Mercurial > repos > recetox > recetox_msfinder

changeset 0:7cda9aef13f3 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox_msfinder commit f655a81cc6289f228ee7f58dc6b3e2d9eb2dc923
author recetox
date Tue, 13 Dec 2022 13:26:29 +0000
parents
children 29fc1af350f5
files macros.xml recetox_msfinder.xml test-data/out.msp test-data/test.msp
diffstat 4 files changed, 364 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Tue Dec 13 13:26:29 2022 +0000
@@ -0,0 +1,77 @@
+<macros>
+    <token name="@TOOL_VERSION@">3.5.2</token>
+    <xml name="requirements">
+        <requirements>
+            <container type="docker">recetox/recetox-msfinder:3.5.2-0</container>
+        </requirements>
+    </xml>
+    <xml name="creator">
+        <creator>
+            <person
+                givenName="Zargham"
+                familyName="Ahmad"
+                url="https://github.com/zargham-ahmad"
+                identifier="0000-0002-6096-224X" />
+            <organization
+                url="https://www.recetox.muni.cz/"
+                email="GalaxyToolsDevelopmentandDeployment@space.muni.cz"
+                name="RECETOX MUNI" />
+        </creator>
+    </xml>
+    <xml name="input">
+        <param name="input_data" type="data" format="msp" label="Input mass spectral library file to which to add peak annotations."
+            help="Formula and InChI (or SMILES) codes are required to be present in the library file" />
+    </xml>
+    <xml name="parameter">
+        <param type="float" value="0.01" name="Ms2Tolerance" label="Ms2Tolerance" help="The mass tolerance used for fragment peak matching and annotation." />
+        <param name="IsTmsMeoxDerivative" type="boolean" checked="False" truevalue="True" falsevalue="False" label="IsTmsMeoxDerivative"
+            help="Check TMS-MeOX derivative to use EIMS database; otherwise, MSMS database is used." />
+        <param type="integer" value="1" name="RelativeAbundanceCutOff" label="RelativeAbundanceCutOff"
+            help="Remove peaks with less than specified % relative intensity from the spectra." />
+        <param type="float" value="0.001" name="Ms1Tolerance" label="Ms1Tolerance" help="The precursor m/z tolerance to generate formula candidates." />
+        <param type="select" name="MassToleranceType" label="MassToleranceType" help="Da stands for Daltons (amu), and Ppm stands for parts per million">
+            <option value="Da" selected="True">Da</option>
+            <option value="Ppm">Ppm</option>
+        </param>
+        <param type="integer" value="-1" name="StructurePredictionTimeOut" label="StructurePredictionTimeOut" help="Time out parameter, value of -1 means no timeout" />
+        <param name="LewisAndSeniorCheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="LewisAndSeniorCheck"
+            help="Generate formula candidates that match the valence rules of formula elements." />
+    </xml>
+    <xml name="element_check_parameter">
+        <!-- Element Checks -->
+        <param name="Ocheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Ocheck" />
+        <param name="Ncheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Ncheck" />
+        <param name="Pcheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Pcheck" />
+        <param name="Scheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Scheck" />
+        <param name="Fcheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Fcheck" />
+        <param name="ClCheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="ClCheck" />
+        <param name="BrCheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="BrCheck" />
+        <param name="Icheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="Icheck" />
+        <param name="SiCheck" type="boolean" checked="True" truevalue="True" falsevalue="False" label="SiCheck" />
+    </xml>
+    <xml name="output">
+        <data name="annotated_data" format="msp" />
+    </xml>
+
+    <token name="@HELP@"><![CDATA[
+        **Description**
+
+        MS-FINDER was launched as a universal program for compound annotation that supports EI-MS (GC/MS) and 
+        MS/MS spectral mining. MS-FINDER provide solution for fragment annotations. The program can annotate 
+        your unknowns by the public spectral databases such as MassBank, LipidBlast, and GNPS. MS-FINDER has 
+        been developed as the collaborative work between Prof. Masanori Arita team (RIKEN, Reifycs Inc.) and 
+        Prof. Oliver Fiehn team (UC Davis) supported by the JST/NSF SICORP Metabolomics for the low carbon society 
+        project.
+
+        This galaxy wrapper only peforms MS2 peak annotation given a correctly formatted mass spectral library file.
+        FORMULA, PRECURSORMZ and SMILES (or INCHI) metadata entries are required to be present in the input mass spectral library file.
