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

Changeset 0:d75b6626e18a (2024-02-22)
Next changeset 1:3c7f20b24047 (2024-02-26)
Commit message:
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/misc commit 0cf8472dcae85c81bc91332a1c9be5e54289a34c
added:
macros.xml
test-data/input.msp
test-data/output_only_annotated.msp
test-data/output_plus_no_annotated.msp
use_theoretical_mz_annotations.xml
b
diff -r 000000000000 -r d75b6626e18a macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Thu Feb 22 10:48:59 2024 +0000
[
@@ -0,0 +1,27 @@
+<macros>
+    <token name="@TOOL_VERSION@">0.3.4</token>
+    <xml name="creator">
+        <creator>
+            <person
+                givenName="Wudmir"
+                familyName="Rojas"
+                url="https://github.com/wverastegui"
+                identifier="0000-0001-7036-9987" />
+            <person
+                givenName="Helge"
+                familyName="Hecht"
+                url="https://github.com/hechth"
+                identifier="0000-0001-6744-996X" />
+            <organization
+                url="https://www.recetox.muni.cz/"
+                email="GalaxyToolsDevelopmentandDeployment@space.muni.cz"
+                name="RECETOX MUNI" />
+        </creator>
+    </xml>
+
+    <token name="@HELP@">
+        <![CDATA[
+        This tool should be used after assigning peak annotations including theoretical mz values and structure annotations using recetox-msfinder. The tool overwrites the experimental peak mz value with the theoretical value from the peak annotation.
+        ]]>
+    </token>
+</macros>
b
diff -r 000000000000 -r d75b6626e18a test-data/input.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/input.msp Thu Feb 22 10:48:59 2024 +0000
[
b'@@ -0,0 +1,270 @@\n+NAME: 3-(4-Aminophenyl)-3-cyclohexylpiperidine-2,6-dione\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 286\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C17H22N2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C17H22N2O2/c18-14-8-6-13(7-9-14)17(12-4-2-1-3-5-12)11-10-15(20)19-16(17)21/h6-9,12H,1-5,10-11,18H2,(H,19,20,21)\n+SMILES: Nc1ccc(cc1)C2(CCC(=O)NC2=O)C3CCCCC3\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 72\n+27\t14.99\n+29\t15.99\t"Theoretical m/z 29.002191, Mass diff 0.002 (75.56 ppm), SMILES O=C, Annotation [CH2O-H]+, Rule of HR True"\n+39\t34.97\n+41\t93.92\t"Theoretical m/z 41.002191, Mass diff 0.002 (53.44 ppm), SMILES O=CC, Annotation [C2H4O-3H]+, Rule of HR True"\n+42\t14.99\n+51\t14.99\n+52\t10.99\n+53\t23.98\t"Theoretical m/z 53.00274, Mass diff 0.002 (0 ppm), Formula C3HO"\n+54\t34.97\t"Theoretical m/z 53.997989, Mass diff -0.003 (0 ppm), Formula C2NO"\n+55\t128.88\n+63\t9.99\n+65\t39.96\t"Theoretical m/z 65.00274, Mass diff 0.002 (0 ppm), Formula C4HO"\n+66\t16.98\n+67\t33.97\n+77\t55.95\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+78\t19.98\n+79\t29.97\n+81\t12.99\t"Theoretical m/z 80.997654, Mass diff -0.003 (0 ppm), Formula C4HO2"\n+82\t25.98\t"Theoretical m/z 81.992903, Mass diff -0.008 (0 ppm), Formula C3NO2"\n+83\t17.98\n+89\t18.98\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+90\t12.99\n+91\t53.95\n+92\t17.98\n+93\t58.95\t"Theoretical m/z 92.997654, Mass diff -0.003 (0 ppm), Formula C5HO2"\n+94\t48.96\n+102\t10.99\t"Theoretical m/z 101.997989, Mass diff -0.003 (0 ppm), Formula C6NO"\n+103\t30.97\n+104\t43.96\n+105\t27.97\n+106\t77.93\t"Theoretical m/z 105.992903, Mass diff -0.008 (0 ppm), Formula C5NO2"\n+107\t17.98\n+115\t77.93\n+116\t27.97\n+117\t117.89\t"Theoretical m/z 