC2C3(CCC1C(C)CCCC12), Annotation [C14H24O-5H]+, Rule of HR True"\r\n+204.14627\t283454\r\n+206.16646\t32118\r\n+209.13243\t45976\t"Theoretical m/z 209.133026, Mass diff 0 (0 ppm), Formula C16H17"\r\n+211.14809\t272618\t"Theoretical m/z 211.148132, Mass diff 0 (-0.2 ppm), SMILES CC1=C(C)C2=C([CH+]CCC=C(C)\\C=C/2)C=C1, Annotation [C16H19]+, Rule of HR True"\r\n+212.15134\t57168\r\n+213.16373\t355360\t"Theoretical m/z 213.163773, Mass diff 0 (-0.2 ppm), SMILES CC1=C(C)C2=C([CH+]CCC=C(C)CC2)C=C1, Annotation [C16H21]+, Rule of HR True"\r\n+214.16698\t92310\r\n+215.143\t60304\t"Theoretical m/z 215.143035, Mass diff 0 (0.16 ppm), SMILES OC3CCC2C3(CCC1C(C(=C)CCC12)C), Annotation [C15H24O-5H]+, Rule of HR True"\r\n+216.15102\t55312\r\n+217.15874\t113508\t"Theoretical m/z 217.158691, Mass diff 0 (0.23 ppm), SMILES OC3CCC2C3(CCC1C2(CCCC1(C)(C))), Annotation [C15H26O-5H]+, Rule of HR True"\r\n+218.16704\t51076\r\n+226.17177\t37673\r\n+227.1797\t204277\t"Theoretical m/z 227.179433, Mass diff 0 (1.18 ppm), SMILES C=C2CCC1C(CC)C(C)CCC1C2(C)CC, Annotation [C17H30-7H]+, Rule of HR True"\r\n+228.1873\t842856\r\n+229.1588\t359919\t"Theoretical m/z 229.158691, Mass diff 0 (0.48 ppm), SMILES OC3CCC2C3(CCC1C2(CCC(=C)C1(C)(C))), Annotation [C16H26O-5H]+, Rule of HR True"\r\n+230.16186\t41138\r\n+231.17433\t428563\t"Theoretical m/z 231.174335, Mass diff 0 (0.02 ppm), SMILES O=C3C=C2CCC1C(C)CCCC1C2(C)CC3, Annotation [C16H24O-H]+, Rule of HR True"\r\n+232.17703\t61957\r\n+237.16373\t184777\t"Theoretical m/z 237.164326, Mass diff 0 (0 ppm), Formula C18H21"\r\n+238.16693\t38109\r\n+241.15854\t66162\t"Theoretical m/z 241.158691, Mass diff 0 (0.62 ppm), SMILES O=C3C=C2CCC1C(CC)CCCC1C2(C)CC3, Annotation [C17H26O-5H]+, Rule of HR True"\r\n+242.16649\t51489\r\n+245.19052\t102650\t"Theoretical m/z 245.189996, Mass diff 0.001 (2.14 ppm), SMILES OC1CCC2C3CCC(=C)C(C)(C)C3(CCC12(C)), Annotation [C17H28O-3H]+, Rule of HR True"\r\n+246.19786\t1126362\r\n+247.2011\t212107\r\n+252.18724\t143505\r\n+255.17436\t288345\t"Theoretical m/z 255.174341, Mass diff 0 (0.08 ppm), SMILES O=C3C=C2CCC1C4CCCC4(CCC1C2(C)CC3), Annotation [C18H26O-3H]+, Rule of HR True"\r\n+256.17764\t54890\r\n+259.16943\t50245\t"Theoretical m/z 259.169244, Mass diff 0 (0.72 ppm), SMILES O=C3C=C2CCC1C(C)C(CO)CCC1C2(C)CC3, Annotation [C17H26O2-3H]+, Rule of HR True"\r\n+260.17758\t70396\r\n+270.19791\t397018\r\n+271.20062\t89701\r\n+273.18549\t199263\t"Theoretical m/z 273.184894, Mass diff 0.001 (2.18 ppm), SMILES O=C3C=C2CCC1C4CCC(O)C4(CCC1C2(C)CC3), Annotation [C18H26O2-H]+, Rule of HR True"\r\n+274.18863\t88305\r\n+288.20841\t1123316\t"Theoretical m/z 288.208375, Mass diff 0 (0.12 ppm), SMILES O=C4C=C3CCC1C(CCC2(C)(C(O)CCC12))C3(C)CC4, Annotation [C19H28O2]+, Rule of HR False"\r\n+289.21173\t220898\r\n+\r\n+\r\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/scores_test1_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/scores_test1_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,175 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+C001\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.01131824210476606\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.048050183216295894\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C002\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\t9.826519226227062e-05\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.058818978905494305\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.012123553350886735\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.003604401443170206\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C003\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001996725260781092\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.003441767933265955\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C004\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t2.962804993140071e-05\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0040278645118103865\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C005\t0.0\t0.0\t0.0\t0.0\t0.9999999999999992\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t'..b'.