last version

1 files changed, 405 insertions, 253 deletions

diff --git a/server.py b/server.py
index 254fdcb..cf8c7a6 100755
--- a/server.py
+++ b/server.py
@@ -6,6 +6,7 @@ import shutil
 from flask import jsonify
 from datetime import datetime
 import bcrypt
+import hashlib
 import tempfile
 import random
 import string
@@ -23,21 +24,22 @@ from collections import Counter
 import numpy as np
 from numpy import array
 import tensorflow
-import keras
-from keras.models import Model
-from keras.preprocessing.text import Tokenizer
-from keras.preprocessing.sequence import pad_sequences
-from keras.layers import *
-from keras.models import Sequential
-from keras.layers import Dense
-from keras.layers import Flatten
-from keras.layers import Embedding
-from keras import metrics
-from keras import optimizers
+import tensorflow.keras
+from tensorflow.keras.models import Model
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.layers import *
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.layers import Flatten
+from tensorflow.keras.layers import Embedding
+from tensorflow.keras import metrics
+from tensorflow.keras import optimizers
 import pickle
 
 app=Flask(__name__)
-datadir="/export/ratspub/"
+#datadir="/export/ratspub/"
+datadir = "."
 app.config['SECRET_KEY'] = '#DtfrL98G5t1dC*4'
 app.config['SQLALCHEMY_DATABASE_URI'] = 'sqlite:///'+datadir+'userspub.sqlite'
 db = SQLAlchemy(app)
@@ -72,6 +74,12 @@ with open('./nlp/tokenizer.pickle', 'rb') as handle:
 with open('./nlp/vocabulary.txt', 'r') as vocab:
     vocab = vocab.read()
 
+def tf_auc_score(y_true, y_pred):
+    return tensorflow.metrics.auc(y_true, y_pred)[1]
+
+from tensorflow.keras import backend as K
+K.clear_session()
+
 # create the CNN model
 def create_model(vocab_size, max_length):
     model = Sequential()
@@ -81,8 +89,8 @@ def create_model(vocab_size, max_length):
     model.add(Flatten())
     model.add(Dense(10, activation='relu'))
     model.add(Dense(1, activation='sigmoid'))
-    opt = keras.optimizers.Adamax(learning_rate=0.002, beta_1=0.9, beta_2=0.999)
-    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=[keras.metrics.AUC()])
+    opt = tensorflow.keras.optimizers.Adamax(lr=0.002, beta_1=0.9, beta_2=0.999)
+    model.compile(loss='binary_crossentropy', optimizer=opt, metrics=[tf_auc_score])
     return model
 
 @app.route("/")
@@ -98,6 +106,8 @@ def login():
         found_user = users.query.filter_by(email=email).first()
         if (found_user and (bcrypt.checkpw(password.encode('utf8'), found_user.password))):
             session['email'] = found_user.email
+            print(bcrypt.hashpw(session['email'].encode('utf8'), bcrypt.gensalt()))
+            session['hashed_email'] = hashlib.md5(session['email'] .encode('utf-8')).hexdigest()
             session['name'] = found_user.name
             session['id'] = found_user.id
         else:
@@ -117,11 +127,13 @@ def signup():
             flash("Already registered, but wrong password!", "loginout")
             return render_template('signup.html')        
         session['email'] = email
+        session['hashed_email'] = hashlib.md5(session['email'] .encode('utf-8')).hexdigest()
         session['name'] = name
         password = bcrypt.hashpw(password.encode('utf8'), bcrypt.gensalt())
         user = users(name=name, email=email, password = password)       
         if found_user:
             session['email'] = found_user.email
+            session['hashed_email'] = hashlib.md5(session['email'] .encode('utf-8')).hexdigest()
             session['id'] = found_user.id
             found_user.name = name
             db.session.commit()
@@ -147,6 +159,7 @@ def signin():
         found_user = users.query.filter_by(email=email).first()
         if (found_user and (bcrypt.checkpw(password.encode('utf8'), found_user.password))):
             session['email'] = found_user.email
+            session['hashed_email'] = hashlib.md5(session['email'] .encode('utf-8')).hexdigest()
             session['name'] = found_user.name
             session['id'] = found_user.id
             flash("Login Succesful!", "loginout")
@@ -168,6 +181,7 @@ def profile(nm_passwd):
             if request.method == "POST":
                 password = request.form['password']
                 session['email'] = found_user.email
+                session['hashed_email'] = hashlib.md5(session['email'] .encode('utf-8')).hexdigest()
                 session['name'] = found_user.name
                 session['id'] = found_user.id
                 password = bcrypt.hashpw(password.encode('utf8'), bcrypt.gensalt())
@@ -220,22 +234,22 @@ def progress():
     genes=genes.replace(",", " ")
     genes=genes.replace(";", " ")
     genes=re.sub(r'\bLOC\d*?\b', "", genes, flags=re.I)
-    genes=genes.split()
-    if len(genes)>=100:
-        message="<span class='text-danger'>Up to 100 terms can be searched at a time</span>"
+    genes1 = [f[1:-1] for f in re.findall('".+?"', genes)]
+    genes2 = [p for p in re.findall(r'([^""]+)',genes) if p not in genes1]
+    genes2_str = ''.join(genes2)
+    genes2 = genes2_str.split()
+    genes3 = genes1 + genes2
+    genes = [re.sub("\s+", '-', s) for s in genes3]
+
+    if len(genes)>=30:
+        message="<span class='text-danger'>Up to 30 terms can be searched at a time</span>"
         return render_template('index.html', message=message)
     elif len(genes)==0:
         message="<span class='text-danger'>Please enter a search term </span>"
