Merge branch 'master' of https://github.com/hakangunturkun/GeneCup

3 files changed, 33 insertions, 28 deletions

diff --git a/more_functions.py b/more_functions.py
index cb070d9..7c21c2a 100755
--- a/more_functions.py
+++ b/more_functions.py
@@ -23,21 +23,10 @@ def findWholeWord(w):
     return re.compile(r'\b({0})\b'.format(w), flags=re.IGNORECASE).search
 
 def getabstracts(gene,query):
-    if query[-1] =='s':
-        query2 = query+"*"
-    else:
-        query2 = query+"s*"
-    query3 = query2.replace("s|", "s* OR ")
-    query4 = query3.replace("|", "s* OR ")
-    
-    #query4=query
-    #query="\"(" + query4 + ") AND ((" + gene + "[tiab]) or (" + gene + "[meSH]))\""
-    query="\"(" + query4 + ") AND (" + gene + " [tiab])\""
-    #query = "neurons* AND (penk [tiab])"
+    query="\"(" + query + ") AND (" + gene + " [tiab])\""
     abstracts = os.popen("esearch -db pubmed -query " +  query \
         + " | efetch -format uid |fetch-pubmed -path "+ pubmed_path \
         + " | xtract -pattern PubmedArticle -element MedlineCitation/PMID,ArticleTitle,AbstractText|sed \"s/-/ /g\"").read()
-    #print(abstracts)
     return(abstracts)
 
 sentences_ls=[]
@@ -57,6 +46,7 @@ def getSentences(gene, sentences_ls):
 def gene_category(gene, cat_d, cat, abstracts,addiction_flag,dictn):
     # e.g. BDNF, addiction_d, undic(addiction_d) "addiction"
     sents=getSentences(gene, abstracts)
+    #print(sents)
     #print(abstracts)
     out=str()
     if (addiction_flag==1):
@@ -66,10 +56,16 @@ def gene_category(gene, cat_d, cat, abstracts,addiction_flag,dictn):
                     key_ad = key+"*"
                 else:
                     key_ad = key+"s*"
-                if findWholeWord(key_ad)(sent) :
-                    sent=sent.replace("<b>","").replace("</b>","") # remove other highlights
-                    sent=re.sub(r'\b(%s)\b' % key_ad, r'<b>\1</b>', sent, flags=re.I) # highlight keyword
-                    out+=gene+"\t"+ cat + "\t"+key+"\t"+sent+"\n"
+                key_ad = key_ad.replace("s|", "s*|")
+                key_ad = key_ad.replace("|", "s*|")
+                key_ad = key_ad.replace("s*s*", "s*")
+                key_ad_ls = key_ad.split('|')
+                for key_ad in key_ad_ls:
+                    re_find = re.compile(r'\b{}\b'.format(key_ad), re.IGNORECASE)
+                    if re_find.findall(sent):
+                        sent=sent.replace("<b>","").replace("</b>","") # remove other highlights
+                        sent=re.sub(r'\b(%s)\b' % key_ad, r'<b>\1</b>', sent, flags=re.I) # highlight keyword
+                        out+=gene+"\t"+ cat + "\t"+key+"\t"+sent+"\n"
     else:
         for key_1 in dictn[cat_d].keys():
             for key_2 in dictn[cat_d][key_1]:
@@ -77,11 +73,17 @@ def gene_category(gene, cat_d, cat, abstracts,addiction_flag,dictn):
                     key_2 = key_2+"*"
                 else:
                     key_2 = key_2+"s*"
+                key_2 = key_2.replace("s|", "s*|")
+                key_2 = key_2.replace("|", "s*|")
+                key_2 = key_2.replace("s*s*", "s*")
+                key_2_ls = key_2.split('|')
                 for sent in sents.split("\n"):
-                    if findWholeWord(key_2)(sent) :
-                        sent=sent.replace("<b>","").replace("</b>","") # remove other highlights
-                        sent=re.sub(r'\b(%s)\b' % key_2, r'<b>\1</b>', sent, flags=re.I) # highlight keyword
-                        out+=gene+"\t"+ cat + "\t"+key_1+"\t"+sent+"\n"
+                    for key_2 in key_2_ls:
+                        re_find = re.compile(r'\b{}\b'.format(key_2), re.IGNORECASE)
+                        if re_find.findall(sent):
+                            sent=sent.replace("<b>","").replace("</b>","") # remove other highlights
+                            sent=re.sub(r'\b(%s)\b' % key_2, r'<b>\1</b>', sent, flags=re.I) # highlight keyword
+                            out+=gene+"\t"+ cat + "\t"+key_1+"\t"+sent+"\n"                       
     return(out)
 
