added MP lookup and various bug fixes

ChemID.py

@@ -6,15 +6,21 @@ import pubchempy as pcp
 import cirpy
 
 import chemicals
-## add custom chemical definitions (i.e., to correct confusion between methane and carbon)
-db = chemicals.identifiers.get_pubchem_db()
-db.load('custom_chemicals_db.tsv')
 
 import bs4
 import urllib
 import requests
 import json
 
+## not sure if this will be possible on pythonanywhere; use this flag to disable related code blocks
+try_dsstox = True
+if try_dsstox:
+    import selenium
+    import selenium.webdriver
+    from selenium.webdriver.chrome.options import Options
+    from selenium.webdriver.chrome.service import Service
+    import chromedriver_binary
+
 from io import BytesIO
 from PIL import ImageOps
 import base64
@@ -23,38 +29,51 @@ import rdkit
 from rdkit.Chem import AllChem as Chem
 from rdkit.Chem import Descriptors,Descriptors3D,Draw,Crippen
 
+## add custom chemical definitions (i.e., to correct confusion between methane and carbon)
+db = chemicals.identifiers.get_pubchem_db()
+db.load('custom_chemicals_db.tsv')
+## load experimental and predicted properties
+dfmp_expt = pd.read_excel('PHYSPROP_MP_data.xlsx')
+#dfmp_pred = pd.read_excel('DSSTOX_MP_pred_data.xlsx')
+df_pred = pd.read_excel('Comptox_pred_data.xlsx')
+
 def ResolveChemical(chemName, IDtype):
 
-    LogP_func = Crippen.MolLogP
+    #LogP_func = Crippen.MolLogP
+    LogP_func = getLogP
     
+    name = None
+    smiles = None
+    cas = None
+    Mw = None
+    LogP = None
+    rho = None
+    mp = None
+    im64 = None
+    error = 0
+
     if IDtype == 'CAS':
         cas = chemName
-        smiles = None
-        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, rho, im64, error)
+            return (name, cas, smiles, Mw, LogP, rho, mp, im64, error)
 
         smiles = cas2smiles(cas)
 
         if smiles:
             name = cas2name(cas)
-            rho = string2density(cas)
-            if not rho and name:
-                rho = string2density(name)
+            rho, rho_origin = string2density(cas)
+            mp, mp_origin = mol2mp(cas, name, smiles)
+            if rho is None and name:
+                rho, rho_origin = string2density(name)
             try:
                 mol = Chem.MolFromSmiles(smiles)
             except:
                 error = 2 #invalid smiles
             if mol:
                 Mw = Descriptors.MolWt(mol)
-                LogP = LogP_func(mol)
+                LogP, LogP_origin = LogP_func(cas, mol)
                 im = ImageFromSmiles(smiles)
                 im64 = Imageto64(im)
             else:
@@ -63,20 +82,15 @@ def ResolveChemical(chemName, IDtype):
             error = 1 # no smiles found
     elif IDtype == 'SMILES':
         smiles = chemName
-        cas = None
-        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)
+            rho, rho_origin = string2density(name)
+        if rho is None and cas:
+            rho, rho_origin = string2density(cas)
+
+        mp, mp_origin = mol2mp(cas, name, smiles)
 
         try:
             mol = Chem.MolFromSmiles(smiles)
@@ -84,44 +98,37 @@ def ResolveChemical(chemName, IDtype):
             error = 2
         if mol:
             Mw = Descriptors.MolWt(mol)
-            LogP = LogP_func(mol)
+            LogP, LogP_origin = LogP_func(cas, mol)
             im = ImageFromSmiles(smiles)
             im64 = Imageto64(im)
         else:
             error = 2
     elif IDtype == 'common':
         name = chemName
-        smiles = None
-        cas = None
-        Mw = None
-        LogP = None
-        rho = None
-        im64 = None
-        error = 0
 
-        rho = string2density(name)
+        # try this first because sometimes iupac names don't work
+        rho, rho_origin = string2density(name)
 
         name, name_origin = name2iupac(name)
         smiles = name2smiles(name)
+        cas = name2cas(name)
         if not smiles:
-            cas = name2cas(name)
             smiles = cas2smiles(cas)
 
