Created
October 29, 2017 16:09
-
-
Save egonw/eb07cf69278c0be78d560c103ef29e5a to your computer and use it in GitHub Desktop.
Bioclipse code to check chemical compounds with isomeric SMILES and no InChI
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// Copyright (C) 2017 Egon Willighagen | |
// MIT license | |
// see https://www.wikidata.org/wiki/Wikidata:WikiProject_Chemistry/Tools#Chemical_compound_without_InChI | |
/* results (2017-10-29): | |
Number of missing InChIs: 2098 | |
InChI too long: 1736 | |
With undefined stereo: 348 | |
Bad SMILES: 2 | |
Compound classes: 12 | |
*/ | |
query = """ | |
PREFIX wdt: <http://www.wikidata.org/prop/direct/> | |
PREFIX wd: <http://www.wikidata.org/entity/> | |
SELECT ?compound ?smiles WHERE { | |
?compound wdt:P31 wd:Q11173 ; | |
wdt:P2017 ?smiles . | |
MINUS {?compound wdt:P234 ?d } | |
} | |
""" | |
service = "https://query.wikidata.org/bigdata/namespace/wdq/sparql" | |
results = rdf.sparqlRemote(service, query) | |
qsFile = "/Wikidata/curation1.quickstatements" | |
def renewFile(file) { | |
if (ui.fileExists(file)) ui.remove(file) | |
ui.newFile(file) | |
return file | |
} | |
renewFile(qsFile) | |
tooLong = 0 | |
undefinedStereo = 0 | |
badSmiles = 0 | |
compoundClass = 0 | |
for (i=1;i<=results.rowCount;i++) { | |
// for (i=1;i<=2;i++) { | |
rowVals = results.getRow(i) | |
item = rowVals[0].substring(3) | |
smiles = rowVals[1] | |
if (!smiles.contains("*")) { // skip compound classes | |
try { | |
mol = cdk.fromSMILES(smiles) | |
inchiObj = inchi.generate(mol) | |
inchiShort = inchiObj.value.substring(6) | |
key = inchiObj.key | |
if (!inchiShort.contains("?")) { // skip undefined stereochemistry | |
if (inchiShort.length() <= 400) { | |
statement = """ | |
CREATE | |
$item\tP31\tQ11173$paperProv | |
$item\tDen\t\"chemical compound\"$paperProv | |
$item\t$smilesProp\t\"$smiles\" | |
$item\tP274\t\"$formula\" | |
$item\tP234\t\"$inchiShort\" | |
$item\tP235\t\"$key\" | |
$pubchemLine | |
""" | |
ui.append(qsFile, statement + "\n") | |
} else { | |
// println "$item has an InChI that is too long: $inchiShort" | |
tooLong++ | |
} | |
} else { | |
// println "$item has undefined stereochemistry(?): $inchiShort" | |
undefinedStereo++ | |
} | |
} catch (Exception e) { | |
// println "$item has bad SMILES: " + e.message | |
badSmiles++ | |
} // skip bad SMILES | |
} else { | |
// println "$item is a compound class (has a '*'): $smiles" | |
compoundClass++ | |
} | |
} | |
println "Number of missing InChIs: " + results.rowCount | |
println "InChI too long: $tooLong" | |
println "With undefined stereo: $undefinedStereo" | |
println "Bad SMILES: $badSmiles" | |
println "Compound classes: $compoundClass" | |
ui.open(qsFile) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment