updated quantity module to use category-based sampling where possible

data/db-polymer-properties-and-categories.xlsx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e2cd733617280ef264e2fdc16cfbe97680d7f2b48655c19127b18f9295fd56c
+size 25960

qrf/functions.py

@@ -51,6 +51,7 @@ def QRF_Ceramic(density, polytg, quantiles=[0.03,0.5,0.97], T=37, worstcase='hi'
 
 
 def QRF_Apply(density, polytg, smiles, quantiles=[0.03,0.5,0.97], T=37):
+    """T and Tg in C"""
     nearest_T = QRF_T_list[np.abs(T-QRF_T_list).argmin()]
     with open(f'qrf/qrf_model_bundle_{int(nearest_T)}.pkl','rb') as f:
         reg, imp, scaler_X, sub_desc_list = pickle.load(f)
@@ -123,4 +124,3 @@ def QRF_DomainExtrap(estimator, X_train, X_test, D=0.0, return_features=False):
         return dij, dij_feats
     else:
         return dij
-

quantity_module/functions.py

@@ -27,7 +27,7 @@ T_cut = 20
 MW_cut = 20
 
 use_new = True
-T_cut_new = 0.5 
+T_cut_new = 0.5
 
 #### read data files
 # CHRIS parameter distributions
@@ -67,7 +67,7 @@ else:
     # add volumes
     df_final = pd.merge(df_final, df_desc[['Solute_InChIKey', 'Vabc', 'VMcGowan']], how='left', on='Solute_InChIKey', suffixes=('', '_dupe'))
 
-#### solvent-specific viscosity 
+#### solvent-specific viscosity
 # add MW
 mws = []
 for solv in df_visc['Solvent_Name']:
@@ -146,7 +146,8 @@ else:
         df_final[f'D_WC_{solv}'] = D_WC
         df_final[f'MW_solvent_{solv}'] = MW_solvent
 
-def get_V(mol):
+def get_V(smiles):
+    mol = Chem.MolFromSmiles(smiles)
     calc = mordred.Calculator([mordred.descriptors.VdwVolumeABC, mordred.descriptors.McGowanVolume])
     Vabc,Vmcg = list(calc(mol).values())
     if not isinstance(Vabc, numbers.Number):
@@ -158,10 +159,10 @@ df_vd_solv = pd.read_excel('quantity_module/data/vrentas-duda-params.xlsx', shee
 df_vd_solv.drop_duplicates(keep='first', inplace=True, ignore_index=True) # drop exact duplicates
 df_vd_poly = pd.read_excel('quantity_module/data/vrentas-duda-params.xlsx', sheet_name='Polymers')
 df_vd_poly.drop_duplicates(keep='first', inplace=True, ignore_index=True) # drop exact duplicates
-#df_vd_poly = pd.merge(df_vd_poly, dfp[['Polymer_Name','Polymer_Tg','Polymer_Tm']], how='left', on='Polymer_Name')
-#df_vd_poly = pd.merge(df_vd_poly, df2[['Polymer_Name', 'CHRIS Class', 'New Class']], how='left', on='Polymer_Name')
-#df_vd_poly['New Class'] = df_vd_poly['New Class'].fillna('none')
-#df_vd_poly['CHRIS Class'] = df_vd_poly['CHRIS Class'].fillna('none')
+df_props = pd.read_excel('data/db-polymer-properties-and-categories.xlsx')
+df_vd_poly = pd.merge(df_vd_poly, df_props[['Polymer_Name','Polymer_Tg','Polymer_Tm', 'CHRIS Class', 'New Class']], how='left', on='Polymer_Name')
+df_vd_poly['New Class'] = df_vd_poly['New Class'].fillna('none')
+df_vd_poly['CHRIS Class'] = df_vd_poly['CHRIS Class'].fillna('none')
 