-        if not rho:
-            rho = string2density(name)
-        if not rho and cas:
-            rho = string2density(cas)
+        if rho is None and cas:
+            rho, rho_origin = string2density(cas)
+        if rho is None:
+            rho, rho_origin = string2density(name)
 
         if smiles:
-            if not cas:
-                cas = name2cas(name)
+            mp, mp_origin = mol2mp(cas, name, smiles)
             try:
                 mol = Chem.MolFromSmiles(smiles)
             except:
                 error = 2
             if mol:
                 Mw = Descriptors.MolWt(mol)
-                LogP = LogP_func(mol)
+                LogP, LogP_origin = LogP_func(cas, mol)
                 im = ImageFromSmiles(smiles)
                 im64 = Imageto64(im)
             else:
@@ -136,6 +143,7 @@ def ResolveChemical(chemName, IDtype):
         Mw = None
         LogP = None
         rho = None
+        mp = None
         im64 = None
         error = 4 # invalid IDtype selection, probably not possible
 
@@ -146,7 +154,7 @@ def ResolveChemical(chemName, IDtype):
         if not cas:
             cas = 'Not found'
 
-    return (name, cas, smiles, Mw, LogP, rho, im64, error)
+    return (name, cas, smiles, Mw, LogP, rho, mp, 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
@@ -309,8 +317,6 @@ def name2iupac(string):
         elif cm.common_name:
             name = cm.common_name
         origin = 'chemicals'
-    except KeyboardInterrupt:
-        raise
     except:
         name = None
         origin = None
@@ -483,8 +489,14 @@ def is_cas(cas):
 