         return render_template('index.html', message=message)
     tf_path=tempfile.gettempdir()
-    session['path']=tf_path+"/tmp" + ''.join(random.choice(string.ascii_letters) for x in range(6)) 
-    # put the query in session cookie
-    session['query']=genes 
-    return render_template('progress.html', url_in="search", url_out="cytoscape")
+    #tf_path = "/tmp/"
 
-@app.route("/search")
-def search():
-    genes=session['query']
     genes_for_folder_name =""
     if len(genes) == 1:
         marker = ""
@@ -254,25 +268,53 @@ def search():
     timestamp = datetime.utcnow().replace(microsecond=0)
     timestamp = timestamp.replace(tzinfo=pytz.utc)
     timestamp = timestamp.astimezone(pytz.timezone("America/Chicago"))
-    session['timestamp'] = timestamp    
     timeextension = str(timestamp)
     timeextension = timeextension.replace(':', '_')
     timeextension = timeextension.replace('-', '_')
     timeextension = timeextension.replace(' ', '_')
     timeextension = timeextension.replace('_06_00', '')
+    session['timeextension'] = timeextension
     user_login=0
     #create a folder for the search
     if ('email' in session):
-        user_login=1
-        os.makedirs(datadir+"user/"+str(session['email']+"/"+timeextension+"_0_"+genes_for_folder_name+marker),exist_ok=True)
-        session['user_folder'] = datadir+"user/"+str(session['email'])
-        user_folder=session['user_folder']
-        session['path'] = datadir+"user/"+str(session['email'])+"/"+timeextension+"_0_"+genes_for_folder_name+marker+"/"+timeextension
+        os.makedirs(datadir + "/user/"+str(session['hashed_email'])+"/"+str(timeextension)+"_0_"+genes_for_folder_name+marker,exist_ok=True)
+        session['user_folder'] = datadir+"/user/"+str(session['hashed_email'])
+        session['path_user'] = datadir+"/user/"+str(session['hashed_email'])+"/"+str(timeextension)+"_0_"+genes_for_folder_name+marker+"/"
+        session['rnd'] = timeextension+"_0_"+genes_for_folder_name+marker
+        rnd = session['rnd']
+    else:
+        rnd = "tmp" + ''.join(random.choice(string.ascii_letters) for x in range(6)) 
+        session['path']=tf_path+ "/" + rnd
+        #os.makedirs(datadir+ session['path'])
+        os.makedirs(session['path'])
+    
+    genes_session = ''
+    for gen in genes:
+        genes_session += str(gen) + "_"
+    genes_session = genes_session[:-1]
+    session['query']=genes
+
+    return render_template('progress.html', url_in="search", url_out="cytoscape?rnd="+rnd+"&genequery="+genes_session)
+
+@app.route("/search")
+def search():
+    genes=session['query']
+    timeextension=session['timeextension']
     percent=round(100/(len(genes)*6),1) # 6 categories 
-    snt_file=session['path']+"_snt"
-    cysdata=open(session['path']+"_cy","w+")
+    if ('email' in session):
+        sessionpath = session['path_user'] + timeextension
+        path_user=session['path_user']
+        user_login=1
+    else:
+        user_login=0
+        sessionpath = session['path']
+        #path_user=datadir+session['path']+"/"
+        path_user=session['path']+"/"
+
+    snt_file=sessionpath+"_snt"
+    cysdata=open(sessionpath+"_cy","w+")
     sntdata=open(snt_file,"w+")
-    zeroLinkNode=open(session['path']+"_0link","w+")
+    zeroLinkNode=open(sessionpath+"_0link","w+")
     search_type = session['search_type']
     #consider the types got from checkbox
     temp_nodes = ""
@@ -300,143 +342,164 @@ def search():
         json_nodes += nj6
     json_nodes = json_nodes[:-2]
     json_nodes =json_nodes+"]}"
+
     def generate(genes, tf_name):
-        sentences=str()
-        edges=str()
-        nodes = temp_nodes
-        progress=0
-        searchCnt=0
-        nodesToHide=str()
-        json_edges = str()
-        for gene in genes:
-            gene=gene.replace("-"," ")
-            # report progress immediately
-            progress+=percent
-            yield "data:"+str(progress)+"\n\n"
-            #addiction terms must present with at least one drug
-            addiction=undic(addiction_d) +") AND ("+undic(drug_d)
-            sent0=gene_category(gene, addiction_d, addiction, "addiction")
-            e0=generate_edges(sent0, tf_name)
-            ej0=generate_edges_json(sent0, tf_name)
-            # drug
-            drug=undic(drug_d)
-            sent1=gene_category(gene, drug_d, drug, "drug")
-            progress+=percent
-            yield "data:"+str(progress)+"\n\n"
-            e1=generate_edges(sent1, tf_name)
-            ej1=generate_edges_json(sent1, tf_name)
-            # function
-            function=undic(function_d)
-            sent2=gene_category(gene, function_d, function, "function")
-            progress+=percent
-            yield "data:"+str(progress)+"\n\n"
-            e2=generate_edges(sent2, tf_name)
-            ej2=generate_edges_json(sent2, tf_name)
-            # brain has its own query terms that does not include the many short acronyms
-            sent3=gene_category(gene, brain_d, brain_query_term, "brain")
-            progress+=percent
-            e3=generate_edges(sent3, tf_name)
-            ej3=generate_edges_json(sent3, tf_name)
-            # stress
-            stress=undic(stress_d)
-            sent4=gene_category(gene, stress_d, stress, "stress")
-            progress+=percent
-            yield "data:"+str(progress)+"\n\n"
-            e4=generate_edges(sent4, tf_name)