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.18149359661870704\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C170\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.2793597601790586\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\n+C171\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.030541540271258622\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\n+C172\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.9156381551854462\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\n+C173\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.00045173712879657656\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.14221557456489292\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\n+C174\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/scores_test3_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/scores_test3_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,387 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+Perylene_2H12\t0.0\t0.0\t0.0005256270959446041\t0.0\t0.03073097535576865\t0.0\t0.0\t6.245570704427149e-05\t0.0\t0.0\t0.0\t0.0\t0.004564716964324222\t0.0\t0.0\t0.013203066603708824\t0.0\t0.0\t0.0\t0.00039214513461787934\t0.0\t0.0\t0.0007918167287744314\t0.0\t0.0\t0.0004447561432835879\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.014053019016690342\t0.0\t0.0\t0.0\t0.0\t0.0\t0.010864712316628122\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.1457986453664692\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07136533213674005\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008502864326957613\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008332485011325066\t0.06707997408159612\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.014331972335452473\t0.0\t0.00279044697331512\t0.0\t0.0\t0.0\t0.0\t0.08644538826313944\t0.0\t0.0230223502665467\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.05194618366505897\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07451431952403163\t0.0\t0.0\t0.0\t0.0\t0.008606424963572753\t0.0\t0.0\t0.0\t0.0\t0.0\t0.029465908012253836\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.06765194944236241\t0.0\t0.0\n+Perylene\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0032741303817077237\t0.0\t0.01059895859620056\t0.0\t0.0\t0.011988179251417755\t0.004445067503941489\t0.0\t0.0\t0.0\t0.0\t0.0\t0.010205422020394999\t0.0\t0.0\t0.07094451588225481\t0.0\t0.0\t0.0012435925952213776\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0028113782310797255\t0.0\t0.0\t0.0015057844692663734\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.015722861787553524\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.04875136828344371\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.023395854503055747\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.07014255094522087\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+Phenanthrene_2H10\t0.0024478437470211957\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.044583058787688194\t0.0\t0.0\t0.010556784103056164\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.053243824199748255\t0.0\t0.7408591267092633\t0.0\t0.0\t0.0\t0.0\t0.12202560685242986\t0.04568269717012136\t0.004157278401108382\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.028649962860904238\t0.0\t0.0391645806143903\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.008485163950429123\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.004892255878207329\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.027071584755955534\t0.0\t0.0\t0.0\n+Phenanthrene\t0.00561720665430217\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0014924956391185538\t0.12453944133920959\t0.0\t0.087078422418'..b'5369148999\t0.0\t0.0\t0.0\t0.05477359359289294\t0.014982137997848574\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.011712224528606202\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+Progesterone\t0.009204773873174418\t0.0003433200025161085\t0.0\t0.0007924296222333302\t0.0\t0.0\t0.009441153443328694\t0.005947519671344408\t0.0\t0.0005356814581771544\t0.006215857342936553\t0.0\t0.009417667