 def string2density(name):
     rho, rho_origin = None, None
+    # predicted values from TEST (CompTox dashboard)
+    if is_cas(name):
+        mask = df_pred['CASRN'] == name
+        if sum(mask):
+            rho = float(df_pred[mask]['DENSITY_G/CM^3_TEST_PRED'])
+            rho_origin = 'pred'
     # try to scrape from PubChem
-    if not rho:
+    if rho is None:
         try:
             content = None
             compounds = pcp.get_compounds(name, namespace='name')
@@ -529,82 +541,513 @@ def string2density(name):
                 intr_qr = q75-q25
                 hi = q75+(1.5*intr_qr)
                 lo = q25-(1.5*intr_qr)
-                mask = (rho_list < hi) & (rho_list > lo)
+                mask = (rho_list <= hi) & (rho_list >= lo)
                 rho_list = rho_list[mask]
                 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
+    if try_dsstox:
+        if rho is None:
+            dtxsid = None
+            try:
+                # try to find it via the dsstox dashboard
+                name_urlsafe = urllib.parse.quote(name)
+                url = f'https://comptox.epa.gov/dashboard/search-results?input_type=synonym_substring&inputs={name_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.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 rho is None:
+                        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 is not None and np.isnan(rho): rho = None
+    if rho is None: rho_origin = None
+    return rho, rho_origin
+
+def return_non_duplicate_index(tuples): ##Given a list of sets return index of non_duplicate items
+    ## from https://github.com/curieshicy/JRgui/
+    ##step 1, create a new tuple, named "new_tuples"
+    new_tuples = [] ##the elements are the sets
+    for i in tuples:
+        for j in i:
+            new_tuples.append(set(j))
+    ##step 2, create a dictionary storing one to one relationship between new_tuple and old_tuple
+    values = []
+    for index, item in enumerate(tuples):
+        if len(item) == 1:
+            values.append(index)
+        else:
+            for i in [index]*len(item):
+                values.append(i)
+    keys = [i for i in range(len(new_tuples))]
+    dict_tuples = {}  ## {0:0, 1:1, 2:2, 3:3, 4:3, 5:3, 6:4, 7:4, 8:4, 9:5, 10:6, 11:7, 12:8}
+    for i, j in zip(keys, values):
+        dict_tuples[i] = j
+    ##step 3, remove duplicates in sets terminology    
+    remove_index = []
+    for index_1, item in enumerate(new_tuples): ##starting from beginning
+        for index_2 in range(index_1 + 1, len(new_tuples)): ##loop over the rest items
+            if len(item & new_tuples[index_2]) != 0:
+                if len(item)>len(new_tuples[index_2]):
+                    remove_index.append(index_2) #indefoirx
+                elif len(item)<len(new_tuples[index_2]):
+                    remove_index.append(index_1) #index
+                elif len(item)==len(new_tuples[index_2]):
+                    remove_index.append(index_2) #index
+    remain_sets = set(range(len(new_tuples))).difference(set(remove_index))
+    ##step 4, spit out final index and length
+    index_1 = [] ## [0,1,2,3,3,3,4,4]
+    index_length = []
+    for i in remain_sets:
+        index_1.append(dict_tuples[i])
+    counts = Counter(index_1) ##this is a dictionary return Counter({3:3, 4:2, 0:1, 1:1, 2:1}) ##index:length
+    list_counts = counts.most_common() ## convert to a list [(3,3), (4,2), (0,1), (1,1), (2,1)]
+    for i in range(len(list_counts)):
+        index_length.append([list_counts[i][0], list_counts[i][1]])
+    index_length = sorted(index_length, key = itemgetter(0))
+    return index_length
+
+def search_func_groups(smiles): ##this is to search functional groups and print out them with numbers
+    ## from https://github.com/curieshicy/JRgui/
+    smarts = ["[$([CX2H0](=*)=*)]", "[$([CX2H1]#[!#7])]", "[$([CX2H0]#[!#7])]", "[OX2H]-[C]=O", "[#6X3H0;!$([#6X3H0](~O)(~O)(~O))](=[#8X1])[#8X2H0]",
+              "[$([#6X3H0](=[OX1]));!$([#6X3](=[#8X1])~[#8X2]);R]=O", "[CH;D2;$(C-!@C)](=O)", "[OX2H;!$([OX2H]-[#6]=[O]);!$([OX2H]-a)]", "[O;H1;$(O-!@c)]", 
+              "[#8X2H0;R;!$([#8X2H0]~[#6]=[#8])]", "[$([CX3H0](=[OX1]));!$([CX3](=[OX1])-[OX2]);!R]=O", "[OX2H0;!R;!$([OX2H0]-[#6]=[#8])]", 
+              "[$([#7X3,#7X3+][!#8])](=[O])~[O-]", "[OX1H0;!$([OX1H0]~[#6X3]);!$([OX1H0]~[#7X3]~[#8])]", "[#7X2H0;R]",  "[#7X3H1;R]", "[#7X2H1]",
+              "[#7X2H0;!R]","[#6X2]#[#7X1H0]","[NX3H2]", "[NX3H1;!R]", "[#7X3H0;!$([#7](~O)~O)]","[SX2H]","[#16X2H0;!R]","[#16X2H0;R]",  "[R;CX3H1,cX3H1]", 
+              "[$([R;#6X3H0]);!$([R;#6X3H0]=[#8])]","[R;CX4H2]","[R;CX4H]","[R;CX4H0]", "[CX3H2]", "[!R;CX3H1;!$([CX3H1](=O))]",
+              "[$([!R;#6X3H0]);!$([!R;#6X3H0]=[#8])]","[CX4H3]","[!R;CX4H2]", "[!R;CX4H]","[!R;CX4H0]","[F]","[Cl]","[Br]", "[I]"]
+    tuples = []
+    index_list = []
+    final_index_and_length = []
+    m = Chem.MolFromSmiles(str(smiles))    
+    for index, smart in enumerate(smarts):
+        if m.HasSubstructMatch(Chem.MolFromSmarts(smart)) == True: 
+            tuples.append(m.GetSubstructMatches(Chem.MolFromSmarts(smart))) ## this is atom position
+            index_list.append(index)
+    temp = return_non_duplicate_index(tuples) # [[0, 1], [1, 1], [3, 1], [4, 7], [5, 6], [6, 1], [7, 1], [8, 1], [9, 1]]
+    for i in temp:
+        final_index_and_length.append([index_list[i[0]], i[1]])
+    return final_index_and_length      
+
+def compute_phys_properties(smiles):
+    ## from https://github.com/curieshicy/JRgui/
+    ## method from: K. G. Joback, R. C. Reid, ESTIMATION OF PURE-COMPONENT PROPERTIES FROM GROUP-CONTRIBUTIONS. Chemical Engineering Communications 57, 233-243 (1987).
+    ## this doesn't look very accurate, but it's a start
+    ##[[], [], ...[]] in total 41 nested list inside a list
+    DB =    [[0.0026,	0.0028,	36,	26.15,	17.78,	142.14,	136.70,	2.74E+1,	-5.57E-2,	1.01E-4,	-5.02E-8,	4.720,	2.661,	None,	None],
+            [0.0027,	-0.0008,46,	9.20,	-11.18,	79.30,	77.71,	2.45E+1,	-2.71E-2,	1.11E-4,	-6.78E-8,	2.322,	1.155,	None,	None],
+            [0.0020,	0.0016,	37,	27.38,	64.32,	115.51,	109.82,	7.87,	         2.01E-2,	-8.33E-6,	1.39E-9,	4.151,	3.302,	None,	None],
+            [0.0791,	0.0077,	89,	169.09,	155.50,	-426.72,-387.87,2.41E+1,	4.27E-2,	8.04E-5,       -6.87E-8,	11.051,	19.537,	1317.23,-2.578],
+            [0.0481,	0.0005,	82,	81.10,	53.60,	-337.92,-301.95,2.45E+1,	4.02E-2,	4.02E-5,	-4.52E-8,	6.959,	9.633,	483.88,	-0.966],
+            [0.0284,	0.0028,	55,	94.97,	75.97,	-164.50,-126.27,3.04E+1,	-8.29E-2,	2.36E-4,       -1.31E-7,	None,	6.645,	None,	None],
+            [0.0379,	0.0030,	82,	72.24,	36.90,	-162.03,-143.48,3.09E+1,	-3.36E-2,	1.60E-4,       -9.88E-8,	3.197,	9.093,	740.92,	-1.713],
+            [0.0741,	0.0112,	28,	92.88,	44.45,	-208.04,-189.20,2.57E+1,	-6.91E-2,	1.77E-4,	-9.88E-8,	2.406,	16.826,	2173.72,-5.057],
+            [0.0240,	0.0184,	-25,	76.34,	82.83,	-221.65,-197.37,-2.81,	         1.11E-1,	-1.16E-4,	4.94E-8,	4.490,	12.499,	3018.17,-7.314],
+            [0.0098,	0.0048,	13,	31.22,	23.05,	-138.16,-98.22,	1.22E+1,	-1.26E-2,	6.03E-5,	-3.86E-8,	5.879,	4.682,	440.24,	-0.953],
+            [0.0380,	0.0031,	62,	76.75,	61.20,	-133.22,-120.50,6.45,	         6.70E-2,	-3.57E-5,	2.86E-9,	4.189,	8.972,	340.35,	-0.350],
+            [0.0168,	0.0015,	18,	22.42,	22.23,	-132.22,-105.00,2.55E+1,	-6.32E-2,	1.11E-4,       -5.48E-8,	1.188,	2.410,	122.09,	-0.386],
+            [0.0437,	0.0064,	91,	152.54,	127.24,	-66.57,	-16.83,	2.59E+1,	-3.74E-3,	1.29E-4,	-8.88E-8,	9.679,	16.738,	None,	None],
+            [0.0143,	0.0101,	36,	-10.50,	2.08,	-247.61,-250.83,6.82,	        1.96E-2,	1.27E-5,	-1.78E-8,	3.624,	5.909,	675.24,	-1.340],
+            [0.0085,	0.0076,	34,	57.55,	68.40,	55.52,	79.93,	8.83,	      -3.84E-3,	         4.35E-5,	-2.60E-8,	3.649,	6.528,	None,	None],
+            [0.0130,	0.0114,	29,	52.82,	101.51,	31.65,75.61,1.18E+1,	        -2.30E-2,	1.07E-4,	-6.28E-8,	7.490,	6.930,	None,	None],
+            [None,  	None,	None,	83.08,	68.91,	93.70,	119.66,	5.69,	       -4.12E-3,	1.28E-4,	-8.88E-8,	None,	12.169,	None,	None],
+            [0.0255,	-0.0099,None,	74.60,	None,	23.61,	None,     None,	         None,	         None,	          None, 	None,	3.335,	None,	None],
+            [0.0496,	-0.0101,91,	125.66,	59.89,	88.43,	89.22,	3.65E+1,	-7.33E-2,	1.84E-4,	-1.03E-7,	2.414,	12.851,	None,	None],
+            [0.0243,	0.0109,	38,	73.23,	66.89,	-2.02,	14.07,2.69E+1,	        -4.12E-2,	1.64E-4,        -9.76E-8,	3.515,	10.788,	None,	None],
+            [0.0295,	0.0077,	35,	50.17,	52.66,	53.47,	89.39,-1.21,	        7.62E-2,	-4.86E-5,	1.05E-8,	5.009,	6.436,	None,	None],
+            [0.0169,	0.0074,	9,	11.74,	48.84,	123.34,	163.16,-3.11E+1,	2.27E-1,	-3.20E-4,	1.46E-7,	4.703,	1.896,	None,	None],
+            [0.0031,	0.0084,	63,	63.56,	20.09,	-17.33,	-22.99,	3.53E+1,	-7.58E-2,	1.85E-4,	-1.03E-7,	2.360,	6.884,	None,	None],
+            [0.0119,	0.0049,	54,	68.78,	34.40,	41.87,	33.12,	1.96E+1,	-5.61E-3,	4.02E-5,	-2.76E-8,	4.130,	6.817,	None,	None],