 ## Calculate c
 dfs_vd_allT = []
@@ -191,6 +192,14 @@ def get_c_dist(T,Tg,MW):
     cs = cs[cs>0]
     return cs
 
+def get_c_dist_cat(T,CHRIS_category,MW):
+    m = (~pd.isna(df_vd_allT['c'])) & (df_vd_allT['T-Tg']>0) & (np.abs(df_vd_allT['T']-T)<T_cut) & (np.abs(df_vd_allT['M1']-MW)<MW_cut) & (df_vd_allT['New Class']==CHRIS_category)
+    cs = df_vd_allT.loc[m, 'c']
+    cs = np.array(cs)
+    cs = cs[~np.isnan(cs)]
+    cs = cs[cs>0]
+    return cs
+
 def get_D_dists(w,T,Polymer_Tg,Solvent_Name,Solvent_MW,Solute_MW,CHRIS_category,rng,N=100000,return_DCs=False,input_Ds=None):
     """
     D_dist_noswell, D_dist_swell, (c, Ds, DWCs, DCs) = get_D_dists(Swelling_wtfrac,T,Polymer_Tg,Solvent_Name,Solvent_MW,Solute_MW,CHRIS_category,return_DCs=True,N=N)
@@ -261,6 +270,63 @@ 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 get_D_dists_new(w,T,Polymer_Tg,Solvent_Name,Solvent_MW,Solute_MW,Solute_Vabc,CHRIS_category,rng,N=10000,return_DCs=False,input_Ds=None):
+    """
+    D_dist_noswell, D_dist_swell = get_D_dists_new(w, 323.15, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, None, CHRIS_category, rng, return_DCs=False, N=int(1e5), input_Ds=diff)
+    """
+    df_final_T = df_final.loc[np.abs(df_final['T']-T)<T_cut_new]
+    if (T <= Polymer_Tg) or (input_Ds is not None):
+        cs = get_c_dist(T,Polymer_Tg,Solvent_MW)
+    else:
+        cs = get_c_dist_cat(T,CHRIS_category,Solvent_MW)
+    if not len(cs):
+        cs = get_c_dist(T,Polymer_Tg,Solvent_MW)
+    c = rng.choice(cs, N)
+    if Solute_Vabc is None:
+        if Solute_MW < 50:
+            m50 = df_final_T['MW']<=50
+        else:
+            m50 = df_final_T['MW']>50
+        ## within cutoffs, with at least N closest (by sorting, separating at MW = 50)
+        m2 = (np.abs(df_final_T['Polymer_Tg']-Polymer_Tg)<T_cut) & (np.abs(df_final_T['MW']-Solute_MW)<MW_cut) & m50
+        if m2.sum()<25:
+            vT = df_final_T.loc[m50,'Polymer_Tg']-Polymer_Tg; vM = df_final_T.loc[m50,'MW']-Solute_MW; m3 = pd.concat([np.abs(vT), np.abs(vM)], axis=1).sort_values(by=['Polymer_Tg', 'MW']).index[1:26]
+            m2 = list(set(m2.index[m2]).union(set(m3)))
+        if return_DCs:
+            Ds,DWCs,DCs = rng.choice([df_final_T.loc[m2,'D'], df_final_T.loc[m2,f'D_WC_{Solvent_Name}'], df_final_T.loc[m2,f'D_CHRIS_q50']], N, axis=1)
+        else:
+            Ds,DWCs = rng.choice([df_final_T.loc[m2,'D'], df_final_T.loc[m2,f'D_WC_{Solvent_Name}']], N, axis=1)
+    else:
+        DWCs, eta, MW_solvent = get_WC(T, Solvent_Name, Solute_Vabc)
+    ## distribution of D_CHRIS
+    if input_Ds is None:
+        if Solute_MW > 50:
+            subkey = f'{CHRIS_category}_hi'
+        else:
+            subkey = f'{CHRIS_category}_lo'
+        allparams = [param_dists[Ti][subkey] for Ti in param_dists if T+T_cut_new >= int(Ti)+273.15 >= T-T_cut_new]
+        D_list = []
+        for params in allparams:
+            if params[0] == 'pir':
+                A_list = params[1:]
+                D_list += [Piringer(Solute_MW, Ai, T) for Ai in A_list]
+            else:
+                Ball = params[1]
+                A_list = params[2:]
+                D_list += [PowerLaw(Solute_MW, Ai, Ball) for Ai in A_list]
+    else:
+        D_list = input_Ds
+    D_dist_noswell = rng.choice(D_list, N)
+    if Solute_Vabc is None:
+        lnD_D0 = c*w/(1+(c-1)*w) * np.log(DWCs/Ds)
+    else:
+        lnD_D0 = c*w/(1+(c-1)*w) * np.log(DWCs/D_dist_noswell)
+    D_dist_swell = np.exp(np.log(D_dist_noswell)+lnD_D0)
+    if return_DCs:
+        return D_dist_noswell, D_dist_swell, (c, Ds, DWCs, DCs)
+    else:
+        return D_dist_noswell, D_dist_swell
+
 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
@@ -311,4 +377,3 @@ def get_M_dist(D_dist, M_expt, PolymerVolume, SurfaceArea, SolventVolume, Extrac
     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