003961789\t0.009918679539108183\t0.00023339501999512072\t0.02671768716952186\t0.00030790986345821436\t0.0\t0.0\t0.0013743163821902838\t0.01723317359032806\t0.0\t0.031565466787107484\t0.012448459343477094\t0.0\t0.007750527312298496\t0.0070234525583043545\t0.02059761160321701\t0.023913761352649478\t0.011281962106545012\t1.6426994248357484e-05\t0.0\t0.03697516657930819\t0.033662224880288756\t0.0\t0.0\t0.023540677910418206\t0.0\t0.036138976947232074\t0.02542494090112982\t0.0\t0.0\t0.011503400057545196\t0.0\t0.00020822196303031898\t0.0\t0.0\t0.0\t0.0\t0.0014763317286047445\t0.0\t0.0012583838846539634\t0.0\t0.003999037208194656\t0.013710430439412245\t0.0013524730258847118\t0.007867754340786993\t0.040527384587716785\t0.010996257146538806\t0.0\t0.0\t0.06835446607134321\t0.0\t0.0\t0.008591363167784043\t0.0\t0.0\t0.0\t0.0\t0.0\t0.007090284250167511\t0.008465564938609326\t0.08040814196887734\t0.0\t0.028294996723359764\t0.0\t0.0\t0.0038398141926578064\t0.16023981186600048\t0.04805946943116568\t0.037035561711554706\t0.0\t0.0005120942309216829\t0.0\t0.0\t0.03494182656191998\t0.0\t0.0\t0.027888357150312005\t0.01258535522221259\t0.03740123828771993\t0.008517825868349588\t0.00913703375472102\t0.0\t0.0\t0.0\t0.0\t0.0\t0.029300775267851735\t0.0\t0.0\t0.0\t0.01295087988307018\t0.0005955124138932553\t0.0\t0.0\t0.0\t0.005304965226057589\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.039134050766579234\t0.2714869727438596\t0.003527160692631183\t0.0\t0.0\t0.020497841819279862\t0.0\t0.002511329287084922\t0.0\t0.3500845873047567\t0.0\t0.002239902702309837\t0.0\t0.005491138035803363\t0.0\t0.0\t0.011672805021412769\t0.02568290039984708\t0.07006608189710377\t0.018632962351792192\t0.0\t0.04153373284622605\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.00786791970310509\t0.0\t0.047481418502903334\t0.0\t0.0\t0.0\t0.10974594417370813\t0.034291658672408076\t0.0\t0.023165391809283516\t0.0\t0.0\t0.0\t0.0002833417563650782\t0.0\t0.0\t0.0\t0.026807362599866824\t0.003975994609085822\t0.0\t0.0\t0.0\t0.0\t0.0\t0.06458445415629567\t0.013061309028202963\t0.0\t0.0\n+Testosterone\t0.00963321193050066\t0.00024864315729290006\t0.0\t0.00023222574210458811\t0.0009261428396286391\t0.0\t0.0\t0.00040034384039336243\t0.0\t6.734322542065858e-05\t0.0016889974488375878\t0.0\t0.1780813812315969\t0.007271975837211051\t0.0001534940265342155\t0.027912903539727703\t0.0\t0.0\t0.0\t0.0005797401705402813\t0.01109882605223559\t0.0\t0.024485309434567656\t0.020836980610370613\t0.0\t0.004730656796420955\t0.009055625850088012\t0.01764485751937845\t0.0342974876068616\t0.003171910470299864\t0.0\t0.0\t0.039580956813763224\t0.008699485073663131\t0.0\t0.0\t0.027921629937492445\t0.0\t0.011883152521337894\t0.00473955367711716\t0.0\t0.0\t0.06041370798509162\t0.0\t0.042697154051077546\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0028714022903154834\t0.021418156386493012\t0.0015186515255164064\t0.006270179831850896\t0.029915893967898583\t0.00688460931497788\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001333543171051696\t0.0\t0.08702752210600657\t0.0\t0.03171198034450119\t0.0\t0.0\t0.0\t0.0\t0.0007660193758873158\t0.010813507002141582\t0.0\t0.0\t0.0\t0.0\t0.004200894168035819\t0.0\t0.0\t0.02349484368553467\t0.01816654272894712\t0.06339867284692742\t0.00859117181156952\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.11646566920503162\t0.0\t0.0\t0.0\t0.0\t0.0031342530947578136\t0.0\t0.15489171142643712\t0.0\t0.013048242174815912\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001658310433454475\t0.03949452321180806\t0.0\t0.0\t0.0\t0.021990926351807643\t0.0\t0.13014922112429483\t0.0\t0.18331721895001493\t0.0\t0.0014411200837741657\t0.0\t0.0\t0.0\t0.0\t0.010921053413542842\t0.00943243671087211\t0.06421886680272976\t0.025882956568067213\t0.0\t0.03618383380922253\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0006655628265325035\t0.0\t0.026485058850513155\t0.0\t0.0\t0.0\t0.10783284756046711\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.12344754627650137\t0.0\t0.0\t0.0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/scores_test4_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/scores_test4_out.tsv Tue Mar 22 16:07:32 2022 +0000