+            [0.0019,	0.0051,	38,	52.10,	79.93,	39.10,	27.76,	1.67E+1,	4.81E-3,	2.77E-5,	-2.11E-8,	1.557,	5.984,	None,	None],
+            [0.0082,	0.0011,	41,	26.73,	8.13,	2.09,	11.30,	-2.14,	        5.74E-2,	-1.64E-6,	-1.59E-8,	1.101,	2.544,	259.65,	-0.702],
+            [0.0143,	0.0008,	32,	31.01,	37.02,	46.43,	54.05,	-8.25,	        1.01E-1,	-1.42E-4,	6.78E-8,	2.394,	3.059,	-245.74,0.912],
+            [0.0100,	0.0025,	48,	27.15,	7.75,	-26.80,	-3.68,	-6.03,	         8.54E-2,	-8.00E-6,	-1.80E-8,	0.490,	2.398,	307.53,	-0.798],
+            [0.0122,	0.0004,	38,	21.78,	19.88,	8.67,	40.99,	-2.05E+1,	1.62E-1,	-1.60E-4,	6.24E-8,	3.243,	1.942,	-394.29,1.251],
+            [0.0042,	0.0061,	27,	21.32,	60.15,	79.72,	87.88,	-9.09E+1,	5.57E-1,	-9.00E-4,	4.69E-7,	-1.373,	0.644,	None,	None],
+            [0.0113,	-0.0028,56,	18.18,	-4.32,	-9.630,	3.77,	2.36E+1,	-3.81E-2,	1.72E-4,	-1.03E-7,	-0.473,	1.724,	495.01,	-1.539],
+            [0.0129,	-0.0006,46,	24.96,	8.73,	37.97,	48.53,	-8.00,	        1.05E-1,	-9.63E-5,	3.56E-8,	2.691,	2.205,	82.28,	-0.242],
+            [0.0117,	0.0011,	38,	24.14,	11.14,	83.99,	92.36,	-2.81E+1,	2.08E-1,	-3.06E-4,	1.46E-7,	3.063,	2.138,	None,	None],
+            [0.0141,	-0.0012,65,	23.58,	-5.10,	-76.45,	-43.96,	1.95E+1,	-8.08E-3,	1.53E-4,	-9.67E-8,	0.908,	2.373,	548.29,	-1.719],
+            [0.0189,	0.0000,	56,	22.88,	11.27,	-20.64,	8.42,	-9.09E-1,	9.50E-2,	-5.44E-5,	1.19E-8,	2.590,	2.226,	94.16,	-0.199],
+            [0.0164,	0.0020,	41,	21.74,	12.64,	29.89,	58.36,	-2.30E+1,	2.04E-1,	-2.65E-4,	1.20E-7,	0.749,	1.691,	-322.15,1.187],
+            [0.0067,	0.0043,	27,	18.25,	46.43,	82.23,	116.02,	-6.62E+1,	4.27E-1,	-6.41E-4,	3.01E-7,	-1.460,	0.636,	-573.56,2.307],
+            [0.0111,	-0.0057,27,	-0.03,	-15.78,	-251.92,-247.19,2.65E+1,	-9.13E-2,	1.91E-4,	-1.03E-7,	1.398,	-0.670,	None,	None],
+            [0.0105,	-0.0049,58,	38.13,	13.55,	-71.55,-64.31,	3.33E+1,	-9.63E-2,	1.87E-4,	-9.96E-8,	2.515,	4.532,	625.45,	-1.814],
+            [0.0133,	0.0057,	71,	66.86,	43.43,	-29.48,	-38.06,	2.86E+1,	-6.49E-2,	1.36E-4,	-7.45E-8,	3.603,	6.582,	738.91,	-2.038],
+            [0.0068,	-0.0034,97,	93.84,	41.69,	21.06,	5.74,	3.21E+1,	-6.41E-2,	1.26E-4,	-6.87E-8,	2.724,	9.520,	809.55,	-2.224]] 
+
+    mol = Chem.MolFromSmiles(str(smiles))
+    NoA = Chem.AddHs(mol).GetNumAtoms()
+    MW = Descriptors.MolWt(Chem.AddHs(mol))
+    LogP = Descriptors.MolLogP(Chem.AddHs(mol))
+    MR = Descriptors.MolMR(Chem.AddHs(mol))
+
+    double_lists = search_func_groups(smiles)
+
+    entry_index_by_users = []
+    entry_data_by_users = []
+
+    for item in double_lists:
+        entry_index_by_users.append(item[0])
+        entry_data_by_users.append(item[1])
+        
+    fiveteen_columns = [] ##length  = 15*len(entry_index_by_users)
+    for index, data in zip(entry_index_by_users, entry_data_by_users):
+        for i in range(15):
+            if DB[index][i] == None:
+                temp = None
+            else:
+                temp = data*DB[index][i]
+            fiveteen_columns.append(temp)
+
+    temperature = 310
+    Tc = []
+    Pc = []
+    Vc = []
+    Tb = []
+    Tm = []
+    Hfor = []
+    Gf = []
+    Cpa = []
+    Cpb = []
+    Cpc = []
+    Cpd = []
+    Hfus = []
+    Hvap = []
+    Ya = []
+    Yb =[]        
+    fc = fiveteen_columns ## short hand
+    for i in range(len(entry_index_by_users)):
+        Tc.append(fc[i*15])
+        Pc.append(fc[i*15 + 1])
+        Vc.append(fc[i*15 + 2])
+        Tb.append(fc[i*15 + 3])
+        Tm.append(fc[i*15 + 4])
+        Hfor.append(fc[i*15 + 5])
+        Gf.append(fc[i*15 + 6])
+        Cpa.append(fc[i*15 + 7])
+        Cpb.append(fc[i*15 + 8])
+        Cpc.append(fc[i*15 + 9])
+        Cpd.append(fc[i*15 + 10])
+        Hfus.append(fc[i*15 + 11])
+        Hvap.append(fc[i*15 + 12])
+        Ya.append(fc[i*15 + 13])
+        Yb.append(fc[i*15 + 14])
+    try:
+        BoilingPoint = 198.2 + sum(Tb)
+    except:
+        BoilingPoint = None        
+    try:
+        MeltingPoint = 122.5 + sum(Tm)
+    except:
+        MeltingPoint = None
+    try:
+        CriticalTemp =  (sum(Tb) + 198.2)/(0.584 + 0.965*sum(Tc) - sum(Tc)**2)
+    except:
+        CriticalTemp = None
+    try:
+        CriticalPress = 1./(0.113 + 0.0032*float(NoA) - sum(Pc))**2
+    except:
+        CriticalPress = None
+    try:
+        CriticalVolume = 17.5 + sum(Vc)
+    except:
+        CriticalVolume = None
+    try:
+        EnthalpyForm = 68.29 + sum(Hfor)
+    except:
+        EnthalpyForm = None
+    try:
+        GibbsEnergy = 53.88 + sum(Gf)
+    except:
+        GibbsEnergy = None
