implemented OPERA melting point prediction

CHRIS.py

@@ -1,4 +1,5 @@
 from flask import Flask, render_template
+from functions import weight_func
 
 app = Flask(__name__)
 app.debug = False

ChemID.py

@@ -6,7 +6,6 @@ import pandas as pd
 import numpy as np
 import pubchempy as pcp
 import cirpy
-
 import chemicals
 
 import bs4
@@ -62,6 +61,25 @@ dfmp_expt = pd.read_csv('PHYSPROP_MP_data.tsv', sep='\t')
 #df_pred = pd.read_excel('Comptox_pred_data.xlsx')
 df_pred = pd.read_csv('Comptox_pred_data.tsv', sep='\t')
 
+## OPERA melting point model
+import pickle
+import sklearn
+import sklearn.neighbors
+import sklearn.metrics
+import padelpy
+from functions import weight_func
+class opera_data_mp():
+    n_neighbors = 5
+    weight_factor = 5e-3
+    desc_list = ['SHBd', 'nN', 'maxHBd', 'ATSC1v', 'AATS1i', 'TopoPSA', 'nT6Ring', 'nHBDon', 'WTPT-5', 'minHBd', 'nHBint2', 'IC0', 'MLFER_S', 'MLFER_BO', 'WTPT-3']
+    with open('mp/model-opera-knn.pkl', 'rb') as fp:
+        knn_all = pickle.load(fp)
+    with open('mp/model-opera-scalerX.pkl', 'rb') as fp:
+        scaler_X = pickle.load(fp)
+    with open('mp/model-opera-scalerY.pkl', 'rb') as fp:
+        scaler_y = pickle.load(fp)
+my_opera_data_mp = opera_data_mp()
+
 def ResolveChemical(chemName, IDtype, debug=False, get_properties=['logp','rho','mp']):
 
     #LogP_func = Crippen.MolLogP
@@ -914,7 +932,7 @@ def compute_phys_properties(smiles):
         AmorphSolub_2 = None
     return MeltingPoint-273.15
 
-def string2mp(name):
+def string2mp(name, namespace='name'):
     mp, mp_origin = None, None
     # try the chemicals package
     if is_cas(name):
@@ -950,7 +968,7 @@ def string2mp(name):
     if pd.isna(mp):
         content = None
         try:
-            compounds = pcp.get_compounds(name, namespace='name')
+            compounds = pcp.get_compounds(name, namespace=namespace)
             c = compounds[0]
             cid = c.cid
             url = f'https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON'
@@ -975,7 +993,7 @@ def string2mp(name):
                                             #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)
+                                            m = re.match('(-?(?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?( ?°?C)',mp_string)
                                             if m is not None:
                                                 groups = m.groups()
                                                 if len(groups):
@@ -985,7 +1003,7 @@ def string2mp(name):
                                                             mp_list.append(tmp_mp)
                                                         except:
                                                             continue
-                                            m = re.match('((?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?( ?°?F)',mp_string)
+                                            m = re.match('(-?(?:\d+(?:\.\d*)?|\.\d+))(?:-((?:\d+(?:\.\d*)?|\.\d+)))?( ?°?F)',mp_string)
                                             if m is not None:
                                                 groups = m.groups()
                                                 if len(groups):
@@ -1095,6 +1113,16 @@ def smiles2mp(smiles):
         mp = None
     return mp
 
+def smiles2mp_opera(smiles):
+    descs = padelpy.from_smiles(smiles, descriptortypes='mp/descriptors.xml')
+    dfd = pd.DataFrame(descs,index=[0])
+    dfd = dfd.replace('',0)
+    dfd = pd.DataFrame(dfd, dtype=float)
+    X = np.array(dfd[my_opera_data_mp.desc_list])
+    X_scale = my_opera_data_mp.scaler_X.transform(X)
+    y_pred = my_opera_data_mp.scaler_y.inverse_transform(my_opera_data_mp.knn_all.predict(X_scale))
+    return y_pred[0][0]
+
 def mol2mp(cas, name, smiles):
     mp, mp_origin = None, None
     if cas:
@@ -1113,6 +1141,12 @@ def mol2mp(cas, name, smiles):
             mp_origin = 'joback-reid/calc'
         except:
             mp, mp_origin = None, None
+    if pd.isna(mp) and smiles:
+        try:
+            mp = smiles2mp_opera(smiles)
+            mp_origin = 'opera/calc'
+        except:
+            mp, mp_origin = None, None
     return mp, mp_origin
 