-            ej4=generate_edges_json(sent4, tf_name)
-            # psychiatric 
-            psychiatric=undic(psychiatric_d)
-            sent5=gene_category(gene, psychiatric_d, psychiatric, "psychiatric")
-            progress+=percent
-            yield "data:"+str(progress)+"\n\n"
-            e5=generate_edges(sent5, tf_name)
-            ej5=generate_edges_json(sent5, tf_name)
-            # GWAS
-            e6=searchArchived('GWAS', gene, 'cys')
-            ej6=searchArchived('GWAS', gene , 'json')
-            #consider the types got from checkbox
-            geneEdges = ""
-            if ("addiction" in search_type):
-                geneEdges += e0
-                json_edges += ej0
-            if ("drug" in search_type):
-                geneEdges += e1   
-                json_edges += ej1    
-            if ("function" in search_type):
-                geneEdges += e2
-                json_edges += ej2
-            if ("brain" in search_type):
-                geneEdges += e3
-                json_edges += ej3
-            if ("stress" in search_type):
-                geneEdges += e4
-                json_edges += ej4
-            if ("psychiatric" in search_type):
-                geneEdges += e5  
-                json_edges += ej5  
-            if ("GWAS" in search_type):
-                geneEdges += e6  
-                json_edges += ej6                           
-            ## there is a bug here. zero link notes are not excluded anymore
-            if len(geneEdges) >1:
-                edges+=geneEdges
-                nodes+="{ data: { id: '" + gene +  "', nodecolor:'#E74C3C', fontweight:700, url:'/startGeneGene?forTopGene="+gene+"'} },\n"
-            else:
-                nodesToHide+=gene +  " "
-            sentences+=sent0+sent1+sent2+sent3+sent4+sent5
-            sent0=None 
-            sent1=None
-            sent2=None
-            sent3=None
-            sent4=None
-            sent5=None
-            #save data before the last yield
-            searchCnt+=1
-            if (searchCnt==len(genes)):
-                progress=100
-                sntdata.write(sentences)
-                sntdata.close()
-                cysdata.write(nodes+edges)               
-                cysdata.close()
-                zeroLinkNode.write(nodesToHide)
-                zeroLinkNode.close()
-            yield "data:"+str(progress)+"\n\n"
-        #edges in json format
-        json_edges="{\"data\":["+json_edges
-        json_edges = json_edges[:-2]
-        json_edges =json_edges+"]}"
-        #write edges to txt file in json format
-        with open(datadir+"edges.json", 'w') as edgesjson:
-            edgesjson.write(json_edges) 
-        #write edges to txt file in json format also in user folder
-        if (user_login == 1):
-            with open(user_folder+"/"+timeextension+"_0_"+genes_for_folder_name+marker+"/edges.json", "w") as temp_file_edges:
-                temp_file_edges.write(json_edges)       
-    #write nodes to txt file in json format
-    with open(datadir+"nodes.json", 'w') as nodesjson:
-        #if (userlogin) == 1:             
-        nodesjson.write(json_nodes)
-    #write nodes to txt file in json format also in user folder
-    if ('email' in session):
-        with open(datadir+"user/"+str(session['email'])+"/"+timeextension+"_0_"+genes_for_folder_name+marker+"/nodes.json", "w") as temp_file_nodes:
-            temp_file_nodes.write(json_nodes)
+        with app.test_request_context():
+            sentences=str()
+            edges=str()
+            nodes = temp_nodes
+            progress=0
+            searchCnt=0
+            nodesToHide=str()
+            json_edges = str()
+            for gene in genes:
+                gene=gene.replace("-"," ")
+                # report progress immediately
+                progress+=percent
+                yield "data:"+str(progress)+"\n\n"
+                #addiction terms must present with at least one drug
+                addiction=undic(addiction_d) +") AND ("+undic(drug_d)
+                sent0=gene_category(gene, addiction_d, addiction, "addiction")
+                e0=generate_edges(sent0, tf_name)
+                ej0=generate_edges_json(sent0, tf_name)
+                # drug
+                drug=undic(drug_d)
+                sent1=gene_category(gene, drug_d, drug, "drug")
+                progress+=percent
+                yield "data:"+str(progress)+"\n\n"
+                e1=generate_edges(sent1, tf_name)
+                ej1=generate_edges_json(sent1, tf_name)
+                # function
+                function=undic(function_d)
+                sent2=gene_category(gene, function_d, function, "function")
+                progress+=percent
+                yield "data:"+str(progress)+"\n\n"
+                e2=generate_edges(sent2, tf_name)
+                ej2=generate_edges_json(sent2, tf_name)
+                # brain has its own query terms that does not include the many short acronyms
+                sent3=gene_category(gene, brain_d, brain_query_term, "brain")
+                progress+=percent
+                e3=generate_edges(sent3, tf_name)
+                ej3=generate_edges_json(sent3, tf_name)
+                # stress
+                stress=undic(stress_d)
+                sent4=gene_category(gene, stress_d, stress, "stress")
+                progress+=percent
+                yield "data:"+str(progress)+"\n\n"