 def generate_nodes(nodes_d, nodetype,nodecolor):
@@ -134,7 +136,6 @@ def generate_edges_json(data, filename):
             elif (edgeID not in edgeCnts) and (pmid+target not in pmid_list):
                 edgeCnts[edgeID]=1
                 pmid_list.append(pmid+target)
-
     for edgeID in edgeCnts:
         (filename, source,target)=edgeID.split("|")
         edges_json0+="{ \"id\": \"" + edgeID + "\", \"source\": \"" + source + "\", \"target\": \"" + target + "\", \"sentCnt\": \"" + str(edgeCnts[edgeID]) + "\",  \"url\":\"/sentences?edgeID=" + edgeID + "\" },\n"
diff --git a/requirements.md b/requirements.md
index 7b90aec..8824016 100644
--- a/requirements.md
+++ b/requirements.md
@@ -47,5 +47,4 @@
 
 * tensorflow-estimator==2.4.0
 
-* python==3.8.5
-
+* python==3.8.5
\ No newline at end of file
diff --git a/server.py b/server.py
index 519eedf..33f3bb0 100755
--- a/server.py
+++ b/server.py
@@ -146,7 +146,6 @@ def login():
         else:
             flash("Invalid username or password!", "inval")
             return render_template('signup.html')
-    print(onto_list)
     return render_template('index.html',onto_len_dir=onto_len_dir, onto_list=onto_list, ontol = 'addiction', dict_onto = dict_onto)
 
 
@@ -570,7 +569,11 @@ def ontoarchive():
     if ('email' in session):
         if os.path.exists(datadir+"/user/"+str(session['hashed_email'])+"/ontology") == False:
             flash("Ontology history doesn't exist!")
-            return render_template('index.html',onto_len_dir=session['onto_len_dir'], onto_list=session['onto_list'])
+            onto_len_dir = 0
+            onto_list = ''
+            onto_cont=open("addiction.onto","r").read()
+            dict_onto=ast.literal_eval(onto_cont)
+            return render_template('index.html',onto_len_dir=onto_len_dir, onto_list=onto_list, ontol = 'addiction', dict_onto = dict_onto) 
         else:
             session['user_folder'] = datadir+"/user/"+str(session['hashed_email'])
     else:
@@ -762,7 +765,7 @@ def search():
     if(len(genes)==1):
         percent_ratio=2
     timeextension=session['timeextension']
-    percent=round(100/percent_ratio,1)-1 # 7 categories + 1 at the beginning
+    percent=100/percent_ratio-0.00000001 # 7 categories + 1 at the beginning
 
     if ('email' in session):
         sessionpath = session['path_user'] + timeextension
@@ -852,6 +855,7 @@ def search():
             yield "data:"+str(progress)+"\n\n"
             for gene in genes:
                 abstracts_raw = getabstracts(gene,all_d)
+                #print(abstracts_raw)
                 sentences_ls=[]
 
                 for row in abstracts_raw.split("\n"):
@@ -891,10 +895,11 @@ def search():
                                 dict_onto=ast.literal_eval(onto_cont)
                                 #ky_d=undic(list(dict_onto[ky].values()))    
                                 sent=gene_category(gene,ky,str(ky), sentences_ls, addiction_flag,dict_onto)
-                            
                             else:
                                 #ky_d=undic(list(dict_onto[ky].values()))
+                                #print(sentences_ls)
                                 sent=gene_category(gene,ky,str(ky), sentences_ls, addiction_flag,dict_onto)
+                                #print(sent)
                             yield "data:"+str(progress)+"\n\n"
                             
                             geneEdges += generate_edges(sent, tf_name)
@@ -918,7 +923,7 @@ def search():
                                             +str(row['MAPPED_TRAIT'])+"</b><br>"
                                         gwas_sent.append(gene+"\t"+"GWAS"+"\t"+nd+"_GWAS\t"+str(row['PUBMEDID'])+"\t"+gwas_text)
                     cys, gwas_json, sn_file = searchArchived('GWAS', gene , 'json',gwas_sent, path_user)
-                    with open(path_user+"gwas_results.tab", "w") as gwas_edges:
+                    with open(path_user+"gwas_results.tab", "a") as gwas_edges:
                         gwas_edges.write(sn_file)
                     geneEdges += cys
                     json_edges += gwas_json