+        Each spectrum has to be separated by a single blank line.
+
+        For detailed documentation of the tool please visit https://mtbinfo-team.github.io/mtbinfo.github.io/MS-FINDER/tutorial
+    ]]>
+    </token>
+
+    <xml name="citations">
+        <citation type="doi">10.1021/acs.analchem.6b00770</citation>
+    </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/recetox_msfinder.xml	Tue Dec 13 13:26:29 2022 +0000
@@ -0,0 +1,78 @@
+<tool id="recetox_msfinder" name="RECETOX MsFinder" version="@TOOL_VERSION@+galaxy0">
+    <description>Annotation of fragment peaks in mass spectral libraries.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator" />
+
+    <expand macro="requirements" />
+    <command>
+        <![CDATA[
+        sh ${write_param} &&
+        mono /MsFinder/MsFinder/bin/Debug/MsfinderConsoleApp.exe annotate -i "$input_data" -m 'MSFINDER.INI' -o "$annotated_data"        
+    ]]>
+    </command>
+
+    <configfiles>
+        <configfile name="write_param">
+            printf "%s\n" "Ms2Tolerance=$Ms2Tolerance" \
+            "IsTmsMeoxDerivative=$IsTmsMeoxDerivative" \
+            "RelativeAbundanceCutOff=$RelativeAbundanceCutOff" \
+            "Ms1Tolerance=$Ms1Tolerance" \
+			"MassToleranceType=$MassToleranceType" \
+			"StructurePredictionTimeOut=$StructurePredictionTimeOut" \
+			"Ocheck=$element_selection.Ocheck" \
+            "Ncheck=$element_selection.Ncheck" \
+            "Pcheck=$element_selection.Pcheck" \
+            "Scheck=$element_selection.Scheck" \
+            "Fcheck=$element_selection.Fcheck" \
+            "ClCheck=$element_selection.ClCheck" \
+            "BrCheck=$element_selection.BrCheck" \
+            "Icheck=$element_selection.Icheck" \
+            "SiCheck=$element_selection.SiCheck" \
+            "LewisAndSeniorCheck=$LewisAndSeniorCheck" \
+			"IsUseRtForFilteringCandidates=False" \
+			"RtToleranceForStructureElucidation=2.5" \
+			"IsUsePredictedRtForStructureElucidation=False" \
+			"Coeff_RtPrediction=-1" \
+			"Intercept_RtPrediction=-1" \
+			"IsUseRtInchikeyLibrary=True" \
+			"IsUsePredictedCcsForStructureElucidation=False" \
+			"IsUseCcsForFilteringCandidates=True" \
+			"CcsToleranceForStructureElucidation=10" \
+			"CanExcuteMS2AdductSearch=False" \
+            "IsUseXlogpPrediction=False" >MSFINDER.INI
+        </configfile>
+    </configfiles>
+
+    <inputs>
+        <expand macro="input" />
+        <expand macro="parameter" />
+        <section name="element_selection" title="Element Selection" expanded="true" help="Generate formula candidates that just contain the elements selected by the users.">
+            <expand macro="element_check_parameter" />
+        </section>
+    </inputs>
+
+    <outputs>
+        <expand macro="output" />
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input_data" value="test.msp" ftype="msp" />
+            <output name="annotated_data" file="out.msp" lines_diff="16	" /> 
+            <!-- This is set to 16 since msfinder sometimes places double bonds between certain atoms and sometimes not - there are 16 such cases in this file. -->
