add new tool: msp_split

tools/msp_split/.shed.yml

@@ -0,0 +1,13 @@
+owner: recetox
+remote_repository_url: "https://github.com/RECETOX/galaxytools/tree/master/tools/msp_split"
+homepage_url: "https://github.com/RECETOX/msp_split"
+categories:
+  - Metabolomics
+repositories:
+  msp_split:
+    description: "split msp spectra."
+
+    include:
+      - splitMSP.xml
+      - splitMSP.py
+      - test-data

tools/msp_split/splitMSP.py

@@ -0,0 +1,45 @@
+import argparse
+import os
+
+from matchms.exporting import save_as_msp
+from matchms.importing import load_from_msp
+
+
+def read_spectra(filename):
+    return list(load_from_msp(filename, False))
+
+
+def get_spectra_names(spectra):
+    return [x.get("compound_name") for x in spectra]
+
+
+def make_outdir(outdir):
+    return os.mkdir(outdir)
+
+
+def write_spectra(filename, outdir):
+    spectra = read_spectra(filename)
+    names = get_spectra_names(spectra)
+    for i in range(len(spectra)):
+        outfile = str(names[i]) + ".msp"
+        outpath = os.path.join(outdir, outfile)
+        save_as_msp(spectra[i], outpath)
+
+
+def split_spectra(filename, outdir):
+    make_outdir(outdir)
+    return write_spectra(filename, outdir)
+
+
+listarg = argparse.ArgumentParser()
+listarg.add_argument('--filename', type=str)
+listarg.add_argument('--outdir', type=str)
+args = listarg.parse_args()
+outdir = args.outdir
+filename = args.filename
+
+
+if __name__ == "__main__":
+    split_spectra(filename, outdir)
+else:
+    print('Do nothing')

tools/msp_split/splitMSP.xml

@@ -0,0 +1,39 @@
+<tool id="splitMSP" name="split spectra" version="0.1.0" python_template_version="3.5">
+    <description>Split MSP spectra file</description>
+    <requirements>
+         <requirement type="package" version="0.14.0">matchms</requirement>
+    </requirements>
+    <command detect_errors="exit_code"><![CDATA[
+        python3  $__tool_directory__/splitMSP.py 
+        --filename '$msp_input'
+        --outdir   'output' 
+    ]]></command>
+    <inputs>
+        <param type="data" name="msp_input" format="msp" />
+    </inputs>
+    <outputs>
+        <collection  format="msp" name="sample" type="list">
+            <discover_datasets pattern="__designation_and_ext__" ext="msp" directory="output"/>
+        </collection >
+    </outputs>
+    <tests>
+        <test>
+            <param name="msp_input" value="sample_input.msp"  />
+            <output_collection name="sample" type="list">
+                <element name="1-NITROPYRENE"         file="1-NITROPYRENE.msp"         ftype="msp" compare="contains"/>
+                <element name="3,5-DICHLOROPHENOL"    file="3,5-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+                <element name="3,4-DICHLOROPHENOL"    file="3,4-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+                <element name="2,6-DICHLOROPHENOL"    file="2,6-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+                <element name="2,5-DICHLOROPHENOL"    file="2,5-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+                <element name="2,4-DINITROPHENOL"     file="2,4-DINITROPHENOL.msp"     ftype="msp" compare="contains"/>
+                <element name="2,4-DICHLOROPHENOL"    file="2,4-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+                <element name="2,4,6-TRICHLOROPHENOL" file="2,4,6-TRICHLOROPHENOL.msp" ftype="msp" compare="contains"/>
+                <element name="2,4,5-TRICHLOROPHENOL" file="2,4,5-TRICHLOROPHENOL.msp" ftype="msp" compare="contains"/>
+                <element name="2,3-DICHLOROPHENOL"    file="2,3-DICHLOROPHENOL.msp"    ftype="msp" compare="contains"/>
+            </output_collection>
+        </test>
+    </tests> 
+    <help><![CDATA[
+        All good
+    ]]></help>
+</tool>