+    try:
+        HeatCapacity = (sum(Cpa) - 37.93) + (sum(Cpb) + 0.210)*float(temperature) + (sum(Cpc) - 3.91*10**(-4))*float(temperature)**2 + (sum(Cpd) + 2.06*10**(-7))*float(temperature)**3
+    except:
+        HeatCapacity = None
+    try:
+        EnthalpyVap = 15.30 + sum(Hvap)
+    except:
+        EnthalpyVap = None
+    try:
+        EnthalpyFus = -0.88 + sum(Hfus)
+    except:
+        EnthalpyFus = None
+    try:
+        LiquidVisco = float(MW)*math.exp((sum(Ya) - 597.82)/float(temperature) + sum(Yb) - 11.202)
+    except:
+        LiquidVisco = None
+    try:
+        CrystalSolub_1 = 10**(0.8 - float(LogP) - 0.01*(sum(Tm)+122.5 - 273.15 - 25.))*1000.*float(MW)
+    except:
+        CrystalSolub_1 = None
+    try:
+        CrystalSolub_2 = 10**(0.5 - float(LogP) - 0.01*(sum(Tm)+122.5 - 273.15 - 25.))*1000.*float(MW)
+    except:
+        CrystalSolub_2 = None
+    try:
+        AmorphSolub_1 = 10**(0.8 - float(LogP) - 0.01*(sum(Tm)+122.5 - 273.15 - 25.)) *1000.*float(MW)*math.exp((sum(Hfus)-0.88)*(sum(Tm) + 122.5 - float(temperature))*float(temperature)/(sum(Tm) + 122.5)**2/(2.479*float(temperature)/298.))
+    except:
+        AmorphSolub_1 = None
+    try:
+        AmorphSolub_2 = 10**(0.5 - float(LogP) - 0.01*(sum(Tm)+122.5 - 273.15 - 25.)) *1000.*float(MW)*math.exp((sum(Hfus)-0.88)*(sum(Tm) + 122.5 - float(temperature))*float(temperature)/(sum(Tm) + 122.5)**2/(2.479*float(temperature)/298.))
+    except:
+        AmorphSolub_2 = None
+    return MeltingPoint-273.15
+
+def string2mp(name):
+    mp, mp_origin = None, None
+    # try the chemicals package
+    if is_cas(name):
+        cas = name
+        if mp is None:
+            mp = chemicals.Tm(cas)
+            if mp: mp = mp-273.15
+            methods = chemicals.Tm_methods(cas)
+            if methods: mp_origin = 'chem/'+methods[0]
+        # experimental values
+        if mp is None:
+            # some rows have multiple comma-separated cas numbers
+            mask = dfmp_expt['CAS'].str.contains(cas)
+            if sum(mask):
+                subdf = dfmp_expt[mask]['CAS'].str.split(', ')
+                for index,subcas in zip(subdf.index,subdf):
+                    if cas in subcas:
+                        mp = float(dfmp_expt.iloc[index]['MP'])
+                        mp_origin = 'expt'
+        # predicted values from Mansouri
+        #if mp is None:
+        #    mask = dfmp_pred['Substance_CASRN'] == cas
+        #    if sum(mask):
+        #        mp = float(dfmp_pred[mask]['NCCT_MP'])
+        #        mp_origin = 'pred'
+        # predicted values from OPERA (CompTox dashboard)
+        if mp is None:
+            mask = df_pred['CASRN'] == cas
+            if sum(mask):
+                mp = float(df_pred[mask]['MELTING_POINT_DEGC_OPERA_PRED'])
+                mp_origin = 'pred'
+    # try to scrape from PubChem
+    if mp is None:
+        try:
+            content = None
+            compounds = pcp.get_compounds(name, namespace='name')
+            c = compounds[0]
+            cid = c.cid
+            url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON'
+            #fid = urllib.request.urlopen(url)
+            #webpage = fid.read().decode('utf-8')
+            webpage = requests.get(url).text
+            content = json.loads(webpage)
+        except:
+            pass
+        if content:
+            mp_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'] == 'Melting Point':
+                                    for ii in k['Information']:
+                                        try:
+                                            mp_string = ii['Value']['StringWithMarkup'][0]['String']
+                                            #rho_string = rho_string.replace('Relative density (water = 1): ', '')
+                                            #print(mp_string)
+                                            #tmp_rho = re.match('(?:\d+(?:\.\d*)?|\.\d+)',rho_string)
+                                            #m = re.match('((?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?',rho_string)
+                                            m = re.match('((?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?( ?°?C)',mp_string)
+                                            if m is not None:
+                                                groups = m.groups()
+                                                if len(groups):
+                                                    for g in groups:
+                                                        try:
