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

Changeset 1:13b3e835aded (2023-05-02)
Previous changeset 0:169c72b2ce79 (2023-04-27) Next changeset 2:86de39226109 (2023-05-18)
Commit message:
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/matchms commit 8989605190816b606fd0bf5be101c6d385a4ce52
added:
test-data/convert/json_out.json
test-data/convert/mgf_out.mgf
test-data/convert/msp_out.msp
b
diff -r 169c72b2ce79 -r 13b3e835aded test-data/convert/json_out.json
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/convert/json_out.json Tue May 02 10:16:11 2023 +0000
[
b'@@ -0,0 +1,1 @@\n+[{"scannumber": "1161", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C4H10NO3PS", "inchikey": "YASYVMFAVPKPKE-SECBINFHSA-N", "inchi": "", "smiles": "COP(=O)(N=C(O)C)SC", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "num_peaks": "16", "compound_name": "Acephate", "retention_time": "1.232997", "precursor_mz": "184.0194", "collision_energy": "", "peaks_json": [[90.09368, 1128.0], [93.11512, 1241.0], [95.10279, 1118.0], [101.31465, 1152.0], [102.90688, 1322.0], [103.98039, 1201.0], [112.01607, 12289.0], [112.99994, 38027.0], [115.00399, 1634.0], [124.98121, 922.0], [128.97701, 9208.0], [132.57193, 1350.0], [135.84808, 1428.0], [142.99275, 16419.0], [147.94205, 1750.0], [173.5094, 2353.0]]}, {"scannumber": "2257", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C12H11NO2", "inchikey": "CVXBEEMKQHEXEN-UHFFFAOYSA-N", "inchi": "", "smiles": "CN=C(Oc1cccc2c1cccc2)O", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"145.06491": "Theoretical m/z 145.064787, Mass diff 0 (0.85 ppm), SMILES OC1=CC=CC=2C=CC=CC12, Annotation [C10H8O+H]+, Rule of HR True"}, "num_peaks": "1", "compound_name": "Carbaryl", "retention_time": "5.259445", "precursor_mz": "202.0863", "collision_energy": "", "peaks_json": [[145.06491, 1326147.0]]}, {"scannumber": "1516", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C8H16NO5P", "inchikey": "VEENJGZXVHKXNB-UHFFFAOYSA-N", "inchi": "", "smiles": "COP(=O)(OC(=CC(=O)N(C)C)C)OC", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"112.07591": "Theoretical m/z 112.075687, Mass diff 0 (1.99 ppm), SMILES O=C(C=CC)N(C)C, Annotation [C6H11NO-H]+, Rule of HR True", "127.01563": "Theoretical m/z 127.01547, Mass diff 0 (1.26 ppm), SMILES O=P(O)(OC)OC, Annotation [C2H7O4P+H]+, Rule of HR True", "193.02605": "Theoretical m/z 193.026035, Mass diff 0 (0.08 ppm), SMILES O=CC=C(OP(=O)(OC)OC)C, Annotation [C6H11O5P-H]+, Rule of HR True", "238.08437": "Theoretical m/z 238.083891, Mass diff 0 (2.01 ppm), SMILES O=C(C=C(OP(=O)(OC)OC)C)N(C)C, Annotation [C8H16NO5P+H]+, Rule of HR True"}, "num_peaks": "5", "compound_name": "Dicrotophos", "retention_time": "2.025499", "precursor_mz": "238.0844", "collision_energy": "", "peaks_json": [[112.074, 102027.0], [112.07591, 9070987.0], [127.01563, 3230337.0], [193.02605, 7897744.0], [238.08437, 