[
b"@@ -0,0 +1,387 @@\n+\tPerylene_2H12\tPerylene\tPhenanthrene_2H10\tPhenanthrene\tAnthracene\tAcenaphthylene\tAcenaphthene\tFluoranthene\tPyrene\tpara-Terphenyl\tRetene\tBenzo[b]naphtho[2,1-d]thiophene\t2,3-Benzofluorene\tBenzo[ghi]fluoranthene\tTriphenylene\tBenzanthracene/Benzophenanthrene\tBenzofluoranthene\tBenzo(k)fluoranthene\tBenzo[e]pyrene\tBenzo(a)pyrene\tIndeno[1,2,3-cd]pyrene\tBenzo(g,h,i)perylene\tAnthanthrene\tDibenzanthracene\tCoronene\tDicofol\tBenzophenone\t2-tert-Butyl-4-methoxyphenol\tButylated hydroxytoluene\tBumetrizole\t4-Methylbenzophenone\t2,4,6-Tribromophenol\t2,6-Dichloro-4-nitroaniline\t1-Methylphenanthrene\tTriclosan\tDrometrizole\tEnzacamene\t2,4-Di-tert-butyl-6-(5-chloro-2H-benzotriazol-2-yl)phenol\tOctrizole\t1,2,7,9-Tetrachlorodibenzofuran\t2,2',3,4,5,5',6-Heptachlorobiphenyl\t2,4,6-Trichlorobiphenyl\t2,2',3,3',4,5',6,6'-Octachlorobiphenyl\tMirex\tbeta-Hexachlorocyclohexane\talpha-1,2,3,4,5,6-Hexachlorocyclohexane\tLindane\tdelta-Hexachlorocyclohexane\tepsilon-Hexachlorocyclohexane\tPentachlorobenzene\tHexachlorobenzene\t2,4'-Dichlorodiphenyldichloroethylene\t2,4'-Dichlorodiphenyldichloroethane\t2,4'-Dichlorodiphenyltrichloroethane\t1,2,7,9-Tetrachlorodibenzo-p-dioxin\t2,4,4'-Trichlorobiphenyl\t2,2',4,5,5'-Pentachlorobiphenyl\t2,3',4,4',5-Pentachlorobiphenyl\t2,2',3,4,4',5'-Hexachlorobiphenyl\t2,2',4,4',5,5'-Hexachlorobiphenyl\t2,2',3,4,4',5,5'-Heptachlorobiphenyl\t2,2',5,5'-Tetrachlorobiphenyl\t2,3',4,6-Tetrachlorobiphenyl\t2,3',5',6-Tetrachlorobiphenyl\t2,2',3,4',5-Pentachlorobiphenyl\t2,3,3',4,5-Pentachlorobiphenyl\t3,3',4,5,5'-Pentachlorobiphenyl\t2,3',4,4',5',6-Hexachlorobiphenyl\t2,3,3',4,5,6-Hexachlorobiphenyl\t2,3,3',4',5',6-Hexachlorobiphenyl\t2,3,3',4',5,6-Hexachlorobiphenyl\t2,3,3',4',5,5',6-Heptachlorobiphenyl\tcis-Prallethrin\ttrans-Prallethrin\tcis-Resmethrin\ttrans-Resmethrin\tcis-Tetramethrin\ttrans-Tetramethrin\tBifenthrin\tFenpropathrin\tcis-Phenothrin\ttrans-Phenothrin\tcis-Cyphenothrin\ttrans-Cyphenothrin\tFlucythrinate_isomer1\tFlucythrinate_isomer2\tcis-Fenvalerate\ttrans-Fenvalerate\tDeltamethrin\tChlorpyrifos oxon\tlambda-Cyhalothrin\tTefluthrin\tTransfluthrin\tcis-Permethrin\ttrans-Permethrin\tcis-Allethrin\ttrans-Allethrin\tcis-Cypermethrin_isomer1\ttrans-Cypermethrin_isomer1\tcis-Cypermethrin_isomer2\ttrans-Cypermethrin_isomer2\tcis-Cyfluthrin_isomer1\ttrans-Cyfluthrin_isomer1\tcis-Cyfluthrin_isomer2\ttrans-Cyfluthrin_Isomer2\t1,2,3,4,7,8-Hexachlorodibenzo-p-dioxin\t1,2,3,4,6,7,8-Heptachlorodibenzo-p-dioxin\tOctachlorodibenzo-p-dioxin\tOctachlorodibenzofuran\t1,2,3,7,8-Pentachlorodibenzofuran\t1,2,3,4,7,8-Hexachlorodibenzofuran\t1,2,3,4,6,7,8-Heptachlorodibenzofuran\t2,3,7,8-Tetrachlorodibenzofuran\t2,3,7,8-Tetrachlorodibenzo-p-dioxin\t1,2,3,7,8-Pentachlorodibenzo-p-dioxin\t2,3,4,5-Tetrabromo-6-chlorotoluene\t2,3,4,5,6-Pentabromotoluene\t2,3,4,5,6-Pentabromoethylbenzene\t2,3,5,6-Tetrabromo-p-xylene\tAllyl 2,4,6-tribromophenyl ether\t2-Bromoallyl(2,4,6-tribromophenyl) ether\tPentabromobenzene\tHexabromobenzene\t2,3,4,5,6-Pentabromobenzyl alcohol\t2-Ethylhexyl 2,3,4,5-Tetrabromobenzoate\tsyn-Dechlorane plus\tanti-Dechlorane plus\talpha-1,2-Dibromo-4-(1,2-dibromoethyl)cyclohexane\tbeta-1,2-Dibromo-4-(1,2-dibromoethyl)cyclohexane\t1,2,5,6-Tetrabromocyclooctane\t1,1-Dibromo-2,3,3,4,4,5-hexachloro-2-cyclopenta-2,4-dien-1-ylcyclooctane\talpha-Amylcinnamaldehyde\ttrans-Cinnamaldehyde\tCitral (Geranial)\t1-Fluronaphthalene\talpha-Hexylcinnamaldehyde\tLilial\talpha-Amylcinnamyl alcohol\tEugenol\tIsoeugenol\t4-Methoxybenzyl alcohol\tMethyleugenol\tCinnamyl alcohol\tBenzyl alcohol\tEstragole\tBenzyl benzoate\tBenzyl cinnamate\tBenzyl salicylate\tCamphor\tEucalyptol\tCoumarin\tLimonene\tIsomethyl-alpha-ionone\tdelta-Iraldeine\tSafrole\tCashmeran\tCelestolide\tPhantolide\tTonalide\tTraseolide\tGalaxolide\tAldrin\tEndosulfan\tHeptachlor\tcis-Heptachlor epoxide\tEndosulfan sulphate\tEndrin ketone\ttrans-Chlordane\tcis-Chlordane\tEndrin