116.997654, Mass diff -0.003 (0 ppm), Formula C7HO2"\n+118\t180.84\t"Theoretical m/z 117.992903, Mass diff -0.008 (0 ppm), Formula C6NO2"\n+119\t63.94\n+120\t26.98\n+127\t15.99\n+128\t18.98\n+129\t11.99\n+130\t155.86\t"Theoretical m/z 129.992903, Mass diff -0.008 (0 ppm), Formula C7NO2"\n+131\t77.93\n+132\t326.71\t"Theoretical m/z 132, Mass diff -0.001 (0 ppm), Formula C11"\n+133\t82.93\n+134\t17.98\n+135\t14.99\n+143\t41.96\n+144\t45.96\t"Theoretical m/z 144, Mass diff -0.001 (0 ppm), Formula C12"\n+145\t18.98\n+146\t16.98\n+147\t29.97\n+148\t25.98\n+156\t20.98\t"Theoretical m/z 156.008, Mass diff 0.008 (51.28 ppm), SMILES O=CNC(=O)CC=1C=CC=CC=1, Annotation [C9H9NO2-7H]+, Rule of HR True"\n+157\t16.98\n+158\t25.98\t"Theoretical m/z 158.003074, Mass diff 0.003 (0 ppm), Formula C12N"\n+159\t56.95\n+160\t24.98\n+161\t22.98\n+162\t84.92\t"Theoretical m/z 161.997989, Mass diff -0.003 (0 ppm), Formula C11NO"\n+163\t56.95\n+174\t11.99\t"Theoretical m/z 173.997989, Mass diff -0.003 (0 ppm), Formula C12NO"\n+175\t386.65\n+176\t101.91\n+177\t9.99\n+186\t17.98\t"Theoretical m/z 185.997989, Mass diff -0.003 (0 ppm), Formula C13NO"\n+202\t17.98\t"Theoretical m/z 201.992903, Mass diff -0.008 (0 ppm), Formula C13NO2"\n+203\t999\n+204\t803.28\n+205\t97.91\n+286\t168.85\n+287\t32.97\n+\n+NAME: 1-(5-Chloro-2-hydroxyphenyl)-3-(4-chlorophenyl)-2-propen-1-one\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 292\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C15H10Cl2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C15H10Cl2O2/c16-11-4-1-10(2-5-11)3-7-14(18)13-9-12(17)6-8-15(13)19/h1-9,19H/b7-3+\n+SMILES: Oc1ccc(Cl)cc1C(=O)\\C=C\\c2ccc(Cl)cc2\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 73\n+38\t10.99\n+39\t25.98\n+50\t56.95\n+51\t88.92\t"Theoretical m/z 51.000153, Mass diff 0 (0 ppm), Formula CH4Cl"\n+52\t15.99\n+53\t26.98\t"Theoretical m/z 53.002191, Mass diff 0.002 (41.34 ppm), SMILES O=CC=C, Annotation [C3H4O-3H]+, Rule of HR True"\n+61\t19.98\t"Theoretical m/z 61.007825, Mass diff 0.007 (0 ppm), Formula C5H"\n+62\t69.94\n+63\t320.71\t"Theoretical m/z 63.000153, Mass diff 0 (0 ppm), Formula C2H4Cl"\n+64\t21.98\n+72\t10.99\t"Theoretical m/z 71.999453, Mass diff 0.001 (7.6 ppm), SMILES C=1C='..b']+, Rule of HR False"\n+157\t42.96\n+163\t10.99\t"Theoretical m/z 162.994516, Mass diff 0.005 (33.65 ppm), SMILES O=C(C=C)C1=CC=CC(=C1)Cl, Annotation [C9H7ClO-3H]+, Rule of HR True"\n+165\t67.94\t"Theoretical m/z 164.997654, Mass diff -0.003 (0 ppm), Formula C11HO2"\n+166\t15.99\n+167\t12.99\n+176\t9.99\n+180\t54.95\t"Theoretical m/z 179.99726, Mass diff 0.003 (15.22 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-2H]+, Rule of HR False"\n+181\t204.82\t"Theoretical m/z 181.005085, Mass diff 0.005 (28.09 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-H]+, Rule of HR True"\n+182\t37.97\n+183\t66.94\t"Theoretical m/z 183.000153, Mass diff 0 (0 ppm), Formula C12H4Cl"\n+194\t9.99\n+257\t54.95\t"Theoretical m/z 256.992481, Mass diff -0.008 (0 ppm), Formula C15H7Cl2"\n+259\t17.98\t"Theoretical m/z 259.008131, Mass diff 0.008 (0 ppm), Formula C15H9Cl2"\n+275\t27.97\t"Theoretical m/z 275.002491, Mass diff 0.002 (9.06 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C2=CC=CC(=C2)Cl, Annotation [C15H10Cl2O-H]+, Rule of HR True"\n+277\t17.98\n+291\t153.86\t"Theoretical m/z 290.99796, Mass diff -0.003 (0 ppm), Formula C15H9Cl2O2"\n+292\t260.76\t"Theoretical m/z 292.00525, Mass diff 0.005 (17.98 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C=2C=C(C=CC=2(O))Cl, Annotation [C15H10Cl2O2]+, Rule