changed to rdflib and rdflib-hdt to read from HDT file directly instead of endpoint

GPs/query_export_tsv_sparql.py

 #!/usr/bin/env python3
 
 """
-Author: Wasin
+Author: Wasin Poncheewin, Bart Nijsse, Jasper Koehorst
 Script to build protein tsv file with all info
 """
+import os, subprocess, sys, re
+from rdflib import Graph
+from rdflib_hdt import HDTStore, optimize_sparql
 
-from SPARQLWrapper import SPARQLWrapper, JSON
-import re
-import os
-import subprocess
+# Calling this function optimizes the RDFlib SPARQL engine for HDT documents
+optimize_sparql()
 
-sparql = SPARQLWrapper("http://nvme1.wurnet.nl:7201/repositories/pseudomonasDB2")
-sparql.setQuery("""
+hdtfile = sys.argv[1]
+graph = Graph(store=HDTStore(sys.argv[1]))
+
+samplesResults = graph.query("""
     PREFIX gbol: <http://gbol.life/0.1/>
     SELECT DISTINCT ?sample ?samplename
     WHERE { 
@@ -19,76 +22,79 @@ sparql.setQuery("""
         ?sample gbol:name ?samplename .
     }
 """)
-sparql.setReturnFormat(JSON)
-results_sample = sparql.query().convert()
 
 if not os.path.exists('prot_tsv/'):
     subprocess.check_output('mkdir prot_tsv', shell=True)
 
-for result_sample in results_sample["results"]["bindings"]:
-    print('%s' % (result_sample["samplename"]["value"]))
-    outFileName = 'prot_tsv/' + result_sample["samplename"]["value"] + ".tsv"
+for sampleRow in samplesResults:
+    samplename = f"{sampleRow.samplename}"
+
+    print('%s' % samplename)
+    outFileName = 'prot_tsv/' + samplename + ".tsv"
     outFile = open(outFileName, 'w')
 
