Repository 'proteomics_moff'
hg clone https://toolshed.g2.bx.psu.edu/repos/galaxyp/proteomics_moff

Changeset 0:b4098353ee73 (2018-01-05)
Next changeset 1:8f0e76ad46ef (2018-01-18)
Commit message:
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/moFF commit bc0fad49e3ba73fa5b5b326e940adf9e11854d94
added:
moff.xml
test-data/input/mbr_output/mbr_test1_match.txt
test-data/input/mbr_output/mbr_test2_match.txt
test-data/input/mbr_test1.mzml
test-data/input/mbr_test1.tabular
test-data/input/mbr_test2.mzml
test-data/input/mbr_test2.tabular
test-data/input/test.mzml
test-data/input/test.tabular
test-data/make_test_data.sh
test-data/output1/mbr_test1_match_moff_result.txt
test-data/output1/mbr_test2_match_moff_result.txt
test-data/output2/moff_test_pepsum.tab
test-data/output2/test_moff_result.txt
b
diff -r 000000000000 -r b4098353ee73 moff.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/moff.xml Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,407 @@\n+<tool id="proteomics_moff" name="moFF" version="@VERSION@">\n+    <description>extracts MS1 intensities from spectrum files</description>\n+    <macros>\n+        <token name="@VERSION@">1.2</token>\n+        <!-- xml macros, used for shared Galaxy parameter inputs -->\n+        <xml name="ident_input_macro" token_allow_multiple="true" token_input_type="data">\n+        <!-- this is exactly the same across all three, except for allowing multiple in MBR and all but not in moff -->\n+            <conditional name="ident_input">\n+                    <param name="input_type_selector" type="select" label="Choose the format for the identification file:">\n+                        <option value="ps">Peptide Shaker PSM report (standard, not extended)</option>\n+                        <option value="generic">Another tabular identification file</option>\n+                    </param>\n+                    <when value="ps">\n+                        <param name="ident_input_file" type="@INPUT_TYPE@" format="tabular" label="Peptide Shaker PSM report" multiple="@ALLOW_MULTIPLE@"/>\n+                    </when>\n+                    <when value="generic">\n+                        <param name="ident_input_file" type="@INPUT_TYPE@" format="tabular" label="A general tabular format" multiple="@ALLOW_MULTIPLE@"\n+                            help="Must have specific columns; see below to select these columns from your file. The file should have at most one header line. "/>\n+                        <param name="remove_header" type="boolean" value="false" label="Remove the header line?" help="This is necessary if the file has a line with column headers"/>\n+                        <param name="peptide"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with peptide-spectrum-match sequence"/>\n+                        <param name="prot"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with protein ID"/>\n+                        <param name="mod_peptide"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with peptide-spectrum-match sequence that contains possible modifications"/>\n+                        <param name="rt"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with PSM retention time (in second)"/>\n+                        <param name="mz"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with m/z (mass over charge)"/>\n+                        <param name="mass"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with mass of the peptide"/>\n+                        <param name="charge"\n+                            type="data_column"\n+                            data_ref="ident_input_file"\n+                            label="Column with charge of ionized peptide"/>\n+                    </when>\n+            </conditional>\n+        </xml>\n+        <xml name="raw_input_macro" token_allow_multiple="true" token_input_type="data">\n+            <conditional name="msms_input">\n+                <param name="input_type_selector" type="select" label="Choose the format for the MS/MS file">\n+                    <option value="raw">Thermo RAW file</option>\n+                    <option value="mzml">mzML</option>\n+                </param>\n+                <when value="raw">\n+                    <param argument="--inputraw" type="@INPUT_TYPE@" multiple="@ALLOW_MULTIPLE@" format="raw" label="RAW file(s)"/>\n+                </when>\n+                <when value="mzml">\n+             '..b'-->\n+        <test>\n+            <param name="task_selector" value="mbr"/>\n+            <param name="input_type_selector" value="ps"/>\n+            <param name="ident_input_file">\n+                <collection type="list">\n+                    <element name="mbr_test1" value="input/mbr_test1.tabular"/>\n+                    <element name="mbr_test2" value="input/mbr_test2.tabular"/>\n+                </collection>\n+            </param>\n+            <param name="ext" value="tabular"/>\n+            <output_collection name="ident_output" type="list" count="2">\n+                <element name="mbr_test1_match" file="input/mbr_output/mbr_test1_match.txt"/>\n+                <element name="mbr_test2_match" file="input/mbr_output/mbr_test2_match.txt"/>\n+            </output_collection>\n+        </test>\n+    </tests>\n+    <help>\n+    <![CDATA[\n+**Description**\n+\n+moFF (a Modest Feature Finder) is an OS independent tool designed to extract\n+apex MS1 intensity using a set of identified MS2 peptides.\n+It currently uses a Go library to directly extract data from Thermo Raw spectrum files,\n+eliminating the need for conversions from other formats.\n+Moreover, moFF also allows one to work directly with mzML files.\n+\n+**Usage**\n+\n+*Modules:*\n+\n+1. Apex Intensity: this is used for a single pair of files, one identification and one spectrum file. \n+2. Match between runs (MBR): for multiple identification files, share MS2 identified peptides between runs and predict the retention time.\n+3. All (match between runs followed by apex intensity): this is used for more than one pair of identification and spectrum files.\n+\n+If both match between runs and apex intensity are desired, it is best to run them both at once (i.e., run the \'All\' module).\n+The MBR module is mainly useful for observing the intermediate steps of the algorithm - its outputs are not able to be used as inputs in moFF or in other tools.\n+\n+\n+*Inputs:*\n+\n+- Identification file: this can either be a generic tabular file or the standard PSM report from PeptideShaker.\n+  If it is a generic tabular file, please select the columns corresponding to the required information.\n+\n+- MS/MS file: this can either be a Thermo raw file or an mzML file.\n+\n+A given pair of files must have the *exact* same display name, not including the extension;\n+e.g. ``example1.tabular`` and ``example1.mzml``.\n+If the display names are different, simply change them in the history menu.\n+\n+For multiple files (the MBR or All modules), the identification and spectrum files must be provided as dataset collections.\n+This allows for usage of the output dataset collections in workflows.\n+\n+*Parameters:*\n+\n+All the parameters related to the the time windows (``rt_w``, ``rt_p``, ``rt_p_match``) are basically the\n+half of the entire time windows where the apex peak is searched or the XIC is retrieved.\n+For correct rt windows, we suggest you set the ``rt_p`` value equal to or slighly greater than the\n+dynamic exclusion duration set in your machine. We suggest also to set the\n+``rt_p_match`` always slightly bigger than tha values used for ``rt_p``.\n+\n+*Outputs:*\n+\n+When used in the single file mode ("Apex intensity" module), the outputs are 2 (or 3) files: a log file, a quantitation file,\n+and (optionally) a peptide summary, with intensities aggregated across peptides. When used in the multiple file mode ("All"),\n+the outputs are a dataset collection of log files (one per identification file), a dataset collection of quantification files, and (optionally) a peptide summary.\n+\n+If used with a generic tabular format, the only columns in the output file are the 7 columns selected while using moFF plus the columns that moFF adds. Other columns are discarded.\n+\n+**More Information**\n+\n+See the moFF Github site at https://github.com/compomics/moFF, \n+and the publication at https://dx.doi.org/10.1038/nmeth.4075 \n+\n+    ]]>\n+    </help>\n+    <citations>\n+        <citation type="doi">10.1038/nmeth.4075</citation>\n+    </citations>\n+</tool>\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_output/mbr_test1_match.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_output/mbr_test1_match.txt Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,265 @@\n+aas after\taas before\tcharge\tcode_unique\tconfidence [%]\td-score\tfixed modifications\tidentification charge\tisotope number\tlocalization confidence\tmass\tmatched\tmod_peptide\tmz\tpeptide\tposition\tprecursor m/z error [ppm]\tprobabilistic ptm score\tprot\trt\tspectrum file\tspectrum scan number\tspectrum title\tvalidation\tvariable modifications\n+DA; ; DA\tIK; ; ; IK; IK\t2+\tNH2-QVEEAVQSDDK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1246.5677\t0\tNH2-QVEEAVQSDDK-COOH\t624.292668193\tQVEEAVQSDDK\t15; 1; 1; 9; 9\t2.44958264245\t\tASDEEKVAIEAGIKQVEEAVQSDDK, QVEEAVQSDDK, QVEEAVQSDDKDAIDEAAK, VAIEAGIKQVEEAVQSDDK, VAIEAGIKQVEEAVQSDDKDAIDEAAK\t2125.86\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.10613.10613.2\tDoubtful\t\n+FT; FT; FT\t\t2+\tNH2-GTTNGTSTDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1298.5739\t0\tNH2-GTTNGTSTDFNGK-COOH\t650.293779699\tGTTNGTSTDFNGK\t1; 1; 1; 1\t-0.666230198055\t\tGTTNGTSTDFNGK, GTTNGTSTDFNGKFTLQAK, GTTNGTSTDFNGKFTLQAKSDSGR, GTTNGTSTDFNGKFTLQSK\t2274.86\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.12577.12577.2\tDoubtful\t\n+\t\t2+\tNH2-ADAHITSNVEANK-COOH\t99.8278829604\t\t\t2+\t1.0\t\t1368.6634\t0\tNH2-ADAHITSNVEANK-COOH\t685.84\tADAHITSNVEANK\t1\t-0.922491400517\t\tADAHITSNVEANK\t2338.13\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13537.13537.2\tDoubtful\t\n+\tEK\t2+\tNH2-AGATANDSLDDGNAGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1475.6488\t0\tNH2-AGATANDSLDDGNAGK-COOH\t738.832041435\tAGATANDSLDDGNAGK\t5\t0.474488705639\t\tAREKAGATANDSLDDGNAGK\t2344.0\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13631.13631.2\tDoubtful\t\n+\tEK\t2+\tNH2-AGATANDSLDDGNAGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1475.6488\t0\tNH2-AGATANDSLDDGNAGK-COOH\t738.833460428\tAGATANDSLDDGNAGK\t5\t2.39507898017\t\tAREKAGATANDSLDDGNAGK\t2349.33\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13710.13710.2\tDoubtful\t\n+KG; ; K; KG; KD; KG; KG; KD; KG\tVR; VR; VR; VR; VR; VR; VR; ; \t2+\tNH2-NPATGESFK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t949.4505\t0\tNH2-NPATGESFK-COOH\t475.732747603\tNPATGESFK\t9; 13; 13; 13; 4; 4; 4; 1; 1\t0.453938376043\t\tERPERMVRNPATGESFKKGADKVVK, IYCRERPERMVRNPATGESFK, IYCRERPERMVRNPATGESFKK, IYCRERPERMVRNPATGESFKKGADK, MVRNPATGESFKKDADKVVKMTIAKALK, MVRNPATGESFKKGADKVVKMTIAK, MVRNPATGESFKKGADKVVKMTIAKALK, NPATGESFKKDADRVVKMTIAKALK, NPATGESFKKGADKVVKMTIAKALK\t2475.54\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15623.15623.2\tDoubtful\t\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.301568419\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t1.41518840069\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2482.71\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15737.15737.2\tDoubtful\tOxidation of M(2)\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.3\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t-1.00036313327\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2494.56\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15923.15923.2\tDoubtful\tOxidation of M(2)\n+SA; SA; SA; ; ; \tVK; ; ; ; VK; VK; VK\t2+\tNH2-EVTTDEYR-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1011.4509\t0\tNH2-EVTTDEYR-COOH\t506.732862123\tEVTTDEYR\t10; 