aldehyde\tEndrin\t4,4'-Dichlorodiphenyldichloroethylene\tMethoxychlor\t4,4'-Dichlorodiphenyldichloroethane\t4,4'-Dichlorodiphenyltrichloroethane\tTris(4-tert-butylphenyl) phosphate\tTri-n-butyl-phosphate\tTris(1,3-dichloro-2-propy"..b'99004\t0.25699522150266857\t0.10086896866641386\t0.19470204063894617\t0.11098877289750769\t0.006075991834095414\t0.12927366381808264\t0.2082286991025265\t0.27240094810916426\t0.1654349689057302\t0.19840999142874\t0.16569982850423232\t0.2161122709425279\t0.14188794086609754\t0.13892041895889107\t0.163316162934255\t0.19714612348281121\t0.11328276368401106\t0.1797393737639574\t0.11912510425789868\t0.1513410655357927\t0.17376963876857818\t0.11727276196549535\t0.18242398225791773\t0.42587475586474854\t0.26019712746688456\t0.14368704499704515\t0.2071878076412335\t0.09453837918890001\t0.17883495196186588\t0.230407695094039\t0.2003708220640954\t0.28221288790938787\t0.1632240149541304\t0.33569524175870596\t0.3064105089065634\t0.06757663229398125\t0.1875387758604876\t0.14809372567415943\t0.0852574772349589\t0.038518437729193764\t0.1694183013806351\t0.15289185256222845\t0.1323269305931256\t0.14183815846488648\t0.11892832652180535\t0.12040055943475189\t0.055133306975097635\t0.059734777165814525\t0.0566711436003959\t0.10411276944449463\t0.09983202384693853\t0.038921466584489514\t0.0866119306764878\t0.06992238111265867\t0.09431159408139042\t0.0938643626333852\t0.08034523157647287\t0.30621301093750836\t0.1961893280957181\t0.1611360617918086\t0.23758939346985095\t0.12271395237074852\t0.1430157698712594\t0.0833933983294341\t0.035843502317569234\t0.1633740133739675\t0.1483671806190231\t0.13613729576468475\t0.13641339521522466\t0.10219746530932572\t0.24528101783913517\t0.22010021314888892\t0.17232404535039347\t0.17930641471345765\t0.15547769438760414\t0.1764623247344844\t0.08065948881320073\t0.19144552461877729\t0.3183099871734532\t0.06306342224555873\t0.05987974210984678\t0.05740354384209485\t0.20721138046115542\t0.328456758896439\t0.32098885468030136\t0.23821868337793292\t0.07145396369303544\t0.19081119513093286\t0.057616601871621285\t0.2340183931599587\t0.23822558856834722\t0.06797270073648182\t0.43003853617809873\t0.02792424887822149\t0.18822156250959438\t0.16114686619257262\t0.22810608062777601\t0.0838224184080167\t0.08443319924123477\t0.1894850392430079\t0.265083072227541\t0.10874839217026484\t0.21783385621466414\t0.006793839193263404\t0.08475249990448121\t0.12988582068761828\t0.2837084520725496\t0.07764215735572715\t0.08398679648212394\t0.09380315448372266\t0.21450922103222061\t0.27742281155579906\t0.04435157844941482\t0.35472454340204307\t0.3010423011492258\t0.06572111033523048\t0.35449933960739016\t0.184212014644299\t0.16510341696367972\t0.22650136131747978\t0.08545503348016772\t0.054746540083621745\t0.07158142375321293\t0.05222918108605921\t0.29873505869435935\t0.1592048730563699\t0.12242150172343544\t0.06834825436267856\t0.11787482883203612\t0.06533075716795377\t0.29220597270428633\t0.3204987910247821\t0.23075740046511872\t0.16013387140172308\t0.1031810078648983\t0.11609557607181138\t0.06536501695877456\t0.07528353746322132\t0.14631099884719126\t0.31686299036015636\t0.15686508283056178\t0.2502894060505306\t0.15632555985381263\t0.06157073783891902\t0.17850524434839174\t0.15082352190116588\t0.10496525194001774\t0.0328681907045638\t0.24179240409750177\t0.20560588522808376\t0.2271655674450096\t0.218989372412798\t0.09854462852017379\t0.1117782001836314\t0.32586231433297036\t0.16492586594387235\t0.1863221551020623\t0.23621550072877454\t0.12483921692480258\t0.16889581762525904\t0.03249926663036536\t0.015295084861858975\t0.20368054392043403\t0.18965962379608556\t0.1016530064450796\t0.12816683398762763\t0.06555661306024704\t0.022930759762077174\t0.019231613914197573\t0.15747279820504434\t0.088105124422038\t0.34732800952940357\t0.12915213761674713\t0.026497694389320044\t0.07320003712462311\t0.15992895420273134\t0.04418658553634053\t0.22031587132600947\t0.10334439566995825\t0.054857312240601364\t0.14588090116315752\t0.0720775597079632\t0.2322377084263006\t0.009182131128330325\t0.08725499132616112\t0.23335439715459685\t0.26456927574996886\t0.20593724958472245\t0.16953436023943352\t0.2915911520785385\t0.1972305838560561\t0.061557676013784396\t0.08503438513801481\t0.16053915107475406\t0.14738299237590127\t0.3485715331892874\t0.331614755581215\t0.149139047638064\t0.14441111333967438\t0.3881349843527812\t0.3574090148392564\t0.8662836910447197\t1.0\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/scores_test5_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/scores_test5_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,175 @@\n+\tC001\tC002\tC003\tC004\tC005\tC006\tC007\tC008\tC009\tC010\tC011\tC012\tC013\tC014\tC015\tC016\tC017\tC018\tC019\tC020\tC021\tC022\tC023\tC024\tC025\tC026\tC027\tC028\tC029\tC030\tC031\tC032\tC033\tC034\tC035\tC036\tC037\tC038\tC039\tC040\tC041\tC042\tC043\tC044\tC045\tC046\tC047\tC048\tC049\tC050\tC051\tC052\tC053\tC054\tC055\tC056\tC057\tC058\tC059\tC060\tC061\tC062\tC063\tC064\tC065\tC066\tC067\tC068\tC069\tC070\tC071\tC072\tC073\tC074\tC075\tC076\tC077\tC078\tC079\tC080\tC081\tC082\tC083\tC084\tC085\tC086\tC087\tC088\tC089\tC090\tC091\tC092\tC093\tC094\tC095\tC096\tC097\tC098\tC099\tC100\tC101\tC102\tC103\tC104\tC105\tC106\tC107\tC108\tC109\tC110\tC111\tC112\tC113\tC114\tC115\tC116\tC117\tC118\tC119\tC120\tC121\tC122\tC123\tC124\tC125\tC126\tC127\tC128\tC129\tC130\tC131\tC132\tC133\tC134\tC135\tC136\tC137\tC138\tC139\tC140\tC141\tC142\tC143\tC144\tC145\tC146\tC147\tC148\tC149\tC150\tC151\tC152\tC153\tC154\tC155\tC156\tC157\tC158\tC159\tC160\tC161\tC162\tC163\tC164\tC165\tC166\tC167\tC168\tC169\tC170\tC171\tC172\tC173\tC174\n+C001\t1.0000000000000002\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.011318242104766061\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0480501832162959\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C002\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\t0.0\t9.826519226227063e-05\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.05881897890549432\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.012123553350886737\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0036044014431702073\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C003\t0.0\t0.0\t0.9999999999999999\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.001996725260781092\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0034417679332659546\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C004\t0.0\t0.0\t0.0\t0.9999999999999998\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t2.96280499314007e-05\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0040278645118103865\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\n+C005\t0.0\t0.0\t0.0\t0.0\t0.9999999999999999\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t'..b'0.0\t0.0\t0.0\t0.0\t0.18149359661870704\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.9999999999999998\t0.0\t0.0\t0.0\t0.0\t0.0\n+C170\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.2793597601790586\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0\t0.0\t0.0\t0.0\t0.0\n+C171\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.030541540271258626\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0000000000000002\t0.0\t0.0\t0.0\n+C172\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.9156381551854463\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0000000000000002\t0.0\t0.0\n+C173\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.00045173712879657656\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.14221557456489292\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0000000000000002\t0.0\n+C174\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t0.0\t1.0000000000000002\n'
b
diff -r 000000000000 -r 30e680e555d4 test-data/similarity/scores_test6_out.tsv
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/similarity/scores_test6_out.tsv Tue Mar 22 16:07:32 2022 +0000
b