+                e4=generate_edges(sent4, tf_name)
+                ej4=generate_edges_json(sent4, tf_name)
+                # psychiatric 
+                psychiatric=undic(psychiatric_d)
+                sent5=gene_category(gene, psychiatric_d, psychiatric, "psychiatric")
+                progress+=percent
+                yield "data:"+str(progress)+"\n\n"
+                e5=generate_edges(sent5, tf_name)
+                ej5=generate_edges_json(sent5, tf_name)
+                # GWAS
+                e6=searchArchived('GWAS', gene, 'cys')
+                ej6=searchArchived('GWAS', gene , 'json')
+                #consider the types got from checkbox
+                geneEdges = ""
+                if ("addiction" in search_type):
+                    geneEdges += e0
+                    json_edges += ej0
+                if ("drug" in search_type):
+                    geneEdges += e1   
+                    json_edges += ej1    
+                if ("function" in search_type):
+                    geneEdges += e2
+                    json_edges += ej2
+                if ("brain" in search_type):
+                    geneEdges += e3
+                    json_edges += ej3
+                if ("stress" in search_type):
+                    geneEdges += e4
+                    json_edges += ej4
+                if ("psychiatric" in search_type):
+                    geneEdges += e5  
+                    json_edges += ej5  
+                if ("GWAS" in search_type):
+                    geneEdges += e6  
+                    json_edges += ej6                           
+                if len(geneEdges) >1:
+                    edges+=geneEdges
+                    nodes+="{ data: { id: '" + gene +  "', nodecolor:'#E74C3C', fontweight:700, url:'/synonyms?node="+gene+"'} },\n"
+                else:
+                    nodesToHide+=gene +  " "
+                sentences+=sent0+sent1+sent2+sent3+sent4+sent5
+                sent0=None 
+                sent1=None
+                sent2=None
+                sent3=None
+                sent4=None
+                sent5=None
+                #save data before the last yield
+                searchCnt+=1
+                if (searchCnt==len(genes)):
+                    progress=100
+                    sntdata.write(sentences)
+                    sntdata.close()
+                    cysdata.write(nodes+edges)               
+                    cysdata.close()
+                    zeroLinkNode.write(nodesToHide)
+                    zeroLinkNode.close()
+                yield "data:"+str(progress)+"\n\n"
+            #edges in json format
+            json_edges="{\"data\":["+json_edges
+            json_edges = json_edges[:-2]
+            json_edges =json_edges+"]}"
+            #write edges to txt file in json format also in user folder
+            with open(path_user+"edges.json", "w") as temp_file_edges:
+                temp_file_edges.write(json_edges) 
+    with open(path_user+"nodes.json", "w") as temp_file_nodes:
+        temp_file_nodes.write(json_nodes)
     return Response(generate(genes, snt_file), mimetype='text/event-stream')
 
-@app.route("/tableview")
+@app.route("/tableview/")
 def tableview():
-    with open(datadir+"nodes.json") as jsonfile:
-        jnodes = json.load(jsonfile)
-    jedges =''
-    file_edges = open(datadir+'edges.json', 'r')
-    for line in file_edges.readlines():
-        if ':' not in line:
-            nodata_temp = 1
-        else: 
-            nodata_temp = 0
-            with open(datadir+"edges.json") as edgesjsonfile:
-                jedges = json.load(edgesjsonfile)
-            break
-    genename=session['query'] 
+    genes_url=request.args.get('genequery')
+    rnd_url=request.args.get('rnd')
+    tf_path=tempfile.gettempdir()
+    if ('email' in session):
+        filename = rnd_url.split("_0_")[0]
+        genes_session_tmp = datadir+"/user/"+str(session['hashed_email'])+"/"+rnd_url+"/"+filename
+        gene_url_tmp = "/user/"+str(session['hashed_email'])+"/"+rnd_url
+        try:
+            with open(datadir+gene_url_tmp+"/nodes.json") as jsonfile:
+                jnodes = json.load(jsonfile)
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        jedges =''
+        file_edges = open(datadir+gene_url_tmp +'/edges.json', 'r')
+        for line in file_edges.readlines():
+            if ':' not in line:
+                nodata_temp = 1
+            else: 
+                nodata_temp = 0
+                with open(datadir+gene_url_tmp +"/edges.json") as edgesjsonfile:
+                    jedges = json.load(edgesjsonfile)
+                break
+    else:
+        genes_session_tmp=tf_path+"/"+rnd_url
+        gene_url_tmp = genes_session_tmp
+        try:
+            with open(gene_url_tmp+"/nodes.json") as jsonfile:
+                jnodes = json.load(jsonfile)
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        jedges =''
+        file_edges = open(gene_url_tmp +'/edges.json', 'r')
+        for line in file_edges.readlines():
+            if ':' not in line:
+                nodata_temp = 1
+            else: 
+                nodata_temp = 0
+                with open(gene_url_tmp +"/edges.json") as edgesjsonfile:
+                    jedges = json.load(edgesjsonfile)
+                break
+    genename=genes_url.split("_")
     if len(genename)>3:
         genename = genename[0:3]
         added = ",..."