 def getLogP(cas,mol):

color2_module/colors.py

@@ -5,7 +5,7 @@ from functions import SigFigs, Piringer, WilkeChang, SheetRelease, SheetRates, R
 from functions import Piecewise, PowerLaw
 from . import blueprint
 from polymers import Polymers, Polymers3
-from ChemID import ResolveChemical, ImageFromSmiles, Imageto64, CeramicOrMetal
+from ChemID import *
 import rdkit
 from rdkit.Chem import AllChem as Chem
 
@@ -98,7 +98,7 @@ def app_post():
     if caIndex == 12:
         isCA = False
 
-    print(chemName)
+    #print(chemName)
 #    if chemName == '68186-90-3':
 #        #IDtype = 'SMILES'
 #        #chemName = 'O=[Ti]=O.O=[Sb]O[Sb](=O)=O.O=[Cr]O[Cr]=O'

color2_module/templates/color2_report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
     <style>

color3_module/colors.py

@@ -7,7 +7,7 @@ from functions import Piecewise, PowerLaw
 from qrf_functions import QRF_Apply, QRF_Ceramic
 from . import blueprint
 from polymers import Polymers, Polymers3
-from ChemID import ResolveChemical, CeramicOrMetal
+from ChemID import *
 import rdkit
 from rdkit.Chem import AllChem as Chem
 

color3_module/templates/color3_report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
     <style>

color_module/templates/report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
 </head>

exposure2_module/exposure.py

@@ -3,9 +3,9 @@ import numpy as np
 from flask import render_template, request
 from functions import SigFigs, Piringer, WilkeChang, SheetRelease, SheetRates, RatePlot
 from functions import Piecewise, PowerLaw
-from . import blueprint
 from polymers import Polymers, Polymers3
-from ChemID import ResolveChemical, CeramicOrMetal
+from ChemID import *
+from . import blueprint
 
 import rdkit
 from rdkit.Chem import AllChem as Chem

exposure2_module/templates/exposure2_report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
     <style>

exposure3_module/exposure.py

@@ -7,7 +7,7 @@ from functions import Piecewise, PowerLaw
 from qrf_functions import QRF_Apply, QRF_Ceramic
 from . import blueprint
 from polymers import Polymers, Polymers3
-from ChemID import ResolveChemical, CeramicOrMetal
+from ChemID import *
 import rdkit
 from rdkit.Chem import AllChem as Chem
 

exposure3_module/templates/exposure3_report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
     <style>

exposure_module/exposure.py

@@ -1,9 +1,11 @@
 import numpy as np
 from flask import render_template, request
+#from functions import *
 from functions import SigFigs, Piringer, WilkeChang, SheetRelease, SheetRates, RatePlot
-from . import blueprint
+
 from polymers import Polymers
 from ChemID import ResolveChemical
+from . import blueprint
 
 import rdkit
 from rdkit.Chem import AllChem as Chem

exposure_module/templates/exposure_report.html

@@ -5,8 +5,8 @@
     <title>CHRIS Report</title>
 
     <!-- <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script> -->
-    <!-- <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script> -->
-    <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script>
+    <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
+    <!-- <script id="MathJax-script" async src="{{ url_for('static',filename='tex-mml-chtml.js') }}"></script> -->
     <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
 
     <style>

functions.py

@@ -150,6 +150,19 @@ def PowerLaw(Mw, A, B):
     logD = A+logMw*B
     return np.exp(logD)
 
+def weight_func(dists):
+    """
+    Returns the weights, based on the method in OPERA
+    Parameter f controls the maximum weight, prevents 1/dist -> inf
+    Set f to a very small number to mimic default sklearn behavior when dist = 0
+    """
+    #f = 1e-15 # OPERA on CompTox?
+    #f = 5e-2 # OPERA in Matlab code
+    #f = 1e-3 # test
+    f = 5e-3
+    tmp = 1/(f+dists)
+    tmp = tmp/tmp.sum(axis=1)[..., None]
+    return tmp
 
 #def func_piringer(Mw,T,Ap):
 #    if Mw > 1100.: # if molecule is greater than 1100 g/mol, default to that value as worst case