Repository 'proteore_data_manager'
hg clone https://toolshed.g2.bx.psu.edu/repos/proteore/proteore_data_manager

Changeset 7:b8565596bb25 (2020-08-20)
Previous changeset 6:8f33a6e6e36c (2020-06-10)
Commit message:
"planemo upload commit 7afd4b3ee25f024257ccbac6e51076d25b2a04e7"
modified:
data_manager/resource_building.py
data_manager/resource_building.xml
b
diff -r 8f33a6e6e36c -r b8565596bb25 data_manager/resource_building.py
--- a/data_manager/resource_building.py Wed Jun 10 03:13:18 2020 -0400
+++ b/data_manager/resource_building.py Thu Aug 20 03:33:35 2020 -0400
[
@@ -554,10 +554,10 @@
     name = "neXtProt release "+time.strftime("%d-%m-%Y")
     release_id = "nextprot_ref_"+time.strftime("%d-%m-%Y")
     
-    output = open(path, 'w')
+    output = open('test.csv', 'w')
     writer = csv.writer(output,delimiter="\t")
         
-    nextprot_file=[["NextprotID","MW","SeqLength","IsoPoint","Chr","SubcellLocations","Diseases","TMDomains","ProteinExistence"]]
+    nextprot_file=[["NextprotID","ProteinName","SeqLength","MW","IsoPoint","TMDomains","SubcellLocations","Diseases","Function","PostTranslationalModifications","ProteinFamily","Pathway","ProteinExistence","Chr"]]
     writer.writerows(nextprot_file)
     
     for id in ids :
@@ -565,8 +565,8 @@
         try:
             resp = requests.get(url=query)
         except :
-            print ("wainting 1 hour before trying again")
-            time.sleep(3600)
+            print ("waiting 15 minutes before trying again")
+            time.sleep(900)
             resp = requests.get(url=query)
         data = resp.json()
 
@@ -576,6 +576,38 @@
         iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"]
         chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"]        
         protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level'])
+        protein_name = data['entry']["overview"]['proteinNames'][0]['name']
+
+        #get families description
+        if 'families' in data['entry']["overview"] and len(data['entry']["overview"]['families']) > 0:
+            families = data['entry']["overview"]['families']
+            families = [entry['description'] for entry in families]
+            protein_family = ";".join(families)
+        else: 
+            protein_family = 'NA'
+
+        #get Protein function
+        if 'function-info' in data['entry']['annotationsByCategory'].keys():
+            function_info = data['entry']['annotationsByCategory']['function-info']
+            function_info = [entry['description'] for entry in function_info if entry['qualityQualifier'] == 'GOLD']
+            function = ';'.join(function_info)
+        else : 
+            function = 'NA'
+
+        #Get ptm-info
+        post_trans_mod = 'NA'
+        if 'ptm-info' in data['entry']['annotationsByCategory'].keys():
+            ptm_info = data['entry']['annotationsByCategory']['ptm-info']
+            infos = [entry['description'] for entry in ptm_info if entry['qualityQualifier'] == 'GOLD']
+            post_trans_mod = ";".join(infos)
+        
+        #Get pathway(s)
+        if 'pathway' in data['entry']['annotationsByCategory'].keys():
+            pathways = data['entry']['annotationsByCategory']['pathway']
+            pathways = [entry['description'] for entry in pathways if entry['qualityQualifier'] == 'GOLD']
+            pathway = ";".join(pathways)
+        else : 
+            pathway = 'NA'
 
         #put all subcell loc in a set
         if "subcellular-location" in data['entry']["annotationsByCategory"].keys() :
@@ -610,11 +642,12 @@
                 nb_domains+=1
                 #print "nb domains ++"
                 #print (nb_domains)
+
         nextprot_file[:] = [] 
-        nextprot_file.append([id,mass_mol,str(seq_length),iso_elec_point,chr_loc,all_subcell_locs,all_diseases,str(nb_domains),protein_existence])
+        nextprot_file.append([id,protein_name,str(seq_length),mass_mol,iso_elec_point,str(nb_domains),all_subcell_locs,all_diseases,function,post_trans_mod,protein_family,pathway,protein_existence,chr_loc])
         writer.writerows(nextprot_file)
 
-        id = str(10000000000 - int(time.strftime("%Y%m%d")))
+    id = str(10000000000 - int(time.strftime("%Y%m%d")))
 
     data_table_entry = dict(id=id, release=release_id, name = name, value = path)
     _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref")
b
diff -r 8f33a6e6e36c -r b8565596bb25 data_manager/resource_building.xml
--- a/data_manager/resource_building.xml Wed Jun 10 03:13:18 2020 -0400
+++ b/data_manager/resource_building.xml Thu Aug 20 03:33:35 2020 -0400
b
@@ -1,4 +1,4 @@
-<tool id="data_manager_proteore" name="Get source files for proteore tools" version="2020.06.10" tool_type="manage_data">
+<tool id="data_manager_proteore" name="Get source files for proteore tools" version="2020.07.31" tool_type="manage_data">
 <description>
 to create or update reference files for proteore tools
 </description>