of HR False"\n+293\t135.88\n+294\t165.85\n+295\t41.96\n+296\t29.97\n+\n+NAME: 3-Benzoylbenzo[f]coumarin\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 300\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C20H12O3\n+INCHIKEY: \n+INCHI: InChI=1S/C20H12O3/c21-19(14-7-2-1-3-8-14)17-12-16-15-9-5-4-6-13(15)10-11-18(16)23-20(17)22/h1-12H\n+SMILES: O=C1Oc2ccc3ccccc3c2C=C1C(=O)c4ccccc4\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 62\n+39\t18.98\n+50\t44.96\n+51\t202.82\t"Theoretical m/z 51.008219, Mass diff 0.008 (0 ppm), Formula H3O3"\n+52\t12.99\n+62\t26.98\n+63\t80.93\t"Theoretical m/z 63.008219, Mass diff 0.008 (0 ppm), Formula CH3O3"\n+65\t15.99\n+74\t28.97\n+75\t32.97\t"Theoretical m/z 75.008219, Mass diff 0.008 (0 ppm), Formula C2H3O3"\n+76\t32.97\t"Theoretical m/z 75.994915, Mass diff -0.006 (0 ppm), Formula C5O"\n+77\t986.11\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+78\t67.94\n+86\t32.97\n+87\t47.96\t"Theoretical m/z 87.007668, Mass diff 0.008 (88.14 ppm), SMILES O=CCC(=O)O, Annotation [C3H3O3]+, Rule of HR False"\n+88\t23.98\n+89\t62.94\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+94\t13.99\n+98\t12.99\n+99\t12.99\t"Theoretical m/z 99.007674, Mass diff 0.008 (77.51 ppm), SMILES O=CC(C(=O)O)C, Annotation [C4H5O3-2H]+, Rule of HR False"\n+105\t999\t"Theoretical m/z 104.997654, Mass diff -0.003 (0 ppm), Formula C6HO2"\n+106\t76.93\n+107\t9.99\n+110\t10.99\n+111\t13.99\t"Theoretical m/z 111.008219, Mass diff 0.008 (0 ppm), Formula C5H3O3"\n+112\t11.99\n+113\t68.94\t"Theoretical m/z 113.00274, Mass diff 0.002 (0 ppm), Formula C8HO"\n+114\t11.99\n+122\t14.99\t"Theoretical m/z 122.000394, Mass diff 0 (0 ppm), Formula C6H2O3"\n+126\t9.99\n+137\t54.95\t"Theoretical m/z 137.00274, Mass diff 0.002 (0 ppm), Formula C10HO"\n+138\t69.94\n+139\t764.31\n+140\t89.92\n+150\t68.94\n+151\t24.98\n+157\t17.98\t"Theoretical m/z 157.007825, Mass diff 0.007 (0 ppm), Formula C13H"\n+187\t10.99\n+189\t10.99\t"Theoretical m/z 188.997654, Mass diff -0.003 (0 ppm), Formula C13HO2"\n+195\t198.82\t"Theoretical m/z 195.008219, Mass diff 0.008 (0 ppm), Formula C12H3O3"\n+196\t27.97\n+213\t32.97\t"Theoretical m/z 212.997654, Mass diff -0.003 (0 ppm), Formula C15HO2"\n+215\t53.95\n+216\t13.99\n+223\t199.82\n+224\t32.97\n+226\t10.99\n+228\t15.99\t"Theoretical m/z 228, Mass diff -0.001 (0 ppm), Formula C19"\n+243\t23.98\t"Theoretical m/z 243.008219, Mass diff 0.008 (0 ppm), Formula C16H3O3"\n+244\t90.92\t"Theoretical m/z 243.994915, Mass diff -0.006 (0 ppm), Formula C19O"\n+245\t15.99\n+254\t11.99\n+255\t49.95\t"Theoretical m/z 255.008219, Mass diff 0.008 (0 ppm), Formula C17H3O3"\n+256\t24.98\n+271\t407.63\n+272\t228.79\n+273\t38.96\n+282\t20.98\n+283\t34.97\n+299\t108.9\n+300\t684.38\n+301\t147.87\n+302\t18.98\n+\n'
b
diff -r 000000000000 -r d75b6626e18a test-data/output_only_annotated.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output_only_annotated.msp Thu Feb 22 10:48:59 2024 +0000
[
b'@@ -0,0 +1,138 @@\n+NAME: 3-(4-Aminophenyl)-3-cyclohexylpiperidine-2,6-dione\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 286\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C17H22N2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C17H22N2O2/c18-14-8-6-13(7-9-14)17(12-4-2-1-3-5-12)11-10-15(20)19-16(17)21/h6-9,12H,1-5,10-11,18H2,(H,19,20,21)\n+SMILES: Nc1ccc(cc1)C2(CCC(=O)NC2=O)C3CCCCC3\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 23\n+29.002191\t15.99\t"Theoretical m/z 29.002191, Mass diff 0.002 (75.56 ppm), SMILES O=C, Annotation [CH2O-H]+, Rule of HR True"\n+41.002191\t93.92\t"Theoretical m/z 41.002191, Mass diff 0.002 (53.44 ppm), SMILES O=CC, Annotation [C2H4O-3H]+, Rule of HR True"\n+53.00274\t23.98\t"Theoretical m/z 53.00274, Mass diff 0.002 (0 ppm), Formula C3HO"\n+53.997989\t34.97\t"Theoretical m/z 53.997989, Mass diff -0.003 (0 ppm), Formula C2NO"\n+65.00274\t39.96\t"Theoretical m/z 65.00274, Mass diff 0.002 (0 ppm), Formula C4HO"\n+77.00274\t55.95\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+80.997654\t12.99\t"Theoretical m/z 80.997654, Mass diff -0.003 (0 ppm), Formula C4HO2"\n+81.992903\t25.98\t"Theoretical m/z 81.992903, Mass diff -0.008 (0 ppm), Formula C3NO2"\n+89.00274\t18.98\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+92.997654\t58.95\t"Theoretical m/z 92.997654, Mass diff -0.003 (0 ppm), Formula C5HO2"\n+101.997989\t10.99\t"Theoretical m/z 101.997989, Mass diff -0.003 (0 ppm), Formula C6NO"\n+105.992903\t77.93\t"Theoretical m/z 105.992903, Mass diff -0.008 (0 ppm), Formula C5NO2"\n+116.997654\t117.89\t"Theoretical m/z 116.997654, Mass diff -0.003 (0 ppm), Formula C7HO2"\n+117.992903\t180.84\t"Theoretical m/z 117.992903, Mass diff -0.008 (0 ppm), Formula C6NO2"\n+129.992903\t155.86\t"Theoretical m/z 129.992903, Mass diff -0.008 (0 ppm), Formula C7NO2"\n+132.0\t326.71\t"Theoretical m/z 132, Mass diff -0.001 (0 ppm), Formula C11"\n+144.0\t45.96\t"Theoretical m/z 144, Mass diff -0.001 (0 ppm), Formula C12"\n+156.008\t20.98\t"Theoretical m/z 156.008, Mass diff 0.008 (51.28 ppm), SMILES O=CNC(=O)CC=1C=CC=CC=1, Annotation [C9H9NO2-7H]+, Rule of HR True"\n+158.003074\t25.98\t"Theoretical m/z 158.003074, Mass diff 0.003 (0 ppm), Formula C12N"\n+161.997989\t84.92\t"Theoretical m/z 161.997989, Mass diff -0.003 (0 ppm), Formula C11NO"\n+173.997989\t11.99\t"Theoretical m/z 173.997989, Mass diff -0.003 (0 ppm), Formula C12NO"\n+185.997989\t17.98\t"Theoretical m/z 185.997989, Mass diff -0.003 (0 ppm), Formula C13NO"\n+201.992903\t17.98\t"Theoretical m/z 201.992903, Mass diff -0.008 (0 ppm), Formula C13NO2"\n+\n+NAME: 1-(5-Chloro-2-hydroxyphenyl)-3-(4-chlorophenyl)-2-propen-1-one\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 292\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C15H10Cl2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C15H10Cl2O2/c16-11-4-1-10(2-5-11)3-7-14(18)13-9-12(17)6-8-15(13)19/h1-9,19H/b7-3+\n+SMILES: Oc1ccc(Cl)cc1C(=O)\\C=C\\c2ccc(Cl)cc2\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 31\n+51.000153\t88.92\t"Theoretical m/z 51.000153, Mass diff 0 (0 ppm), Formula CH4Cl"\n+53.002191\t26.98\t"Theoretical m/z 53.002191, Mass diff 0.002 (41.34 ppm), SMILES O=CC=C, Annotation [C3H4O-3H]+, Rule of HR True"\n+61.007825\t19.98\t"Theoretical m/z 61.007825, Mass diff 0.007 (0 ppm), Formula C5H"\n+63.000153\t320.71\t"Theoretical m/z 63.000153, Mass diff 0 (0 ppm), Formula C2H4Cl"\n+71.999453\t10.99\t"Theoretical m/z 71.999453, Mass diff 0.001 (7.6 ppm), SMILES C=1C=CC=CC=1, Annotation [C6H6-6H]+, Rule of HR False"\n+73.007278\t35.97\t"Theoretical m/z 73.007278, Mass diff 0.007 (99.69 ppm), SMILES C=1C=CC=CC=1, Annotation [C6H6-5H]+, Rule of HR True"\n+75.000153\t128.88\t"Theoretical m/z 75.000153, Mass diff 0 (0 ppm), Formula C3H4Cl"\n+77.00274\t150.86\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+85.007825\t10.99\t"Theoretical m/z 85.007825, Mass diff'..b'136.007422\t16.98\t"Theoretical m/z 136.007422, Mass diff 0.007 (54.57 ppm), SMILES C=CC=1C=CC(=CC=1)Cl, Annotation [C8H7Cl-2H]+, Rule of HR False"\n+137.00274\t67.94\t"Theoretical m/z 137.00274, Mass diff 0.002 (0 ppm), Formula