2973124.0]]}, {"scannumber": "1865", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C5H12NO3PS2", "inchikey": "MCWXGJITAZMZEV-UHFFFAOYSA-N", "inchi": "", "smiles": "CN=C(CSP(=S)(OC)OC)O", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"88.0219": "Theoretical m/z 88.021549, Mass diff 0 (3.99 ppm), SMILES SCC=NC, Annotation [C3H7NS-H]+, Rule of HR True", "124.98233": "Theoretical m/z 124.982067, Mass diff 0 (2.11 ppm), SMILES S=P(OC)OC, Annotation [C2H7O2PS-H]+, Rule of HR True", "142.99275": "Theoretical m/z 142.993177, Mass diff 0 (0 ppm), Formula C2H8O3PS", "156.95422": "Theoretical m/z 156.954136, Mass diff 0 (0.54 ppm), SMILES S=P(S)(OC)OC, Annotation [C2H7O2PS2-H]+, Rule of HR True", "170.97": "Theoretical m/z 170.969791, Mass diff 0 (1.22 ppm), SMILES S=P(OC)(OC)SC, '..b' diff 0.001 (4.38 ppm), SMILES OC1=CC=C(C(=C1)C)N(C)C, Annotation [C9H13NO-H]+, Rule of HR True", "151.09932": "Theoretical m/z 151.099168, Mass diff 0 (1.01 ppm), SMILES OC1=CC=C(C(=C1)C)N(C)C, Annotation [C9H13NO]+, Rule of HR False", "166.12282": "Theoretical m/z 166.122633, Mass diff 0 (1.13 ppm), SMILES OC=1C=C(C(=C(C1)C)N(C)C)C, Annotation [C10H15NO+H]+, Rule of HR True"}, "num_peaks": "5", "compound_name": "Mexacarbate", "retention_time": "1.682191", "precursor_mz": "223.1443", "collision_energy": "", "peaks_json": [[134.07283, 2632951.0], [136.07611, 26036728.0], [150.092, 1572118.0], [151.09932, 54847764.0], [166.12282, 1541928.0]]}, {"scannumber": "3999", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C19H21N2OCl", "inchikey": "OGYFATSSENRIKG-UHFFFAOYSA-N", "inchi": "", "smiles": "Clc1ccc(cc1)CN(C(=Nc1ccccc1)O)C1CCCC1", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"89.03881": "Theoretical m/z 89.038575, Mass diff 0 (2.63 ppm), SMILES C=1C=CC(=CC1)C, Annotation [C7H8-3H]+, Rule of HR True", "94.06543": "Theoretical m/z 94.065123, Mass diff 0 (3.27 ppm), SMILES NC=1C=CC=CC1, Annotation [C6H7N+H]+, Rule of HR True", "106.06545": "Theoretical m/z 106.065123, Mass diff 0 (3.09 ppm), SMILES N(=C)C=1C=CC=CC1, Annotation [C7H7N+H]+, Rule of HR True", "125.01532": "Theoretical m/z 125.015255, Mass diff 0 (0.52 ppm), SMILES ClC1=CC=C(C=C1)C, Annotation [C7H7Cl-H]+, Rule of HR True"}, "num_peaks": "5", "compound_name": "Monceren", "retention_time": "7.14553", "precursor_mz": "329.1426", "collision_energy": "", "peaks_json": [[89.03881, 550831.0], [94.06543, 635265.0], [106.06545, 446416.0], [125.01307, 512150.0], [125.01532, 37442116.0]]}, {"scannumber": "2271", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C16H16N2O4", "inchikey": "WZJZMXBKUWKXTQ-UHFFFAOYSA-N", "inchi": "", "smiles": "CCOC(=Nc1cccc(c1)OC(=Nc1ccccc1)O)O", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"136.03947": "Theoretical m/z 136.03931, Mass diff 0 (1.18 ppm), SMILES OC(O)=NC=1C=CC=CC1, Annotation [C7H7NO2-H]+, Rule of HR True", "154.04993": "Theoretical m/z 154.049864, Mass diff 0 (0.43 ppm), SMILES OC(O)=NC=1C=CC=C(O)C1, Annotation [C7H7NO3+H]+, Rule of HR True", "182.08162": "Theoretical m/z 182.081175, Mass diff 0 (2.45 ppm), SMILES OC(=NC=1C=CC=C(O)C1)OCC, Annotation [C9H11NO3+H]+, Rule of HR True"}, "num_peaks": "3", "compound_name": "Desmedipham", "retention_time": "6.430396", "precursor_mz": "301.1192", "collision_energy": "", "peaks_json": [[136.03947, 1773399.0], [154.04993, 1002798.0], [182.08162, 6480130.0]]}, {"scannumber": "2458", "precursortype": "[M+H]+", "ionmode": "Positive", "spectrumtype": "Centroid", "formula": "C16H16N2O4", "inchikey": "IDOWTHOLJBTAFI-UHFFFAOYSA-N", "inchi": "", "smiles": "COC(=Nc1cccc(c1)OC(=Nc1cccc(c1)C)O)O", "authors": "Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)", "instrument": "LC Orbitrap Fusion Tribrid MS", "instrumenttype": "LC-ESI-Orbitrap", "ionization": "ESI+", "license": "CC BY-NC", "comment": "", "peak_comments": {"136.03947": "Theoretical m/z 136.03931, Mass diff 0 (1.18 ppm), SMILES OC(O)=NC=1C=CC=CC1, Annotation [C7H7NO2-H]+, Rule of HR True", "168.06587": "Theoretical m/z 168.065519, Mass diff 0 (2.09 ppm), SMILES OC(=NC=1C=CC=C(O)C1)OC, Annotation [C8H9NO3+H]+, Rule of HR True"}, "num_peaks": "2", "compound_name": "Phenmedipham", "retention_time": "6.570995", "precursor_mz": "301.1185", "collision_energy": "", "peaks_json": [[136.03947, 2596929.0], [168.06587, 7038054.0]]}]\n\\ No newline at end of file\n'
b
diff -r 169c72b2ce79 -r 13b3e835aded test-data/convert/mgf_out.mgf
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/convert/mgf_out.mgf Tue May 02 10:16:11 2023 +0000
[
b"@@ -0,0 +1,7057 @@\n+BEGIN IONS\n+SCANNUMBER=1161\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C4H10NO3PS\n+INCHIKEY=YASYVMFAVPKPKE-SECBINFHSA-N\n+INCHI=\n+SMILES=COP(=O)(N=C(O)C)SC\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+NUM_PEAKS=16\n+COMPOUND_NAME=Acephate\n+RETENTION_TIME=1.232997\n+PRECURSOR_MZ=184.0194\n+COLLISION_ENERGY=\n+90.09368 1128.0 \n+93.11512 1241.0 \n+95.10279 1118.0 \n+101.31465 1152.0 \n+102.90688 1322.0 \n+103.98039 1201.0 \n+112.01607 12289.0 \n+112.99994 38027.0 \n+115.00399 1634.0 \n+124.98121 922.0 \n+128.97701 9208.0 \n+132.57193 1350.0 \n+135.84808 1428.0 \n+142.99275 16419.0 \n+147.94205 1750.0 \n+173.5094 2353.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=2257\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C12H11NO2\n+INCHIKEY=CVXBEEMKQHEXEN-UHFFFAOYSA-N\n+INCHI=\n+SMILES=CN=C(Oc1cccc2c1cccc2)O\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={145.06491: 'Theoretical m/z 145.064787, Mass diff 0 (0.85 ppm), SMILES OC1=CC=CC=2C=CC=CC12, Annotation [C10H8O+H]+, Rule of HR True'}\n+NUM_PEAKS=1\n+COMPOUND_NAME=Carbaryl\n+RETENTION_TIME=5.259445\n+PRECURSOR_MZ=202.0863\n+COLLISION_ENERGY=\n+145.06491 1326147.