1; 1; 1; 20; 20; 20\t0.263474422335\t\tDVGINNTVKE'..b'EQVK, AMGVDNSYFKSTTELTSSEQVK, GTMEVLMDAKGVNNSFFKSTTELTSSEQVK, GTMEVLMDAKGVSNSFFKSTTELTSSEQVK, GVDNSFFKSTTELTSSEQVK, GVDNSFFKSTTELTSSEQVKALCDGK, GVKNSFFKSTTELTSSEQVK, GVKNSFFKSTTELTSSEQVKALCDGK, GVNNNFFKSTTELTSSEQVK, GVNNNFFKSTTELTSSEQVKALCDGK, GVNNSFFKSTTELTSSEQVK, GVNNSFFKSTTELTSSEQVKALCDGK, GVNNSFFKSTTELTSSEQVKALCDGKR, GVSNSFFKSTTELTSSEQVK, GVSNSFFKSTTELTSSEQVKALCDGK, NSFFKSTTELTSSEQVKALCDGK, SAKGVNNSFFKSTTELTSSEQVK, SDAKGVSNSFFKSTTELTSSEQVK, SNSFFKSTTELTSSEQVKALCDGK, SSDLFKSTTELTSSEQVKALCDGK, STTELTSSEQVK, STTELTSSEQVKADRK, STTELTSSEQVKALCDGK, STTELTSSEQVKALCDGKIDAFGR, STTELTSSEQVKALCDGKIDAFGYR, STTELTSSEQVKALCDGKIDAFGYSEIGR, STTELTSSEQVKALCDGKIDAFGYSVR, STTELTSSEQVKALCDGKIDAFRSEER, SVLMDAKGVNNSFFKSTTELTSSEQVK\t2821.27314818\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1952.0215\t1\t\t977.52\tTAGGIIIPDTAQEKPQEGK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4102.46028615\t\t\t\t\t\n+\t\t3+\t\t\t\t\t\t\t\t1952.0215\t1\t\t651.684056525\tTAGGIIIPDTAQEKPQEGK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4097.89567617\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t951.5025\t1\t\t476.76\tTAGTFASVAK\t\t\t\tDLDKSFGSMPGSMNKKTAGTFASVAK, DLNKSFGSIPGSMNEKTAGTFASVAK, DLNKSFGSIPGSMNKKTAGTFASVAK, DLNKSFGSMPGSMNEKTAGTFASVAK, DLNKSFGSMPGSMNKKTAGTFASVAK, KTAGTFASVAK, SFGSIPGSMNKKTAGTFASVAK, SFGSLPGSMNEKTAGTFASVAK, SFGSMPGSMNEKTAGTFASVAK, SFGSMPGSMNKKTAGTFASVAK, SGSMNKKTAGTFASVAK, TAGTFASVAK\t3093.88124482\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t2089.0539\t1\t\t1046.03\tTNDEAGDGTTTATILAQAIVK\t\t\t\tEVASRTNDEAGDGTTTATILAQAIVK, TNDEAGDGTTTATILAQAIVK, TNDEAGDGTTTATILAQAIVKEGMK\t6407.89796011\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1074.5306\t1\t\t538.271566384\tTTGDIQVEGR\t\t\t\tTTGDIQVEGR, TTGDIQVEGRVDGDIR, TTGDIQVEGRVEGDIR\t2772.79039798\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1436.7147\t1\t\t719.37\tTTPSIVAFTESER\t\t\t\tTTPSIVAFTESER, TTPSIVAFTESERLVGQPAK, TTPSIVAFTESERLVGQPAKR, VIENAEGARTTPSIVAFTESER, VIENAEGARTTPSIVAFTESERLVGQPAK\t5425.87755759\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1479.7093\t1\t\t740.86\tTTPSVVAFTEDGEK\t\t\t\tSENAEGARTTPSVVAFTEDGEK, SGARTTPSVVAFTEDGEK, TTPSVVAFTEDGEK, TTPSVVAFTEDGEKLEIGRAVQQECRDR, TTPSVVAFTEDGEKLVGQPAK, TTPSVVAFTEDGEKLVGQPAKR, TTPSVVAFTEDGEKLVGQPAKRQDRK, TTPSVVAFTEDGEKLVGQPDRK, TTPSVVAFTEDGEKLVGQSAKR, VLENAEGARTTPSVVAFTEDGEK, VLENAEGARTTPSVVAFTEDGEKLVGQPAK, VLENAEGTRTTPSVVAFTEDGEK, VLENTEGARTTPSVVAFTEDGEK\t4801.18521199\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1072.5401\t1\t\t537.28\tVEADLVENGK\t\t\t\tDIEVGSPKIEGAKVEADLVENGKNR, GAKVEADLVENGKNRTILIFKKRRR, IIEVGSPTVEGAKVEADLVENGKNR, NIEVGSPIVEGAKVEADLVENGKNR, NIEVGSPTVEGAKVEADLVENGK, NIEVGSPTVEGAKVEADLVENGKNR, SIEVGSPTVEGAKVEADLVENGK, SIEVGSPTVEGAKVEADLVENGKNR, SIEVGSPVVEGAKVEADLVENGK, SIEVGSPVVEGAKVEADLVENGKNR, TIEVGSPTVEGAKVEADLVENGKNR, TIEVGSPTVKGAKVEADLVENGKNR, TIEVGSPVVEGAKVEADLVENGK, TIEVGSPVVEGAKVEADLVENGKNR, VEADLVENGK, VEADLVENGKNR, VEADLVENGKNRTDRK, VEADLVENGKNRTILIFK, VEADLVENGKNRTILIFKK, VEADLVENGKNRTILIFKKR, VEADLVENGKNRTILIFKKRR, VEADLVENGKNRTILIFKKRRKIGR, VEADLVENGKNRTILIFKKRRR, VEADLVENGKNRTILIFKKRRRQNSKIGR, VEADLVENGKNRTILIFKKRRRQNSR, VEADLVENGKNRTILIFKKRRRQNSRDRK, VEADLVENGKNRTILIFKKRRRQNSRR, VEADLVENGKNRTILIFKKRRRQNSRRK\t3019.65888868\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1073.5175\t1\t\t537.77\tVIDNMPETR\t\t\t\tIAHVDYQRVIDNMPETR, IAHVDYQRVIDNMPETRALTVTLEK, IGHIDYQRVIDNMPETRALGTTLEKLGK, IGHVDYQRVIDNMPETR, IGHVDYQRVIDNMPETRALTVTLEK, IGHVDYQRVIDNMPETRALTVTLEKLGK, VIDNMPETRALGTTLEKLGK, VIDNMPETRALTVTLEKLGK, VIDNMPETRALTVTLEKLGKSYQSEIEGLK\t3137.58963272\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1124.4887\t1\t\t563.252254136\tWADETGGSFR\t\t\t\tFDKSFNEAAFAGAQRWADETGGSFR, FDKSFNEAAFKGAERWADETGGSFR, GAERWADETGGSFREVELQSEAQR, SFNEAAFAGAQRWADETGGSFR, SFNESAFTGAQRWADETGGSFR, WADETGGSFR, WADETGGSFREIELQSEAQR, WADETGGSFREIELQSEAQREQALR, WADETGGSFREIELQSEAQREQALRR\t3912.1250394\t\t\t\t\t\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_output/mbr_test2_match.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_output/mbr_test2_match.txt Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,260 @@\n+aas after\taas before\tcharge\tcode_unique\tconfidence [%]\td-score\tfixed modifications\tidentification charge\tisotope number\tlocalization confidence\tmass\tmatched\tmod_peptide\tmz\tpeptide\tposition\tprecursor m/z error [ppm]\tprobabilistic ptm score\tprot\trt\tspectrum file\tspectrum scan number\tspectrum title\tvalidation\tvariable modifications\n+EV; ; EV; ; EV\tNW; NW; NW; NW; NW; NW\t2+\tNH2-RDVGINNTVK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1114.6095\t0\tNH2-RDVGINNTVK-COOH\t558.312235432\tRDVGINNTVK\t10; 10; 10; 10; 10; 10\t0.400593042907\t\tLVELAGQNWRDVGINNTVK, LVELAGQNWRDVGINNTVKEVTTDEYR, LVEVAGQNWRDVGINNTVK, LVEVAGQNWRDVGINNTVKEVTTDEYR, LVEVTGQNWRDVGINNTVK, LVEVTGQNWRDVGINNTVKEVTTDEYR\t2322.17\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13283.13283.2\tDoubtful\t\n+\t\t3+\tNH2-ADAHITSNVEANK-COOH\t99.8278829604\t\t\t3+\t0.0\t\t1368.6634\t0\tNH2-ADAHITSNVEANK-COOH\t457.23\tADAHITSNVEANK\t1\t3.50950236447\t\tADAHITSNVEANK\t2335.35\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13493.13493.3\tDoubtful\t\n+DF; DF; DF; DF; ; DF; DF; DF; \tAK; AK; ; ; ; AK; AK; AK; S; AK\t2+\tNH2-HQIVEAPAR-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1019.5512\t0\tNH2-HQIVEAPAR-COOH\t510.783866967\tHQIVEAPAR\t8; 8; 1; 1; 1; 8; 8; 8; 2; 16\t1.91229342584\t\tDFFPNAKHQIVEAPAR, DFFPNAKHQIVEAPARDFQEVLSMR, HQIVEAPARDFQEVLSMR, HQIVEAPARDFQEVLSMRADAHITSNVEAK, HQIVEAPARDFQEVLSMRDRK, QFFPNAKHQIVEAPAR, QFFPNAKHQIVEAPARDFQEVLSMR, QFFPNAKHQIVEAPARDFQEVR, SHQIVEAPARDFQEVLSMR, STQETQVKQFFPNAKHQIVEAPAR\t2384.64\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.14185.14185.2\tDoubtful\t\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.301048825\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t0.614952377062\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2476.83\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15644.15644.2\tDoubtful\tOxidation of M(2)\n+\tIK\t2+\tNH2-GTTNGTETDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1340.5844\t0\tNH2-GTTNGTETDFNGK-COOH\t671.300172985\tGTTNGTETDFNGK\t1; 6\t1.00953138271\t\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\t2482.1\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15728.15728.2\tDoubtful\t\n+\tIK\t2+\tNH2-GTTNGTETDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1340.5844\t0\tNH2-GTTNGTETDFNGK-COOH\t671.3\tGTTNGTETDFNGK\t1; 6\t0.751844938295\t\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\t2494.5\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15922.15922.2\tDoubtful\t\n+SD\t\t2+\tNH2-EGGEDM<ox>FVHK-COOH\t99.8278829604\tOxidation of M (6: 100.0)\t\t2+\t0.0\tOxidation of M (6: Very Confident)\t1163.4917\t0\tNH2-EGGEDM<ox>FVHK-COOH\t582.752485263\tEGGEDMFVHK\t1\t-1.12051106098\tOxidation of M (6: 100.0)\tEGGEDMFVHKSDVDGFINEGDK\t2536.63\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.16595.16595.2\tDoubtful\tOxidation of M(6)\n+\t\t2+\tNH2-GSNSGTETDFDGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1313.5372\t0\tNH2-GSNSGTETDFDGK-COOH\t657.775415728\tGSNSGTETDFDGK\t1\t-0.664794466436\t\tGSNSGTETDFDGK\t2545.26\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.16731.16731.2\tDoubtful\t\n+GN\tDK; ; \t2+\tNH2-SAQEAM<ox>DSVVER-COOH\t99.8278829604\tOxidation of M (6: 100.0)\t\t2+\t0.0\tOxidation of M (6: Very Confident)\t1336.5929\t0\tNH2-SAQEAM<ox>DSVVER-COOH\t669.3\tSAQEAMDSVVER\t16; 1; 1\t-5.56330571801\tOxidation of M (6: 100.0)\tGIIDEELEAIWAGDKSAQEAMDSVVER, SAQEAMDSVVER, SAQEAMDSVVERGNPLLRR\t2569.05\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.17104.17104.2\tDoubtful\tOxidation of M(6)\n+SD\t\t2+\tNH2-EGGEDM<ox>FVHK-COOH\t99.8278829604\tOxidation of M (6: 100.0)\t\t2+\t0.0\tOxidation of M (6: Very Confident)\t1163.4917\t0\tNH2-EGGEDM<ox>FVHK-COOH\t582.753674136\tEGGEDMFVHK\t1\t0.919585786126\tOxidation of M (6: 100.0)\tEGGEDMFVHKSDVDGFINEGDK\t258'..b'PSVQAVLCCDNVNRGLGYGDGK, QDPSVQAVLCCDNVNRGLGYGNGK, VVWSYFPKQDPSVQAVLCCDNVNR\t4936.73430292\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1451.7157\t1\t\t726.87\tQGAFYNQIVEQR\t\t\t\tDKPVCGKQGAFYNQIVEQRYGAK\t4936.29391884\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1283.6544\t1\t\t642.834266294\tQLPGGEIQPAMK\t\t\t\tQLPGGEIQPAMK, QLPGGEIQPAMKTGLIDAAEFNNQIGR, QLPGGEIQPAMKTGLIDRSEERFSR, QLPGGEIQPAMKTGLIR, RSSDLVRQLPGGEIQPAMK, SMGMVVRQLPGGEIQPAMK, SVRQLPGGEIQPAMK, TVGLAADVLLEMGMSVVQLPGGEIQPAMK, TVGLAADVLMEMGMSVVQLPGGEIQPAMK, TVGLATNVLTAMGMVVRQLPGGEIQPAMK\t3363.02180749\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1246.5677\t1\t\t624.292668193\tQVEEAVQSDDK\t\t\t\tASDEEKVAIEAGIKQVEEAVQSDDK, QVEEAVQSDDK, QVEEAVQSDDKDAIDEAAK, VAIEAGIKQVEEAVQSDDK, VAIEAGIKQVEEAVQSDDKDAIDEAAK\t2123.81104393\t\t\t\t\t\n+\t\t3+\t\t\t\t\t\t\t\t1339.7208\t1\t\t447.580299459\tRNIADTGILPDR\t\t\t\tIIKQVGNYGESYKRNIADTGILPDR, IIKQVGNYGESYKRNIADTGILPDRGDRK, IIKQVGNYGESYKRNIADTGILPDRGPNR, IIKQVGNYGESYKRNIADTGILPDRK, IIKQVGNYGESYKRNLADTGILPDR, QVGNYGESYKRNIADTGILPDR, RNIADTGILPDR, RNIADTGILPDRGPNALWTK, RNIADTGILPDRGPNNIWTK, RNIADTGILPDRGPNNIWTQGGLLYK, RNIADTGILPDRGPNQIWTK, RNIADTGILPDRGPNQLWTK, RNIADTGILPDRSEERFSR\t4216.94654823\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1304.6725\t1\t\t653.344403594\tSNDLQNIVQFK\t\t\t\tASEPVYRSNDLQNIVQFK, ASEPVYRSNDLQNIVQFKTTSYDFYR, SNDLQNIVQFK, SNDLQNIVQFKTTSYDFYR\t5603.17553205\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1138.6598\t1\t\t570.339000439\tSPLPIDIVSAK\t\t\t\tSNTKSPLPIDIVSAK, SNTKSPLPIDIVSAKDLVATGQTTFDK, SNTKSPLPIDIVSAKDLVSTGQTTFDK, TPQRSNTKSPLPIDIVSAK\t5586.98140853\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1573.8464\t1\t\t787.933125991\tSVQAVQPSGNYAIIK\t\t\t\tIIAKSVQAVQPSGNYAIIK, SVQAVQPSGNYAIIK\t4580.01319267\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1412.7511\t1\t\t707.38\tTAGGIIIPDTAQEK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPDRK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4444.24478379\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1564.8348\t1\t\t783.42\tTFDTITNTILDALK\t\t\t\tADAERTFDTITNTILDALK, ADAERTFDTITNTILDALKGDDSVK, ADAERTFDTITNTILDALKGDDTVK, ADAERTFDTITNTILDALKGDR, LSGSLNLSKADAERTFDTITNTILDALK, TFDTITNTILDALK, TFDTITNTILDALKGDDTVK, TFDTITNTILDALKGDDTVKIAGFGTYK, TFDTITNTILDALKGDEIGR\t8085.1301405\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t858.4811\t1\t\t430.248420613\tTGEAIQIK\t\t\t\tAATTGRNPRTGEAIQIK, AATTGRNPRTGEAIQIKASKQPKFK, NPRTGEAIQIKASKQPKFK, NPRTGEAIQIKASKQPKFKAGSPLK\t3005.20974577\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1117.5979\t1\t\t559.806407705\tVAATLGTTQEK\t\t\t\tFKDWDDLNKPDVRVAATLGTTQEK, FKDWDDLNKPDVRVAATLGTTQEKQVK, SNADRFKDWDDLNKPDVRVAATLGTTQEK, VAATLGTTQEKQVK, VAATLGTTQEKQVKEYFPNAK, VAATLGTTQEKQVKSYFPDAK\t2519.96654644\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1080.5088\t1\t\t541.261769908\tVGYQVDGDTK\t\t\t\tEASLHISNVMLVEDGVAVRVGYQVDGDTK, EASLHISNVMLVEGGVAVRVGYQVDGDTK, KEASLHISNVMLVEDGVAVRVGYQVDGDTK, KEASLHISNVMLVEGGVAVRVGYQVDGDTK, VGYQVDGDTKTR, VGYQVDGDTKTRISK, VGYQVDGDTKTRISKK, VGYQVDGDTKTRVSK\t2778.59210377\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1352.7228\t1\t\t677.87\tVLIDYLVDEFK\t\t\t\tVLIDYLVDEFKKKEGVDLTSDSTAMTRIR\t7737.85727042\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1405.6937\t1\t\t703.854502277\tVTSDEESGQTIIK\t\t\t\tEDPSFRVTSDEESGQTIIK, EDPSFRVTSDEESGQTIIKGMEIGR, LAKEDPSFRVTSDEESGQTIIK, LAKEDPSFRVTSDEESGQTIIKGDRK, LAKEDPSFRVTSDEESGQTIIKGMGR, LAKEDPSFRVTSDEESGQTIIKGMR, LAKEDPSFRVTSDEESGQTIIKGR, MGEALARLAKEDPSFRVTSDEESGQTIIK, MGEALGRLAKEDPSFRVTSDEESGQTIIK, SALARLAKEDPSFRVTSDEESGQTIIK, SVTSDEESGQTIIK, VTSDEESGQTIIK, VTSDEESGQTIIKGMGELHLDIIVDR, VTSDEESGQTIIKGMGELHLDIIVDRMK, VTSDEESGQTIIKGMGELHLDIIVDRMKR, VTSDEESGQTIIKGMRSEERFSR\t3269.48022626\t\t\t\t\t\n+\t\t2+\t\t\t\t\t\t\t\t1170.6105\t1\t\t586.312380654\tVVNIGNAGSGQR\t\t\t\tAKVKDFAGLKGKVVNIGNAGSGQR, DFAGLEGKVVNIGNAGSGQR, DFAGLKGKVVNIGNAGSGQR, DFAGLKGKVVNIGNAGSGQRGTMEVLMDAK, GKVVNIGNAGSGQR, GKVVNIGNAGSGQRGTMEVLMDAK, GKVVNIGNAGSGQRGTMEVLMDAKGVK, GKVVNIGNAGSGQRGTMEVLMNAK, KAKVKDFAGLEGKVVNIGNAGSGQR, KAKVKDFAGLKGKVVNIGNAGSGQR, KAKVKDFAGLKGKVVNIGNAGSGQRGDRK, KKAKVKDFAGLEGKVVNIGNAGSGQR, KKAKVKDFAGLKGKVVNIGNAGSGQR, VKDFAGLEGKVVNIGNAGSGQR, VKDFAGLKGKVVNIGNAGSGQR, VVNIGNAGSGQR, VVNIGNAGSGQRGTMEVLMDAK, VVNIGNAGSGQRGTMEVLMDAKGVK, VVNIGNAGSGQRGTMEVLMDAKGVNNSFFK\t2759.48544012\t\t\t\t\t\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_test1.mzml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_test1.mzml Fri Jan 05 12:47:36 2018 -0500
