find top genes

1 files changed, 50 insertions, 0 deletions

diff --git a/topGene_step3_generate_html.py b/topGene_step3_generate_html.py
new file mode 100755
index 0000000..dfcd6fe
--- /dev/null
+++ b/topGene_step3_generate_html.py
@@ -0,0 +1,50 @@
+import re
+
+## generate the html page for the top genes
+
+## put gene names and alias in a dictionary
+geneNames={}
+with open ("./ncbi_gene_symb_syno_name_txid9606_absCnt_sorted_absCnt_sorted.txt","r") as f:
+    for line in f:
+        (genes, count)=line.strip().split("\t")
+        gene=genes.split("|")
+        geneNames[gene[0]]=genes.strip()
+
+out=str()
+html=str()
+with open("./topGeneAbstractCount.tab" ,"r") as gc:
+    cnt=0
+    for  line in gc:
+        cnt+=1
+        line=re.sub(r'^\s+','',line)
+        print (line)
+        pmid_cnt, symb=line.strip().split()
+        out+= symb+"\t"+geneNames[symb]+"\n"
+        html+="<li><a href=\"/showTopGene?topGene="+symb+"\">"+symb+"</a><br>\n"
+        if cnt==500:
+            break
+
+with open("topGene_symb_alias.txt", "w+")  as tg:
+    tg.write(out)
+    tg.close()
+
+
+htmlout='''
+{% extends "layout.html" %}
+{% block content %}
+
+<h3> Top addiction related genes </h3>
+
+<br>
+These genes are ranked by the number of PubMed abstracts that contain the name of the gene and one or more addiction related keyword.
+<hr>
+
+<ol>''' + html  + '''
+</ol>
+{% endblock %}
+'''
+
+with open("./templates/topAddictionGene.html", "w+")  as html_f:
+    html_f.write(htmlout)
+    html_f.close()
+