@@ -447,24 +510,56 @@ def tableview():
     gene_name=gene_name.replace("'","")
     gene_name = gene_name+added
     num_gene = gene_name.count(',')+1
-    message3="<b> Actions: </b><li> <font color=\"#E74C3C\">Click on the abstract count to read sentences linking the keyword and the gene</font> <li> Click on a gene to search its relations with top 200 addiction genes. <li> Click on a keyword to see the terms included in the search. <li>View the results in <a href='cytoscape'><b> a graph.</b></a><li>All results will appear in a new Browser window (or tab)"
-    return render_template('tableview.html', nodata_temp=nodata_temp, num_gene=num_gene,session_path = session['path'], jedges=jedges, jnodes=jnodes,gene_name=gene_name, message3=message3)
 
-@app.route("/tableview0")
+    message3="<b> Actions: </b><li> <font color=\"#E74C3C\">Click on the abstract count to read sentences linking the keyword and the gene</font> <li> Click on a gene to search its relations with top 200 addiction genes. <li> Click on a keyword to see the terms included in the search. <li>View the results in <a href='\\cytoscape/?rnd={}&genequery={}'\ ><b> a graph.</b></a>".format(rnd_url,genes_url)
+    return render_template('tableview.html', genes_session_tmp = genes_session_tmp, nodata_temp=nodata_temp, num_gene=num_gene, jedges=jedges, jnodes=jnodes,gene_name=gene_name, message3=message3, rnd_url=rnd_url, genes_url=genes_url)
+
+@app.route("/tableview0/")
 def tableview0():
-    with open(datadir+"nodes.json") as jsonfile:
-        jnodes = json.load(jsonfile)
-    jedges =''
-    file_edges = open(datadir+'edges.json', 'r')
-    for line in file_edges.readlines():
-        if ':' not in line:
-            nodata_temp = 1
-        else: 
-            nodata_temp = 0
-            with open(datadir+"edges.json") as edgesjsonfile:
-                jedges = json.load(edgesjsonfile)
-            break
-    genename=session['query'] 
+    genes_url=request.args.get('genequery')
+    rnd_url=request.args.get('rnd')
+    tf_path=tempfile.gettempdir()
+    if ('email' in session):
+        filename = rnd_url.split("_0_")[0]
+        genes_session_tmp = datadir+"/user/"+str(session['hashed_email'])+"/"+rnd_url+"/"+filename
+        gene_url_tmp = "/user/"+str(session['hashed_email'])+"/"+rnd_url
+        try:
+            with open(datadir+gene_url_tmp+"/nodes.json") as jsonfile:
+                jnodes = json.load(jsonfile)
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        jedges =''
+        file_edges = open(datadir+gene_url_tmp+'/edges.json', 'r')
+        for line in file_edges.readlines():
+            if ':' not in line:
+                nodata_temp = 1
+            else: 
+                nodata_temp = 0
+                with open(datadir+gene_url_tmp+"/edges.json") as edgesjsonfile:
+                    jedges = json.load(edgesjsonfile)
+                break
+    else:
+        genes_session_tmp=tf_path+"/"+rnd_url
+        gene_url_tmp = genes_session_tmp
+        try:
+            with open(gene_url_tmp+"/nodes.json") as jsonfile:
+                jnodes = json.load(jsonfile)
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        jedges =''
+        file_edges = open(gene_url_tmp+'/edges.json', 'r')
+        for line in file_edges.readlines():
+            if ':' not in line:
+                nodata_temp = 1
+            else: 
+                nodata_temp = 0
+                with open(gene_url_tmp+"/edges.json") as edgesjsonfile:
+                    jedges = json.load(edgesjsonfile)
+                break
+    genes_url=request.args.get('genequery')
+    genename=genes_url.split("_")
     if len(genename)>3:
         genename = genename[0:3]
         added = ",..."