b
b'@@ -0,0 +1,26908 @@\n+<?xml version="1.0" encoding="utf-8"?>\n+<indexedmzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.2_idx.xsd">\n+  <mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0.xsd" id="2016_Jan_12_QE2_47" version="1.1.0">\n+    <cvList count="2">\n+      <cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" version="3.74.0" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"/>\n+      <cv id="UO" fullName="Unit Ontology" version="12:10:2011" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo"/>\n+    </cvList>\n+    <fileDescription>\n+      <fileContent>\n+        <cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000580" name="MSn spectrum" value=""/>\n+      </fileContent>\n+      <sourceFileList count="3">\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.raw" name="2016_Jan_12_QE2_47.raw" location="">\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="6f65a1287b2d7522c5fb90a8a5304212b3568b67"/>\n+          <cvParam cvRef="MS" accession="MS:1000563" name="Thermo RAW format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000768" name="Thermo nativeID format" value=""/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzXML" name="2016_Jan_12_QE2_47.mzXML" location="file:///">\n+          <cvParam cvRef="MS" accession="MS:1000776" name="scan number only nativeID format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000566" name="ISB mzXML format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="d9c6278c1c6a8f8ca6c69133bacd00efc5f2e706"/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzML" name="2016_Jan_12_QE2_47.mzML" location="file:////Users/kumar207/Documents/Projects/Pratik/script/../mzML">\n+        </sourceFile>\n+      </sourceFileList>\n+    </fileDescription>\n+    <softwareList count="4">\n+      <software id="Xcalibur_x0020_software" version="2.6-264001/2.6.0.2640">\n+        <cvParam cvRef="MS" accession="MS:1000532" name="Xcalibur" value=""/>\n+      </software>\n+      <software id="ReAdW_x0020_software" version="2015.1.0(build Jun 29 2015 14:09:50)">\n+        <cvParam cvRef="MS" accession="MS:1000541" name="ReAdW" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.8990" version="3.0.8990">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.7680" version="3.0.7680">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+    </softwareList>\n+    <instrumentConfigurationList count="1">\n+      <instrumentConfiguration id="IC1">\n+        <userParam name="msManufacturer" value="Thermo Finnigan"/>\n+        <userParam name="msModel" value="unknown"/>\n+        <componentList count="3">\n+          <source order="1">\n+            <userParam name="msIonisation" value="NSI"/>\n+          </source>\n+          <analyzer order="1">\n+            <cvParam cvRef="MS" accession="MS:1000079" name="fourier transform ion cyclotron resonance mass spectrometer" value=""/>\n+          </analyzer>\n+          <detector order="1">\n+            <userParam name="msDetector" value="unknown"/>\n+          </detector>\n+        </componentList>\n+        <softwareRef ref="Xcalibur_x0020_software"/>\n+      </instrumentConfiguration>\n+    </instrumentConfigurationList>\n+    <dataProcessingList count="3">\n+      <dataProcessing id="dataProces'..b'ntrollerNumber=1 scan=90261">2414719</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90324">2418981</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90325">2422771</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90389">2426417</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90825">2430097</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90896">2434045</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90952">2438179</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90967">2441823</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91020">2445963</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91036">2449647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91084">2453875</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91100">2457676</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91151">2462056</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91167">2465804</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91234">2469798</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91304">2473755</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91379">2477398</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91464">2481055</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92113">2484679</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92168">2488404</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92183">2492017</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92238">2495975</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92249">2499652</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92303">2503647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92318">2507303</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92389">2511184</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94116">2514904</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94183">2518552</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94258">2522503</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94332">2526517</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94729">2530126</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94857">2534084</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94919">2538185</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94980">2541937</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=95063">2545506</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96694">2549319</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96764">2552999</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96836">2556647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96918">2560122</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96993">2563742</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=97169">2567598</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99329">2571216</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99385">2574908</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99446">2578708</offset>\n+    </index>\n+    <index name="chromatogram">\n+    </index>\n+  </indexList>\n+  <indexListOffset>2582386</indexListOffset>\n+  <fileChecksum>23b8703ddaf744e69e1ba72be2584fd3df6f2dc4</fileChecksum>\n+</indexedmzML>\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_test1.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_test1.tabular Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,200 @@\n+\tProtein(s)\tSequence\tAAs Before\tAAs After\tPosition\tModified Sequence\tVariable Modifications\tFixed Modifications\tSpectrum File\tSpectrum Title\tSpectrum Scan Number\tRT\tm/z\tMeasured Charge\tIdentification Charge\tTheoretical Mass\tIsotope Number\tPrecursor m/z Error [ppm]\tLocalization Confidence\tProbabilistic PTM score\tD-score\tConfidence [%]\tValidation\n+1\tAARAGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGKALK, AGRNPQTGAEIQIKAANVPSFKARSEER, HRAARAGRNPQTGAEIQIK, HRAARAGRNPQTGAEIQIKAANVPSFK, HRAARAGRNPQTGAEIQIKAANVPSFKAGK, KGRNPQTGAEIQIKAK\tGRNPQTGAEIQIK\tRA; A; A; A; RA; RA; RA; K\tAA; AA; AA; AA; ; AA; AA; AK\t5; 2; 2; 2; 7; 7; 7; 2\tNH2-GRNPQTGAEIQIK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.24409.24409.2\t\t3023.92\t706.39\t2+\t2+\t1410.7579257583402\t0\t5.323792860535044\t\t\t\t99.82788296041308\tDoubtful\n+2\tNIAELGIYPAVDPLDSTSR\tNIAELGIYPAVDPLDSTSR\t\t\t1\tNH2-NIAELGIYPAVDPLDSTSR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.77693.77693.2\t\t6459.24\t1016.02684441294\t2+\t2+\t2030.03203490277\t0\t3.494501321200086\t\t\t\t99.82788296041308\tDoubtful\n+3\tDHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.49000.49000.2\t\t4619.72\t804.36\t2+\t2+\t1606.7110947052206\t0\t-3.510628958399463\t\t\t\t99.82788296041308\tDoubtful\n+4\tFGCGYEQGAK, FGCGYEQGAKHINANIK, FGCGYEQGAKHINANIKVLQK, FGCGYEQGAKHINANIKVLQKMTR, FGCGYEQGAKHINANITVLQK, FGCGYEQGAKHINTNITVLQK, SESNTIGFIGGMDIPLIAVFGCGYEQGAK, SETGTIGFVGGMDIPLISRFGCGYEQGAK, SGFVGGMDIPLISRFGCGYEQGAK\tFGCGYEQGAK\tAV; SR; SR\tHI; HI; HI; HI; HI; ; ; \t1; 1; 1; 1; 1; 1; 20; 20; 15\tNH2-FGC<cmm>GYEQGAK-COOH\t\tCarbamidomethylation of C(3)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.21525.21525.2\t\t2843.8\t558.74278031655\t2+\t2+\t1115.4705941881903\t0\t0.3700373885771707\t\t\t\t99.82788296041308\tDoubtful\n+5\tDVRVAVFTQGENVEK, DVRVAVFTQGENVEKATAAGDRK, EVRVAVFTQGENVEK, GSTVLPNGTGKDVRVAVFTQGENVEK, GSTVLPNGTGKEVRVAVFTQGENVEK, SGKDVRVAVFTQGENVEK, STGKDVRVAVFTQGENVEK, VAVFTQGENVEK\tVAVFTQGENVEK\tVR; VR; VR; VR; VR; VR; VR; \tAT; ; ; ; ; ; \t4; 4; 4; 15; 15; 7; 8; 1\tNH2-VAVFTQGENVEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.37428.37428.2\t\t3858.93\t660.84407029524\t2+\t2+\t1319.6721304457103\t0\t1.1025390237788624\t\t\t\t99.82788296041308\tDoubtful\n+6\tEVASQTSDVAGDGTTTATVLAQAILNEGLK\tEVASQTSDVAGDGTTTATVLAQAILNEGLK\t\t\t1\tNH2-EVASQTSDVAGDGTTTATVLAQAILNEGLK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.96993.96993.3\t\t7882.73\t987.84\t3+\t3+\t2959.4985892563404\t1\t-1.2737446644704296\t\t\t\t99.82788296041308\tDoubtful\n+7\tAYAKKVMKYLLMNQPNYKLAYENEFGPIGK, KTMKYLLMNQPNYKLAYENEFGPIGKVK, KVMKYLLMNQPNYKLAYENEFGPIGK, KVMKYLLMNQPNYKLAYENEFGPIGKVK, LAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGKVK, YLLMNQPNYKLAYENEFGPIGK\tLAYENEFGPIGK\tYK; YK; YK; YK; ; YK; YK; YK\tVK; ; VK; ; ; VK; \t19; 15; 15; 15; 1; 15; 15; 11\tNH2-LAYENEFGPIGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.58393.58393.2\t\t5223.31\t669.34135435161\t2+\t2+\t1336.6663167892802\t0\t1.373725700567889\t\t\t\t99.82788296041308\tDoubtful\n+8\tEASLHISNVMLVEDGVAVRVGYQVDGDTK, EASLHISNVMLVEGGVAVRVGYQVDGDTK, KEASLHISNVMLVEDGVAVRVGYQVDGDTK, KEASLHISNVMLVEGGVAVRVGYQVDGDTK, VGYQVDGDTKTR, VGYQVDGDTKTRISK, VGYQVDGDTKTRISKK, VGYQVDGDTKTRVSK\tVGYQVDGDTK\tVR; VR; VR; VR; ; ; ; \tTR; TR; TR; TR\t20; 20; 21; 21; 1; 1; 1; 1\tNH2-VGYQVDGDTK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20503.20503.2\t\t2780.07\t541.26176990816\t2+\t2+\t1080.5087535187201\t0\t0.2155740890529847\t\t\t\t99.82788296041308\tDoubtful\n+9\tFKDWDDLNKPDVRVAATLGTTQEK, FKDWDDLNKPDVRVAATLGTTQEKQVK, SNADRFKDWDDLNKPDVRVAATLGTTQEK, VAATLGTTQEKQVK, VAATLGTTQEKQVKEYFPNAK, VAATLGTTQEKQVKSYFPDAK\tVAATLGTTQEK\tVR; VR; VR; ; ; \tQV; ; QV; QV; QV\t14; 14; 19; 1; 1; 1\tNH2-VAATLGTTQEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.16356.16356.2\t\t2521.67\t559.80640770461\t2+\t2+\t1117.5979028762904\t0\t0.32118194438209224\t\t\t\t99.82788296041308\tDo'..b'41308\tDoubtful\n+188\tLDPAASGGSFGGR, SASDFTRLDPAASGGSFGGR, TLPTISRSASDFTRLDPAASGGSFGGR\tLDPAASGGSFGGR\tTR; TR\t\t1; 8; 15\tNH2-LDPAASGGSFGGR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.32027.32027.2\t\t3502.9\t596.29\t2+\t2+\t1190.56799973034\t0\t-2.1404505361495096\t\t\t\t99.82788296041308\tDoubtful\n+189\tIIAKSVQAVQPSGNYAIIK, SVQAVQPSGNYAIIK\tSVQAVQPSGNYAIIK\tAK; \t\t5; 