-    sampleIRI = result_sample["sample"]["value"]
-    sparql.setQuery("""
-    PREFIX gbol: <http://gbol.life/0.1/>
-    SELECT DISTINCT ?gene ?strand ?gbeginpos ?gendpos ?cdsbeginpos ?cdsendpos ?featurebeginpos ?featureendpos ?acc ?singnaturedes ?dbname ?evalue 
-    WHERE { 
-        ?s gbol:sample ?sample .
-        VALUES ?sample {<"""+sampleIRI+""">}
-        ?s gbol:feature ?gene.
-        ?gene gbol:location ?glocation .
-        ?glocation gbol:begin ?gbegin .
-        ?gbegin gbol:position ?gbeginpos .
-        ?glocation gbol:end ?gend .
-        ?gend gbol:position ?gendpos .
-        ?glocation gbol:strand ?strand .
-        ?gene gbol:transcript ?mrna .
-        ?mrna gbol:feature ?cds .
-        ?cds gbol:location ?cdslocation .
-        ?cdslocation gbol:begin ?cdsbegin .
-        ?cdsbegin gbol:position ?cdsbeginpos .
-        ?cdslocation gbol:end ?cdsend .
-        ?cdsend gbol:position ?cdsendpos .
-        ?cds gbol:protein ?prot .
-        ?prot gbol:feature ?feature .
-        ?feature gbol:signature ?signature .
-        ?signature gbol:accession ?acc . 
-        ?signature gbol:db ?db .
-        ?db gbol:id ?dbname .
-        ?feature gbol:signatureDesc ?singnaturedes .
-        ?feature gbol:location ?featurelocation .
-        ?featurelocation gbol:begin ?featurebegin .
-        ?featurebegin gbol:position ?featurebeginpos .
-        ?featurelocation gbol:end ?featureend .
-        ?featureend gbol:position ?featureendpos .
-        ?feature gbol:provenance ?provenance .
-        ?provenance gbol:annotation ?annot .
-        ?annot gbol:evalue ?evalue .
-    }
-""")
-    sparql.setReturnFormat(JSON)
-    results_interpro = sparql.query().convert()
+    sampleIRI = (f"{sampleRow.sample}")
+
+    interproResults = graph.query("""
+        PREFIX gbol: <http://gbol.life/0.1/>
+        SELECT DISTINCT ?gene ?strand ?gbeginpos ?gendpos ?cdsbeginpos ?cdsendpos ?featurebeginpos ?featureendpos ?acc ?singnaturedes ?dbname ?evalue
+        WHERE {
+            ?s gbol:sample ?sample .
+            VALUES ?sample {<""" + sampleIRI + """>}
+            ?s gbol:feature ?gene.
+            ?gene gbol:location ?glocation .
+            ?glocation gbol:begin ?gbegin .
+            ?gbegin gbol:position ?gbeginpos .
+            ?glocation gbol:end ?gend .
+            ?gend gbol:position ?gendpos .
+            ?glocation gbol:strand ?strand .
+            ?gene gbol:transcript ?mrna .
+            ?mrna gbol:feature ?cds .
+            ?cds gbol:location ?cdslocation .
+            ?cdslocation gbol:begin ?cdsbegin .
+            ?cdsbegin gbol:position ?cdsbeginpos .
+            ?cdslocation gbol:end ?cdsend .
+            ?cdsend gbol:position ?cdsendpos .
+            ?cds gbol:protein ?prot .
+            ?prot gbol:feature ?feature .
+            ?feature gbol:signature ?signature .
+            ?signature gbol:accession ?acc .
+            ?signature gbol:db ?db .
+            ?db gbol:id ?dbname .
+            ?feature gbol:signatureDesc ?singnaturedes .
+            ?feature gbol:location ?featurelocation .
+            ?featurelocation gbol:begin ?featurebegin .
+            ?featurebegin gbol:position ?featurebeginpos .
+            ?featurelocation gbol:end ?featureend .
+            ?featureend gbol:position ?featureendpos .
+            ?feature gbol:provenance ?provenance .
+            ?provenance gbol:annotation ?annot .
+            ?annot gbol:evalue ?evalue .
+        }
+    """)
+
     data = []
-    for result_interpro in results_interpro["results"]["bindings"]:
-        samplename = result_sample["samplename"]["value"]
-        gene = result_interpro["gene"]["value"]
+    for interproRow in interproResults:
+        gene = f"{interproRow.gene}"
         genename = re.sub(r'gene/.*', '', gene)
-        strand = result_interpro["strand"]["value"]
+        strand = f"{interproRow.strand}"
         strandname = re.sub(r'http://gbol\.life/0\.1/', '', strand)
-        gbeginpos = result_interpro["gbeginpos"]["value"]
-        gendpos = result_interpro["gendpos"]["value"]
-        cdsbeginpos = result_interpro["cdsbeginpos"]["value"]
-        cdsendpos = result_interpro["cdsendpos"]["value"]
-        featurebeginpos = result_interpro["featurebeginpos"]["value"]
-        featureendpos = result_interpro["featureendpos"]["value"]
-        acc = result_interpro["acc"]["value"]
-        singnaturedes = result_interpro["singnaturedes"]["value"]
-        dbname = result_interpro["dbname"]["value"]
-        evalue = result_interpro["evalue"]["value"]
-        data += [(samplename,genename,strandname,int(gbeginpos),int(gendpos),int(cdsbeginpos),int(cdsendpos),int(featurebeginpos),int(featureendpos),acc,singnaturedes,dbname,float(evalue))]
+        gbeginpos = f"{interproRow.gbeginpos}"
+        gendpos = f"{interproRow.gendpos}"
+        cdsbeginpos = f"{interproRow.cdsbeginpos}"
+        cdsendpos = f"{interproRow.cdsendpos}"
+        featurebeginpos = f"{interproRow.featurebeginpos}"
+        featureendpos = f"{interproRow.featureendpos}"
+        acc = f"{interproRow.acc}"
+        singnaturedes = f"{interproRow.singnaturedes}"
+        dbname = f"{interproRow.dbname}"
+        evalue = f"{interproRow.evalue}"
+        data += [(samplename, gene, strandname, int(gbeginpos), int(gendpos), int(cdsbeginpos), int(cdsendpos),
+                int(featurebeginpos), int(featureendpos), acc, singnaturedes, dbname, float(evalue))]
     data.sort()
     for element in data:
         outFile.write('\t'.join(str(x) for x in element) + '\n')
     outFile.close()
+
+
+