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=1516\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C8H16NO5P\n+INCHIKEY=VEENJGZXVHKXNB-UHFFFAOYSA-N\n+INCHI=\n+SMILES=COP(=O)(OC(=CC(=O)N(C)C)C)OC\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={112.07591: 'Theoretical m/z 112.075687, Mass diff 0 (1.99 ppm), SMILES O=C(C=CC)N(C)C, Annotation [C6H11NO-H]+, Rule of HR True', 127.01563: 'Theoretical m/z 127.01547, Mass diff 0 (1.26 ppm), SMILES O=P(O)(OC)OC, Annotation [C2H7O4P+H]+, Rule of HR True', 193.02605: 'Theoretical m/z 193.026035, Mass diff 0 (0.08 ppm), SMILES O=CC=C(OP(=O)(OC)OC)C, Annotation [C6H11O5P-H]+, Rule of HR True', 238.08437: 'Theoretical m/z 238.083891, Mass diff 0 (2.01 ppm), SMILES O=C(C=C(OP(=O)(OC)OC)C)N(C)C, Annotation [C8H16NO5P+H]+, Rule of HR True'}\n+NUM_PEAKS=5\n+COMPOUND_NAME=Dicrotophos\n+RETENTION_TIME=2.025499\n+PRECURSOR_MZ=238.0844\n+COLLISION_ENERGY=\n+112.074 102027.0 \n+112.07591 9070987.0 \n+127.01563 3230337.0 \n+193.02605 7897744.0 \n+238.08437 2973124.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=1865\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C5H12NO3PS2\n+INCHIKEY=MCWXGJITAZMZEV-UHFFFAOYSA-N\n+INCHI=\n+SMILES=CN=C(CSP(=S)(OC)OC)O\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={88.0219: 'Theoretical m/z 88.021549, Mass diff 0 (3.99 ppm), SMILES SCC=NC, Annotation [C3H7NS-H]+, Rule of HR True', 124.98233: 'Theoretical m/z 124.982067, Mass diff 0 (2.11 ppm), SMILES S=P(OC)OC, Annotation [C2H7O2PS-H]+, Rule of HR True', 142.99275: 'Theoretical m/z 142.993177, Mass diff 0 (0 ppm), Formula C2H8O3PS', 156.95422: 'Theoretical m/z 156.954136, Mass diff 0 (0.54 ppm), SMILES S=P(S)(OC)OC, Annotation [C2H7O2PS2-H]+, Rule of HR True', 170.97: 'Theoretical m/z 170.969791, Mass diff 0 (1.22 ppm), SMILES S=P(OC)(OC)SC, Annotation [C3H9O2PS2-H]+, Rule of HR True', 197.98123: 'Theoretical m/z 197.980686, Mass diff 0.001 (2.75 ppm), SMILES S=P(OC)SCC(O)=NC, Annotation [C4H10NO2PS2-H]+, Rule of HR True', 198.96501: 'Theoretical m/z 198.965248, Mass diff 0 (0 ppm), Formula C4H8O3PS2', 230.00722: 'Theoretical m/z 230.006895, Mass diff 0 (1.41 ppm), SMILES S=P(OC)(OC)SCC(O)=NC, Annotation [C5H12NO3PS2+H]+, Rule of H"..b"MENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={134.07283: 'Theoretical m/z 134.072623, Mass diff 0 (1.55 ppm), SMILES O(C=1C=C(C=C(C1)C)C)C, Annotation [C9H12O-2H]+, Rule of HR False', 136.07611: 'Theoretical m/z 136.076239, Mass diff 0 (0 ppm), Formula C8H10NO', 150.092: 'Theoretical m/z 150.091343, Mass diff 0.001 (4.38 ppm), SMILES OC1=CC=C(C(=C1)C)N(C)C, Annotation [C9H13NO-H]+, Rule of HR True', 151.09932: 'Theoretical m/z 151.099168, Mass diff 0 (1.01 ppm), SMILES OC1=CC=C(C(=C1)C)N(C)C, Annotation [C9H13NO]+, Rule of HR False', 166.12282: 'Theoretical m/z 166.122633, Mass diff 0 (1.13 ppm), SMILES OC=1C=C(C(=C(C1)C)N(C)C)C, Annotation [C10H15NO+H]+, Rule of HR True'}\n+NUM_PEAKS=5\n+COMPOUND_NAME=Mexacarbate\n+RETENTION_TIME=1.682191\n+PRECURSOR_MZ=223.1443\n+COLLISION_ENERGY=\n+134.07283 2632951.0 \n+136.07611 26036728.0 \n+150.092 1572118.0 \n+151.09932 54847764.0 \n+166.12282 1541928.