ChemID update: check for valid smiles before doing other work. quantity module updates: added effect of swelling on solvent volume; added check for non-physical amount of swelling; updated error templates to be more informative

ChemID.py

@@ -22,6 +22,8 @@ with open('data/salt_list.txt', 'r') as fp:
     lines = fp.readlines()
 SALT_SET = {line.strip() for line in lines}
 
+ERROR_CODES = {0:None, 1:'Structure could not be determined from the identifier', 2:'Invalid SMILES code', 3:'Invalid CAS number', 4:'Invalid identifier type selected'}
+
 ## not sure if this will be possible on pythonanywhere; use this flag to disable related code blocks
 try_dsstox = True
 if try_dsstox:
@@ -136,17 +138,6 @@ def ResolveChemical(chemName, IDtype, debug=False, get_properties=['logp','rho',
     elif IDtype == 'SMILES':
         smiles = chemName
 
-        name = smiles2name(smiles)
-        if name:
-            cas = name2cas(name)
-            if 'rho' in get_properties:
-                rho, rho_origin = string2density(name)
-        if 'rho' in get_properties and pd.isna(rho) and cas:
-            rho, rho_origin = string2density(cas)
-
-        if 'mp' in get_properties:
-            mp, mp_origin = mol2mp(cas, name, smiles)
-
         try:
             mol = Chem.MolFromSmiles(smiles)
         except:
@@ -159,6 +150,19 @@ def ResolveChemical(chemName, IDtype, debug=False, get_properties=['logp','rho',
             im64 = Imageto64(im)
         else:
             error = 2
+
+        # if SMILES is not valid, skip the other stuff
+        if not error:
+            name = smiles2name(smiles)
+            if name:
+                cas = name2cas(name)
+                if 'rho' in get_properties:
+                    rho, rho_origin = string2density(name)
+            if 'rho' in get_properties and pd.isna(rho) and cas:
+                rho, rho_origin = string2density(cas)
+
+            if 'mp' in get_properties:
+                mp, mp_origin = mol2mp(cas, name, smiles)
     elif IDtype == 'common':
         name = chemName
 

quantity_module/functions.py

@@ -76,6 +76,8 @@ for solv in df_visc['Solvent_Name']:
 df_visc['MW'] = mws
 ## selected solvent MWs
 Solvent_MWs = {solv:df_visc.loc[df_visc['Solvent_Name']==solv,'MW'].iloc[0] for solv in solvents}
+#Solvent_Densities = {solv:string2density(solv)[0] for solv in solvents}
+Solvent_Densities = {'ethanol': 0.79, 'isopropanol': 0.787515, 'acetonitrile': 0.78467, 'toluene': 0.86925, 'dichloromethane': 1.326875, 'hexane': 0.6602}
 # linear relation to estimate Vabc when it fails for a molecule
 Vabc = df_desc['Vabc']
 Vmcg = df_desc['VMcGowan']
@@ -259,10 +261,11 @@ def get_D_dists(w,T,Polymer_Tg,Solvent_Name,Solvent_MW,Solute_MW,CHRIS_category,
     else:
         return D_dist_noswell, D_dist_swell
 
-def PlaneSheetFiniteBathMass(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms):
+def PlaneSheetFiniteBathMass(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms,Qv=1):
     ### works with scalar- or vector-valued M0 and D
     L = PolymerVolume/SurfaceArea #effective length scale of the component
-    alpha = SolventVolume/PolymerVolume/K
+    #alpha = SolventVolume/PolymerVolume/K
+    alpha = (SolventVolume-PolymerVolume*(Qv-1))/(Qv*PolymerVolume*K)
     Minfty = M0/(1.+1./(alpha))
     eps = 1e-12
     f = lambda x: np.tan(x)+alpha*x
@@ -276,10 +279,10 @@ def PlaneSheetFiniteBathMass(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,Extr
     result = Minfty*result
     return result
 
-def PlaneSheetFiniteBathMassApprox(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime):
+def PlaneSheetFiniteBathMassApprox(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,Qv=1):
     ### works with scalar- or vector-valued M0 and D
     L = PolymerVolume/SurfaceArea #effective length scale of the component
-    alpha = SolventVolume/PolymerVolume/K
+    alpha = (SolventVolume-PolymerVolume*(Qv-1))/(Qv*PolymerVolume*K)
     Minfty = M0/(1.+1./(alpha))
     T = D*ExtractionTime/L**2.
     # if exp will blow up, use asymptotic expansion instead
@@ -297,15 +300,15 @@ def PlaneSheetFiniteBathMassApprox(M0,D,K,PolymerVolume,SurfaceArea,SolventVolum
     result = Minfty*result
     return result
 
-def PlaneSheetAnalytical(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms=5):
+def PlaneSheetAnalytical(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms=5,Qv=1):
     L = PolymerVolume/SurfaceArea #effective length scale of the component
     T = D*ExtractionTime/L**2.
-    result = (T>0.05) *  PlaneSheetFiniteBathMass(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms) + \
-             (T<=0.05) * PlaneSheetFiniteBathMassApprox(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime)
+    result = (T>0.05) *  PlaneSheetFiniteBathMass(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,nterms,Qv=Qv) + \
+             (T<=0.05) * PlaneSheetFiniteBathMassApprox(M0,D,K,PolymerVolume,SurfaceArea,SolventVolume,ExtractionTime,Qv=Qv)
     return result
 