1\tNH2-SVQAVQPSGNYAIIK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.48100.48100.2\t\t4563.57\t787.93312599061\t2+\t2+\t1573.8464064095701\t0\t3.3585691646471707\t\t\t\t99.82788296041308\tDoubtful\n+190\tDSFTIVPLVDRGR, GELGKKMNDMLTKDSFTIVPLVDRGR, KMNDMLTKDSFTIVPLVDRGR, MNDMLTKDSFTIVPLVDRGR, RGELGKKMNDMLTKDSFTIVPLVDR, RGELGKKMNDMLTKDSFTIVPLVDRGR\tDSFTIVPLVDR\tTK; TK; TK; TK; TK\tGR; GR; GR; GR; ; GR\t1; 14; 9; 8; 15; 15\tNH2-DSFTIVPLVDR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.74998.74998.2\t\t6286.26\t631.34401461983\t2+\t2+\t1260.67140216972\t0\t1.6426383039728303\t\t\t\t99.82788296041308\tDoubtful\n+191\tCDVYTTDASGLASTR, CDVYTTDASGLASTRAK\tCDVYTTDASGLASTR\t\tAK\t1; 1\tNH2-C<cmm>DVYTTDASGLASTR-COOH\t\tCarbamidomethylation of C(1)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.43005.43005.3\t\t4239.95\t539.57900862594\t3+\t3+\t1615.7148001866701\t0\t0.24481481831098903\t\t\t\t99.82788296041308\tDoubtful\n+192\tEPLGPVVRQGDAVWEDIVR, QGDAVWEDIVR, QGDAVWEDIVRWSLNVMRSEERRVGK, SVRQGDAVWEDIVR, SVVRQGDAVWEDIVR, VLPETISKEPLGPVVRQGDAVWEDIVR\tQGDAVWEDIVR\tVR; ; ; VR; VR; VR\tWS; ; ; \t9; 1; 1; 4; 5; 17\tNH2-QGDAVWEDIVR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.71032.71032.2\t\t6031.75\t644.3209167999\t2+\t2+\t1286.6255146064602\t0\t1.3704833181721212\t\t\t\t99.82788296041308\tDoubtful\n+193\tRNIADTGILPDRGPNNIWTK, RNIADTGILPDRGPNNIWTQGGLLYK\tNIADTGILPDRGPNN\tR; R\tIW; IW\t2; 2\tNH2-NIADTGILPDRGPNN-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.49353.49353.2\t\t4642.5\t783.89\t2+\t2+\t1565.77978340173\t0\t-9.144270407038235\t\t\t\t99.82788296041308\tDoubtful\n+194\tAYAKKVMKYLLMNQPNYKLAYENEFGPIGK, KTMKYLLMNQPNYKLAYENEFGPIGKVK, KVMKYLLMNQPNYKLAYENEFGPIGK, KVMKYLLMNQPNYKLAYENEFGPIGKVK, LAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGKVK, YLLMNQPNYKLAYENEFGPIGK\tLAYENEFGPIGK\tYK; YK; YK; YK; ; YK; YK; YK\tVK; ; VK; ; ; VK; \t19; 15; 15; 15; 1; 15; 15; 11\tNH2-LAYENEFGPIGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.58237.58237.2\t\t5212.69\t669.34509968344\t2+\t2+\t1336.6663167892802\t0\t6.969281616456162\t\t\t\t99.82788296041308\tDoubtful\n+195\tATIVADDGGQVVFR, ATIVADDGGQVVFRVAADATKPEIK, ATIVADDGGQVVFRVAADATKPEIKK, IYQVLLGPHISEKATIVADDGGQVVFR\tATIVADDGGQVVFR\tEK\tVA; VA; \t1; 1; 1; 14\tNH2-ATIVADDGGQVVFR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.55517.55517.2\t\t5038.3\t724.38\t2+\t2+\t1446.7466923683003\t0\t-0.8595632499598641\t\t\t\t99.82788296041308\tDoubtful\n+196\tDAGMNGLDEGQALTFEVEDGPK, DAGMNGLDEGQALTFEVEDGPKGDRK, DAGMNGLDEGQALTFEVEDGPKGPSAVNLK\tDAGMNGLDEGQALTFEVEDGPK\t\tGD; GP\t1; 1; 1\tNH2-DAGM<ox>NGLDEGQALTFEVEDGPK-COOH\tOxidation of M(4)\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.70521.70521.2\t\t5999.32\t1155.01556849432\t2+\t2+\t2308.0165210612704\t0\t0.0272696528062818\tOxidation of M (4: Very Confident)\tOxidation of M (4: 100.0)\tOxidation of M (4: 100.0)\t99.82788296041308\tDoubtful\n+197\tGKRVAAAVGTVPEQEWLK, KVAAAVGTVPEQEWLK, RVAAAVGTVPEQEWLK, TFEDMRGKRVAAAVGTVPEQEWLK, TVEDMYNKKVAAAVGTVPEQEWLK\tVAAAVGTVPEQEWLK\tKR; K; R; KR; KK\t\t4; 2; 2; 10; 10\tNH2-VAAAVGTVPEQEWLK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.63561.63561.2\t\t5553.83\t799.43430508696\t2+\t2+\t1596.8511574368404\t0\t1.81366292154\t\t\t\t99.82788296041308\tDoubtful\n+198\tIIAKSVQAVQPSGNYAIIK, SVQAVQPSGNYAIIK\tSVQAVQPSGNYAIIK\tAK; \t\t5; 1\tNH2-SVQAVQPSGNYAIIK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.48275.48275.2\t\t4574.55\t787.9308763449\t2+\t2+\t1573.8464064095701\t0\t0.5034369313670704\t\t\t\t99.82788296041308\tDoubtful\n+199\tAREKAGATANDSLDDGNAGK\tAGATANDSLDDGNAGK\tEK\t\t5\tNH2-AGATANDSLDDGNAGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.13631.13631.2\t\t2344.0\t738.83204143502\t2+\t2+\t1475.6488288018304\t0\t0.4744887056389979\t\t\t\t99.82788296041308\tDoubtful\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_test2.mzml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_test2.mzml Fri Jan 05 12:47:36 2018 -0500
b
b'@@ -0,0 +1,26908 @@\n+<?xml version="1.0" encoding="utf-8"?>\n+<indexedmzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.2_idx.xsd">\n+  <mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0.xsd" id="2016_Jan_12_QE2_47" version="1.1.0">\n+    <cvList count="2">\n+      <cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" version="3.74.0" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"/>\n+      <cv id="UO" fullName="Unit Ontology" version="12:10:2011" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo"/>\n+    </cvList>\n+    <fileDescription>\n+      <fileContent>\n+        <cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000580" name="MSn spectrum" value=""/>\n+      </fileContent>\n+      <sourceFileList count="3">\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.raw" name="2016_Jan_12_QE2_47.raw" location="">\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="6f65a1287b2d7522c5fb90a8a5304212b3568b67"/>\n+          <cvParam cvRef="MS" accession="MS:1000563" name="Thermo RAW format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000768" name="Thermo nativeID format" value=""/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzXML" name="2016_Jan_12_QE2_47.mzXML" location="file:///">\n+          <cvParam cvRef="MS" accession="MS:1000776" name="scan number only nativeID format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000566" name="ISB mzXML format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="d9c6278c1c6a8f8ca6c69133bacd00efc5f2e706"/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzML" name="2016_Jan_12_QE2_47.mzML" location="file:////Users/kumar207/Documents/Projects/Pratik/script/../mzML">\n+        </sourceFile>\n+      </sourceFileList>\n+    </fileDescription>\n+    <softwareList count="4">\n+      <software id="Xcalibur_x0020_software" version="2.6-264001/2.6.0.2640">\n+        <cvParam cvRef="MS" accession="MS:1000532" name="Xcalibur" value=""/>\n+      </software>\n+      <software id="ReAdW_x0020_software" version="2015.1.0(build Jun 29 2015 14:09:50)">\n+        <cvParam cvRef="MS" accession="MS:1000541" name="ReAdW" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.8990" version="3.0.8990">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.7680" version="3.0.7680">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+    </softwareList>\n+    <instrumentConfigurationList count="1">\n+      <instrumentConfiguration id="IC1">\n+        <userParam name="msManufacturer" value="Thermo Finnigan"/>\n+        <userParam name="msModel" value="unknown"/>\n+        <componentList count="3">\n+          <source order="1">\n+            <userParam name="msIonisation" value="NSI"/>\n+          </source>\n+          <analyzer order="1">\n+            <cvParam cvRef="MS" accession="MS:1000079" name="fourier transform ion cyclotron resonance mass spectrometer" value=""/>\n+          </analyzer>\n+          <detector order="1">\n+            <userParam name="msDetector" value="unknown"/>\n+          </detector>\n+        </componentList>\n+        <softwareRef ref="Xcalibur_x0020_software"/>\n+      </instrumentConfiguration>\n+    </instrumentConfigurationList>\n+    <dataProcessingList count="3">\n+      <dataProcessing id="dataProces'..b'ntrollerNumber=1 scan=90261">2414719</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90324">2418981</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90325">2422771</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90389">2426417</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90825">2430097</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90896">2434045</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90952">2438179</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90967">2441823</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91020">2445963</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91036">2449647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91084">2453875</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91100">2457676</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91151">2462056</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91167">2465804</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91234">2469798</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91304">2473755</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91379">2477398</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91464">2481055</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92113">2484679</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92168">2488404</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92183">2492017</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92238">2495975</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92249">2499652</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92303">2503647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92318">2507303</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92389">2511184</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94116">2514904</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94183">2518552</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94258">2522503</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94332">2526517</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94729">2530126</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94857">2534084</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94919">2538185</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94980">2541937</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=95063">2545506</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96694">2549319</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96764">2552999</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96836">2556647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96918">2560122</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96993">2563742</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=97169">2567598</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99329">2571216</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99385">2574908</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99446">2578708</offset>\n+    </index>\n+    <index name="chromatogram">\n+    </index>\n+  </indexList>\n+  <indexListOffset>2582386</indexListOffset>\n+  <fileChecksum>23b8703ddaf744e69e1ba72be2584fd3df6f2dc4</fileChecksum>\n+</indexedmzML>\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/mbr_test2.