C10HO"\n+155.997254\t320.71\t"Theoretical m/z 155.997254, Mass diff 0.003 (17.6 ppm), SMILES O=CC=1C=C(C=CC=1(O))Cl, Annotation [C7H5ClO2]+, Rule of HR False"\n+162.994516\t10.99\t"Theoretical m/z 162.994516, Mass diff 0.005 (33.65 ppm), SMILES O=C(C=C)C1=CC=CC(=C1)Cl, Annotation [C9H7ClO-3H]+, Rule of HR True"\n+164.997654\t67.94\t"Theoretical m/z 164.997654, Mass diff -0.003 (0 ppm), Formula C11HO2"\n+179.99726\t54.95\t"Theoretical m/z 179.99726, Mass diff 0.003 (15.22 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-2H]+, Rule of HR False"\n+181.005085\t204.82\t"Theoretical m/z 181.005085, Mass diff 0.005 (28.09 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-H]+, Rule of HR True"\n+183.000153\t66.94\t"Theoretical m/z 183.000153, Mass diff 0 (0 ppm), Formula C12H4Cl"\n+256.992481\t54.95\t"Theoretical m/z 256.992481, Mass diff -0.008 (0 ppm), Formula C15H7Cl2"\n+259.008131\t17.98\t"Theoretical m/z 259.008131, Mass diff 0.008 (0 ppm), Formula C15H9Cl2"\n+275.002491\t27.97\t"Theoretical m/z 275.002491, Mass diff 0.002 (9.06 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C2=CC=CC(=C2)Cl, Annotation [C15H10Cl2O-H]+, Rule of HR True"\n+290.99796\t153.86\t"Theoretical m/z 290.99796, Mass diff -0.003 (0 ppm), Formula C15H9Cl2O2"\n+292.00525\t260.76\t"Theoretical m/z 292.00525, Mass diff 0.005 (17.98 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C=2C=C(C=CC=2(O))Cl, Annotation [C15H10Cl2O2]+, Rule of HR False"\n+\n+NAME: 3-Benzoylbenzo[f]coumarin\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 300\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C20H12O3\n+INCHIKEY: \n+INCHI: InChI=1S/C20H12O3/c21-19(14-7-2-1-3-8-14)17-12-16-15-9-5-4-6-13(15)10-11-18(16)23-20(17)22/h1-12H\n+SMILES: O=C1Oc2ccc3ccccc3c2C=C1C(=O)c4ccccc4\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 21\n+51.008219\t202.82\t"Theoretical m/z 51.008219, Mass diff 0.008 (0 ppm), Formula H3O3"\n+63.008219\t80.93\t"Theoretical m/z 63.008219, Mass diff 0.008 (0 ppm), Formula CH3O3"\n+75.008219\t32.97\t"Theoretical m/z 75.008219, Mass diff 0.008 (0 ppm), Formula C2H3O3"\n+75.994915\t32.97\t"Theoretical m/z 75.994915, Mass diff -0.006 (0 ppm), Formula C5O"\n+77.00274\t986.11\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+87.007668\t47.96\t"Theoretical m/z 87.007668, Mass diff 0.008 (88.14 ppm), SMILES O=CCC(=O)O, Annotation [C3H3O3]+, Rule of HR False"\n+89.00274\t62.94\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+99.007674\t12.99\t"Theoretical m/z 99.007674, Mass diff 0.008 (77.51 ppm), SMILES O=CC(C(=O)O)C, Annotation [C4H5O3-2H]+, Rule of HR False"\n+104.997654\t999.0\t"Theoretical m/z 104.997654, Mass diff -0.003 (0 ppm), Formula C6HO2"\n+111.008219\t13.99\t"Theoretical m/z 111.008219, Mass diff 0.008 (0 ppm), Formula C5H3O3"\n+113.00274\t68.94\t"Theoretical m/z 113.00274, Mass diff 0.002 (0 ppm), Formula C8HO"\n+122.000394\t14.99\t"Theoretical m/z 122.000394, Mass diff 0 (0 ppm), Formula C6H2O3"\n+137.00274\t54.95\t"Theoretical m/z 137.00274, Mass diff 0.002 (0 ppm), Formula C10HO"\n+157.007825\t17.98\t"Theoretical m/z 157.007825, Mass diff 0.007 (0 ppm), Formula C13H"\n+188.997654\t10.99\t"Theoretical m/z 188.997654, Mass diff -0.003 (0 ppm), Formula C13HO2"\n+195.008219\t198.82\t"Theoretical m/z 195.008219, Mass diff 0.008 (0 ppm), Formula C12H3O3"\n+212.997654\t32.97\t"Theoretical m/z 212.997654, Mass diff -0.003 (0 ppm), Formula C15HO2"\n+228.0\t15.99\t"Theoretical m/z 228, Mass diff -0.001 (0 ppm), Formula C19"\n+243.008219\t23.98\t"Theoretical m/z 243.008219, Mass diff 0.008 (0 ppm), Formula C16H3O3"\n+243.994915\t90.92\t"Theoretical m/z 243.994915, Mass diff -0.006 (0 ppm), Formula C19O"\n+255.008219\t49.95\t"Theoretical m/z 255.008219, Mass diff 0.008 (0 ppm), Formula C17H3O3"\n+\n'