+                                                            tmp_mp = float(g)
+                                                            mp_list.append(tmp_mp)
+                                                        except:
+                                                            continue
+                                            m = re.match('((?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?( ?°?F)',mp_string)
+                                            if m is not None:
+                                                groups = m.groups()
+                                                if len(groups):
+                                                    for g in groups:
+                                                        try:
+                                                            # (T/F − 32) × 5/9 = T/C
+                                                            tmp_mp = (float(g)-32)*5/9
+                                                            mp_list.append(tmp_mp)
+                                                        except:
+                                                            continue
+                                        except:
+                                            continue
+            if mp_list:
+                ## remove outliers using interquartile range (IQR)
+                mp_list = np.array(mp_list)
+                q75,q25 = np.percentile(mp_list,[75,25])
+                intr_qr = q75-q25
+                hi = q75+(1.5*intr_qr)
+                lo = q25-(1.5*intr_qr)
+                mask = (mp_list <= hi) & (mp_list >= lo)
+                mp_list = mp_list[mask]
+                mp = np.mean(mp_list)
+                mp_origin = 'pubchem'
+            else:
+                mp, mp_origin = None, None
+    # try to scrape from DSSTOX website...
+    if try_dsstox:
+        if mp is None:
+            dtxsid = None
+            # try to find it via the dsstox dashboard
+            try:
+                name_urlsafe = urllib.parse.quote(name)
+                url = f'https://comptox.epa.gov/dashboard/search-results?input_type=synonym_substring&inputs={name_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 = selenium.webdriver.Firefox()
+                    #driver.set_page_load_timeout(15)
+                    #driver.get(url)
+                    #driver_exe = 'chromedriver'
+                    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:
+                    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 'Melting Point' 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:
+                        mp = float(value)
+                        mp_origin = 'expt/dsstox'
+                    except:
+                        mp, mp_origin = None, None
+                    if mp is None:
+                        rows = mysoup.find_all('div', attrs={'col-id':'predavg'})
+                        text = rows[ifound].text
+                        value = re.sub(' \([0-9]*\)', '', text.strip())
+                        try:
+                            mp = float(value)
+                            mp_origin = 'pred/dsstox'
+                        except:
+                            mp, mp_origin = None, None
+                else:
+                    mp, mp_origin = None, None
+            else:
+                mp, mp_origin = None, None
+    if mp is not None and np.isnan(mp): mp = None
+    if mp is None: mp_origin = None
+    return mp, mp_origin
+
+def smiles2mp(smiles):
+    try:
+        mp = compute_phys_properties(smiles)
+    except:
+        mp = None
+    return mp
+
+def mol2mp(cas, name, smiles):
+    mp, mp_origin = None, None
+    if cas:
+        try:
+            mp, mp_origin = string2mp(cas)
+        except:
+            mp, mp_origin = None, None
+    if mp is None and name:
+        try:
+            mp, mp_origin = string2mp(name)
+        except:
+            mp, mp_origin = None, None
+    if mp is None and smiles:
+        try:
+            mp = smiles2mp(smiles)
+            mp_origin = 'calc'
+        except:
+            mp, mp_origin = None, None
+    return mp, mp_origin
+
+def getLogP(cas,mol):
+    LogP, LogP_origin = None, None
+    if cas:
+        mask = df_pred['CASRN'] == cas
+        if sum(mask):
+            LogP = float(df_pred[mask]['OCTANOL_WATER_PARTITION_LOGP_OPERA_PRED'])
+            LogP_origin = 'pred'
+    if LogP is None and mol:
+        LogP = Crippen.MolLogP(mol)
+        LogP_origin = 'calc'
+    return LogP, LogP_origin
 