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=3999\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C19H21N2OCl\n+INCHIKEY=OGYFATSSENRIKG-UHFFFAOYSA-N\n+INCHI=\n+SMILES=Clc1ccc(cc1)CN(C(=Nc1ccccc1)O)C1CCCC1\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={89.03881: 'Theoretical m/z 89.038575, Mass diff 0 (2.63 ppm), SMILES C=1C=CC(=CC1)C, Annotation [C7H8-3H]+, Rule of HR True', 94.06543: 'Theoretical m/z 94.065123, Mass diff 0 (3.27 ppm), SMILES NC=1C=CC=CC1, Annotation [C6H7N+H]+, Rule of HR True', 106.06545: 'Theoretical m/z 106.065123, Mass diff 0 (3.09 ppm), SMILES N(=C)C=1C=CC=CC1, Annotation [C7H7N+H]+, Rule of HR True', 125.01532: 'Theoretical m/z 125.015255, Mass diff 0 (0.52 ppm), SMILES ClC1=CC=C(C=C1)C, Annotation [C7H7Cl-H]+, Rule of HR True'}\n+NUM_PEAKS=5\n+COMPOUND_NAME=Monceren\n+RETENTION_TIME=7.14553\n+PRECURSOR_MZ=329.1426\n+COLLISION_ENERGY=\n+89.03881 550831.0 \n+94.06543 635265.0 \n+106.06545 446416.0 \n+125.01307 512150.0 \n+125.01532 37442116.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=2271\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C16H16N2O4\n+INCHIKEY=WZJZMXBKUWKXTQ-UHFFFAOYSA-N\n+INCHI=\n+SMILES=CCOC(=Nc1cccc(c1)OC(=Nc1ccccc1)O)O\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={136.03947: 'Theoretical m/z 136.03931, Mass diff 0 (1.18 ppm), SMILES OC(O)=NC=1C=CC=CC1, Annotation [C7H7NO2-H]+, Rule of HR True', 154.04993: 'Theoretical m/z 154.049864, Mass diff 0 (0.43 ppm), SMILES OC(O)=NC=1C=CC=C(O)C1, Annotation [C7H7NO3+H]+, Rule of HR True', 182.08162: 'Theoretical m/z 182.081175, Mass diff 0 (2.45 ppm), SMILES OC(=NC=1C=CC=C(O)C1)OCC, Annotation [C9H11NO3+H]+, Rule of HR True'}\n+NUM_PEAKS=3\n+COMPOUND_NAME=Desmedipham\n+RETENTION_TIME=6.430396\n+PRECURSOR_MZ=301.1192\n+COLLISION_ENERGY=\n+136.03947 1773399.0 \n+154.04993 1002798.0 \n+182.08162 6480130.0 \n+END IONS\n+\n+BEGIN IONS\n+SCANNUMBER=2458\n+PRECURSORTYPE=[M+H]+\n+IONMODE=Positive\n+SPECTRUMTYPE=Centroid\n+FORMULA=C16H16N2O4\n+INCHIKEY=IDOWTHOLJBTAFI-UHFFFAOYSA-N\n+INCHI=\n+SMILES=COC(=Nc1cccc(c1)OC(=Nc1cccc(c1)C)O)O\n+AUTHORS=Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT=LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE=LC-ESI-Orbitrap\n+IONIZATION=ESI+\n+LICENSE=CC BY-NC\n+COMMENT=\n+PEAK_COMMENTS={136.03947: 'Theoretical m/z 136.03931, Mass diff 0 (1.18 ppm), SMILES OC(O)=NC=1C=CC=CC1, Annotation [C7H7NO2-H]+, Rule of HR True', 168.06587: 'Theoretical m/z 168.065519, Mass diff 0 (2.09 ppm), SMILES OC(=NC=1C=CC=C(O)C1)OC, Annotation [C8H9NO3+H]+, Rule of HR True'}\n+NUM_PEAKS=2\n+COMPOUND_NAME=Phenmedipham\n+RETENTION_TIME=6.570995\n+PRECURSOR_MZ=301.1185\n+COLLISION_ENERGY=\n+136.03947 2596929.0 \n+168.06587 7038054.0 \n+END IONS\n+\n"
b
diff -r 169c72b2ce79 -r 13b3e835aded test-data/convert/msp_out.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/convert/msp_out.msp Tue May 02 10:16:11 2023 +0000
[