tools/msp_split/test-data/1-NITROPYRENE.msp

@@ -0,0 +1,100 @@
+SYNONYM: 1-NITROPYRENE
+DB#: JP000001
+INCHIKEY: ALRLPDGCPYIVHP-UHFFFAOYSA-N
+MW: 247.063328528
+FORMULA: C16H9NO2
+ACCESSION: JP000001
+AUTHOR: KOGA M, UNIV. OF OCCUPATIONAL AND ENVIRONMENTAL HEALTH
+LICENSE: CC BY-NC-SA
+INSTRUMENT: VARIAN MAT-44
+SMILES: [O-1][N+1](=O)c(c4)c(c1)c(c3c4)c(c2cc3)c(ccc2)c1
+INCHI: InChI=1S/C16H9NO2/c18-17(19)14-9-7-12-5-4-10-2-1-3-11-6-8-13(14)16(12)15(10)11/h1-9H
+SMILES_2: [H]C=1C([H])=C2C([H])=C([H])C3=C([H])C([H])=C(C=4C([H])=C([H])C(C1[H])=C2C34)N(=O)=O
+INSTRUMENT_TYPE: EI-B
+MS_LEVEL: MS1
+IONIZATION_ENERGY: 70 eV
+ION_TYPE: [M]+*
+IONIZATION_MODE: positive
+LAST_AUTO-CURATION: 1495210335755
+MOLECULAR_FORMULA: C16H9NO2
+TOTAL_EXACT_MASS: 247.063328528
+COMPOUND_NAME: 1-NITROPYRENE
+PRECURSOR_MZ: 0
+PARENT_MASS: 247.06333
+NUM PEAKS: 75
+51.0        2.66
+55.0        8.0
+57.0        7.33
+58.0        1.33
+59.0        1.33
+60.0        14.0
+61.0        1.33
+62.0        3.33
+63.0        3.33
+66.0        1.33
+68.0        8.66
+70.0        2.0
+72.0        5.33
+73.0        7.33
+74.0        3.33
+75.0        2.66
+76.0        2.0
+78.0        1.33
+80.0        4.0
+81.0        2.0
+82.0        1.33
+83.0        3.33
+86.0        12.66
+87.0        8.66
+92.0        2.0
+93.0        10.0
+94.0        6.0
+98.0        14.66
+99.0        83.33
+100.0       60.66
+104.0       4.0
+107.0       1.33
+108.0       1.33
+110.0       3.33
+112.0       1.33
+113.0       1.33
+115.0       1.33
+116.0       1.33
+120.0       1.33
+122.0       4.0
+123.0       2.66
+124.0       2.66
+125.0       2.0
+126.0       1.33
+134.0       1.33
+135.0       2.0
+137.0       1.33
+147.0       1.33
+149.0       2.0
+150.0       4.66
+151.0       3.33
+159.0       2.0
+162.0       2.0
+163.0       2.66
+173.0       2.0
+174.0       8.66
+175.0       4.66
+177.0       2.0
+187.0       5.33
+188.0       4.66
+189.0       56.66
+190.0       12.0
+191.0       16.66
+198.0       10.66
+199.0       9.33
+200.0       72.66
+201.0       99.99
+202.0       16.0
+203.0       1.33
+207.0       1.33
+214.0       1.33
+217.0       25.33
+218.0       5.33
+247.0       52.66
+248.0       10.16
+