Comptox_pred_data.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a77e80c823abf37881e942649f9b4afa21b2b70928629cfbf6407efa3300c6c
+size 23755078

PHYSPROP_MP_data.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85bcaed57718ed6ef0e6454a6351ef16f64f4d255b16f595ea5e4d8ef240842e
+size 162360

exposure_module/exposure.py

@@ -21,7 +21,7 @@ def exp_post():
     chemName = request.form["chemName"]
     IDtype = request.form["IDtype"]
 
-    iupac, cas, smiles, MW, LogP, rho, molImage, error = ResolveChemical(chemName, IDtype)
+    iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype)
 
     if error > 0:
         return render_template('chemError.html')
@@ -33,7 +33,9 @@ def exp_post():
             rho = SigFigs(rho, 4)
         else:
             rho = 'Not found'
-        return render_template('MwError.html', chemName=chemName, MW=MW, LogP=LogP, rho=rho, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)
+        if mp is None:
+            mp = 'Not found'
+        return render_template('MwError.html', chemName=chemName, MW=MW, LogP=LogP, rho=rho, mp=mp, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)
 
     amount = float(request.form["amount"])
     mass = float(request.form["mass"])
@@ -76,6 +78,8 @@ def exp_post():
         rho = SigFigs(rho, 4)
     else:
         rho = 'Not found'
+    if mp is None:
+        mp = 'Not found'
 
     # Generate the rate plot using matplotlib
     tarray = np.arange(1., 31., 1.)
@@ -84,4 +88,5 @@ 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, rho=rho, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)
+                           MOS=MOS, chemName=chemName, image=pngImageB64String, MW=MW, LogP=LogP, rho=rho, mp=mp, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage)
+

exposure_module/templates/MwError.html

@@ -46,8 +46,9 @@
       IUPAC Name ::  {{iupac}} <br> <br>
       CAS ::  {{cas}} <br> <br>
       Molecular weight :: {{MW}} <br> <br>
-      LogKow :: {{LogP}} <br> <br>
+      LogKow :: {{'%0.2f'%LogP|float}} <br> <br>
       Density :: {{rho}} <br> <br>
+      Melting point :: {{'%0.1f'%mp|float}} <br> <br>
       SMILES :: {{smiles}}
   </div>
   <div class="column">

exposure_module/templates/exposure_report.html

@@ -54,8 +54,9 @@
       IUPAC Name ::  {{iupac}} <br> <br>
       CAS ::  {{cas}} <br> <br>
       Molecular weight :: {{MW}} <br> <br>
-      LogKow :: {{LogP}} <br> <br>
+      LogKow :: {{'%0.2f'%LogP|float}} <br> <br>
       Density :: {{rho}} <br> <br>
+      Melting point :: {{'%0.1f'%mp|float}} <br> <br>
       SMILES :: {{smiles}}
   </div>
   <div class="column">

functions.py

@@ -8,7 +8,7 @@ import io
 import base64
 
 def SigFigs(number, n):
-
+    if number == 0: return number
     return round(number, n - int(math.floor(math.log10(math.fabs(number)))) - 1)
 
 def Piringer(Mw, Ap):