+
+        </test>
+    </tests>
+
+    <help>
+        <![CDATA[
+            @HELP@
+        ]]>
+    </help>
+
+    <citations>
+        <expand macro="citations" />
+    </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out.msp	Tue Dec 13 13:26:29 2022 +0000
@@ -0,0 +1,105 @@
+NAME: Acetylserotonin_2TMS isomer 2
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2520.736
+PRECURSORMZ: 362.18381
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C18H30N2O2Si2
+INCHIKEY: BITJWWNGDAOCJT-UHFFFAOYSA-N
+INCHI: 
+SMILES: C[Si](C)(C)Oc1cc2c(cc1)n(cc2CC\N=C(/C)O)[Si](C)(C)C
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: 
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 84
+73.04681	6882	"Theoretical m/z 73.046802, Mass diff 0 (0.11 ppm), SMILES C[Si](C)C, Annotation [C3H10Si-H]+, Rule of HR True"
+74.04642	3441
+76.01821	5005	"Theoretical m/z 76.018724, Mass diff 0 (0 ppm), Formula C5H2N"
+77.02173	4634
+78.03387	2401
+78.91781	4925
+79.04164	36910	"Theoretical m/z 79.042199, Mass diff 0 (0 ppm), Formula C5H5N"
+80.91575	12768
+81.06992	1588	"Theoretical m/z 81.070425, Mass diff 0 (0 ppm), Formula C6H9"
+89.03854	1372	"Theoretical m/z 89.041721, Mass diff 0.003 (35.73 ppm), SMILES O[Si](C)(C)C, Annotation [C3H10OSi-H]+, Rule of HR True"
+91.05424	1324	"Theoretical m/z 91.057371, Mass diff 0.003 (34.39 ppm), SMILES O[Si](C)(C)C, Annotation [C3H10OSi+H]+, Rule of HR True"
+92.06213	3591	"Theoretical m/z 92.0626, Mass diff 0 (0 ppm), Formula C7H8"
+93.03666	8343	"Theoretical m/z 93.03404, Mass diff -0.003 (0 ppm), Formula C6H5O"
+94.93144	2656
+95.04466	8498	"Theoretical m/z 95.04969, Mass diff 0.004 (0 ppm), Formula C6H7O"
+95.93922	1565
+103.05418	2844	"Theoretical m/z 103.054775, Mass diff 0 (0 ppm), Formula C8H7"
+104.06204	1384
+105.06992	2211	"Theoretical m/z 105.070425, Mass diff 0 (0 ppm), Formula C8H9"
+106.89473	3073
+106.94908	3532
+108.94706	3679	"Theoretical m/z 108.956593, Mass diff 0.009 (0 ppm), Formula C3HOSi2"
+111.04412	1592	"Theoretical m/z 111.044604, Mass diff 0 (0 ppm), Formula C6H7O2"
+113.03857	1585	"Theoretical m/z 113.039125, Mass diff 0 (0 ppm), Formula C9H5"
+115.05422	7216	"Theoretical m/z 115.054775, Mass diff 0 (0 ppm), Formula C9H7"
+120.05695	3247	"Theoretical m/z 120.057515, Mass diff 0 (0 ppm), Formula C8H8O"
+120.94707	4091	"Theoretical m/z 120.956593, Mass diff 0.009 (0 ppm), Formula C4HOSi2"
+120.96468	3380	"Theoretical m/z 120.967826, Mass diff 0.003 (0 ppm), Formula C3HN2Si2"
+122.06804	4192	"Theoretical m/z 122.073165, Mass diff 0.005 (0 ppm), Formula C8H10O"
+123.93423	1315	"Theoretical m/z 123.943682, Mass diff 0.009 (0 ppm), Formula C3O2Si2"
+124.94194	4725	"Theoretical m/z 124.951507, Mass diff 0.009 (0 ppm), Formula C3HO2Si2"
+127.02392	3504	"Theoretical m/z 127.021531, Mass diff -0.003 (0 ppm), Formula C5H7O2Si"
+129.06982	2726	"Theoretical m/z 129.070425, Mass diff 0 (0 ppm), Formula C10H9"
+130.06831	4067	"Theoretical m/z 130.065674, Mass diff -0.003 (0 ppm), Formula C9H8N"
+141.06976	3435	"Theoretical m/z 141.070425, Mass diff 0 (0 ppm), Formula C11H9"