b'@@ -0,0 +1,6548 @@\n+SCANNUMBER: 1161\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C4H10NO3PS\n+INCHIKEY: YASYVMFAVPKPKE-SECBINFHSA-N\n+INCHI: \n+SMILES: COP(=O)(N=C(O)C)SC\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Acephate\n+RETENTION_TIME: 1.232997\n+PRECURSOR_MZ: 184.0194\n+COLLISION_ENERGY: \n+NUM PEAKS: 16\n+90.09368    1128.0\n+93.11512    1241.0\n+95.10279    1118.0\n+101.31465   1152.0\n+102.90688   1322.0\n+103.98039   1201.0\n+112.01607   12289.0\n+112.99994   38027.0\n+115.00399   1634.0\n+124.98121   922.0\n+128.97701   9208.0\n+132.57193   1350.0\n+135.84808   1428.0\n+142.99275   16419.0\n+147.94205   1750.0\n+173.5094    2353.0\n+\n+SCANNUMBER: 2257\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C12H11NO2\n+INCHIKEY: CVXBEEMKQHEXEN-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CN=C(Oc1cccc2c1cccc2)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Carbaryl\n+RETENTION_TIME: 5.259445\n+PRECURSOR_MZ: 202.0863\n+COLLISION_ENERGY: \n+NUM PEAKS: 1\n+145.06491   1326147.0\n+\n+SCANNUMBER: 1516\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C8H16NO5P\n+INCHIKEY: VEENJGZXVHKXNB-UHFFFAOYSA-N\n+INCHI: \n+SMILES: COP(=O)(OC(=CC(=O)N(C)C)C)OC\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Dicrotophos\n+RETENTION_TIME: 2.025499\n+PRECURSOR_MZ: 238.0844\n+COLLISION_ENERGY: \n+NUM PEAKS: 5\n+112.074     102027.0\n+112.07591   9070987.0\n+127.01563   3230337.0\n+193.02605   7897744.0\n+238.08437   2973124.0\n+\n+SCANNUMBER: 1865\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C5H12NO3PS2\n+INCHIKEY: MCWXGJITAZMZEV-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CN=C(CSP(=S)(OC)OC)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Dimethoate\n+RETENTION_TIME: 2.866696\n+PRECURSOR_MZ: 230.0072\n+COLLISION_ENERGY: \n+NUM PEAKS: 8\n+88.0219     548446.0\n+124.98233   183861.0\n+142.99275   722053.0\n+156.95422   80792.0\n+170.97      1426256.0\n+197.98123   240915.0\n+198.96501   5415933.0\n+230.00722   497851.0\n+\n+SCANNUMBER: 3852\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C21H22NO4Cl\n+INCHIKEY: QNBTYORWCCMPQP-UHFFFAOYSA-N\n+INCHI: \n+SMILES: COc1cc(ccc1OC)C(=CC(=O)N1CCOCC1)c1ccc(cc1)Cl\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Dimethomorph\n+RETENTION_TIME: 7.060486\n+PRECURSOR_MZ: 388.1316\n+COLLISION_ENERGY: \n+NUM PEAKS: 22\n+114.05532   468862.0\n+125.01571   886745.0\n+138.99484   4138370.0\n+155.0705    425164.0\n+165.05519   15513399.0\n+165.06543   350695.0\n+195.08057   386226.0\n+215.0262    490061.0\n+223.07544   702025.0\n+227.02576   230514.0\n+229.04225   216308.0\n+235.07555   241142.0\n+238.09914   1323577.0\n+242.04929   2449236.0\n+243.02142   891584.0\n+257.03726   578874.0\n+258.04443   3232295.0\n+266.0943    358273.0\n+270.04492   608851.0\n+273.06772   3866006.0\n+286.03912   483547.0\n+301.06311   4060551.0\n+\n+SCANNUMBER: 1009\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C2H8NO2PS\n+INCHIKEY: NNKVPIKMPCQWCG-ZCFIWIBFSA-N\n+INCHI: \n+SMILES: COP(=O)(SC)N\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+'..b'   2507023.0\n+\n+SCANNUMBER: 711\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C11H15N3O2\n+INCHIKEY: MYPKGPZHHQEODQ-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CN=C(Oc1cccc(c1)N=CN(C)C)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Formetanate_1\n+RETENTION_TIME: 