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/mbr_test2.tabular Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,200 @@\n+\tProtein(s)\tSequence\tAAs Before\tAAs After\tPosition\tModified Sequence\tVariable Modifications\tFixed Modifications\tSpectrum File\tSpectrum Title\tSpectrum Scan Number\tRT\tm/z\tMeasured Charge\tIdentification Charge\tTheoretical Mass\tIsotope Number\tPrecursor m/z Error [ppm]\tLocalization Confidence\tProbabilistic PTM score\tD-score\tConfidence [%]\tValidation\n+384\tAQLEEVANIKMKDLNANDLDAAVK, MKDLNANDLDAAVK, MKDLNANDLDAAVKIVAGTAR\tDLNANDLDAAVK\tMK; MK; MK\tIV\t13; 3; 3\tNH2-DLNANDLDAAVK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.50271.50271.2\t\t4700.47\t629.81767452497\t2+\t2+\t1257.6200948728504\t0\t0.5567038559547145\t\t\t\t99.82788296041308\tDoubtful\n+385\tDAIAPAIEAAANEGIPVIGYDR, DAIAPAIEAAANEGIPVIGYDRLIEDAR\tDAIAPAIEAAANEGIPVIGYDR\t\tLI\t1; 1\tNH2-DAIAPAIEAAANEGIPVIGYDR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.89972.89972.2\t\t7340.77\t1113.58\t2+\t2+\t2225.1328115732003\t0\t5.673397897567815\t\t\t\t99.82788296041308\tDoubtful\n+386\tDAIAPAIEAAANEGIPVIGYDR, DAIAPAIEAAANEGIPVIGYDRLIEDAR\tDAIAPAIEAAANEGIPVIGYDR\t\tLI\t1; 1\tNH2-DAIAPAIEAAANEGIPVIGYDR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.90389.90389.3\t\t7373.36\t743.05\t3+\t3+\t2225.1328115732003\t1\t-3.5885352343819306\t\t\t\t99.82788296041308\tDoubtful\n+387\tDIGVAAVAMGGGDILPALEK\tDIGVAAVAMGGGDILPALEK\t\t\t1\tNH2-DIGVAAVAM<ox>GGGDILPALEK-COOH\tOxidation of M(9)\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.88315.88315.2\t\t7208.05\t957.00784740725\t2+\t2+\t1911.9975639703503\t0\t1.869324908638352\tOxidation of M (9: Very Confident)\tOxidation of M (9: 100.0)\tOxidation of M (9: 100.0)\t99.82788296041308\tDoubtful\n+388\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\tEMTSTEGLAGSAK\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\tYI; YI; ; ; YI; ; ; ; ; ; YI; YI\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\tNH2-EMTSTEGLAGSAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25290.25290.2\t\t3079.13\t641.3\t2+\t2+\t1280.5918315196802\t0\t-4.977718325629822\t\t\t\t99.82788296041308\tDoubtful\n+389\tGADLSAYATPALRKQGEILSNATTFR, KQGEILSNATTFR, KQGEILSNATTFRFDASDLMR, QGEILSNATTFR\tQGEILSNATTFR\tRK; K; K; \tFD; \t15; 2; 2; 1\tNH2-QGEILSNATTFR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.50359.50359.2\t\t4705.97\t668.84700584093\t2+\t2+\t1335.6782784553102\t0\t0.8823347916760429\t\t\t\t99.82788296041308\tDoubtful\n+390\tIAMAFEQDAFSQDVR, IAMAFEQDAFSQDVRLGILDAAER, IAMAFEQDAFSQDVRLGILDAAK, IAMAFEQDAFSQDVRLGILDAAKRTGSK, IAMAFEQDAFSQDVRLGILDAAKRTK, IAMAFEQDAFSQDVRLGILDAAKRTKSK, IAMAFEQDAFSQDVRLGILDADRK, IAMAFEQDAFSQDVRLGIVEAAK, IAMAFEQDAFSQDVRLGIVEAAKR, IAMAFEQDAFSQDVRLGIVEAAKRTGSK, IAMAFEQDAFSQDVRLGIVEAAKRTKSK, NGGKPVKIAMAFEQDAFSQDVR, NGGKPVKIAMAFEQDAFSQDVRLGIVEAAK, NGGKPVKIAMAFEQDAFSQDVRLGIVEADR, NGGKPVTIAMAFEQDAFSQDVR, SGKPVKIAMAFEQDAFSQDVR\tIAMAFEQDAFSQDVR\tVK; VK; VK; VT; VK\tLG; LG; LG; LG; LG; LG; LG; LG; LG; LG; ; LG; LG; ; \t1; 1; 1; 1; 1; 1; 1; 1; 1; 1; 1; 8; 8; 8; 8; 7\tNH2-IAM<ox>AFEQDAFSQDVR-COOH\tOxidation of M(3)\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.58409.58409.2\t\t5224.32\t872.41\t2+\t2+\t1742.7933848605403\t0\t6.913199770709718\tOxidation of M (3: Very Confident)\tOxidation of M (3: 100.0)\tOxidation of M (3: 100.0)\t99.82788296041308\tDoubtful\n+391\tGLCPGLPDWTALK, GLCPGLPDWTALKNPACAK, GLCPGLPDWTALKNPACAKNFTDRK, GLCPGLPDWTALKNPACAKNFTTPDSGGK, GLCPGLPDWTALKNPDCAK, GLCPGLPDWTALKNPECAANFATPDSDGK, GLCPGLPDWTALKNPECAANFTTPDSDGK, GLCPGLPDWTALKNPECAK, TLEDMGYPNWVADKGLCPGLPDWTALK, TLEDMGYPNWVAEKGLCPGLPDWTALK, TLEDMGYPNWVTDKGLCPGLPDWTALK, TLEDMGYPNWVTEKGLCPGLPDWTALK\tGLCPGLPDWTALK\tDK; EK; DK; EK\tNP; NP; NP; NP; NP; NP; NP; ; ; ; \t1; 1; 1; 1; 1; 1; 1; 1; 15; 15; 15; 15\tNH2-GLC<cmm>PGLPDWTALK-COOH\t\tCarbamidomethylation of C(3)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.79529.79529.2\t\t6580.09\t714.37\t2+\t2+\t1426.7278715000202\t0\t-1.6969004369877572\t\t\t\t9'..b'PNVGESALAK, LGSEEITSDIPNVGESALAK\tLGSEEITSDIPNVGESALAK\tTK; \t\t4; 1\tNH2-LGSEEITSDIPNVGESALAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.68946.68946.2\t\t5898.1\t1015.52\t2+\t2+\t2029.0215297887205\t0\t1.9287090409876295\t\t\t\t99.82788296041308\tDoubtful\n+572\tDVASANKSLGQFNLEGIPNAPK, EIASANKSLGQFNLEGIPNAPK, EVASANKSLGQFNLEGIPNAPK, SLGQFNLEGIPNAPK\tSLGQFNLEGIPNAPK\tNK; NK; NK; \t\t8; 8; 8; 1\tNH2-SLGQFNLEGIPNAPK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.69858.69858.2\t\t5956.17\t792.92060946913\t2+\t2+\t1583.8307563454302\t0\t-2.579281075183206\t\t\t\t99.82788296041308\tDoubtful\n+573\tAQIEETTSDYDKEKLQERLAK, CNQIRAQIEETTSDYDKEKLQERLAK, DDIAARCNQIRAQIEETTSDYDK\tAQIEETTSDYDK\tIR; IR\tEK; EK; \t1; 6; 12\tNH2-AQIEETTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25447.25447.2\t\t3088.77\t700.32\t2+\t2+\t1398.6150690620602\t0\t7.409527938541451\t\t\t\t99.82788296041308\tDoubtful\n+574\tGSNSGTETDFDGK\tGSNSGTETDFDGK\t\t\t1\tNH2-GSNSGTETDFDGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.16731.16731.2\t\t2545.26\t657.77541572833\t2+\t2+\t1313.5371530945304\t0\t-0.6647944664360367\t\t\t\t99.82788296041308\tDoubtful\n+575\tDHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.42848.42848.2\t\t4230.29\t804.36331490613\t2+\t2+\t1606.7110947052206\t0\t0.6105288472506972\t\t\t\t99.82788296041308\tDoubtful\n+576\tETLDVDGVEYPLVK, ETLDVDGVEYPLVKLEISR, ETLDVDGVEYPLVKLEISRTSHPFYTGK, ETLDVDGVEYPLVKLEISRTSHPFYTGKSK, STADTKETLDVDGVEYPLVK, STADTKETLDVDGVEYPLVKLEISR, STAETKETLDVDGVEYPLVK, STAETKETLDVDGVEYPLVKLEISR, STVDTKETLDVDGVEYPLVKLEISR\tETLDVDGVEYPLVK\tTK; TK; TK; TK; TK\tLE; LE; LE; ; LE; ; LE; LE\t1; 1; 1; 1; 7; 7; 7; 7; 7\tNH2-ETLDVDGVEYPLVK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.71416.71416.2\t\t6056.55\t789.41\t2+\t2+\t1575.8032041849103\t1\t-0.7047431996558765\t\t\t\t99.82788296041308\tDoubtful\n+577\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\tGTTNGTETDFNGK\tIK\t\t1; 6\tNH2-GTTNGTETDFNGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.15728.15728.2\t\t2482.1\t671.30017298478\t2+\t2+\t1340.5844376401205\t0\t1.0095313827112857\t\t\t\t99.82788296041308\tDoubtful\n+578\tILTVGDAVNFIAGK\tILTVGDAVNFIAGK\t\t\t1\tNH2-ILTVGDAVNFIAGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.92389.92389.2\t\t7528.49\t709.40717550511\t2+\t2+\t1416.7976653120004\t0\t1.503204277505799\t\t\t\t99.82788296041308\tDoubtful\n+579\tAQIESSTSDYDKEK, AQIESSTSDYDKEKLQERLAK, ARINQIKAQIESSTSDYDK, ARINQIKAQIESSTSDYDKEK, ARINQIKAQIESSTSDYDKEKLQER, ARINQIKAQIESSTSDYDKEKLQERLAK, INQIKAQIESSTSDYDKEKLQERLAK\tAQIESSTSDYDK\tIK; IK; IK; IK; IK\tEK; EK; ; EK; EK; EK; EK\t1; 1; 8; 8; 8; 8; 6\tNH2-AQIESSTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20057.20057.2\t\t2752.89\t672.30099242395\t2+\t2+\t1342.5888543142203\t0\t-1.0578583519601172\t\t\t\t99.82788296041308\tDoubtful\n+580\tEGQAVTMEVTQGQK, RSLQEGQKVTMEVTQGQK, SLKEGQAVTMEVTQGQK, SLKEGQAVTMEVTQGQKGAQAENRSEER\tVTMEVTQGQK\tQA; QK; QA; QA\tGA\t5; 9; 8; 8\tNH2-VTMEVTQGQK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.33393.33393.2\t\t3592.24\t560.78512057349\t2+\t2+\t1119.5594091925902\t0\t-3.317640530281516\t\t\t\t99.82788296041308\tDoubtful\n+581\tDLDKSFGSMPGSMNKKTAGTFASVAK, DLNKSFGSIPGSMNEKTAGTFASVAK, DLNKSFGSIPGSMNKKTAGTFASVAK, DLNKSFGSMPGSMNEKTAGTFASVAK, DLNKSFGSMPGSMNKKTAGTFASVAK, KTAGTFASVAK, SFGSIPGSMNKKTAGTFASVAK, SFGSLPGSMNEKTAGTFASVAK, SFGSMPGSMNEKTAGTFASVAK, SFGSMPGSMNKKTAGTFASVAK, SGSMNKKTAGTFASVAK, TAGTFASVAK\tTAGTFASVAK\tKK; EK; KK; EK; KK; K; KK; EK; EK; KK; KK; \t\t17; 17; 17; 17; 17; 2; 13; 13; 13; 13; 8; 1\tNH2-TAGTFASVAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25503.25503.2\t\t3092.13\t476.76\t2+\t2+\t951.5025459394703\t0\t3.0425536250530647\t\t\t\t99.82788296041308\tDoubtful\n+582\tCGGEPKPSSQWQGENINR\tCGGEPKPSSQWQGENINR\t\t\t1\tNH2-C<cmm>GGEPKPSSQWQGENINR-COOH\t\tCarbamidomethylation of C(1)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.31423.31423.3\t\t3464.93\t681.98\t3+\t3+\t2042.9228358903\t0\t-2.2802624210593576\t\t\t\t99.82788296041308\tDoubtful\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/test.mzml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/test.mzml Fri Jan 05 12:47:36 2018 -0500
b
b'@@ -0,0 +1,26908 @@\n+<?xml version="1.0" encoding="utf-8"?>\n+<indexedmzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.2_idx.xsd">\n+  <mzML xmlns="http://psi.hupo.org/ms/mzml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://psi.hupo.org/ms/mzml http://psidev.info/files/ms/mzML/xsd/mzML1.1.0.xsd" id="2016_Jan_12_QE2_47" version="1.1.0">\n+    <cvList count="2">\n+      <cv id="MS" fullName="Proteomics Standards Initiative Mass Spectrometry Ontology" version="3.74.0" URI="http://psidev.cvs.sourceforge.net/*checkout*/psidev/psi/psi-ms/mzML/controlledVocabulary/psi-ms.obo"/>\n+      <cv id="UO" fullName="Unit Ontology" version="12:10:2011" URI="http://obo.cvs.sourceforge.net/*checkout*/obo/obo/ontology/phenotype/unit.obo"/>\n+    </cvList>\n+    <fileDescription>\n+      <fileContent>\n+        <cvParam cvRef="MS" accession="MS:1000579" name="MS1 spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000127" name="centroid spectrum" value=""/>\n+        <cvParam cvRef="MS" accession="MS:1000580" name="MSn spectrum" value=""/>\n+      </fileContent>\n+      <sourceFileList count="3">\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.raw" name="2016_Jan_12_QE2_47.raw" location="">\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="6f65a1287b2d7522c5fb90a8a5304212b3568b67"/>\n+          <cvParam cvRef="MS" accession="MS:1000563" name="Thermo RAW format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000768" name="Thermo nativeID format" value=""/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzXML" name="2016_Jan_12_QE2_47.mzXML" location="file:///">\n+          <cvParam cvRef="MS" accession="MS:1000776" name="scan number only nativeID format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000566" name="ISB mzXML format" value=""/>\n+          <cvParam cvRef="MS" accession="MS:1000569" name="SHA-1" value="d9c6278c1c6a8f8ca6c69133bacd00efc5f2e706"/>\n+        </sourceFile>\n+        <sourceFile id="_x0032_016_Jan_12_QE2_47.mzML" name="2016_Jan_12_QE2_47.mzML" location="file:////Users/kumar207/Documents/Projects/Pratik/script/../mzML">\n+        </sourceFile>\n+      </sourceFileList>\n+    </fileDescription>\n+    <softwareList count="4">\n+      <software id="Xcalibur_x0020_software" version="2.6-264001/2.6.0.2640">\n+        <cvParam cvRef="MS" accession="MS:1000532" name="Xcalibur" value=""/>\n+      </software>\n+      <software id="ReAdW_x0020_software" version="2015.1.0(build Jun 29 2015 14:09:50)">\n+        <cvParam cvRef="MS" accession="MS:1000541" name="ReAdW" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.8990" version="3.0.8990">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+      <software id="pwiz_3.0.7680" version="3.0.7680">\n+        <cvParam cvRef="MS" accession="MS:1000615" name="ProteoWizard software" value=""/>\n+      </software>\n+    </softwareList>\n+    <instrumentConfigurationList count="1">\n+      <instrumentConfiguration id="IC1">\n+        <userParam name="msManufacturer" value="Thermo Finnigan"/>\n+        <userParam name="msModel" value="unknown"/>\n+        <componentList count="3">\n+          <source order="1">\n+            <userParam name="msIonisation" value="NSI"/>\n+          </source>\n+          <analyzer order="1">\n+            <cvParam cvRef="MS" accession="MS:1000079" name="fourier transform ion cyclotron resonance mass spectrometer" value=""/>\n+          </analyzer>\n+          <detector order="1">\n+            <userParam name="msDetector" value="unknown"/>\n+          </detector>\n+        </componentList>\n+        <softwareRef ref="Xcalibur_x0020_software"/>\n+      </instrumentConfiguration>\n+    </instrumentConfigurationList>\n+    <dataProcessingList count="3">\n+      <dataProcessing id="dataProces'..b'ntrollerNumber=1 scan=90261">2414719</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90324">2418981</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90325">2422771</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90389">2426417</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90825">2430097</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90896">2434045</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90952">2438179</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=90967">2441823</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91020">2445963</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91036">2449647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91084">2453875</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91100">2457676</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91151">2462056</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91167">2465804</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91234">2469798</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91304">2473755</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91379">2477398</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=91464">2481055</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92113">2484679</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92168">2488404</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92183">2492017</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92238">2495975</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92249">2499652</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92303">2503647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92318">2507303</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=92389">2511184</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94116">2514904</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94183">2518552</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94258">2522503</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94332">2526517</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94729">2530126</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94857">2534084</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94919">2538185</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=94980">2541937</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=95063">2545506</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96694">2549319</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96764">2552999</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96836">2556647</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96918">2560122</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=96993">2563742</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=97169">2567598</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99329">2571216</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99385">2574908</offset>\n+      <offset idRef="controllerType=0 controllerNumber=1 scan=99446">2578708</offset>\n+    </index>\n+    <index name="chromatogram">\n+    </index>\n+  </indexList>\n+  <indexListOffset>2582386</indexListOffset>\n+  <fileChecksum>23b8703ddaf744e69e1ba72be2584fd3df6f2dc4</fileChecksum>\n+</indexedmzML>\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/input/test.tabular
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input/test.tabular Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,583 @@\n+\tProtein(s)\tSequence\tAAs Before\tAAs After\tPosition\tModified Sequence\tVariable Modifications\tFixed Modifications\tSpectrum File\tSpectrum Title\tSpectrum Scan Number\tRT\tm/z\tMeasured Charge\tIdentification Charge\tTheoretical Mass\tIsotope Number\tPrecursor m/z Error [ppm]\tLocalization Confidence\tProbabilistic PTM score\tD-score\tConfidence [%]\tValidation\n+1\tAARAGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGKALK, AGRNPQTGAEIQIKAANVPSFKARSEER, HRAARAGRNPQTGAEIQIK, HRAARAGRNPQTGAEIQIKAANVPSFK, HRAARAGRNPQTGAEIQIKAANVPSFKAGK, KGRNPQTGAEIQIKAK\tGRNPQTGAEIQIK\tRA; A; A; A; RA; RA; RA; K\tAA; AA; AA; AA; ; AA; AA; AK\t5; 2; 2; 2; 7; 7; 7; 2\tNH2-GRNPQTGAEIQIK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.24409.24409.2\t\t3023.92\t706.39\t2+\t2+\t1410.7579257583402\t0\t5.323792860535044\t\t\t\t99.82788296041308\tDoubtful\n+2\tNIAELGIYPAVDPLDSTSR\tNIAELGIYPAVDPLDSTSR\t\t\t1\tNH2-NIAELGIYPAVDPLDSTSR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.77693.77693.2\t\t6459.24\t1016.02684441294\t2+\t2+\t2030.03203490277\t0\t3.494501321200086\t\t\t\t99.82788296041308\tDoubtful\n+3\tDHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.49000.49000.2\t\t4619.72\t804.36\t2+\t2+\t1606.7110947052206\t0\t-3.510628958399463\t\t\t\t99.82788296041308\tDoubtful\n+4\tFGCGYEQGAK, FGCGYEQGAKHINANIK, FGCGYEQGAKHINANIKVLQK, FGCGYEQGAKHINANIKVLQKMTR, FGCGYEQGAKHINANITVLQK, FGCGYEQGAKHINTNITVLQK, SESNTIGFIGGMDIPLIAVFGCGYEQGAK, SETGTIGFVGGMDIPLISRFGCGYEQGAK, SGFVGGMDIPLISRFGCGYEQGAK\tFGCGYEQGAK\tAV; SR; SR\tHI; HI; HI; HI; HI; ; ; \t1; 1; 1; 1; 1; 1; 20; 20; 15\tNH2-FGC<cmm>GYEQGAK-COOH\t\tCarbamidomethylation of C(3)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.21525.21525.2\t\t2843.8\t558.74278031655\t2+\t2+\t1115.4705941881903\t0\t0.3700373885771707\t\t\t\t99.82788296041308\tDoubtful\n+5\tDVRVAVFTQGENVEK, DVRVAVFTQGENVEKATAAGDRK, EVRVAVFTQGENVEK, GSTVLPNGTGKDVRVAVFTQGENVEK, GSTVLPNGTGKEVRVAVFTQGENVEK, SGKDVRVAVFTQGENVEK, STGKDVRVAVFTQGENVEK, VAVFTQGENVEK\tVAVFTQGENVEK\tVR; VR; VR; VR; VR; VR; VR; \tAT; ; ; ; ; ; \t4; 4; 4; 15; 15; 7; 8; 1\tNH2-VAVFTQGENVEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.37428.37428.2\t\t3858.93\t660.84407029524\t2+\t2+\t1319.6721304457103\t0\t1.1025390237788624\t\t\t\t99.82788296041308\tDoubtful\n+6\tEVASQTSDVAGDGTTTATVLAQAILNEGLK\tEVASQTSDVAGDGTTTATVLAQAILNEGLK\t\t\t1\tNH2-EVASQTSDVAGDGTTTATVLAQAILNEGLK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.96993.96993.3\t\t7882.73\t987.84\t3+\t3+\t2959.4985892563404\t1\t-1.2737446644704296\t\t\t\t99.82788296041308\tDoubtful\n+7\tAYAKKVMKYLLMNQPNYKLAYENEFGPIGK, KTMKYLLMNQPNYKLAYENEFGPIGKVK, KVMKYLLMNQPNYKLAYENEFGPIGK, KVMKYLLMNQPNYKLAYENEFGPIGKVK, LAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGKVK, YLLMNQPNYKLAYENEFGPIGK\tLAYENEFGPIGK\tYK; YK; YK; YK; ; YK; YK; YK\tVK; ; VK; ; ; VK; \t19; 15; 15; 15; 1; 15; 15; 11\tNH2-LAYENEFGPIGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.58393.58393.2\t\t5223.31\t669.34135435161\t2+\t2+\t1336.6663167892802\t0\t1.373725700567889\t\t\t\t99.82788296041308\tDoubtful\n+8\tEASLHISNVMLVEDGVAVRVGYQVDGDTK, EASLHISNVMLVEGGVAVRVGYQVDGDTK, KEASLHISNVMLVEDGVAVRVGYQVDGDTK, KEASLHISNVMLVEGGVAVRVGYQVDGDTK, VGYQVDGDTKTR, VGYQVDGDTKTRISK, VGYQVDGDTKTRISKK, VGYQVDGDTKTRVSK\tVGYQVDGDTK\tVR; VR; VR; VR; ; ; ; \tTR; TR; TR; TR\t20; 20; 21; 21; 1; 1; 1; 1\tNH2-VGYQVDGDTK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20503.20503.2\t\t2780.07\t541.26176990816\t2+\t2+\t1080.5087535187201\t0\t0.2155740890529847\t\t\t\t99.82788296041308\tDoubtful\n+9\tFKDWDDLNKPDVRVAATLGTTQEK, FKDWDDLNKPDVRVAATLGTTQEKQVK, SNADRFKDWDDLNKPDVRVAATLGTTQEK, VAATLGTTQEKQVK, VAATLGTTQEKQVKEYFPNAK, VAATLGTTQEKQVKSYFPDAK\tVAATLGTTQEK\tVR; VR; VR; ; ; \tQV; ; QV; QV; QV\t14; 14; 19; 1; 1; 1\tNH2-VAATLGTTQEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.16356.16356.2\t\t2521.67\t559.80640770461\t2+\t2+\t1117.5979028762904\t0\t0.32118194438209224\t\t\t\t99.82788296041308\tDo'..b'PNVGESALAK, LGSEEITSDIPNVGESALAK\tLGSEEITSDIPNVGESALAK\tTK; \t\t4; 1\tNH2-LGSEEITSDIPNVGESALAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.68946.68946.2\t\t5898.1\t1015.52\t2+\t2+\t2029.0215297887205\t0\t1.9287090409876295\t\t\t\t99.82788296041308\tDoubtful\n+572\tDVASANKSLGQFNLEGIPNAPK, EIASANKSLGQFNLEGIPNAPK, EVASANKSLGQFNLEGIPNAPK, SLGQFNLEGIPNAPK\tSLGQFNLEGIPNAPK\tNK; NK; NK; \t\t8; 8; 8; 1\tNH2-SLGQFNLEGIPNAPK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.69858.69858.2\t\t5956.17\t792.92060946913\t2+\t2+\t1583.8307563454302\t0\t-2.579281075183206\t\t\t\t99.82788296041308\tDoubtful\n+573\tAQIEETTSDYDKEKLQERLAK, CNQIRAQIEETTSDYDKEKLQERLAK, DDIAARCNQIRAQIEETTSDYDK\tAQIEETTSDYDK\tIR; IR\tEK; EK; \t1; 6; 12\tNH2-AQIEETTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25447.25447.2\t\t3088.77\t700.32\t2+\t2+\t1398.6150690620602\t0\t7.409527938541451\t\t\t\t99.82788296041308\tDoubtful\n+574\tGSNSGTETDFDGK\tGSNSGTETDFDGK\t\t\t1\tNH2-GSNSGTETDFDGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.16731.16731.2\t\t2545.26\t657.77541572833\t2+\t2+\t1313.5371530945304\t0\t-0.6647944664360367\t\t\t\t99.82788296041308\tDoubtful\n+575\tDHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.42848.42848.2\t\t4230.29\t804.36331490613\t2+\t2+\t1606.7110947052206\t0\t0.6105288472506972\t\t\t\t99.82788296041308\tDoubtful\n+576\tETLDVDGVEYPLVK, ETLDVDGVEYPLVKLEISR, ETLDVDGVEYPLVKLEISRTSHPFYTGK, ETLDVDGVEYPLVKLEISRTSHPFYTGKSK, STADTKETLDVDGVEYPLVK, STADTKETLDVDGVEYPLVKLEISR, STAETKETLDVDGVEYPLVK, STAETKETLDVDGVEYPLVKLEISR, STVDTKETLDVDGVEYPLVKLEISR\tETLDVDGVEYPLVK\tTK; TK; TK; TK; TK\tLE; LE; LE; ; LE; ; LE; LE\t1; 1; 1; 1; 7; 7; 7; 7; 7\tNH2-ETLDVDGVEYPLVK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.71416.71416.2\t\t6056.55\t789.41\t2+\t2+\t1575.8032041849103\t1\t-0.7047431996558765\t\t\t\t99.82788296041308\tDoubtful\n+577\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\tGTTNGTETDFNGK\tIK\t\t1; 6\tNH2-GTTNGTETDFNGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.15728.15728.2\t\t2482.1\t671.30017298478\t2+\t2+\t1340.5844376401205\t0\t1.0095313827112857\t\t\t\t99.82788296041308\tDoubtful\n+578\tILTVGDAVNFIAGK\tILTVGDAVNFIAGK\t\t\t1\tNH2-ILTVGDAVNFIAGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.92389.92389.2\t\t7528.49\t709.40717550511\t2+\t2+\t1416.7976653120004\t0\t1.503204277505799\t\t\t\t99.82788296041308\tDoubtful\n+579\tAQIESSTSDYDKEK, AQIESSTSDYDKEKLQERLAK, ARINQIKAQIESSTSDYDK, ARINQIKAQIESSTSDYDKEK, ARINQIKAQIESSTSDYDKEKLQER, ARINQIKAQIESSTSDYDKEKLQERLAK, INQIKAQIESSTSDYDKEKLQERLAK\tAQIESSTSDYDK\tIK; IK; IK; IK; IK\tEK; EK; ; EK; EK; EK; EK\t1; 1; 8; 8; 8; 8; 6\tNH2-AQIESSTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20057.20057.2\t\t2752.89\t672.30099242395\t2+\t2+\t1342.5888543142203\t0\t-1.0578583519601172\t\t\t\t99.82788296041308\tDoubtful\n+580\tEGQAVTMEVTQGQK, RSLQEGQKVTMEVTQGQK, SLKEGQAVTMEVTQGQK, SLKEGQAVTMEVTQGQKGAQAENRSEER\tVTMEVTQGQK\tQA; QK; QA; QA\tGA\t5; 9; 8; 8\tNH2-VTMEVTQGQK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.33393.33393.2\t\t3592.24\t560.78512057349\t2+\t2+\t1119.5594091925902\t0\t-3.317640530281516\t\t\t\t99.82788296041308\tDoubtful\n+581\tDLDKSFGSMPGSMNKKTAGTFASVAK, DLNKSFGSIPGSMNEKTAGTFASVAK, DLNKSFGSIPGSMNKKTAGTFASVAK, DLNKSFGSMPGSMNEKTAGTFASVAK, DLNKSFGSMPGSMNKKTAGTFASVAK, KTAGTFASVAK, SFGSIPGSMNKKTAGTFASVAK, SFGSLPGSMNEKTAGTFASVAK, SFGSMPGSMNEKTAGTFASVAK, SFGSMPGSMNKKTAGTFASVAK, SGSMNKKTAGTFASVAK, TAGTFASVAK\tTAGTFASVAK\tKK; EK; KK; EK; KK; K; KK; EK; EK; KK; KK; \t\t17; 17; 17; 17; 17; 2; 13; 13; 13; 13; 8; 1\tNH2-TAGTFASVAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25503.25503.2\t\t3092.13\t476.76\t2+\t2+\t951.5025459394703\t0\t3.0425536250530647\t\t\t\t99.82788296041308\tDoubtful\n+582\tCGGEPKPSSQWQGENINR\tCGGEPKPSSQWQGENINR\t\t\t1\tNH2-C<cmm>GGEPKPSSQWQGENINR-COOH\t\tCarbamidomethylation of C(1)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.31423.31423.3\t\t3464.93\t681.98\t3+\t3+\t2042.9228358903\t0\t-2.2802624210593576\t\t\t\t99.82788296041308\tDoubtful\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/make_test_data.sh
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/make_test_data.sh Fri Jan 05 12:47:36 2018 -0500
b
@@ -0,0 +1,41 @@
+#!/bin/bash
+
+#must be run within tools-galaxyp/tools/moFF/test-data
+
+conda create -n mofftestdata moff
+source activate mofftestdata
+
+moff_all.py --inputtsv input/mbr_test1.tabular input/mbr_test2.tabular \
+    --inputraw input/mbr_test1.mzml input/mbr_test2.mzml \
+    --tol 10 \
+    --rt_w 3 \
+    --rt_p 1 \
+    --rt_p_match 1.2 \
+    --peptide_summary 1 \
+    --output_folder output1
+
+moff.py --inputtsv input/test.tabular \
+    --inputraw input/test.mzml \
+    --tol 10 \
+    --rt_w 3 \
+    --rt_p 1 \
+    --rt_p_match 1.2 \
+    --peptide_summary 1 \
+    --output_folder output2
+mv output2/peptide_summary_intensity_moFF_run.tab output2/moff_test_pepsum.tab
+
+moff_mbr.py \
+    --inputF input \
+    --ext tabular \
+    --sample mbr_*
+
+
+# clean up 
+# mbr outputs for moff all
+rm -r output1/mbr_output
+
+# logs
+rm output1/*.log output2/*.log
+
+# peptide summary for all
+rm output1/peptide_summary_intensity_moFF_run.tab
b