+145.06465	1876	"Theoretical m/z 145.06534, Mass diff 0 (0 ppm), Formula C10H9O"
+149.06238	3354	"Theoretical m/z 149.060255, Mass diff -0.003 (0 ppm), Formula C9H9O2"
+152.06189	6328	"Theoretical m/z 152.071154, Mass diff 0.009 (0 ppm), Formula C8H10NO2"
+164.94904	1697	"Theoretical m/z 164.957655, Mass diff 0.008 (0 ppm), Formula C4HN2O2Si2"
+167.05533	3051	"Theoretical m/z 167.060923, Mass diff 0.005 (0 ppm), Formula C11H7N2"
+170.0343	2446	"Theoretical m/z 170.042601, Mass diff 0.008 (0 ppm), Formula C10H8NSi"
+171.95171	10548	"Theoretical m/z 171.943682, Mass diff -0.009 (0 ppm), Formula C7O2Si2"
+172.95517	1555
+173.94968	10065	"Theoretical m/z 173.946756, Mass diff -0.003 (0 ppm), Formula C6NO2Si2"
+174.95305	1284
+178.07762	1953	"Theoretical m/z 178.07825, Mass diff 0 (0 ppm), Formula C14H10"
+183.08034	6206	"Theoretical m/z 183.08099, Mass diff 0 (0 ppm), Formula C13H11O"
+184.08812	6315	"Theoretical m/z 184.097778, Mass diff 0.009 (0 ppm), Formula C8H18NSi2"
+185.09143	2274
+192.98021	1819	"Theoretical m/z 192.985814, Mass diff 0.005 (0 ppm), Formula C10HN2OSi"
+194.07246	1646	"Theoretical m/z 194.073165, Mass diff 0 (0 ppm), Formula C14H10O"
+197.97484	2121	"Theoretical m/z 197.980001, Mass diff 0.005 (0 ppm), Formula C13NSi"
+198.97534	5042	"Theoretical m/z 198.978391, Mass diff 0.003 (0 ppm), Formula C8H3N2OSi2"
+204.08408	1545	"Theoretical m/z 204.083912, Mass diff 0 (0.83 ppm), SMILES O(C1=CC=C2NC=CC2(=C1))[Si](C)(C)C, Annotation [C11H15NOSi-H]+, Rule of HR True"
+208.03126	3799	"Theoretical m/z 208.025007, Mass diff -0.007 (0 ppm), Formula C8H10NO2Si2"
+209.01154	5448	"Theoretical m/z 209.013973, Mass diff 0.002 (0 ppm), Formula C15HN2"
+210.99068	3675	"Theoretical m/z 210.996379, Mass diff 0.005 (0 ppm), Formula C10H3N2O2Si"
+211.06046	5392	"Theoretical m/z 211.061058, Mass diff 0 (0 ppm), Formula C9H15O2Si2"
+214.10466	3080	"Theoretical m/z 214.104654, Mass diff 0 (0.03 ppm), SMILES C1=CC=C2C(=C1)C(=CN2[Si](C)(C)C)CC, Annotation [C13H19NSi-3H]+, Rule of HR True"
+220.07869	6462	"Theoretical m/z 220.07938, Mass diff 0 (0 ppm), Formula C11H14NO2Si"
+226.0417	4848	"Theoretical m/z 226.050827, Mass diff 0.009 (0 ppm), Formula C12H12NSi2"
+227.02208	14828	"Theoretical m/z 227.024538, Mass diff 0.002 (0 ppm), Formula C15H3N2O"
+230.00099	2388	"Theoretical m/z 230.003074, Mass diff 0.002 (0 ppm), Formula C18N"
+230.09961	2241	"Theoretical m/z 230.099573, Mass diff 0 (0.16 ppm), SMILES O(C1=CC=C2NC=C(C2(=C1))CC)[Si](C)(C)C, Annotation [C13H19NOSi-3H]+, Rule of HR True"
+240.94661	1761	"Theoretical m/z 240.956593, Mass diff 0.009 (0 ppm), Formula C14HOSi2"
+254.96269	2484	"Theoretical m/z 254.972243, Mass diff 0.009 (0 ppm), Formula C15H3OSi2"
+257.06641	1341	"Theoretical m/z 257.071488, Mass diff 0.005 (0 ppm), Formula C17H9N2O"
+273.14221	1338	"Theoretical m/z 273.141773, Mass diff 0 (1.6 ppm), SMILES OC(=NCCC2=CN(C1=CC=CC=C12)[Si](C)(C)C)C, Annotation [C15H22N2OSi-H]+, Rule of HR True"
+288.12326	15718	"Theoretical m/z 288.123437, Mass diff 0 (0.62 ppm), SMILES O(C1=CC=C2C(=C1)C(=CN2[Si](C)(C)C)CC)[Si](C)C, Annotation [C15H25NOSi2-3H]+, Rule of HR True"
