added density lookup

ChemID.py

@@ -6,6 +6,10 @@ import pubchempy as pcp
 import cirpy
 import chemicals
 
+import bs4
+import urllib
+import json
+
 from io import BytesIO
 from PIL import ImageOps
 import base64
@@ -24,17 +28,21 @@ def ResolveChemical(chemName, IDtype):
         name = None
         Mw = None
         LogP = None
+        rho = None
         im64 = None
         error = 0
 
         if not is_cas(cas):
             error = 3 #invalid cas
-            return (name, cas, smiles, Mw, LogP, im64, error)
+            return (name, cas, smiles, Mw, LogP, rho, im64, error)
 
         smiles = cas2smiles(cas)
 
         if smiles:
             name = cas2name(cas)
+            rho = string2density(cas)
+            if not rho and name:
+                rho = string2density(name)
             try:
                 mol = Chem.MolFromSmiles(smiles)
             except:
@@ -54,12 +62,16 @@ def ResolveChemical(chemName, IDtype):
         name = None
         Mw = None
         LogP = None
+        rho = None
         im64 = None
         error = 0
 
         name = smiles2name(smiles)
         if name:
             cas = name2cas(name)
+            rho = string2density(name)
+        if not rho and cas:
+            rho = string2density(cas)
 
         try:
             mol = Chem.MolFromSmiles(smiles)
@@ -78,6 +90,7 @@ def ResolveChemical(chemName, IDtype):
         cas = None
         Mw = None
         LogP = None
+        rho = None
         im64 = None
         error = 0
 
@@ -87,6 +100,10 @@ def ResolveChemical(chemName, IDtype):
             cas = name2cas(name)
             smiles = cas2smiles(cas)
 
+        rho = string2density(name)
+        if not rho and cas:
+            rho = string2density(cas)
+
         if smiles:
             if not cas:
                 cas = name2cas(name)
@@ -110,6 +127,7 @@ def ResolveChemical(chemName, IDtype):
         cas = None
         Mw = None
         LogP = None
+        rho = None
         im64 = None
         error = 4 # invalid IDtype selection, probably not possible
 
@@ -119,8 +137,10 @@ def ResolveChemical(chemName, IDtype):
             name = 'Not found'
         if not cas:
             cas = 'Not found'
+        if not rho:
+            rho = 'Not found'
 
-    return (name, cas, smiles, Mw, LogP, im64, error)
+    return (name, cas, smiles, Mw, LogP, rho, im64, error)
 
 #Generates an image of the molecule represented by the SMILES code given.
 #Returns None if the image cannot be generated. From https://github.com/ronaldo-prata/flask-test/blob/master/functions.py
@@ -455,3 +475,111 @@ def is_cas(cas):
     except:
         return False
 