tools/msp_split/test-data/2,3-DICHLOROPHENOL.msp

@@ -0,0 +1,67 @@
+SYNONYM: 2,3-DICHLOROPHENOL
+DB#: JP000006
+INCHIKEY: UMPSXRYVXUPCOS-UHFFFAOYSA-N
+MW: 161.963920108
+FORMULA: C6H4Cl2O
+ACCESSION: JP000006
+AUTHOR: KOGA M, UNIV. OF OCCUPATIONAL AND ENVIRONMENTAL HEALTH
+LICENSE: CC BY-NC-SA
+INSTRUMENT: VARIAN MAT-44
+SMILES: Oc(c1)c(Cl)c(Cl)cc1
+INCHI: InChI=1S/C6H4Cl2O/c7-4-2-1-3-5(9)6(4)8/h1-3,9H
+SMILES_2: [H]OC=1C([H])=C([H])C([H])=C(Cl)C1Cl
+INSTRUMENT_TYPE: EI-B
+MS_LEVEL: MS1
+IONIZATION_ENERGY: 70 eV
+ION_TYPE: [M]+*
+IONIZATION_MODE: positive
+LAST_AUTO-CURATION: 1495210335870
+MOLECULAR_FORMULA: C6H4Cl2O
+TOTAL_EXACT_MASS: 161.963920108
+COMPOUND_NAME: 2,3-DICHLOROPHENOL
+PRECURSOR_MZ: 0
+PARENT_MASS: 161.96392
+NUM PEAKS: 42
+51.0        4.43
+53.0        10.39
+60.0        9.21
+61.0        24.93
+62.0        43.19
+63.0        99.99
+64.0        12.57
+65.0        4.81
+66.0        3.39
+71.0        3.67
+72.0        15.34
+73.0        25.07
+74.0        11.84
+75.0        8.79
+81.0        4.78
+82.0        3.25
+83.0        2.63
+84.0        3.87
+85.0        2.49
+87.0        5.09
+89.0        2.21
+91.0        6.02
+96.0        3.11
+97.0        12.05
+98.0        35.88
+99.0        22.09
+100.0       13.5
+101.0       6.26
+107.0       3.33
+109.0       2.73
+125.0       3.11
+126.0       59.16
+127.0       5.61
+128.0       19.32
+133.0       5.33
+135.0       2.84
+161.0       2.52
+162.0       68.96
+163.0       6.51
+164.0       51.64
+165.0       2.9
+166.0       7.58
+

tools/msp_split/test-data/2,4,5-TRICHLOROPHENOL.msp

@@ -0,0 +1,90 @@
+SYNONYM: 2,4,5-TRICHLOROPHENOL
+DB#: JP000009
+INCHIKEY: LHJGJYXLEPZJPM-UHFFFAOYSA-N
+MW: 195.924947756
+FORMULA: C6H3Cl3O
+ACCESSION: JP000009
+AUTHOR: KOGA M, UNIV. OF OCCUPATIONAL AND ENVIRONMENTAL HEALTH
+LICENSE: CC BY-NC-SA
+INSTRUMENT: VARIAN MAT-44
+SMILES: Oc(c1)c(Cl)cc(Cl)c(Cl)1
+INCHI: InChI=1S/C6H3Cl3O/c7-3-1-5(9)6(10)2-4(3)8/h1-2,10H
+SMILES_2: [H]OC1=C([H])C(Cl)=C(Cl)C([H])=C1Cl
+INSTRUMENT_TYPE: EI-B
+MS_LEVEL: MS1
+IONIZATION_ENERGY: 70 eV
+ION_TYPE: [M]+*
+IONIZATION_MODE: positive
+LAST_AUTO-CURATION: 1495210336033
+MOLECULAR_FORMULA: C6H3Cl3O
+TOTAL_EXACT_MASS: 195.924947756
+COMPOUND_NAME: 2,4,5-TRICHLOROPHENOL
+PRECURSOR_MZ: 0
+PARENT_MASS: 195.92495
+NUM PEAKS: 65
+51.0        2.58
+53.0        14.73
+59.0        2.03
+60.0        12.75
+61.0        30.62
+62.0        36.79
+63.0        19.11
+64.0        2.15
+65.0        5.23
+66.0        13.42
+67.0        7.46
+69.0        2.46
+71.0        6.55
+72.0        13.85
+73.0        16.02
+74.0        7.55
+75.0        4.47
+79.0        2.34
+80.0        8.06
+81.0        5.21
+82.0        3.22
+83.0        7.1
+84.0        6.05
+85.0        6.38
+86.0        2.53
+87.0        3.44
+89.0        1.93
+95.0        3.8
+96.0        33.63
+97.0        67.27
+98.0        25.02
+99.0        31.7
+100.0       5.86
+106.0       2.03
+107.0       8.66
+108.0       3.94
+109.0       6.55
+131.0       12.51
+132.0       48.06
+133.0       32.0
+134.0       33.42
+135.0       18.37
+136.0       6.55
+137.0       2.96
+149.0       6.48
+151.0       3.39
+160.0       10.69
+161.0       4.76
+162.0       10.76
+163.0       3.58
+164.0       3.61
+167.0       4.06
+169.0       3.89
+177.0       4.76
+179.0       2.94
+192.0       6.69
+194.0       4.64
+195.0       6.79
+196.0       99.99
+197.0       11.45
+198.0       92.58
+199.0       7.82
+200.0       29.54
+201.0       2.08
+202.0       3.15
+