agaist top 150 addiction genes

1 files changed, 49 insertions, 1 deletions

diff --git a/server.py b/server.py
index 3c124d3..286f071 100755
--- a/server.py
+++ b/server.py
@@ -5,6 +5,7 @@ import random
 import string
 from ratspub import *
 import time
+import os
 
 app=Flask(__name__)
 app.config['SECRET_KEY'] = '#DtfrL98G5t1dC*4'
@@ -46,7 +47,7 @@ def search():
         nodes=default_nodes
         progress=0
         for  gene in genes:
-            nodes+="{ data: { id: '" + gene +  "', nodecolor:'#FADBD8', fontweight:700, url:'https://www.ncbi.nlm.nih.gov/gene/?term="+gene+"'} },\n"
+            nodes+="{ data: { id: '" + gene +  "', nodecolor:'#E74C3C', fontweight:700, url:'/gene_gene?gene="+gene+"'} },\n"
             progress+=percent
             yield "data:"+str(progress)+"\n\n"
             sent0=gene_addiction(gene)
@@ -97,5 +98,52 @@ def shownode():
     out="<p>"+node.upper()+"<hr><li>"+ allnodes[node].replace("|", "<li>")
     return render_template('sentences.html', sentences=out+"<p>")
 
+@app.route("/gene_gene")
+def gene_gene():
+    query=request.args.get("gene")
+    tmp_ggPMID=session['path']+"_ggPMID"
+    os.system("esearch -db pubmed -query \"" +  query + "\" | efetch -format uid |sort >" + tmp_ggPMID)
+    abstracts=os.popen("comm -1 -2 top_150_addiction_genes_uniq.pmid " + tmp_ggPMID + " |fetch-pubmed -path /run/media/hao/PubMed/Archive/ | xtract -pattern PubmedArticle -element MedlineCitation/PMID,ArticleTitle,AbstractText|sed \"s/-/ /g\"").read()
+    os.system("rm "+tmp_ggPMID)
+    topGenes=dict()
+    out=str()
+    hitGenes=dict()
+    with open("./top_150_genes_symb_alias.txt", "r") as top_f:
+        for line in top_f:
+            (symb, alias)=line.strip().split("\t")
+            topGenes[symb]=alias
+    for row in abstracts.split("\n"):
+        tiab=row.split("\t")
+        pmid = tiab.pop(0)
+        tiab= " ".join(tiab)
+        sentences = sent_tokenize(tiab)
+        ## keep the sentence only if it contains the gene 
+        for sent in sentences:
+            if findWholeWord(query)(sent):
+                sent=re.sub(r'\b(%s)\b' % query, r'<strong>\1</strong>', sent, flags=re.I)
+                for symb in topGenes:
+                    if findWholeWord(topGenes[symb])(sent) :
+                        sent=sent.replace("<b>","").replace("</b>","")
+                        sent=re.sub(r'\b(%s)\b' % topGenes[symb], r'<b>\1</b>', sent, flags=re.I)
+                        out+=query+"\t"+"gene\t" + symb+"\t"+pmid+"\t"+sent+"\n"
+                        if symb in hitGenes.keys():
+                            hitGenes[symb]+=1
+                        else:
+                            hitGenes[symb]=1
+    gg_file=session['path']+"_ggSent" #gene_gene
+    with open(gg_file, "w+") as gg:
+        gg.write(out)
+        gg.close()
+    nodecolor={'query':"#E74C3C", 'top150': "#ccd1d1"}
+    nodes= "{ data: { id: '" + query +  "', nodecolor: '" + nodecolor['query'] + "', nodetype: 'ggquery', fontweight:700,  url:'/shownode?nodetype=ggquery&node="+query+"' } },\n"
+    edges=str()
+    for key in hitGenes.keys():
+        #nodes += "{ data: { id: '" + key +  "', nodecolor: '" + nodecolor['top150'] + "', nodetype: 'top150', fontcolor:'#F2D7D5', url:'/shownode?nodetype=top150&node="+key+"' } },\n"
+        nodes += "{ data: { id: '" + key +  "', nodecolor: '" + nodecolor['top150'] + "', nodetype: 'top150', url:'/shownode?nodetype=top150&node="+key+"' } },\n"
+        edgeID=gg_file+"|"+query+"|"+key
+        edges+="{ data: { id: '" + edgeID+ "', source: '" + query + "', target: '" + key + "', sentCnt: " + str(hitGenes[key]) + ",  url:'/sentences?edgeID=" + edgeID + "' } },\n"
+    return render_template("cytoscape.html", elements=nodes+edges)
+
+
 if __name__ == '__main__':
     app.run(debug=True)