| Previous changeset 21:4d712d80bd35 (2017-10-22) Next changeset 23:478f5587f12a (2017-10-22) |
|
Commit message:
Deleted selected files |
|
removed:
sparql_uniprot |
| b |
| diff -r 4d712d80bd35 -r 84c9f65ed7c6 sparql_uniprot --- a/sparql_uniprot Sun Oct 22 15:25:33 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,300 +0,0 @@\n-from SPARQLWrapper import SPARQLWrapper, JSON\n-import sys\n-\n-# Constante con los prefijos comunes a usar en queries\n-COMMON_PREFIXES = """\n-\tPREFIX up:<http://purl.uniprot.org/core/>\n-\tPREFIX keywords:<http://purl.uniprot.org/keywords/>\n-\tPREFIX uniprotkb:<http://purl.uniprot.org/uniprot/>\n-\tPREFIX taxon:<http://purl.uniprot.org/taxonomy/>\n-\tPREFIX ec:<http://purl.uniprot.org/enzyme/>\n-\tPREFIX rdf:<http://www.w3.org/1999/02/22-rdf-syntax-ns#>\n-\tPREFIX rdfs:<http://www.w3.org/2000/01/rdf-schema#>\n-\tPREFIX skos:<http://www.w3.org/2004/02/skos/core#>\n-\tPREFIX owl:<http://www.w3.org/2002/07/owl#>\n-\tPREFIX bibo:<http://purl.org/ontology/bibo/>\n-\tPREFIX dc:<http://purl.org/dc/terms/>\n-\tPREFIX xsd:<http://www.w3.org/2001/XMLSchema#>\n-\tPREFIX faldo:<http://biohackathon.org/resource/faldo#>\n-"""\n-\n-# Lista con los nombres de las variables que obtenemos de la base de datos.\n-paramList = [\'protein\', \'proteinFullName\', \'geneName\', \'organismName\', \'diseaseAnnotationText\', \'domainFullName\', \'similarityAnnotationText\', \'locationAnnotationText\', \'functionAnnotationText\', \'pharmaceuticalAnnotationText\'];\n-\n-def buildQuery(proteinId, proteinName, geneName, organismName, diseaseAnnotation, domainName, similarityAnnotation, locationAnnotation, functionAnnotation, pharmaceuticalAnnotation):\n-\tquery = COMMON_PREFIXES\n-\tquery += "select distinct \\n"\n-\tquery += "\t?protein\\n"\n-\tquery += "\t?proteinFullName\\n"\n-\tquery += "\t?geneName\\n"\n-\tquery += "\t?organismName\\n"\n-\tquery += "\t?diseaseAnnotationText\\n"\n-\tquery += "\t?domainFullName\\n"\n-\tquery += "\t?similarityAnnotationText\\n"\n-\tquery += "\t?locationAnnotationText\\n"\n-\tquery += "\t?functionAnnotationText\\n"\n-\tquery += "\t?pharmaceuticalAnnotationText\\n"\n-\tquery += "where{\\n"\n-\n-\tquery += "\t?protein a up:Protein .\\n"\n-\n-\tif (proteinId != \'\'):\n-\t\tquery += "\tVALUES ?protein {uniprotkb:"+ proteinId + "}\\n"\n-\n-\tquery += "\\n"\n-\n-\tif (proteinName == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:recommendedName ?proteinName .\\n"\n-\tquery += "\t?proteinName up:fullName ?proteinFullName . \\n"\n-\tif (proteinName !=\'\'):\n-\t\tquery += "\tfilter( regex(str(?proteinFullName), " + \'"\' + proteinName + \'"\' + ",\\"i\\" )) .\\n"\n-\tif (proteinName == \'\'):\n-\t\tquery += "\t}\\n"\n-\tquery += "\\n"\n-\n-\tif (geneName == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:encodedBy ?gene .\\n"\n-\tquery += "\t?gene skos:prefLabel ?geneName .\\n"\n-\tif (geneName != \'\'):\n-\t\tquery += "\tfilter( regex(str(?geneName), " + \'"\' + geneName + \'"\' + ",\\"i\\" )) .\\n"\n-\tif (geneName == \'\'):\n-\t\tquery += "\t}\\n"\n-\n-\tquery += "\\n"\n-\n-\tif (organismName == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:organism ?organism .\\n"\n-\tquery += "\t?organism up:scientificName ?organismName .\\n"\n-\tif (organismName != \'\'):\n-\t\tquery += "\tfilter( regex(str(?organismName), " + \'"\' + organismName + \'"\' + ",\\"i\\" )) .\\n"\n-\tif (organismName == \'\'):\n-\t\tquery += "\t}\\n"\n-\n-\tquery += "\\n"\n-\n-\tif (diseaseAnnotation == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:annotation ?diseaseAnnotation .\\n"\n-\tquery += "\t?diseaseAnnotation a up:Disease_Annotation .\\n"\n-\tquery += "\t?diseaseAnnotation up:disease ?disease .\\n"\n-\tquery += "\t?disease rdfs:comment ?diseaseAnnotationText\\n"\n-\tif (diseaseAnnotation != \'\'):\n-\t\tquery += "\tfilter( regex(str(?diseaseAnnotationText), " + \'"\' + diseaseAnnotation + \'"\' + ",\\"i\\" )) .\\n"\n-\tif (diseaseAnnotation == \'\'):\n-\t\tquery += "\t}\\n"\n-\n-\tquery += "\\n"\n-\n-\tif (domainName == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:domain ?domain .\\n"\n-\tquery += "\t?domain up:recommendedName ?domainName .\\n"\n-\tquery += "\t?domainName up:fullName ?domainFullName .