@@ -475,16 +570,20 @@ def tableview0():
     gene_name=gene_name.replace("'","")
     gene_name = gene_name+added
     num_gene = gene_name.count(',')+1
-    message4="<b> Notes: </b><li> These are the keywords that have <b>zero</b> abstract counts. <li>View all the results in <a href='cytoscape'><b> a graph.</b></a>"
-    return render_template('tableview0.html',nodata_temp=nodata_temp, num_gene=num_gene,session_path = session['path'], jedges=jedges, jnodes=jnodes,gene_name=gene_name, message4=message4)
+    message4="<b> Notes: </b><li> These are the keywords that have <b>zero</b> abstract counts. <li>View all the results in <a href='\\cytoscape/?rnd={}&genequery={}'><b> a graph.</b></a>".format(rnd_url,genes_url)
+    return render_template('tableview0.html',nodata_temp=nodata_temp, num_gene=num_gene, jedges=jedges, jnodes=jnodes,gene_name=gene_name, message4=message4)
 
 @app.route("/userarchive")
 def userarchive():
-    if os.path.exists(datadir+"user/"+str(session['email'])) == False:
-        flash("Search history doesn't exist!")
-        return render_template('index.html')
     if ('email' in session):
-        session['user_folder'] = datadir+"user/"+str(session['email'])
+        if os.path.exists(datadir+"/user/"+str(session['hashed_email'])) == False:
+            flash("Search history doesn't exist!")
+            return render_template('index.html')
+        else:
+            session['user_folder'] = datadir+"/user/"+str(session['hashed_email'])
+    else:
+        flash("You logged out!")
+        return render_template('index.html')
     session_id=session['id']
     def sorted_alphanumeric(data):
         convert = lambda text: int(text) if text.isdigit() else text.lower()
@@ -512,81 +611,105 @@ def userarchive():
 # delete this search
 @app.route('/remove', methods=['GET', 'POST'])
 def remove():
-    remove_folder = request.args.get('remove_folder')
-    shutil.rmtree(datadir+"user/"+str(session['email']+"/"+remove_folder), ignore_errors=True)
-    return redirect(url_for('userarchive'))
+    if('email' in session):
+        remove_folder = request.args.get('remove_folder')
+        shutil.rmtree(datadir+"/user/"+str(session['hashed_email']+"/"+remove_folder), ignore_errors=True)
+        return redirect(url_for('userarchive'))
+    else:
+        flash("You logged out!")
+        return render_template('index.html')
 
 @app.route('/date', methods=['GET', 'POST'])
 def date():
     select_date = request.args.get('selected_date')
     #open the cache folder for the user
-    tf_path=datadir+"user"
+    tf_path=datadir+"/user"
     if ('email' in session):
         time_extension = str(select_date)
         time_extension = time_extension.split('_0_')[0]
         gene_name1 = str(select_date).split('_0_')[1]
         time_extension = time_extension.replace(':', '_')
         time_extension = time_extension.replace('-', '_')
-        session['path'] = tf_path+"/"+str(session['email'])+"/"+select_date+"/"+time_extension
-        session['user_folder'] = tf_path+"/"+str(session['email'])
-    else:
-        tf_path=tempfile.gettempdir()
-        session['path']=tf_path+"/tmp" + ''.join(random.choice(string.ascii_letters) for x in range(6)) 
-    with open(tf_path+"/"+str(session['email'])+"/"+select_date+"/edges.json", "r") as archive_file:
-        with open(datadir+"edges.json", "w") as temp_file:
-            for line in archive_file:
-                temp_file.write(line)        
-    with open(tf_path+"/"+str(session['email'])+"/"+select_date+"/nodes.json", "r") as archive_file:
-        with open(datadir+"nodes.json", "w") as temp_file:
-            for line in archive_file:
-                temp_file.write(line) 
-    with open(datadir+"nodes.json", "r") as jsonfile:
-        jnodes = json.load(jsonfile)
-
-    jedges =''
-    file_edges = open(datadir+'edges.json', 'r')
-    for line in file_edges.readlines():
-        if ':' not in line:
-            nodata_temp = 1
+        session['user_folder'] = tf_path+"/"+str(session['hashed_email'])
+        genes_session_tmp = tf_path+"/"+str(session['hashed_email'])+"/"+select_date+"/"+time_extension
+        with open(tf_path+"/"+str(session['hashed_email'])+"/"+select_date+"/nodes.json", "r") as jsonfile:
+            jnodes = json.load(jsonfile)
+        jedges =''
+        file_edges = open(tf_path+"/"+str(session['hashed_email'])+"/"+select_date+"/edges.json", "r")
+        for line in file_edges.readlines():
+            if ':' not in line:
+                nodata_temp = 1
+            else: 
+                nodata_temp = 0
+                with open(tf_path+"/"+str(session['hashed_email'])+"/"+select_date+"/edges.json", "r") as edgesjsonfile:
+                    jedges = json.load(edgesjsonfile)
+                break
+        gene_list_all=[]
+        gene_list=[]
+        if nodata_temp == 0:
+            for p in jedges['data']:
+                if p['source'] not in gene_list:
+                    gene_list_all.append(p['source'])
+                    gene_list.append(p['source'])
+            if len(gene_list)>3:
+                gene_list = gene_list[0:3]
+                added = ",..."