+289.12668	5715
+290.13898	125444	"Theoretical m/z 290.139087, Mass diff 0 (0.37 ppm), SMILES O(C1=CC=C2C(=C1)C(=CN2[Si](C)(C)C)C)[Si](C)(C)C, Annotation [C15H25NOSi2-H]+, Rule of HR True"
+291.14282	16150
+292.1355	12595
+293.13925	1290	"Theoretical m/z 293.139308, Mass diff 0 (0 ppm), Formula C15H25O2Si2"
+302.1391	2508	"Theoretical m/z 302.139642, Mass diff 0 (0 ppm), Formula C16H24NOSi2"
+303.14676	109060	"Theoretical m/z 303.146918, Mass diff 0 (0.52 ppm), SMILES O(C1=CC=C2C(=C1)C(=CN2[Si](C)(C)C)CC)[Si](C)(C)C, Annotation [C16H27NOSi2-2H]+, Rule of HR False"
+304.1492	19700
+305.143	7792
+306.13388	4148	"Theoretical m/z 306.134557, Mass diff 0 (0 ppm), Formula C15H24NO2Si2"
+328.98126	2010
+345.1445	7128	"Theoretical m/z 345.145456, Mass diff 0 (0 ppm), Formula C17H25N2O2Si2"
+360.16812	2877
+362.18381	10542	"Theoretical m/z 362.184022, Mass diff 0 (0.58 ppm), SMILES OC(=NCCC2=CN(C1=CC=C(O[Si](C)(C)C)C=C12)[Si](C)(C)C)C, Annotation [C18H30N2O2Si2]+, Rule of HR False"
+363.18671	4306
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/test.msp	Tue Dec 13 13:26:29 2022 +0000
@@ -0,0 +1,104 @@
+NAME: Acetylserotonin_2TMS isomer 2
+SCANNUMBER: -1
+RETENTIONTIME: -1
+RETENTIONINDEX: 2520.736
+PRECURSORMZ: 362.18381
+PRECURSORTYPE: [M]+
+IONMODE: Positive
+SPECTRUMTYPE: Centroid
+FORMULA: C18H30N2O2Si2
+INCHIKEY: BITJWWNGDAOCJT-UHFFFAOYSA-N
+INCHI: 
+SMILES: C[Si](C)(C)Oc1cc2c(cc1)n(cc2CC\N=C(/C)O)[Si](C)(C)C
+AUTHORS: Price et al., RECETOX, Masaryk University (CZ)
+COLLISIONENERGY: 70
+INSTRUMENT: Q Exactive GC Orbitrap GC-MS/MS
+INSTRUMENTTYPE: GC-EI-Orbitrap
+IONIZATION: EI+
+LICENSE: CC BY-NC
+COMMENT: 
+Num Peaks: 84
+73.04681	6882
+74.04642	3441
+76.01821	5005
+77.02173	4634
+78.03387	2401
+78.91781	4925
+79.04164	36910
+80.91575	12768
+81.06992	1588
+89.03854	1372
+91.05424	1324
+92.06213	3591
+93.03666	8343
+94.93144	2656
+95.04466	8498
+95.93922	1565
+103.05418	2844
+104.06204	1384
+105.06992	2211
+106.89473	3073
+106.94908	3532
+108.94706	3679
+111.04412	1592
+113.03857	1585
+115.05422	7216
+120.05695	3247
+120.94707	4091
+120.96468	3380
+122.06804	4192
+123.93423	1315
+124.94194	4725
+127.02392	3504
+129.06982	2726
+130.06831	4067
+141.06976	3435
+145.06465	1876
+149.06238	3354
+152.06189	6328
+164.94904	1697
+167.05533	3051
+170.0343	2446
+171.95171	10548
+172.95517	1555
+173.94968	10065
+174.95305	1284
+178.07762	1953
+183.08034	6206
+184.08812	6315
+185.09143	2274
+192.98021	1819
+194.07246	1646
+197.97484	2121
+198.97534	5042
+204.08408	1545
+208.03126	3799
+209.01154	5448
+210.99068	3675
+211.06046	5392
+214.10466	3080
+220.07869	6462
+226.0417	4848
+227.02208	14828
+230.00099	2388
+230.09961	2241
+240.94661	1761
+254.96269	2484
+257.06641	1341
+273.14221	1338
+288.12326	15718
+289.12668	5715
+290.13898	125444
+291.14282	16150
+292.1355	12595
+293.13925	1290
+302.1391	2508
+303.14676	109060
+304.1492	19700
+305.143	7792
+306.13388	4148
+328.98126	2010
+345.1445	7128
+360.16812	2877
+362.18381	10542
+363.18671	4306
\ No newline at end of file