b
diff -r 000000000000 -r d75b6626e18a test-data/output_plus_no_annotated.msp
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/output_plus_no_annotated.msp Thu Feb 22 10:48:59 2024 +0000
[
b'@@ -0,0 +1,270 @@\n+NAME: 3-(4-Aminophenyl)-3-cyclohexylpiperidine-2,6-dione\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 286\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C17H22N2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C17H22N2O2/c18-14-8-6-13(7-9-14)17(12-4-2-1-3-5-12)11-10-15(20)19-16(17)21/h6-9,12H,1-5,10-11,18H2,(H,19,20,21)\n+SMILES: Nc1ccc(cc1)C2(CCC(=O)NC2=O)C3CCCCC3\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 72\n+27.0\t14.99\n+29.002191\t15.99\t"Theoretical m/z 29.002191, Mass diff 0.002 (75.56 ppm), SMILES O=C, Annotation [CH2O-H]+, Rule of HR True"\n+39.0\t34.97\n+41.002191\t93.92\t"Theoretical m/z 41.002191, Mass diff 0.002 (53.44 ppm), SMILES O=CC, Annotation [C2H4O-3H]+, Rule of HR True"\n+42.0\t14.99\n+51.0\t14.99\n+52.0\t10.99\n+53.00274\t23.98\t"Theoretical m/z 53.00274, Mass diff 0.002 (0 ppm), Formula C3HO"\n+53.997989\t34.97\t"Theoretical m/z 53.997989, Mass diff -0.003 (0 ppm), Formula C2NO"\n+55.0\t128.88\n+63.0\t9.99\n+65.00274\t39.96\t"Theoretical m/z 65.00274, Mass diff 0.002 (0 ppm), Formula C4HO"\n+66.0\t16.98\n+67.0\t33.97\n+77.00274\t55.95\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+78.0\t19.98\n+79.0\t29.97\n+80.997654\t12.99\t"Theoretical m/z 80.997654, Mass diff -0.003 (0 ppm), Formula C4HO2"\n+81.992903\t25.98\t"Theoretical m/z 81.992903, Mass diff -0.008 (0 ppm), Formula C3NO2"\n+83.0\t17.98\n+89.00274\t18.98\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+90.0\t12.99\n+91.0\t53.95\n+92.0\t17.98\n+92.997654\t58.95\t"Theoretical m/z 92.997654, Mass diff -0.003 (0 ppm), Formula C5HO2"\n+94.0\t48.96\n+101.997989\t10.99\t"Theoretical m/z 101.997989, Mass diff -0.003 (0 ppm), Formula C6NO"\n+103.0\t30.97\n+104.0\t43.96\n+105.0\t27.97\n+105.992903\t77.93\t"Theoretical m/z 105.992903, Mass diff -0.008 (0 ppm), Formula C5NO2"\n+107.0\t17.98\n+115.0\t77.93\n+116.0\t27.97\n+116.997654\t117.89\t"Theoretical m/z 116.997654, Mass diff -0.003 (0 ppm), Formula C7HO2"\n+117.992903\t180.84\t"Theoretical m/z 117.992903, Mass diff -0.008 (0 ppm), Formula C6NO2"\n+119.0\t63.94\n+120.0\t26.98\n+127.0\t15.99\n+128.0\t18.98\n+129.0\t11.99\n+129.992903\t155.86\t"Theoretical m/z 129.992903, Mass diff -0.008 (0 ppm), Formula C7NO2"\n+131.0\t77.93\n+132.0\t326.71\t"Theoretical m/z 132, Mass diff -0.001 (0 ppm), Formula C11"\n+133.0\t82.93\n+134.0\t17.98\n+135.0\t14.99\n+143.0\t41.96\n+144.0\t45.96\t"Theoretical m/z 144, Mass diff -0.001 (0 ppm), Formula C12"\n+145.0\t18.98\n+146.0\t16.98\n+147.0\t29.97\n+148.0\t25.98\n+156.008\t20.98\t"Theoretical m/z 156.008, Mass diff 0.008 (51.28 ppm), SMILES O=CNC(=O)CC=1C=CC=CC=1, Annotation [C9H9NO2-7H]+, Rule of HR True"\n+157.0\t16.98\n+158.003074\t25.98\t"Theoretical m/z 158.003074, Mass diff 0.003 (0 ppm), Formula C12N"\n+159.0\t56.95\n+160.0\t24.98\n+161.0\t22.98\n+161.997989\t84.92\t"Theoretical m/z 161.997989, Mass diff -0.003 (0 ppm), Formula C11NO"\n+163.0\t56.95\n+173.997989\t11.99\t"Theoretical m/z 173.997989, Mass diff -0.003 (0 ppm), Formula C12NO"\n+175.0\t386.65\n+176.0\t101.91\n+177.0\t9.99\n+185.997989\t17.98\t"Theoretical m/z 185.997989, Mass diff -0.003 (0 ppm), Formula