diff -r 000000000000 -r b4098353ee73 test-data/output1/mbr_test1_match_moff_result.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output1/mbr_test1_match_moff_result.txt Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,265 @@\n+aas after\taas before\tcharge\tcode_unique\tconfidence [%]\td-score\tfixed modifications\tidentification charge\tisotope number\tlocalization confidence\tmass\tmatched\tmod_peptide\tmz\tpeptide\tposition\tprecursor m/z error [ppm]\tprobabilistic ptm score\tprot\trt\tspectrum file\tspectrum scan number\tspectrum title\tvalidation\tvariable modifications\tintensity\trt_peak\tlwhm\trwhm\t5p_noise\t10p_noise\tSNR\tlog_L_R\tlog_int\n+DA; ; DA\tIK; ; ; IK; IK\t2+\tNH2-QVEEAVQSDDK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1246.5677\t0\tNH2-QVEEAVQSDDK-COOH\t624.292668193\tQVEEAVQSDDK\t15; 1; 1; 9; 9\t2.44958264245\t\tASDEEKVAIEAGIKQVEEAVQSDDK, QVEEAVQSDDK, QVEEAVQSDDKDAIDEAAK, VAIEAGIKQVEEAVQSDDK, VAIEAGIKQVEEAVQSDDKDAIDEAAK\t2125.86\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.10613.10613.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+FT; FT; FT\t\t2+\tNH2-GTTNGTSTDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1298.5739\t0\tNH2-GTTNGTSTDFNGK-COOH\t650.293779699\tGTTNGTSTDFNGK\t1; 1; 1; 1\t-0.666230198055\t\tGTTNGTSTDFNGK, GTTNGTSTDFNGKFTLQAK, GTTNGTSTDFNGKFTLQAKSDSGR, GTTNGTSTDFNGKFTLQSK\t2274.86\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.12577.12577.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\tNH2-ADAHITSNVEANK-COOH\t99.8278829604\t\t\t2+\t1.0\t\t1368.6634\t0\tNH2-ADAHITSNVEANK-COOH\t685.84\tADAHITSNVEANK\t1\t-0.922491400517\t\tADAHITSNVEANK\t2338.13\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13537.13537.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\tEK\t2+\tNH2-AGATANDSLDDGNAGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1475.6488\t0\tNH2-AGATANDSLDDGNAGK-COOH\t738.832041435\tAGATANDSLDDGNAGK\t5\t0.474488705639\t\tAREKAGATANDSLDDGNAGK\t2344.0\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13631.13631.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\tEK\t2+\tNH2-AGATANDSLDDGNAGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1475.6488\t0\tNH2-AGATANDSLDDGNAGK-COOH\t738.833460428\tAGATANDSLDDGNAGK\t5\t2.39507898017\t\tAREKAGATANDSLDDGNAGK\t2349.33\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13710.13710.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+KG; ; K; KG; KD; KG; KG; KD; KG\tVR; VR; VR; VR; VR; VR; VR; ; \t2+\tNH2-NPATGESFK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t949.4505\t0\tNH2-NPATGESFK-COOH\t475.732747603\tNPATGESFK\t9; 13; 13; 13; 4; 4; 4; 1; 1\t0.453938376043\t\tERPERMVRNPATGESFKKGADKVVK, IYCRERPERMVRNPATGESFK, IYCRERPERMVRNPATGESFKK, IYCRERPERMVRNPATGESFKKGADK, MVRNPATGESFKKDADKVVKMTIAKALK, MVRNPATGESFKKGADKVVKMTIAK, MVRNPATGESFKKGADKVVKMTIAKALK, NPATGESFKKDADRVVKMTIAKALK, NPATGESFKKGADKVVKMTIAKALK\t2475.54\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15623.15623.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.301568419\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t1.41518840069\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2482.71\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15737.15737.2\tDoubtful\tOxidation of M(2)\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.3\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t-1.00036313327\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2494.56\ttrimmed_2016_Jan_12_QE2'..b'NSFFKSTTELTSSEQVKALCDGKR, GVSNSFFKSTTELTSSEQVK, GVSNSFFKSTTELTSSEQVKALCDGK, NSFFKSTTELTSSEQVKALCDGK, SAKGVNNSFFKSTTELTSSEQVK, SDAKGVSNSFFKSTTELTSSEQVK, SNSFFKSTTELTSSEQVKALCDGK, SSDLFKSTTELTSSEQVKALCDGK, STTELTSSEQVK, STTELTSSEQVKADRK, STTELTSSEQVKALCDGK, STTELTSSEQVKALCDGKIDAFGR, STTELTSSEQVKALCDGKIDAFGYR, STTELTSSEQVKALCDGKIDAFGYSEIGR, STTELTSSEQVKALCDGKIDAFGYSVR, STTELTSSEQVKALCDGKIDAFRSEER, SVLMDAKGVNNSFFKSTTELTSSEQVK\t2821.27314818\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1952.0215\t1\t\t977.52\tTAGGIIIPDTAQEKPQEGK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4102.46028615\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t3+\t\t\t\t\t\t\t\t1952.0215\t1\t\t651.684056525\tTAGGIIIPDTAQEKPQEGK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4097.89567617\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t951.5025\t1\t\t476.76\tTAGTFASVAK\t\t\t\tDLDKSFGSMPGSMNKKTAGTFASVAK, DLNKSFGSIPGSMNEKTAGTFASVAK, DLNKSFGSIPGSMNKKTAGTFASVAK, DLNKSFGSMPGSMNEKTAGTFASVAK, DLNKSFGSMPGSMNKKTAGTFASVAK, KTAGTFASVAK, SFGSIPGSMNKKTAGTFASVAK, SFGSLPGSMNEKTAGTFASVAK, SFGSMPGSMNEKTAGTFASVAK, SFGSMPGSMNKKTAGTFASVAK, SGSMNKKTAGTFASVAK, TAGTFASVAK\t3093.88124482\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t2089.0539\t1\t\t1046.03\tTNDEAGDGTTTATILAQAIVK\t\t\t\tEVASRTNDEAGDGTTTATILAQAIVK, TNDEAGDGTTTATILAQAIVK, TNDEAGDGTTTATILAQAIVKEGMK\t6407.89796011\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1074.5306\t1\t\t538.271566384\tTTGDIQVEGR\t\t\t\tTTGDIQVEGR, TTGDIQVEGRVDGDIR, TTGDIQVEGRVEGDIR\t2772.79039798\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1436.7147\t1\t\t719.37\tTTPSIVAFTESER\t\t\t\tTTPSIVAFTESER, TTPSIVAFTESERLVGQPAK, TTPSIVAFTESERLVGQPAKR, VIENAEGARTTPSIVAFTESER, VIENAEGARTTPSIVAFTESERLVGQPAK\t5425.87755759\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1479.7093\t1\t\t740.86\tTTPSVVAFTEDGEK\t\t\t\tSENAEGARTTPSVVAFTEDGEK, SGARTTPSVVAFTEDGEK, TTPSVVAFTEDGEK, TTPSVVAFTEDGEKLEIGRAVQQECRDR, TTPSVVAFTEDGEKLVGQPAK, TTPSVVAFTEDGEKLVGQPAKR, TTPSVVAFTEDGEKLVGQPAKRQDRK, TTPSVVAFTEDGEKLVGQPDRK, TTPSVVAFTEDGEKLVGQSAKR, VLENAEGARTTPSVVAFTEDGEK, VLENAEGARTTPSVVAFTEDGEKLVGQPAK, VLENAEGTRTTPSVVAFTEDGEK, VLENTEGARTTPSVVAFTEDGEK\t4801.18521199\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1072.5401\t1\t\t537.28\tVEADLVENGK\t\t\t\tDIEVGSPKIEGAKVEADLVENGKNR, GAKVEADLVENGKNRTILIFKKRRR, IIEVGSPTVEGAKVEADLVENGKNR, NIEVGSPIVEGAKVEADLVENGKNR, NIEVGSPTVEGAKVEADLVENGK, NIEVGSPTVEGAKVEADLVENGKNR, SIEVGSPTVEGAKVEADLVENGK, SIEVGSPTVEGAKVEADLVENGKNR, SIEVGSPVVEGAKVEADLVENGK, SIEVGSPVVEGAKVEADLVENGKNR, TIEVGSPTVEGAKVEADLVENGKNR, TIEVGSPTVKGAKVEADLVENGKNR, TIEVGSPVVEGAKVEADLVENGK, TIEVGSPVVEGAKVEADLVENGKNR, VEADLVENGK, VEADLVENGKNR, VEADLVENGKNRTDRK, VEADLVENGKNRTILIFK, VEADLVENGKNRTILIFKK, VEADLVENGKNRTILIFKKR, VEADLVENGKNRTILIFKKRR, VEADLVENGKNRTILIFKKRRKIGR, VEADLVENGKNRTILIFKKRRR, VEADLVENGKNRTILIFKKRRRQNSKIGR, VEADLVENGKNRTILIFKKRRRQNSR, VEADLVENGKNRTILIFKKRRRQNSRDRK, VEADLVENGKNRTILIFKKRRRQNSRR, VEADLVENGKNRTILIFKKRRRQNSRRK\t3019.65888868\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1073.5175\t1\t\t537.77\tVIDNMPETR\t\t\t\tIAHVDYQRVIDNMPETR, IAHVDYQRVIDNMPETRALTVTLEK, IGHIDYQRVIDNMPETRALGTTLEKLGK, IGHVDYQRVIDNMPETR, IGHVDYQRVIDNMPETRALTVTLEK, IGHVDYQRVIDNMPETRALTVTLEKLGK, VIDNMPETRALGTTLEKLGK, VIDNMPETRALTVTLEKLGK, VIDNMPETRALTVTLEKLGKSYQSEIEGLK\t3137.58963272\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1124.4887\t1\t\t563.252254136\tWADETGGSFR\t\t\t\tFDKSFNEAAFAGAQRWADETGGSFR, FDKSFNEAAFKGAERWADETGGSFR, GAERWADETGGSFREVELQSEAQR, SFNEAAFAGAQRWADETGGSFR, SFNESAFTGAQRWADETGGSFR, WADETGGSFR, WADETGGSFREIELQSEAQR, WADETGGSFREIELQSEAQREQALR, WADETGGSFREIELQSEAQREQALRR\t3912.1250394\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/output1/mbr_test2_match_moff_result.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output1/mbr_test2_match_moff_result.txt Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,260 @@\n+aas after\taas before\tcharge\tcode_unique\tconfidence [%]\td-score\tfixed modifications\tidentification charge\tisotope number\tlocalization confidence\tmass\tmatched\tmod_peptide\tmz\tpeptide\tposition\tprecursor m/z error [ppm]\tprobabilistic ptm score\tprot\trt\tspectrum file\tspectrum scan number\tspectrum title\tvalidation\tvariable modifications\tintensity\trt_peak\tlwhm\trwhm\t5p_noise\t10p_noise\tSNR\tlog_L_R\tlog_int\n+EV; ; EV; ; EV\tNW; NW; NW; NW; NW; NW\t2+\tNH2-RDVGINNTVK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1114.6095\t0\tNH2-RDVGINNTVK-COOH\t558.312235432\tRDVGINNTVK\t10; 10; 10; 10; 10; 10\t0.400593042907\t\tLVELAGQNWRDVGINNTVK, LVELAGQNWRDVGINNTVKEVTTDEYR, LVEVAGQNWRDVGINNTVK, LVEVAGQNWRDVGINNTVKEVTTDEYR, LVEVTGQNWRDVGINNTVK, LVEVTGQNWRDVGINNTVKEVTTDEYR\t2322.17\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13283.13283.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t3+\tNH2-ADAHITSNVEANK-COOH\t99.8278829604\t\t\t3+\t0.0\t\t1368.6634\t0\tNH2-ADAHITSNVEANK-COOH\t457.23\tADAHITSNVEANK\t1\t3.50950236447\t\tADAHITSNVEANK\t2335.35\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.13493.13493.3\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DF; DF; DF; DF; ; DF; DF; DF; \tAK; AK; ; ; ; AK; AK; AK; S; AK\t2+\tNH2-HQIVEAPAR-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1019.5512\t0\tNH2-HQIVEAPAR-COOH\t510.783866967\tHQIVEAPAR\t8; 8; 1; 1; 1; 8; 8; 8; 2; 16\t1.91229342584\t\tDFFPNAKHQIVEAPAR, DFFPNAKHQIVEAPARDFQEVLSMR, HQIVEAPARDFQEVLSMR, HQIVEAPARDFQEVLSMRADAHITSNVEAK, HQIVEAPARDFQEVLSMRDRK, QFFPNAKHQIVEAPAR, QFFPNAKHQIVEAPARDFQEVLSMR, QFFPNAKHQIVEAPARDFQEVR, SHQIVEAPARDFQEVLSMR, STQETQVKQFFPNAKHQIVEAPAR\t2384.64\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.14185.14185.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+YI; YI; ; ; YI; ; ; ; ; ; YI; YI\tLR; LR; LR; LR; ; ; LR; LR; LR; LA; LR; LR; LR\t2+\tNH2-EM<ox>TSTEGLAGSAK-COOH\t99.8278829604\tOxidation of M (2: 100.0)\t\t2+\t0.0\tOxidation of M (2: Very Confident)\t1296.5867\t0\tNH2-EM<ox>TSTEGLAGSAK-COOH\t649.301048825\tEMTSTEGLAGSAK\t7; 7; 7; 16; 1; 1; 16; 16; 16; 4; 4; 4; 4\t0.614952377062\tOxidation of M (2: 100.0)\tAMKVLREMTSTEGLAGSAK, AMKVLREMTSTEGLAGSAKYIAYAPWR, AMKVLREMTSTEGLAGSAKYIAYAPWRK, DGPGYADGSAMKVLREMTSTEGLAGSAK, EMTSTEGLAGSAK, EMTSTEGLAGSAKYIAYAPWRK, GGPNDANGEAMKVLREMTSTEGLAGSAK, GGPNDANGKAMKVLREMTSTEGLAGSAK, GGPNDANGNAMKVLREMTSTEGLAGSAK, VLAEMTSTEGLAGSAK, VLREMTSTEGLAGSAK, VLREMTSTEGLAGSAKYIAYAPWR, VLREMTSTEGLAGSAKYIAYAPWRK\t2476.83\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15644.15644.2\tDoubtful\tOxidation of M(2)\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\tIK\t2+\tNH2-GTTNGTETDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1340.5844\t0\tNH2-GTTNGTETDFNGK-COOH\t671.300172985\tGTTNGTETDFNGK\t1; 6\t1.00953138271\t\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\t2482.1\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15728.15728.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\tIK\t2+\tNH2-GTTNGTETDFNGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1340.5844\t0\tNH2-GTTNGTETDFNGK-COOH\t671.3\tGTTNGTETDFNGK\t1; 6\t0.751844938295\t\tGTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\t2494.5\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.15922.15922.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+SD\t\t2+\tNH2-EGGEDM<ox>FVHK-COOH\t99.8278829604\tOxidation of M (6: 100.0)\t\t2+\t0.0\tOxidation of M (6: Very Confident)\t1163.4917\t0\tNH2-EGGEDM<ox>FVHK-COOH\t582.752485263\tEGGEDMFVHK\t1\t-1.12051106098\tOxidation of M (6: 100.0)\tEGGEDMFVHKSDVDGFINEGDK\t2536.63\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.16595.16595.2\tDoubtful\tOxidation of M(6)\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\tNH2-GSNSGTETDFDGK-COOH\t99.8278829604\t\t\t2+\t0.0\t\t1313.5372\t0\tNH2-GSNSGTETDFDGK-COOH\t657.775415728\tGSNSGTETDFDGK\t1\t-0.664794466436\t\tGSNSGTETDFDGK\t2545.26\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.16731.16731.2\tDoubtful\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+GN\tDK; ; \t2+\tNH2-SAQEAM<ox>DSVVER-COOH\t99.8278829604\tOxidation of M (6: 100.0)\t\t2+\t0.0\tOxidation of M (6: Very Confident)\t1336.5929\t0\tNH2-SAQEAM<ox>DSVVER-COOH\t669.3\tSAQEAMDSVVER\t16; 1; 1\t-5.56330571801\tOxidation of M (6: 