@@ -35,7 +35,7 @@ def exposure():
 def exp_post():
 
     Polymer_Tg = float(request.form['Polymer_Tg'])  ## NOTE Tg is provided in C
-    T = float(request.form['T']) 
+    T = float(request.form['T'])
     Polymer_Tg += 273.15
     T += 273.15
     rng = np.random.Generator(np.random.PCG64(seed=12345))
@@ -49,7 +49,7 @@ def exp_post():
 
     if debug:
         iupac, cas, smiles, MW, LogP, LogP_origin, rho, rho_origin, mp, mp_origin, molImage, error = ResolveChemical(chemName, IDtype, debug=debug, get_properties=['logp','rho','mp'])
-        LogP_origin, rho_origin, mp_origin = f' ({LogP_origin})', f' ({rho_origin})', f' ({mp_origin})', 
+        LogP_origin, rho_origin, mp_origin = f' ({LogP_origin})', f' ({rho_origin})', f' ({mp_origin})',
     else:
         LogP_origin, rho_origin, mp_origin = '','',''
         iupac, cas, smiles, MW, LogP, rho, mp, molImage, error = ResolveChemical(chemName, IDtype, get_properties=get_properties)
@@ -81,7 +81,7 @@ def exp_post():
     else:
         is_metal, is_ceramic = CeramicOrMetal(smiles,100)
     if is_metal:
-        return render_template('quantity_metalError.html', show_properties=show_properties, chemName=chemName, MW=MW, 
+        return render_template('quantity_metalError.html', show_properties=show_properties, chemName=chemName, MW=MW,
                                LogP=LogP, rho=rho, mp=mp, iupac=iupac,
                                cas=cas, smiles=smiles, molImage=molImage,
                                LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin)
@@ -89,24 +89,29 @@ def exp_post():
         MW = 1100.
 
     M_expt = float(request.form['amount']) # amount
-    units = request.form['units'] 
+    units = request.form['units']
     mass = float(request.form['mass'])
     Polymer_Density = float(request.form['density'])
     Polymer_Volume = mass / Polymer_Density # vol
     Surface_Area = float(request.form['area']) # area
-    Solvent_Volume = float(request.form['solventvol']) 
-    Solvent_Name = request.form['solventname'] 
-    Swelling_percent = float(request.form['swelling']) 
+    Solvent_Volume = float(request.form['solventvol'])
+    Solvent_Name = request.form['solventname']
+    Swelling_percent = float(request.form['swelling'])
     Swelling_wtfrac = Swelling_percent/100
-    Extraction_Time = float(request.form['time']) 
-    K_expt = float(request.form['K']) 
+    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
+    Solute_Vabc = get_V(smiles)
 
     ## 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)
+    if Swelling_wtfrac > 0:
+        Swelling_volfrac = Polymer_Density / (Solvent_Density * (1/Swelling_wtfrac-1) + Polymer_Density)
+        Qv = 1+Swelling_volfrac/(1-Swelling_volfrac)
+    else:
+        Swelling_volfrac = 0
+        Qv = 1
     # check that swelling is physically possible (swollen polymer volume is less than polymer+solvent volume)
     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.')
@@ -118,6 +123,7 @@ def exp_post():
 
     polymer = request.form['polymer']
 