+            else:
+                added = ""
+            gene_name = str(gene_list)[1:]
+            gene_name=gene_name[:-1]
+            gene_name=gene_name.replace("'","")
+            gene_name = gene_name+added
+            num_gene = gene_name.count(',')+1
         else: 
-            nodata_temp = 0
-            with open(datadir+"edges.json") as edgesjsonfile:
-                jedges = json.load(edgesjsonfile)
-            break
-    gene_list=[]
-    if nodata_temp == 0:
-        for p in jedges['data']:
-            if p['source'] not in gene_list:
-                gene_list.append(p['source'])
-        if len(gene_list)>3:
-            gene_list = gene_list[0:3]
-            added = ",..."
-        else:
-            added = ""
-        gene_name = str(gene_list)[1:]
-        gene_name=gene_name[:-1]
-        gene_name=gene_name.replace("'","")
-        gene_name = gene_name+added
-        num_gene = gene_name.count(',')+1
-    else: 
-        gene_name1 = gene_name1.replace("_", ", ")
-        gene_name = gene_name1
-        num_gene = gene_name1.count(',')+1
-        for i in range(0,num_gene):
-            gene_list.append(gene_name1.split(',')[i])
-    session['query'] = gene_list
-    message3="<b> Actions: </b><li><font color=\"#E74C3C\">Click on the keywords to see the indicated number of abstracts </font><li> Click on a gene to search its relations with top 200 addiction genes<li>Click on a keyword to see the terms included in the search<li>Hover your pointer over a node to hide other links <li>Move nodes around to adjust visibility, reload the page to restore the default layout<li> View the results in <a href='cytoscape'><b>a graph.</b></a>"
-    return render_template('tableview.html', title='',nodata_temp=nodata_temp, date=select_date, num_gene=num_gene,session_path = session['path'], jedges=jedges, jnodes=jnodes,gene_name=gene_name, message3=message3)
-
-@app.route('/cytoscape')
+            gene_name1 = gene_name1.replace("_", ", ")
+            gene_name = gene_name1
+            num_gene = gene_name1.count(',')+1
+            for i in range(0,num_gene):
+                gene_list.append(gene_name1.split(',')[i])
+        genes_session = ''
+        for gen in gene_list_all:
+            genes_session += str(gen) + "_"
+        genes_session = genes_session[:-1]
+    else:
+        flash("You logged out!")
+        return render_template('index.html')
+    message3="<b> Actions: </b><li> <font color=\"#E74C3C\">Click on the abstract count to read sentences linking the keyword and the gene</font> <li> Click on a gene to search its relations with top 200 addiction genes. <li> Click on a keyword to see the terms included in the search. <li>View the results in <a href='\\cytoscape/?rnd={}&genequery={}'\ ><b> a graph.</b></a>".format(select_date,genes_session)
+    return render_template('tableview.html',nodata_temp=nodata_temp, num_gene=num_gene,genes_session_tmp = genes_session_tmp, rnd_url=select_date ,jedges=jedges, jnodes=jnodes,gene_name=gene_name, genes_url=genes_session, message3=message3)
+
+@app.route('/cytoscape/')
 def cytoscape():
-    message2="<b> Actions: </b><li><font color=\"#E74C3C\">Click on a line to see the indicated number of abstracts </font> <li> Click on a gene to search its relations with top 200 addiction genes<li>Click on a keyword to see the terms included in the search<li>Hover your pointer over a node to hide other links <li>Move nodes around to adjust visibility, reload the page to restore the default layout<li>View the results in <a href='tableview'><b>a table. </b></a> <li>All results will appear in a new Browser window (or tab)"
-    with open(session['path']+"_cy","r") as f:
-        elements=f.read()
-    with open(session['path']+"_0link","r") as z:
-        zeroLink=z.read()
-        if (len(zeroLink)>0):
-            message2+="<span style=\"color:darkred;\">No result was found for these genes: " + zeroLink + "</span>"
+    genes_url=request.args.get('genequery')
+    rnd_url=request.args.get('rnd')
+    tf_path=tempfile.gettempdir()
+    genes_session_tmp=tf_path + "/" + genes_url
+
+    message2="<b> Actions: </b><li><font color=\"#E74C3C\">Click on a line to see the indicated number of abstracts </font> <li> Click on a gene to search its relations with top 200 addiction genes<li>Click on a keyword to see the terms included in the search<li>Hover your pointer over a node to hide other links <li>Move nodes around to adjust visibility, reload the page to restore the default layout<li>View the results in <a href='\\tableview/?rnd={}&genequery={}'\ ><b>a table. </b></a> <li>All results will appear in a new Browser window (or tab)".format(rnd_url,genes_url)
+    if ('email' in session):
+        filename = rnd_url.split("_0_")[0]
+        rnd_url_tmp = datadir+"/user/"+str(session['hashed_email'])+"/"+rnd_url+"/"+filename
+        try:
+            with open(rnd_url_tmp+"_cy","r") as f:
+                elements=f.read()
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        with open(rnd_url_tmp+"_0link","r") as z:
+            zeroLink=z.read()
+            if (len(zeroLink)>0):
+                message2+="<span style=\"color:darkred;\">No result was found for these genes: " + zeroLink + "</span>"
+    else:
+        rnd_url_tmp=tf_path +"/" + rnd_url
+        try:
+            with open(rnd_url_tmp+"_cy","r") as f:
+                elements=f.read()
+        except FileNotFoundError:
+            flash("You logged out!")