C13NO"\n+201.992903\t17.98\t"Theoretical m/z 201.992903, Mass diff -0.008 (0 ppm), Formula C13NO2"\n+203.0\t999.0\n+204.0\t803.28\n+205.0\t97.91\n+286.0\t168.85\n+287.0\t32.97\n+\n+NAME: 1-(5-Chloro-2-hydroxyphenyl)-3-(4-chlorophenyl)-2-propen-1-one\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 292\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C15H10Cl2O2\n+INCHIKEY: \n+INCHI: InChI=1S/C15H10Cl2O2/c16-11-4-1-10(2-5-11)3-7-14(18)13-9-12(17)6-8-15(13)19/h1-9,19H/b7-3+\n+SMILES: Oc1ccc(Cl)cc1C(=O)\\C=C\\c2ccc(Cl)cc2\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 73\n+38.0\t10.99\n+39.0\t25.98\n+50.0\t56.95\n+51.000153\t88.92\t"Theoretical m/z 51.000153, Mass diff 0 (0 ppm), Formula CH4Cl"\n+52.0\t15.99\n+53.002191\t26.98\t"Theoretical m/z 53.002191, Mass diff 0.002 (41.34 ppm), SMILES O=CC=C, Annotation [C3H4O-3H]+, '..b'9\n+179.99726\t54.95\t"Theoretical m/z 179.99726, Mass diff 0.003 (15.22 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-2H]+, Rule of HR False"\n+181.005085\t204.82\t"Theoretical m/z 181.005085, Mass diff 0.005 (28.09 ppm), SMILES O=C(C=C)C=1C=C(C=CC=1(O))Cl, Annotation [C9H7ClO2-H]+, Rule of HR True"\n+182.0\t37.97\n+183.000153\t66.94\t"Theoretical m/z 183.000153, Mass diff 0 (0 ppm), Formula C12H4Cl"\n+194.0\t9.99\n+256.992481\t54.95\t"Theoretical m/z 256.992481, Mass diff -0.008 (0 ppm), Formula C15H7Cl2"\n+259.008131\t17.98\t"Theoretical m/z 259.008131, Mass diff 0.008 (0 ppm), Formula C15H9Cl2"\n+275.002491\t27.97\t"Theoretical m/z 275.002491, Mass diff 0.002 (9.06 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C2=CC=CC(=C2)Cl, Annotation [C15H10Cl2O-H]+, Rule of HR True"\n+277.0\t17.98\n+290.99796\t153.86\t"Theoretical m/z 290.99796, Mass diff -0.003 (0 ppm), Formula C15H9Cl2O2"\n+292.00525\t260.76\t"Theoretical m/z 292.00525, Mass diff 0.005 (17.98 ppm), SMILES O=C(C=CC=1C=CC(=CC=1)Cl)C=2C=C(C=CC=2(O))Cl, Annotation [C15H10Cl2O2]+, Rule of HR False"\n+293.0\t135.88\n+294.0\t165.85\n+295.0\t41.96\n+296.0\t29.97\n+\n+NAME: 3-Benzoylbenzo[f]coumarin\n+SCANNUMBER: -1\n+RETENTIONTIME: 0\n+RETENTIONINDEX: 0\n+PRECURSORMZ: 300\n+PRECURSORTYPE: [M]+.\n+IONMODE: Positive\n+SPECTRUMTYPE: Centroid\n+FORMULA: C20H12O3\n+INCHIKEY: \n+INCHI: InChI=1S/C20H12O3/c21-19(14-7-2-1-3-8-14)17-12-16-15-9-5-4-6-13(15)10-11-18(16)23-20(17)22/h1-12H\n+SMILES: O=C1Oc2ccc3ccccc3c2C=C1C(=O)c4ccccc4\n+AUTHORS: \n+COLLISIONENERGY: 40\n+INSTRUMENT: \n+INSTRUMENTTYPE: \n+IONIZATION: \n+LICENSE: \n+COMMENT: \n+Num Peaks: 62\n+39.0\t18.98\n+50.0\t44.96\n+51.008219\t202.82\t"Theoretical m/z 51.008219, Mass diff 0.008 (0 ppm), Formula H3O3"\n+52.0\t12.99\n+62.0\t26.98\n+63.008219\t80.93\t"Theoretical m/z 63.008219, Mass diff 0.008 (0 ppm), Formula CH3O3"\n+65.0\t15.99\n+74.0\t28.97\n+75.008219\t32.97\t"Theoretical m/z 75.008219, Mass diff 0.008 (0 ppm), Formula C2H3O3"\n+75.994915\t32.97\t"Theoretical m/z 75.994915, Mass diff -0.006 (0 ppm), Formula C5O"\n+77.00274\t986.11\t"Theoretical m/z 77.00274, Mass diff 0.002 (0 ppm), Formula C5HO"\n+78.0\t67.94\n+86.0\t32.97\n+87.007668\t47.96\t"Theoretical m/z 87.007668, Mass diff 0.008 (88.14 ppm), SMILES O=CCC(=O)O, Annotation [C3H3O3]+, Rule of HR False"\n+88.0\t23.98\n+89.00274\t62.94\t"Theoretical m/z 89.00274, Mass diff 0.002 (0 ppm), Formula C6HO"\n+94.0\t13.99\n+98.0\t12.99\n+99.007674\t12.99\t"Theoretical m/z 99.007674, Mass diff 0.008 (77.51 ppm), SMILES O=CC(C(=O)O)C, Annotation [C4H5O3-2H]+, Rule of HR False"\n+104.997654\t999.0\t"Theoretical m/z 104.997654, Mass diff -0.003 (0 ppm), Formula