+def string2density(string):
+    rho, rho_origin = None, None
+    # try to scrape from PubChem
+    if not rho:
+        try:
+            content = None
+            compounds = pcp.get_compounds(string, namespace='name')
+            c = compounds[0]
+            cid = c.cid
+            fid = urllib.request.urlopen(f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON')
+            webpage = fid.read().decode('utf-8')
+            content = json.loads(webpage)
+        except:
+            pass
+        if content:
+            rho_list = []
+            for i in content['Record']['Section']:
+                if i['TOCHeading'] == 'Chemical and Physical Properties':
+                    for j in i['Section']:
+                        if j['TOCHeading'] == 'Experimental Properties':
+                            for k in j['Section']:
+                                if k['TOCHeading'] == 'Density':
+                                    for ii in k['Information']:
+                                        rho_string = ii['Value']['StringWithMarkup'][0]['String']
+                                        try:
+                                            tmp_rho = re.match('(?:\d+(?:\.\d*)?|\.\d+)',rho_string)
+                                            tmp_rho = float(tmp_rho.group())
+                                            rho_list.append(tmp_rho)
+                                        except:
+                                            continue
+            if rho_list:
+                rho = np.mean(rho_list)
+                rho_origin = 'pubchem'
+            else:
+                rho, rho_origin = None, None
+    # try to scrape from DSSTOX
+#    if not rho:
+#        dtxsid = None
+#        try:
+#            # try to find it via the dsstox dashboard
+#            string_urlsafe = urllib.parse.quote(string)
+#            url = f'https://comptox.epa.gov/dashboard/search-results?input_type=synonym_substring&inputs={string_urlsafe}'
+#            fid = urllib.request.urlopen(url)
+#            webpage = fid.read().decode('utf-8')
+#            hits = re.findall('DTXSID[0-9]+', webpage)
+#            if len(hits):
+#                dtxsid = hits[0]
+#        except:
+#            pass
+#        if dtxsid:
+#            url = f'https://comptox.epa.gov/dashboard/chemical/properties/{dtxsid}'
+#            #print(url)
+#            try:
+#                driver_exe = chromedriver_binary.chromedriver_filename
+#                options = Options()
+#                options.add_argument("--headless") # runs in background instead of showing browser window
+#                service = Service(driver_exe)
+#                driver = selenium.webdriver.Chrome(service=service, options=options)
+#                #driver = selenium.webdriver.Chrome(driver_exe, options=options)
+#                driver.set_page_load_timeout(15)
+#                driver.get(url)
+#            except KeyboardInterrupt:
+#                raise
+#            except:
+#                pass
+#                #print("timeout")
+#            webpage = driver.page_source
+#            driver.quit()
+#            mysoup = bs4.BeautifulSoup(webpage, features='lxml')
+#            # column of property names
+#            ifound = None
+#            rows = mysoup.find_all('div', attrs={'col-id':'property'})
+#            for i,row in enumerate(rows):
+#                if 'Density' in row.text:
+#                    ifound = i
+#                    break
+#            if ifound:
+#                rows = mysoup.find_all('div', attrs={'col-id':'exavg'})
+#                text = rows[ifound].text
+#                value = re.sub(' \([0-9]*\)', '', text.strip())
+#                try:
+#                    rho = float(value)
+#                    rho_origin = 'expt/dsstox'
+#                except:
+#                    rho, rho_origin = None, None
+#                if not rho:
+#                    rows = mysoup.find_all('div', attrs={'col-id':'predavg'})
+#                    text = rows[ifound].text
+#                    value = re.sub(' \([0-9]*\)', '', text.strip())
+#                    try:
+#                        rho = float(value)
+#                        rho_origin = 'pred/dsstox'
+#                    except:
+#                        rho, rho_origin = None, None
+#            else:
+#                rho, rho_origin = None, None
+#        else:
+#            rho, rho_origin = None, None
+#    if rho:
+#        myrho_dict[string] = rho, rho_origin
+    if rho and np.isnan(rho): rho = None
+    if not rho: rho_origin = None
+    #print(rho, rho_origin)
+#    with open('/Users/robert.elder/Documents/experiments/07-data-mining/databases/custom_density_data.json', 'w') as fp:
+#        json.dump(myrho_dict, fp, indent=True, sort_keys=True)
+    return rho
+    #return rho, rho_origin
+

exposure_module/exposure.py

@@ -21,7 +21,7 @@ def exp_post():
     chemName = request.form["chemName"]
     IDtype = request.form["IDtype"]
 
-    iupac, cas, smiles, MW, LogP, molImage, error = ResolveChemical(chemName, IDtype)
+    iupac, cas, smiles, MW, LogP, rho, molImage, error = ResolveChemical(chemName, IDtype)
 
     if error > 0:
         return render_template('chemError.html')
@@ -66,6 +66,7 @@ def exp_post():
     diff = SigFigs(diff, 2)
     MW = SigFigs(MW, 6)
     LogP = SigFigs(LogP, 6)
+    #rho = SigFigs(rho[0], 4)
 
     # Generate the rate plot using matplotlib
     tarray = np.arange(1., 31., 1.)
@@ -74,4 +75,4 @@ def exp_post():
 
     return render_template('exposure_report.html', polymers=polymers, pIndex=pIndex, release=release,
                            assume=assume, area=area, vol=vol, amount=amount, diff=diff, time=time, exposure=exposure, TTC=TTC,
-                           MOS=MOS, chemName=chemName, image=pngImageB64String, MW=MW, LogP=LogP, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)
+                           MOS=MOS, chemName=chemName, image=pngImageB64String, MW=MW, LogP=LogP, rho=rho, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)

exposure_module/templates/exposure_report.html

@@ -55,6 +55,7 @@
       CAS ::  {{cas}} <br> <br>
       Molecular weight :: {{MW}} <br> <br>
       LogKow :: {{LogP}} <br> <br>
+      Density :: {{rho}} <br> <br>
       SMILES :: {{smiles}}
   </div>
   <div class="column">