\\n"\n-\tif (domainName != \'\'):\n-\t\tquery += "\tfilter( regex(str(?domainFullName), " + \'"\' + domainName + \'"\' + ",\\"i\\" )) .\\n"\n-\tif (domainName == \'\'):\n-\t\tquery += "\t}\\n"\n-\n-\tquery += "\\n"\n-\n-\tif (similarityAnnotation == \'\'):\n-\t\tquery += "\tOPTIONAL {\\n"\n-\tquery += "\t?protein up:annotation ?similarityAnnotation .\\n"\n-\tquery += "\t?similarityAnnotation a up:Sim'..b'hay que\n-\t# tratar.\n-\tprint ("Ejecutando query")\n-\tresults = sparql.query()\n-\n-\t# Con esto, convertimos el objeto devuelto por\n-\t# el servicio al formato que especificamos antes.\n-\t# En este caso, json.\n-\tprint ("Conviertiendo a json")\n-\tjson = results.convert()\n-\tprint ("Fin conversion a json")\n-\n-\t# Dentro de la variable results tenemos informacion\n-\t# (metadatos) de lo que ha devuelto el servidor de\n-\t# uniprot.\n-\tprint (results.info())\n-\n-\t# Imprimir resultados\n-\tprintResults(json, output)\n-\n-\n-# Obtener parametros de la linea de comandos.\n-proteinId = sys.argv[1]\n-proteinName = sys.argv[2]\n-geneName = sys.argv[3]\n-organismName = sys.argv[4]\n-diseaseAnnotation = sys.argv[5]\n-domainName =sys.argv[6]\n-similarityAnnotation = sys.argv[7]\n-locationAnnotation = sys.argv[8]\n-functionAnnotation = sys.argv[9]\n-pharmaceuticalAnnotation = sys.argv[10]\n-output = sys.argv[11]\n-\n-# Llamada a la funcion que realiza la consulta.\n-sparqlwrap(proteinId, proteinName, geneName, organismName, diseaseAnnotation, domainName, similarityAnnotation, locationAnnotation, functionAnnotation, pharmaceuticalAnnotation, output)\n-\n-<?xml version="1.0"?>\n-<tool_dependency>\n- <package name="SPARQLWrapper" version="1.7.6">\n- <readme>\n- Install SPARQLWrapper via virtualenv.\n- </readme>\n- <install version="1.0">\n- <actions>\n- <action type="setup_virtualenv">SPARQLWrapper==1.7.6</action>\n- </actions>\n- </install>\n- </package>\n-</tool_dependency>\n-<tool id="sparql_uniprot" name="Uniprot Sparql" version="0.1.0">\n- <description>Perform a search into uniprot database using its sparql interface.</description>\n- <requirements>\n- <requirement type="binary">python</requirement>\n- <requirement type="package" version="1.7.6">SPARQLWrapper</requirement>\n- </requirements>\n- <command interpreter="python">sparql_uniprot.py "${protein}" "${proteinName}" "${geneName}" "${organismName}" "${diseaseAnnotation}" "${domainName}" "${similarityAnnotation}" "${locationAnnotation}" "${functionAnnotation}" "${pharmaceuticalAnnotation}" "${output}"</command>\n- <inputs>\n- <param name="protein" type="text" label="Uniprot Identifier"/>\n-\n- <param name="proteinName" type="text" label="Protein Name">\n-\t<!-- sanitizer to use \'$\' character -->\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="geneName" type="text" label="Gene Name">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="organismName" type="text" label="Organism">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="diseaseAnnotation" type="text" label="Disease Annotation">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="domainName" type="text" label="Domain">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="similarityAnnotation" type="text" label="Similarity Annotation">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="locationAnnotation" type="text" label="Location Annotation">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="functionAnnotation" type="text" label="Function Annotation">\n-\t<sanitizer sanitize="False"/>\n- </param>\n-\n- <param name="pharmaceuticalAnnotation" type="text" label="Pharmaceutical Annotation">\n-\t<sanitizer sanitize="False"/>\n- </param>\n- </inputs>\n-\n- <outputs>\n- <data format="tabular" name="output" />\n- </outputs>\n-\n- <help>\n-\tWith this tool you can search proteins using regular expressions by the following fields: uniprot identifier, protein name, gene name , organism name, disease annotation, domain name, similarity annotation, location annotation, function annotation or pharmaceutical annotationText. You can fill the fields you want and the tool will return all the data found in uniprot by filling the other fields. Results will be stored in a tabular format. If you want to search the exact match of a field you should use ^parameter$, for example ^insulin$.\n- </help>\n-\n-</tool>\n' |