C6HO2"\n+106.0\t76.93\n+107.0\t9.99\n+110.0\t10.99\n+111.008219\t13.99\t"Theoretical m/z 111.008219, Mass diff 0.008 (0 ppm), Formula C5H3O3"\n+112.0\t11.99\n+113.00274\t68.94\t"Theoretical m/z 113.00274, Mass diff 0.002 (0 ppm), Formula C8HO"\n+114.0\t11.99\n+122.000394\t14.99\t"Theoretical m/z 122.000394, Mass diff 0 (0 ppm), Formula C6H2O3"\n+126.0\t9.99\n+137.00274\t54.95\t"Theoretical m/z 137.00274, Mass diff 0.002 (0 ppm), Formula C10HO"\n+138.0\t69.94\n+139.0\t764.31\n+140.0\t89.92\n+150.0\t68.94\n+151.0\t24.98\n+157.007825\t17.98\t"Theoretical m/z 157.007825, Mass diff 0.007 (0 ppm), Formula C13H"\n+187.0\t10.99\n+188.997654\t10.99\t"Theoretical m/z 188.997654, Mass diff -0.003 (0 ppm), Formula C13HO2"\n+195.008219\t198.82\t"Theoretical m/z 195.008219, Mass diff 0.008 (0 ppm), Formula C12H3O3"\n+196.0\t27.97\n+212.997654\t32.97\t"Theoretical m/z 212.997654, Mass diff -0.003 (0 ppm), Formula C15HO2"\n+215.0\t53.95\n+216.0\t13.99\n+223.0\t199.82\n+224.0\t32.97\n+226.0\t10.99\n+228.0\t15.99\t"Theoretical m/z 228, Mass diff -0.001 (0 ppm), Formula C19"\n+243.008219\t23.98\t"Theoretical m/z 243.008219, Mass diff 0.008 (0 ppm), Formula C16H3O3"\n+243.994915\t90.92\t"Theoretical m/z 243.994915, Mass diff -0.006 (0 ppm), Formula C19O"\n+245.0\t15.99\n+254.0\t11.99\n+255.008219\t49.95\t"Theoretical m/z 255.008219, Mass diff 0.008 (0 ppm), Formula C17H3O3"\n+256.0\t24.98\n+271.0\t407.63\n+272.0\t228.79\n+273.0\t38.96\n+282.0\t20.98\n+283.0\t34.97\n+299.0\t108.9\n+300.0\t684.38\n+301.0\t147.87\n+302.0\t18.98\n+\n'
b
diff -r 000000000000 -r d75b6626e18a use_theoretical_mz_annotations.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/use_theoretical_mz_annotations.xml Thu Feb 22 10:48:59 2024 +0000
[
@@ -0,0 +1,50 @@
+<tool id="use_theoretical_mz" name="use theoretical m/z values" version="@TOOL_VERSION@+galaxy4" profile="21.09">
+    <description>Overwrite experimentally measured mz values for peaks with theoretical values from peak comments.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="creator"/>
+
+    <command detect_errors="exit_code"><![CDATA[
+    python '$__tool_directory__/use_theoretical_mz_annotations.py'
+    -i '${input}'
+    -o '${output_data}' 
+    #if $only_theoretical_annotated
+    -a
+    #end if
+    ]]>
+    </command>
+
+    <inputs>
+        <param name="input" type="data" format="msp,mgf" label="Input mass spectral library with peak comments in RIKEN format." />
+        <param name="only_theoretical_annotated" type="boolean" label="only retain annotated peaks" truevalue="True" falsevalue="False" checked="false" />
+    </inputs>
+
+    <outputs>
+        <data name="output_data" format_source="input" />
+    </outputs>
+
+    <tests>
+        <test>
+            <param name="input" value="input.msp" ftype="msp"/>
+            <param name="only_theoretical_annotated" value="True"/>
+            <output name="output_data" value="output_only_annotated.msp"/>
+        </test>
+        <test>
+            <param name="input" value="input.msp" ftype="msp"/>
+            <param name="only_theoretical_annotated" value="False"/>
+            <output name="output_data" value="output_plus_no_annotated.msp"/>
+        </test>
+    </tests>
+
+    <help>
+        <![CDATA[
+        This tool uses theoretical M/Z annotations in the input MSP or MGF file. 
+        You can choose whether to include non-annotated peaks in the output.
+        ]]>
+    </help>
+    <!-- check is this is the correct citation -->
+    <citations>
+        <citation type="doi">10.21105/joss.04337</citation>
+    </citations>
+</tool>