+            return render_template('index.html')
+        with open(rnd_url_tmp+"_0link","r") as z:
+            zeroLink=z.read()
+            if (len(zeroLink)>0):
+                message2+="<span style=\"color:darkred;\">No result was found for these genes: " + zeroLink + "</span>"
     return render_template('cytoscape.html', elements=elements, message2=message2)
 
 @app.route("/sentences")
@@ -607,6 +730,7 @@ def sentences():
         else:
             return 'pos'
     pmid_list=[]
+    pmid_string=''
     edge=request.args.get('edgeID')
     (tf_name, gene0, cat0)=edge.split("|")
     if(cat0=='stress'):
@@ -617,7 +741,7 @@ def sentences():
     out_neg = ""
     num_abstract = 0
     stress_cellular = "<br><br><br>"+"</ol><b>Sentence(s) describing celluar stress (classified using a deep learning model):</b><hr><ol>"
-    stress_systemic = "<b>Sentence(s) describing systemic stress (classified using a deep learning model):</b><hr>"
+    stress_systemic = "<b></ol>Sentence(s) describing systemic stress (classified using a deep learning model):</b><hr><ol>"
     with open(tf_name, "r") as df:
         all_sents=df.read()
     for sent in all_sents.split("\n"):
@@ -627,6 +751,7 @@ def sentences():
                 out3+= "<li> "+ text + " <a href=\"https://www.ncbi.nlm.nih.gov/pubmed/?term=" + pmid +"\" target=_new>PMID:"+pmid+"<br></a>"
                 num_abstract += 1
                 if(pmid+cat0 not in pmid_list):
+                    pmid_string = pmid_string + ' ' + pmid
                     pmid_list.append(pmid+cat0)
                 if(cat0=='stress'):
                     out4 = predict_sent(text)
@@ -638,9 +763,9 @@ def sentences():
                         out_neg += out_pred_neg
     out1="<h3>"+gene0 + " and " + cat0  + "</h3>\n"
     if len(pmid_list)>1:
-        out2 = str(num_abstract) + ' sentences in ' + str(len(pmid_list)) + ' studies' + "<br><br>"
+        out2 = str(num_abstract) + ' sentences in ' + " <a href=\"https://www.ncbi.nlm.nih.gov/pubmed/?term=" + pmid_string +"\" target=_new>"+ str(len(pmid_list)) + ' studies' +"<br></a>" + "<br><br>"
     else:
-        out2 = str(num_abstract) + ' sentence(s) in ' + str(len(pmid_list)) + ' study' "<br><br>"
+        out2 = str(num_abstract) + ' sentence(s) in '+ " <a href=\"https://www.ncbi.nlm.nih.gov/pubmed/?term=" + pmid_string +"\" target=_new>"+ str(len(pmid_list)) + ' study' +"<br></a>" "<br><br>"
     if(out_neg == "" and out_pos == ""):
         out= out1+ out2 +out3
     elif(out_pos != "" and out_neg!=""):
@@ -649,6 +774,7 @@ def sentences():
         out= out1+ out2 + stress_systemic + out_pos
     elif(out_neg != "" and out_pos == ""):
         out = out1 +out2+stress_cellular+out_neg
+    K.clear_session()
     return render_template('sentences.html', sentences="<ol>"+out+"</ol><p>")
 ## show the cytoscape graph for one gene from the top gene list
 @app.route("/showTopGene")
@@ -665,6 +791,32 @@ def shownode():
     out="<p>"+node.upper()+"<hr><li>"+ allnodes[node].replace("|", "<li>")
     return render_template('sentences.html', sentences=out+"<p>")
 
+@app.route("/synonyms")
+def synonyms():
+    node=request.args.get('node')
+    node=node.upper()
+    allnodes={**genes}
+    try:
+        synonym_list = list(allnodes[node].split("|")) 
+        session['synonym_list'] = synonym_list
+        session['main_gene'] = node.upper()
+        out="<hr><li>"+ allnodes[node].replace("|", "<li>")
+        synonym_list_str = ';'.join([str(syn) for syn in synonym_list]) 
+        synonym_list_str +=';' + node
+        case = 1
+        return render_template('genenames.html', case = case, gene = node.upper(), synonym_list = synonym_list, synonym_list_str=synonym_list_str)
+    except:
+        try:
+         #if(node in session['synonym_list']):
+            synonym_list = session['synonym_list']
+            synonym_list_str = ';'.join([str(syn) for syn in synonym_list]) 
+            synonym_list_str +=';' + node
+            case = 1
+            return render_template('genenames.html', case=case, gene = session['main_gene'] , synonym_list = synonym_list, synonym_list_str=synonym_list_str)
+        except:
+            case = 2
+            return render_template('genenames.html', gene = node, case = case)
+
 @app.route("/startGeneGene")
 def startGeneGene():
     session['forTopGene']=request.args.get('forTopGene')