+    pIndex = np.argmax(polymers == polymer)
     # QRF is implemented for 25-75 C
     if polymer == 'Other polymer':
         use_qrf = True
@@ -128,28 +134,30 @@ def exp_post():
         quantiles = list(np.linspace(0.0,1.0,201))
         #quantiles = list(np.linspace(0.05,0.95,181))
         if is_ceramic:
-            diff,domain_extrap = QRF_Ceramic(Polymer_Density, Polymer_Tg, quantiles=quantiles, T=T-273.15, worstcase='lo')
+            diff,domain_extrap = QRF_Ceramic(Polymer_Density, Polymer_Tg-273.15, quantiles=quantiles, T=T-273.15, worstcase='lo')
         else:
-            diff,domain_extrap = QRF_Apply(Polymer_Density, Polymer_Tg, smiles, quantiles=quantiles, T=T-273.15)
+            diff,domain_extrap = QRF_Apply(Polymer_Density, Polymer_Tg-273.15, smiles, quantiles=quantiles, T=T-273.15)
         if domain_extrap:
             # 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)
+            D_dist_noswell, D_dist_swell = get_D_dists_new(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, Solute_Vabc, 'G2', rng, return_DCs=False, N=N_sample)
+            # 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, 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)
+            D_dist_noswell, D_dist_swell = get_D_dists_new(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, Solute_Vabc, CHRIS_category, rng, return_DCs=False, N=N_sample, input_Ds=diff)
+            #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, Qv=Qv)
     else:
         ## use categories
-        pIndex = np.argmax(polymers == polymer)
         CHRIS_category = categories[pIndex]
         CHRIS_flag = None
         if CHRIS_category is None:
             ## worst-case for a generic polymer --> G2
             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)
+        D_dist_noswell, D_dist_swell = get_D_dists_new(Swelling_wtfrac, T, Polymer_Tg, Solvent_Name, Solvent_MW, Solute_MW, Solute_Vabc, CHRIS_category, rng, return_DCs=False, N=N_sample, input_Ds=None)
+        #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, Qv=Qv)
         if CHRIS_flag is None:
             method = 'category'
@@ -164,10 +172,10 @@ def exp_post():
         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, Qv=Qv)
-        print(np.nanquantile(V2, [0.05,0.5,0.95]))
-        print(np.nanquantile(V3, [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, Qv=Qv)
+        #print(np.nanquantile(V2, [0.05,0.5,0.95]))
+        #print(np.nanquantile(V3, [0.05,0.5,0.95]))
 
     # Generate the rate plot using matplotlib
     #pngImageB64String = CdfPlot(M0_pred[~np.isnan(M0_pred)], units=units)
@@ -192,10 +200,9 @@ def exp_post():
     tau_out = SigFigs(tau,6)
     mass_units = SigFigs(mass_units,6)
 
-    return render_template('quantity_report.html', show_properties=show_properties, polymers=polymers, pIndex=pIndex, 
-                           area=Surface_Area, vol=Polymer_Volume, units=units, M=M_expt, M0=M0_out, time=Extraction_Time, 
+    return render_template('quantity_report.html', show_properties=show_properties, polymers=polymers, pIndex=pIndex,
+                           area=Surface_Area, vol=Polymer_Volume, units=units, M=M_expt, M0=M0_out, time=Extraction_Time,
                            solventvol=Solvent_Volume, solventname=Solvent_Name, swelling=Swelling_percent, K=K_expt, T=T, tau=tau_out,
                            chemName=chemName, MW=MW, LogP=LogP, rho=rho, mp=mp, iupac=iupac, cas=cas, smiles=smiles, molImage=molImage, table=table,
                            LogP_origin=LogP_origin, rho_origin=rho_origin, mp_origin=mp_origin, ceramic=is_ceramic, methods=[method,round(Polymer_Tg-273.15),Polymer_Density],
                            mass=mass, mass_units=mass_units, density=Polymer_Density)
-