-def get_M_dist(D_dist, M_expt, PolymerVolume, SurfaceArea, SolventVolume, ExtractionTime, K_expt=10):
-    M_M0 = PlaneSheetAnalytical(1.0, D_dist, K_expt, PolymerVolume, SurfaceArea, SolventVolume, ExtractionTime, nterms=5) # much faster and indistinguishable distribution from Mfunc_film
+def get_M_dist(D_dist, M_expt, PolymerVolume, SurfaceArea, SolventVolume, ExtractionTime, K_expt=10, Qv=1):
+    M_M0 = PlaneSheetAnalytical(1.0, D_dist, K_expt, PolymerVolume, SurfaceArea, SolventVolume, ExtractionTime, nterms=5, Qv=Qv) # much faster and indistinguishable distribution from Mfunc_film
     M0_pred = M_expt/M_M0
     return M0_pred
 

quantity_module/quantity.py

@@ -42,7 +42,7 @@ def exp_post():
     CHRIS_category = None
 
     if T<Polymer_Tg:
-        return render_template('quantity_temperatureError.html')
+        return render_template('quantity_error.html', message='Unfortunately, the CHRIS-Total Quantity module can only be used for polymers with glass transition temperatures lower than the extraction temperature.')
 
     chemName = request.form['chemName']
     IDtype = request.form['IDtype']
@@ -56,7 +56,7 @@ def exp_post():
 
     if error > 0:
         # TODO output more useful info
-        return render_template('quantity_chemError.html')
+        return render_template('quantity_error.html', message=f'Uh-oh! Something went wrong. We were unable to match your chemical. Please return to the previous page and try a different identifier. <br><br>Error code: {error} <br>Error message: {ERROR_CODES[error]} ')
 
     #MW = SigFigs(MW, 6)
     if 'logp' not in get_properties:
@@ -102,8 +102,17 @@ def exp_post():
     Extraction_Time = float(request.form['time']) 
     K_expt = float(request.form['K']) 
     Solvent_MW = Solvent_MWs[Solvent_Name]
+    Solvent_Density = Solvent_Densities[Solvent_Name]
     Solute_MW = MW
 
+    ## extent of swelling, V_swelled/V_unswelled
+    Swelling_volfrac = Polymer_Density / (Solvent_Density * (1/Swelling_wtfrac-1) + Polymer_Density)
+    Qv = 1+Swelling_volfrac/(1-Swelling_volfrac)
+    # TODO check that swelling is physically possible
+    if Solvent_Volume < Polymer_Volume*(Qv-1):
+        return render_template('quantity_error.html', message=f'Based on the information provided, the amount of swelling appears physically impossible. Please check the values you entered.')
+        #return render_template('quantity_error.html', message=f'Based on the swelling weight percent ({Swelling_percent}%), the polymer density ({Polymer_Density} g/cm<sup>3</sup>), and the solvent density ({Solvent_Density} g/cm<sup>3</sup>), the   polymer volume ({Polymer_Volume} cm<sup>3</sup>), ')
+
     if units == 'mg':
         mass_units = mass*1e3
     elif units == 'µg':
@@ -129,11 +138,11 @@ def exp_post():
             # outside training domain, default to Wilke-Chang
             method = 'qrf/wc'
             D_dist_noswell, D_dist_swell = get_D_dists(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, 'G2', rng, return_DCs=False, N=N_sample)
-            M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt)
+            M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt, Qv=Qv)
         else:
             method = 'qrf'
             D_dist_noswell, D_dist_swell = get_D_dists(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, None, rng, return_DCs=False, N=N_sample, input_Ds=diff)
-            M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt)
+            M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt, Qv=Qv)
     else:
         ## use categories
         CHRIS_category = categories[pIndex]
@@ -143,7 +152,7 @@ def exp_post():
             CHRIS_flag = 'wc'
             CHRIS_category = 'G2'
         D_dist_noswell, D_dist_swell = get_D_dists(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, CHRIS_category, rng, return_DCs=False, N=N_sample)
-        M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt)
+        M0_pred = get_M_dist(D_dist_swell, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt, Qv=Qv)
         if CHRIS_flag is None:
             method = 'category'
         else:
@@ -154,11 +163,11 @@ def exp_post():
         print(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, CHRIS_category)
         print(np.nanquantile(D_dist_noswell, [0.05,0.5,0.95]))
         print(np.nanquantile(D_dist_swell, [0.05,0.5,0.95]))
-        print('M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method')
-        print(M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method)
+        print('M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method, Qv, Swelling_volfrac')
+        print(M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt, method, Qv, Swelling_volfrac)
         print(np.nanquantile(M0_pred, [0.05,0.5,0.95]))
         V1,V2 = get_D_dists(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, 'G2', rng, return_DCs=False, N=N_sample)
-        V3 = get_M_dist(V2, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt)
+        V3 = get_M_dist(V2, M_expt, Polymer_Volume, Surface_Area, Solvent_Volume, Extraction_Time*3600, K_expt=K_expt, Qv=Qv)
         print(np.nanquantile(V2, [0.05,0.5,0.95]))
         print(np.nanquantile(V3, [0.05,0.5,0.95]))
 

quantity_module/templates/quantity_error.html

@@ -0,0 +1,23 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <title>CHRIS-Error</title>
+    <link rel= "stylesheet" type= "text/css" href= "{{ url_for('static',filename='styles.css') }}">
+
+</head>
+
+<img src="{{ url_for('static',filename='images/FDAlogo.png') }}" style="float: left;" height="100"/>
+<img src="{{ url_for('static',filename='images/FDAgraphic.png') }}" style="float: right;"  height="100"/>
+<br clear="all" />
+
+<body>
+
+<div style="font-size:5rem;text-align:center"> &#129318; </div>
+
+<p style="font-size:2rem;text-align:center">
+{{ message|safe }}
+</p>
+
+
+</body>