b'@@ -0,0 +1,387 @@\n+\tC041\tC078\tC115\tC072\tC050\tC069\tC108\tC121\tC085\tC122\tC114\tC084\tC014\tC029\tC006\tC113\tC107\tC129\tC037\tC092\tC021\tC016\tC109\tC079\tC116\tC123\tC135\tC134\tC070\tC056\tC062\tC082\tC061\tC133\tC087\tC025\tC096\tC009\tC075\tC052\tC130\tC015\tC060\tC131\tC132\tC073\tC090\tC091\tC007\tC074\tC104\tC102\tC103\tC001\tC042\tC010\tC127\tC101\tC004\tC110\tC086\tC051\tC002\tC032\tC039\tC057\tC105\tC095\tC033\tC137\tC138\tC066\tC003\tC040\tC011\tC043\tC106\tC048\tC128\tC058\tC088\tC031\tC100\tC053\tC081\tC023\tC099\tC049\tC044\tC017\tC064\tC098\tC008\tC077\tC119\tC094\tC093\tC124\tC083\tC063\tC035\tC047\tC024\tC022\tC097\tC076\tC030\tC118\tC126\tC038\tC080\tC136\tC117\tC125\tC112\tC026\tC005\tC013\tC034\tC046\tC055\tC071\tC036\tC027\tC067\tC120\tC111\tC068\tC089\tC028\tC045\tC059\tC054\tC018\tC012\tC065\tC020\tC019\n+Perylene_2H12\t0.034042320821081655\t0.0\t0.009403305812291722\t0.0\t0.0\t0.0007629860430236488\t0.0\t0.02266571495909087\t0.0\t0.00042930183801011794\t0.0010942178146441293\t0.0\t0.0001117117003335653\t0.05556820858114851\t0.03887203120835998\t0.021564634193163717\t0.0022083391714712306\t0.0\t0.0004061839030021898\t0.0\t0.0018210079574397177\t0.0044706250747301906\t0.01250288907877498\t0.006335694044596287\t0.003011359279134579\t0.0\t0.0\t0.003930271682883756\t0.029864036675543378\t0.033018049711041476\t0.0004687982349281314\t0.007804473039067054\t0.002244789787464286\t0.029628841784107067\t0.014383091871802837\t0.014161550072453797\t0.001128422100278789\t0.013544568179924128\t0.0\t0.00132564265609464\t0.011781737207632755\t0.05804594652851786\t0.0004594194032417144\t0.0\t0.022569744034791155\t0.003620342432401012\t0.0\t0.0\t0.03613854198839842\t0.0286726434703242\t0.001143688038067479\t0.005799936661442363\t0.13493653247562692\t0.002638979226994201\t0.028778571241930968\t0.029072485853110962\t0.013627299382366974\t0.0\t0.017403160411527552\t0.0\t0.01696060588991595\t0.03346178919132061\t0.006537280745228869\t0.2724163273071701\t0.0011885136685260815\t0.0\t0.0\t0.0\t0.01407550398904445\t0.0\t0.0\t0.007488357223206149\t0.0054751753426494736\t0.04711906877095722\t0.016701752360186138\t0.0\t0.0003863811526605843\t0.09590552038673016\t0.0016953565887339343\t0.0\t0.0\t0.0011884667247023498\t0.0005586376752260124\t0.0\t0.0\t0.009836286834224597\t0.031057411717545502\t0.020241422379465534\t0.0017303898195810917\t0.01643181731678299\t0.006973253922278287\t0.0029680242363230892\t0.01637963228496475\t0.0027421080262169137\t0.004213724397739657\t0.004913056324491477\t0.0\t0.01662703683355905\t0.09138073163058372\t0.0007929414781066192\t0.0009284532952288166\t0.0032169859262519544\t0.00042486350067965484\t0.020684766458239814\t0.0\t0.009401490687877585\t0.0001566128276370904\t0.0\t0.0\t0.01845259904863743\t0.010148692871241129\t0.0\t0.0\t0.0\t0.0\t0.011101259469173343\t0.004936023674032282\t0.074777491052486\t0.004057752902340233\t0.0\t0.0042980737432896194\t0.0019457316265322528\t0.010236242948902087\t0.009683977809973808\t0.010313078597559113\t0.0\t0.01973961112268132\t0.003127566702438563\t0.0015951608764421129\t0.026946864038107345\t0.0\t0.0\t0.04404385643133546\t0.008207060848564535\t0.009884819221109377\t0.00021371301103211425\t0.0\t0.017348705935088908\n+Perylene\t0.0\t0.0\t0.0\t0.0011051022816824852\t0.000542635114331976\t0.0\t0.001974323722348113\t0.0\t0.00036528875300253366\t0.0\t0.0\t0.0\t0.00014947393267217954\t0.0010447997154295929\t0.00010856751348875029\t0.0\t0.0\t0.0\t0.0954644571424393\t0.0013743898833611904\t0.0\t0.00010959251829602013\t0.004400336771811676\t0.005640218359074094\t0.0034705539472536817\t0.0\t0.0007418715312107792\t0.0\t0.00484873460276118\t0.0\t9.037583761987847e-05\t0.000622866201243807\t0.001347941327641855\t0.001852257860353395\t0.004606412002464841\t0.006353382143201052\t0.0\t0.015172321265656215\t0.0009621639812959181\t0.00019203912971202535\t0.0\t0.002656194724082899\t0.0018101204979896026\t0.0\t0.01595010968620319\t0.00010352564653640499\t0.05326947187783303\t0.0\t2.180451050181285e-05\t0.0013102161710618133\t0.0\t0.00016015256120527178\t0.00034724475140860604\t0.0001415619197232959\t0.0\t0.0004607881598805477\t0.0\t0.00031825716888322155\t0.0008604144211635554\t0.0\t0.018538826563359888\t0.0006458912475918673\t0.006566648646852698\t0.08002800104674827\t0.0\t0.03711581410513316\t0.004394308382007739\t0'..b'83988276892\t0.0035207292343569317\t0.10987461344359015\t0.0995552931947784\t0.0\t0.02603057