0.7730471\n+PRECURSOR_MZ: 222.1239\n+COLLISION_ENERGY: \n+NUM PEAKS: 13\n+93.03365    1796.0\n+107.04935   1981.0\n+111.04435   82262.0\n+118.04142   1927.0\n+120.04462   150907.0\n+121.03984   67610.0\n+122.06016   5909.0\n+122.75254   1678.0\n+150.98424   1930.0\n+165.1024    143887.0\n+173.50876   2616.0\n+200.05632   2056.0\n+208.52768   2170.0\n+\n+SCANNUMBER: 1161\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C11H15N3O2\n+INCHIKEY: MYPKGPZHHQEODQ-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CN=C(Oc1cccc(c1)N=CN(C)C)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Formetanate_2\n+RETENTION_TIME: 1.13043\n+PRECURSOR_MZ: 222.1239\n+COLLISION_ENERGY: \n+NUM PEAKS: 15\n+91.05441    6330.0\n+93.03365    27201.0\n+107.04935   4024.0\n+111.04435   131558.0\n+115.05429   3711.0\n+117.06996   5571.0\n+118.04177   4476.0\n+120.04462   274740.0\n+121.03984   113412.0\n+122.06016   7843.0\n+124.07605   4049.0\n+135.04427   4178.0\n+145.06488   3067.0\n+164.95049   3848.0\n+165.1024    263802.0\n+\n+SCANNUMBER: 1328\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C12H18N2O2\n+INCHIKEY: YNEVBPNZHBAYOA-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CN=C(Oc1cc(C)c(c(c1)C)N(C)C)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Mexacarbate\n+RETENTION_TIME: 1.682191\n+PRECURSOR_MZ: 223.1443\n+COLLISION_ENERGY: \n+NUM PEAKS: 5\n+134.07283   2632951.0\n+136.07611   26036728.0\n+150.092     1572118.0\n+151.09932   54847764.0\n+166.12282   1541928.0\n+\n+SCANNUMBER: 3999\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C19H21N2OCl\n+INCHIKEY: OGYFATSSENRIKG-UHFFFAOYSA-N\n+INCHI: \n+SMILES: Clc1ccc(cc1)CN(C(=Nc1ccccc1)O)C1CCCC1\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Monceren\n+RETENTION_TIME: 7.14553\n+PRECURSOR_MZ: 329.1426\n+COLLISION_ENERGY: \n+NUM PEAKS: 5\n+89.03881    550831.0\n+94.06543    635265.0\n+106.06545   446416.0\n+125.01307   512150.0\n+125.01532   37442116.0\n+\n+SCANNUMBER: 2271\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C16H16N2O4\n+INCHIKEY: WZJZMXBKUWKXTQ-UHFFFAOYSA-N\n+INCHI: \n+SMILES: CCOC(=Nc1cccc(c1)OC(=Nc1ccccc1)O)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Desmedipham\n+RETENTION_TIME: 6.430396\n+PRECURSOR_MZ: 301.1192\n+COLLISION_ENERGY: \n+NUM PEAKS: 3\n+136.03947   1773399.0\n+154.04993   1002798.0\n+182.08162   6480130.0\n+\n+SCANNUMBER: 2458\n+PRECURSORTYPE: [M+H]+\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C16H16N2O4\n+INCHIKEY: IDOWTHOLJBTAFI-UHFFFAOYSA-N\n+INCHI: \n+SMILES: COC(=Nc1cccc(c1)OC(=Nc1cccc(c1)C)O)O\n+AUTHORS: Biomarker Analytical Laboratories, RECETOX, Masaryk University (CZ)\n+INSTRUMENT: LC Orbitrap Fusion Tribrid MS\n+INSTRUMENTTYPE: LC-ESI-Orbitrap\n+IONIZATION: ESI+\n+LICENSE: CC BY-NC\n+COMMENT: \n+COMPOUND_NAME: Phenmedipham\n+RETENTION_TIME: 6.570995\n+PRECURSOR_MZ: 301.1185\n+COLLISION_ENERGY: \n+NUM PEAKS: 2\n+136.03947   2596929.0\n+168.06587   7038054.0\n+\n'