100.0)\tGIIDEELEAIWAGDKSAQEAMDSVVER, SAQEAMDSVVER, SAQEAMDSVVERGNPLLRR\t2569.05\ttrimmed_2016_Jan_12_QE2_47.mgf\t\t2016_Jan_12_QE2_47.171'..b'PGGEIQPAMK, TVGLAADVLLEMGMSVVQLPGGEIQPAMK, TVGLAADVLMEMGMSVVQLPGGEIQPAMK, TVGLATNVLTAMGMVVRQLPGGEIQPAMK\t3363.02180749\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1246.5677\t1\t\t624.292668193\tQVEEAVQSDDK\t\t\t\tASDEEKVAIEAGIKQVEEAVQSDDK, QVEEAVQSDDK, QVEEAVQSDDKDAIDEAAK, VAIEAGIKQVEEAVQSDDK, VAIEAGIKQVEEAVQSDDKDAIDEAAK\t2123.81104393\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t3+\t\t\t\t\t\t\t\t1339.7208\t1\t\t447.580299459\tRNIADTGILPDR\t\t\t\tIIKQVGNYGESYKRNIADTGILPDR, IIKQVGNYGESYKRNIADTGILPDRGDRK, IIKQVGNYGESYKRNIADTGILPDRGPNR, IIKQVGNYGESYKRNIADTGILPDRK, IIKQVGNYGESYKRNLADTGILPDR, QVGNYGESYKRNIADTGILPDR, RNIADTGILPDR, RNIADTGILPDRGPNALWTK, RNIADTGILPDRGPNNIWTK, RNIADTGILPDRGPNNIWTQGGLLYK, RNIADTGILPDRGPNQIWTK, RNIADTGILPDRGPNQLWTK, RNIADTGILPDRSEERFSR\t4216.94654823\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1304.6725\t1\t\t653.344403594\tSNDLQNIVQFK\t\t\t\tASEPVYRSNDLQNIVQFK, ASEPVYRSNDLQNIVQFKTTSYDFYR, SNDLQNIVQFK, SNDLQNIVQFKTTSYDFYR\t5603.17553205\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1138.6598\t1\t\t570.339000439\tSPLPIDIVSAK\t\t\t\tSNTKSPLPIDIVSAK, SNTKSPLPIDIVSAKDLVATGQTTFDK, SNTKSPLPIDIVSAKDLVSTGQTTFDK, TPQRSNTKSPLPIDIVSAK\t5586.98140853\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1573.8464\t1\t\t787.933125991\tSVQAVQPSGNYAIIK\t\t\t\tIIAKSVQAVQPSGNYAIIK, SVQAVQPSGNYAIIK\t4580.01319267\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1412.7511\t1\t\t707.38\tTAGGIIIPDTAQEK\t\t\t\tSSEKTAGGIIIPDTAQEKPQEGK, SSSEKTAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPDRK, TAGGIIIPDTAQEKPQEGK, TAGGIIIPDTAQEKPQEGKVIAVEIGR, TAGGIIIPDTAQEKPQEGKVIAVGGGAK, TAGGIIIPDTAQEKPQEGKVIAVGR, TAGGIIIPDTAQEKPQEGKVVAVGDRK, VLIEVLDSSEKTAGGIIIPDTAQEK, VLIEVLDSSEKTAGGIIIPDTAQEKPQEGK, VLIEVLNSSEKTAGGIIIPDTAQEKPQEGK, VLIQVLDSSEKTAGGIIIPDTAQEKPQEGK\t4444.24478379\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1564.8348\t1\t\t783.42\tTFDTITNTILDALK\t\t\t\tADAERTFDTITNTILDALK, ADAERTFDTITNTILDALKGDDSVK, ADAERTFDTITNTILDALKGDDTVK, ADAERTFDTITNTILDALKGDR, LSGSLNLSKADAERTFDTITNTILDALK, TFDTITNTILDALK, TFDTITNTILDALKGDDTVK, TFDTITNTILDALKGDDTVKIAGFGTYK, TFDTITNTILDALKGDEIGR\t8085.1301405\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t858.4811\t1\t\t430.248420613\tTGEAIQIK\t\t\t\tAATTGRNPRTGEAIQIK, AATTGRNPRTGEAIQIKASKQPKFK, NPRTGEAIQIKASKQPKFK, NPRTGEAIQIKASKQPKFKAGSPLK\t3005.20974577\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1117.5979\t1\t\t559.806407705\tVAATLGTTQEK\t\t\t\tFKDWDDLNKPDVRVAATLGTTQEK, FKDWDDLNKPDVRVAATLGTTQEKQVK, SNADRFKDWDDLNKPDVRVAATLGTTQEK, VAATLGTTQEKQVK, VAATLGTTQEKQVKEYFPNAK, VAATLGTTQEKQVKSYFPDAK\t2519.96654644\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1080.5088\t1\t\t541.261769908\tVGYQVDGDTK\t\t\t\tEASLHISNVMLVEDGVAVRVGYQVDGDTK, EASLHISNVMLVEGGVAVRVGYQVDGDTK, KEASLHISNVMLVEDGVAVRVGYQVDGDTK, KEASLHISNVMLVEGGVAVRVGYQVDGDTK, VGYQVDGDTKTR, VGYQVDGDTKTRISK, VGYQVDGDTKTRISKK, VGYQVDGDTKTRVSK\t2778.59210377\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1352.7228\t1\t\t677.87\tVLIDYLVDEFK\t\t\t\tVLIDYLVDEFKKKEGVDLTSDSTAMTRIR\t7737.85727042\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1405.6937\t1\t\t703.854502277\tVTSDEESGQTIIK\t\t\t\tEDPSFRVTSDEESGQTIIK, EDPSFRVTSDEESGQTIIKGMEIGR, LAKEDPSFRVTSDEESGQTIIK, LAKEDPSFRVTSDEESGQTIIKGDRK, LAKEDPSFRVTSDEESGQTIIKGMGR, LAKEDPSFRVTSDEESGQTIIKGMR, LAKEDPSFRVTSDEESGQTIIKGR, MGEALARLAKEDPSFRVTSDEESGQTIIK, MGEALGRLAKEDPSFRVTSDEESGQTIIK, SALARLAKEDPSFRVTSDEESGQTIIK, SVTSDEESGQTIIK, VTSDEESGQTIIK, VTSDEESGQTIIKGMGELHLDIIVDR, VTSDEESGQTIIKGMGELHLDIIVDRMK, VTSDEESGQTIIKGMGELHLDIIVDRMKR, VTSDEESGQTIIKGMRSEERFSR\t3269.48022626\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+\t\t2+\t\t\t\t\t\t\t\t1170.6105\t1\t\t586.312380654\tVVNIGNAGSGQR\t\t\t\tAKVKDFAGLKGKVVNIGNAGSGQR, DFAGLEGKVVNIGNAGSGQR, DFAGLKGKVVNIGNAGSGQR, DFAGLKGKVVNIGNAGSGQRGTMEVLMDAK, GKVVNIGNAGSGQR, GKVVNIGNAGSGQRGTMEVLMDAK, GKVVNIGNAGSGQRGTMEVLMDAKGVK, GKVVNIGNAGSGQRGTMEVLMNAK, KAKVKDFAGLEGKVVNIGNAGSGQR, KAKVKDFAGLKGKVVNIGNAGSGQR, KAKVKDFAGLKGKVVNIGNAGSGQRGDRK, KKAKVKDFAGLEGKVVNIGNAGSGQR, KKAKVKDFAGLKGKVVNIGNAGSGQR, VKDFAGLEGKVVNIGNAGSGQR, VKDFAGLKGKVVNIGNAGSGQR, VVNIGNAGSGQR, VVNIGNAGSGQRGTMEVLMDAK, VVNIGNAGSGQRGTMEVLMDAKGVK, VVNIGNAGSGQRGTMEVLMDAKGVNNSFFK\t2759.48544012\t\t\t\t\t\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n'
b
diff -r 000000000000 -r b4098353ee73 test-data/output2/moff_test_pepsum.tab
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output2/moff_test_pepsum.tab Fri Jan 05 12:47:36 2018 -0500
b
@@ -0,0 +1,1 @@
+peptide prot sumIntensity_test
b
diff -r 000000000000 -r b4098353ee73 test-data/output2/test_moff_result.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output2/test_moff_result.txt Fri Jan 05 12:47:36 2018 -0500
[
b'@@ -0,0 +1,583 @@\n+prot\tpeptide\taas before\taas after\tposition\tmod_peptide\tvariable modifications\tfixed modifications\tspectrum file\tspectrum title\tspectrum scan number\trt\tmz\tcharge\tidentification charge\tmass\tisotope number\tprecursor m/z error [ppm]\tlocalization confidence\tprobabilistic ptm score\td-score\tconfidence [%]\tvalidation\tintensity\trt_peak\tlwhm\trwhm\t5p_noise\t10p_noise\tSNR\tlog_L_R\tlog_int\n+AARAGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGK, AGRNPQTGAEIQIKAANVPSFKAGKALK, AGRNPQTGAEIQIKAANVPSFKARSEER, HRAARAGRNPQTGAEIQIK, HRAARAGRNPQTGAEIQIKAANVPSFK, HRAARAGRNPQTGAEIQIKAANVPSFKAGK, KGRNPQTGAEIQIKAK\tGRNPQTGAEIQIK\tRA; A; A; A; RA; RA; RA; K\tAA; AA; AA; AA; ; AA; AA; AK\t5; 2; 2; 2; 7; 7; 7; 2\tNH2-GRNPQTGAEIQIK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.24409.24409.2\t\t3023.92\t706.39\t2+\t2+\t1410.75792576\t0\t5.32379286054\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+NIAELGIYPAVDPLDSTSR\tNIAELGIYPAVDPLDSTSR\t\t\t1\tNH2-NIAELGIYPAVDPLDSTSR-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.77693.77693.2\t\t6459.24\t1016.02684441\t2+\t2+\t2030.0320349\t0\t3.4945013212\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.49000.49000.2\t\t4619.72\t804.36\t2+\t2+\t1606.71109471\t0\t-3.5106289584\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+FGCGYEQGAK, FGCGYEQGAKHINANIK, FGCGYEQGAKHINANIKVLQK, FGCGYEQGAKHINANIKVLQKMTR, FGCGYEQGAKHINANITVLQK, FGCGYEQGAKHINTNITVLQK, SESNTIGFIGGMDIPLIAVFGCGYEQGAK, SETGTIGFVGGMDIPLISRFGCGYEQGAK, SGFVGGMDIPLISRFGCGYEQGAK\tFGCGYEQGAK\tAV; SR; SR\tHI; HI; HI; HI; HI; ; ; \t1; 1; 1; 1; 1; 1; 20; 20; 15\tNH2-FGC<cmm>GYEQGAK-COOH\t\tCarbamidomethylation of C(3)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.21525.21525.2\t\t2843.8\t558.742780317\t2+\t2+\t1115.47059419\t0\t0.370037388577\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DVRVAVFTQGENVEK, DVRVAVFTQGENVEKATAAGDRK, EVRVAVFTQGENVEK, GSTVLPNGTGKDVRVAVFTQGENVEK, GSTVLPNGTGKEVRVAVFTQGENVEK, SGKDVRVAVFTQGENVEK, STGKDVRVAVFTQGENVEK, VAVFTQGENVEK\tVAVFTQGENVEK\tVR; VR; VR; VR; VR; VR; VR; \tAT; ; ; ; ; ; \t4; 4; 4; 15; 15; 7; 8; 1\tNH2-VAVFTQGENVEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.37428.37428.2\t\t3858.93\t660.844070295\t2+\t2+\t1319.67213045\t0\t1.10253902378\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+EVASQTSDVAGDGTTTATVLAQAILNEGLK\tEVASQTSDVAGDGTTTATVLAQAILNEGLK\t\t\t1\tNH2-EVASQTSDVAGDGTTTATVLAQAILNEGLK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.96993.96993.3\t\t7882.73\t987.84\t3+\t3+\t2959.49858926\t1\t-1.27374466447\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+AYAKKVMKYLLMNQPNYKLAYENEFGPIGK, KTMKYLLMNQPNYKLAYENEFGPIGKVK, KVMKYLLMNQPNYKLAYENEFGPIGK, KVMKYLLMNQPNYKLAYENEFGPIGKVK, LAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGK, RTMKYLLMNQPNYKLAYENEFGPIGKVK, YLLMNQPNYKLAYENEFGPIGK\tLAYENEFGPIGK\tYK; YK; YK; YK; ; YK; YK; YK\tVK; ; VK; ; ; VK; \t19; 15; 15; 15; 1; 15; 15; 11\tNH2-LAYENEFGPIGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.58393.58393.2\t\t5223.31\t669.341354352\t2+\t2+\t1336.66631679\t0\t1.37372570057\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+EASLHISNVMLVEDGVAVRVGYQVDGDTK, EASLHISNVMLVEGGVAVRVGYQVDGDTK, KEASLHISNVMLVEDGVAVRVGYQVDGDTK, KEASLHISNVMLVEGGVAVRVGYQVDGDTK, VGYQVDGDTKTR, VGYQVDGDTKTRISK, VGYQVDGDTKTRISKK, VGYQVDGDTKTRVSK\tVGYQVDGDTK\tVR; VR; VR; VR; ; ; ; \tTR; TR; TR; TR\t20; 20; 21; 21; 1; 1; 1; 1\tNH2-VGYQVDGDTK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20503.20503.2\t\t2780.07\t541.261769908\t2+\t2+\t1080.50875352\t0\t0.215574089053\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+FKDWDDLNKPDVRVAATLGTTQEK, FKDWDDLNKPDVRVAATLGTTQEKQVK, SNADRFKDWDDLNKPDVRVAATLGTTQEK, VAATLGTTQEKQVK, VAATLGTTQEKQVKEYFPNAK, VAATLGTTQEKQVKSYFPDAK\tVAATLGTTQEK\tVR; VR; VR; ; ; \tQV; ; QV; QV; QV\t14; 14; 19; 1; 1; 1\tNH2-VAATLGTTQEK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_4'..b'_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.68946.68946.2\t\t5898.1\t1015.52\t2+\t2+\t2029.02152979\t0\t1.92870904099\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DVASANKSLGQFNLEGIPNAPK, EIASANKSLGQFNLEGIPNAPK, EVASANKSLGQFNLEGIPNAPK, SLGQFNLEGIPNAPK\tSLGQFNLEGIPNAPK\tNK; NK; NK; \t\t8; 8; 8; 1\tNH2-SLGQFNLEGIPNAPK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.69858.69858.2\t\t5956.17\t792.920609469\t2+\t2+\t1583.83075635\t0\t-2.57928107518\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+AQIEETTSDYDKEKLQERLAK, CNQIRAQIEETTSDYDKEKLQERLAK, DDIAARCNQIRAQIEETTSDYDK\tAQIEETTSDYDK\tIR; IR\tEK; EK; \t1; 6; 12\tNH2-AQIEETTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25447.25447.2\t\t3088.77\t700.32\t2+\t2+\t1398.61506906\t0\t7.40952793854\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+GSNSGTETDFDGK\tGSNSGTETDFDGK\t\t\t1\tNH2-GSNSGTETDFDGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.16731.16731.2\t\t2545.26\t657.775415728\t2+\t2+\t1313.53715309\t0\t-0.664794466436\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DHFVHISGLIDEINEGDQVEFDLQEGNK, DHFVHISGLVDEIREGDQVEFDLQEGNK, EGDQVEFDLQEGNK, EGDQVEFDLQEGNKGLNAVNVK\tEGDQVEFDLQEGNK\tIN; IR; ; \tGL\t15; 15; 1; 1\tNH2-EGDQVEFDLQEGNK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.42848.42848.2\t\t4230.29\t804.363314906\t2+\t2+\t1606.71109471\t0\t0.610528847251\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+ETLDVDGVEYPLVK, ETLDVDGVEYPLVKLEISR, ETLDVDGVEYPLVKLEISRTSHPFYTGK, ETLDVDGVEYPLVKLEISRTSHPFYTGKSK, STADTKETLDVDGVEYPLVK, STADTKETLDVDGVEYPLVKLEISR, STAETKETLDVDGVEYPLVK, STAETKETLDVDGVEYPLVKLEISR, STVDTKETLDVDGVEYPLVKLEISR\tETLDVDGVEYPLVK\tTK; TK; TK; TK; TK\tLE; LE; LE; ; LE; ; LE; LE\t1; 1; 1; 1; 7; 7; 7; 7; 7\tNH2-ETLDVDGVEYPLVK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.71416.71416.2\t\t6056.55\t789.41\t2+\t2+\t1575.80320418\t1\t-0.704743199656\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+GTTNGTETDFNGK, SVVIKGTTNGTETDFNGK\tGTTNGTETDFNGK\tIK\t\t1; 6\tNH2-GTTNGTETDFNGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.15728.15728.2\t\t2482.1\t671.300172985\t2+\t2+\t1340.58443764\t0\t1.00953138271\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+ILTVGDAVNFIAGK\tILTVGDAVNFIAGK\t\t\t1\tNH2-ILTVGDAVNFIAGK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.92389.92389.2\t\t7528.49\t709.407175505\t2+\t2+\t1416.79766531\t0\t1.50320427751\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+AQIESSTSDYDKEK, AQIESSTSDYDKEKLQERLAK, ARINQIKAQIESSTSDYDK, ARINQIKAQIESSTSDYDKEK, ARINQIKAQIESSTSDYDKEKLQER, ARINQIKAQIESSTSDYDKEKLQERLAK, INQIKAQIESSTSDYDKEKLQERLAK\tAQIESSTSDYDK\tIK; IK; IK; IK; IK\tEK; EK; ; EK; EK; EK; EK\t1; 1; 8; 8; 8; 8; 6\tNH2-AQIESSTSDYDK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.20057.20057.2\t\t2752.89\t672.300992424\t2+\t2+\t1342.58885431\t0\t-1.05785835196\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+EGQAVTMEVTQGQK, RSLQEGQKVTMEVTQGQK, SLKEGQAVTMEVTQGQK, SLKEGQAVTMEVTQGQKGAQAENRSEER\tVTMEVTQGQK\tQA; QK; QA; QA\tGA\t5; 9; 8; 8\tNH2-VTMEVTQGQK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.33393.33393.2\t\t3592.24\t560.785120573\t2+\t2+\t1119.55940919\t0\t-3.31764053028\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+DLDKSFGSMPGSMNKKTAGTFASVAK, DLNKSFGSIPGSMNEKTAGTFASVAK, DLNKSFGSIPGSMNKKTAGTFASVAK, DLNKSFGSMPGSMNEKTAGTFASVAK, DLNKSFGSMPGSMNKKTAGTFASVAK, KTAGTFASVAK, SFGSIPGSMNKKTAGTFASVAK, SFGSLPGSMNEKTAGTFASVAK, SFGSMPGSMNEKTAGTFASVAK, SFGSMPGSMNKKTAGTFASVAK, SGSMNKKTAGTFASVAK, TAGTFASVAK\tTAGTFASVAK\tKK; EK; KK; EK; KK; K; KK; EK; EK; KK; KK; \t\t17; 17; 17; 17; 17; 2; 13; 13; 13; 13; 8; 1\tNH2-TAGTFASVAK-COOH\t\t\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.25503.25503.2\t\t3092.13\t476.76\t2+\t2+\t951.502545939\t0\t3.04255362505\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n+CGGEPKPSSQWQGENINR\tCGGEPKPSSQWQGENINR\t\t\t1\tNH2-C<cmm>GGEPKPSSQWQGENINR-COOH\t\tCarbamidomethylation of C(1)\ttrimmed_2016_Jan_12_QE2_47.mgf\t2016_Jan_12_QE2_47.31423.31423.3\t\t3464.93\t681.98\t3+\t3+\t2042.92283589\t0\t-2.28026242106\t\t\t\t99.8278829604\tDoubtful\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\t-1\n'