882086362\t0.009163429668087301\t0.02701827652600082\t0.022851348027207164\t0.04035205759985755\t0.04134708497797248\t0.026834397514291654\t0.036093227930548616\t0.049759012683381856\t0.06076472314328744\t0.0038450623653801695\t0.06544561163320242\t0.06983291785111552\t0.03160141790195927\t0.07628840476846281\t0.005542902834667562\t0.013414348590015168\t0.044447880021334804\t0.01875953929934765\t0.018835245212120343\t0.11131586647362307\t0.04963681669908816\t0.07105010197627538\t0.011450582126856977\t0.0011712769771746697\t0.016098230627855103\t0.08322073490829028\t0.23390437333814124\t0.16039438008281268\t0.06954275494932319\t0.0024221700476814824\t0.00515804448520173\t0.0\t0.006769627476754328\t0.07889307267504196\t0.2685116670683215\t0.06358431078870092\t0.45729034645969496\t0.02451177284259372\t0.022641541906193757\t0.03192716680053657\t0.023420455855089645\t0.04691670387498694\t0.09237915075575202\t0.14564090824538856\t0.061712990090093754\t0.027358994739280263\t0.2626873489921074\t0.015328708395240063\t0.004284778300052697\t0.025826592848464523\t0.04489331319056179\t0.0060044469175185656\t0.013332538298288591\t0.012104481515422903\t0.01788173240386975\t0.017753153886406584\n+Testosterone\t0.01832692827067662\t0.25708889616547254\t0.016914214486909\t0.010497459637120093\t0.011292136765007413\t0.07854326470849173\t0.051828612471147714\t0.0\t0.11096263600615171\t0.03803625569335047\t0.015466574193938263\t0.017464224629416103\t0.0396498515658372\t0.032589892401115664\t0.0026573741974754107\t0.0726094461747022\t0.02206836401133249\t0.024890595444292736\t0.013977499326825365\t0.07313925552406138\t0.04916903577114806\t0.04487541380179884\t0.04595696180372116\t0.04744571805625805\t0.023246262561604055\t0.0\t0.03289082001742213\t0.04884873910759355\t0.048168833082862426\t0.015585669464735831\t0.01209683117745796\t0.052398588924045406\t0.047567855409756755\t0.06615763961573513\t0.060938760179256146\t0.01190326771842562\t0.03956148300556824\t0.17890025658323153\t0.05591745580873676\t0.02052732719153347\t0.13675793453833146\t0.08604104970406877\t0.02492325451805615\t0.007729713027817932\t0.0046637252740731406\t0.05714734644623649\t0.07364438632599457\t0.05511099607220748\t0.000679415365897095\t0.0418936622077723\t0.008561483499184369\t0.03557953743498848\t0.01586924211004424\t0.08684508499736211\t0.026287115042115554\t0.07301044868347491\t0.07768802849611274\t0.019715395473745297\t0.08442913483594439\t0.01607198520998351\t0.022453348279262646\t0.03197257076686277\t0.041931622310372695\t0.05750504025406854\t0.011916728202806962\t0.01333295417764225\t0.012399253949021666\t0.02808811327069467\t0.0017074187504466961\t0.009967834769456748\t0.02085554563859335\t0.04997999547771599\t0.07382128524155089\t0.0592555937705767\t0.017659881197733138\t0.011889639783467538\t0.012176004401160437\t0.0004723102800365613\t0.016649821311006625\t0.027469483924424637\t0.0\t0.05594561264602909\t0.012288159447706781\t0.007666303250554177\t0.016540735726608774\t0.023082025894639396\t0.026639982888311486\t0.04448912738354493\t0.009933275607301548\t0.05341603733927623\t0.04602566615753049\t0.017005814943264502\t0.041353430266686524\t0.023668803021640105\t0.01360918918861156\t0.04440523963398467\t0.006955417605978499\t0.012764216194926174\t0.025888417423570304\t0.01834094573679885\t0.05957704402307372\t0.027036820079779453\t0.053440578853859756\t0.038509279502523946\t0.012270337045054125\t0.017373773531144204\t0.02012565918099467\t0.03949543012957574\t0.19810047128279942\t0.15106267412048285\t0.0439090832339104\t0.002894347700864888\t0.04555678906035976\t0.0\t0.006309598786227622\t0.03377929250085494\t0.29261470974897175\t0.054180994026571\t0.5075004294506457\t0.011524692855668317\t0.025537735184035078\t0.014312333948356435\t0.01295964420252676\t0.029658562360474372\t0.05668464836056643\t0.16354511815610986\t0.06606186066097765\t0.033704054022056514\t0.32384244954413266\t0.015660645267203253\t0.007194353196421112\t0.014491355395205706\t0.018079814914925284\t0.006996524338430169\t0.013851529589089768\t0.011755444979303921\t0.014872175594096931\t0.005640163093614845\n'