Upload 3 files

app.py

@@ -0,0 +1,73 @@
+import streamlit as st
+import pandas as pd
+import rdkit
+import streamlit_ketcher
+from streamlit_ketcher import st_ketcher
+import run
+import screen
+
+# Page setup
+st.set_page_config(page_title="DeepDAP", page_icon="🔋", layout="wide")
+st.title("🔋DeepDAP")
+st.subheader('',divider='rainbow')
+# Connect to the Google Sheet
+
+url1= r"https://docs.google.com/spreadsheets/d/1AKkZS04VF3osFT36aNHIb4iUbV8D1uNfsldcpHXogj0/gviz/tq?tqx=out:csv&sheet=dap"
+df1 = pd.read_csv(url1, dtype=str, encoding='utf-8')
+col1, col2 = st.columns(2)
+with col1:
+	st.header("🔍**Search papers or molecules**")
+	text_search = st.text_input(label="_", value="",label_visibility="hidden" )
+	m1 = df1["Donor_Name"].str.contains(text_search)
+	m2 = df1["reference"].str.contains(text_search)
+	m3 = df1["Acceptor_Name"].str.contains(text_search)
+	df_search = df1[m1 | m2|m3]
+with col2:
+	st.link_button(":black[📝**DATABASE**]",  r"https://docs.google.com/spreadsheets/d/1AKkZS04VF3osFT36aNHIb4iUbV8D1uNfsldcpHXogj0")
+	st.caption(':black[👆If you want to update the origin database, click the button.]')
+if text_search:
+    st.write(df_search)
+    st.download_button( "⬇️Download edited files as .csv", df_search.to_csv(), "df_search.csv", use_container_width=True)
+edited_df = st.data_editor(df1, num_rows="dynamic")
+
+st.download_button(
+    "⬇️ Download edited files as .csv", edited_df.to_csv(), "edited_df.csv", use_container_width=True
+)
+st.subheader("👇 :red[***Select the type of active layer...***]")
+option = st.radio(
+ "👇 :red[**Select the type of active layer...**]",
+   [":black[**Donor**]", ":black[**Acceptor**]"], label_visibility="hidden"
+)
+if option ==":black[**Acceptor**]":
+	st.subheader("👨‍🔬**Input the SMILES of Acceptor Molecule**")
+	molecule = st.text_input("👨‍🔬**Input the SMILES of Acceptor Molecule**", label_visibility="hidden" )
+	acceptor= st_ketcher(molecule )
+	st.subheader(f"🏆**New SMILES of edited acceptor molecules**: {acceptor}")
+	st.subheader(":black[**🧡Input the SMILES of Donor Molecule**]")
+	donor= st.text_input(":black[**🧡Input the SMILES of Donor Molecule**]", label_visibility="hidden")
+if option ==":black[**Donor**]":
+	st.subheader("👨‍🔬**Input the SMILES of Donor Molecule**" )
+	do= st.text_input("👨‍🔬**Input the SMILES of Donor Molecule**" , label_visibility="hidden")
+	donor = st_ketcher(do)
+	st.subheader(f"🏆**New SMILES of edited donor molecules**: {donor}")
+	st.subheader(":black[**🧡Input the SMILES of Acceptor Molecule**]")
+	acceptor = st.text_input(":black[**🧡Input the SMILES of Acceptor Molecule**]", label_visibility="hidden")
+try:
+ 
+    pce = run.smiles_aas_test( str(acceptor ), str(donor) )
+    st.subheader(f"⚡**PCE**: ``{pce}``")
+except:
+    st.subheader(f"⚡**PCE**:  None  ")
+st.subheader(":black[**🧡Batch screening for high-performance D/A pairs**]")
+uploaded_files = st.file_uploader("Choose a CSV file")
+st.write( "🎈upload a csv file containing ['donor' ] and ['acceptor']")
+if st.button("📑PREDICT"):
+	if uploaded_files is not None:
+		text = st.markdown(":red[Predictions are being made... Please wait...]")
+		st.progress(100, text=None)
+		x = screen.smiles_aas_test(uploaded_files )	
+		x = pd.DataFrame(x)
+		
+		st.download_button( "⬇️Download  the predicted files as .csv", x.to_csv(), "predict results.csv", use_container_width=True)
+	else:
+		st.markdown(":red[Please upload the file first!]")

run.py

@@ -0,0 +1,124 @@
+import os
+import pandas as pd
+
+import torch
+from torch.nn import functional as F
+from transformers import AutoTokenizer
+
+from util.utils import *
+from rdkit import Chem
+from tqdm import tqdm
+from train import markerModel
+
+os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = '0 '
+
+device_count = torch.cuda.device_count()
+device_biomarker = torch.device('cuda' if torch.cuda.is_available() else "cpu")
+
+device = torch.device('cpu')
+a_model_name = 'DeepChem/ChemBERTa-10M-MLM'
+d_model_name = 'DeepChem/ChemBERTa-10M-MTR'
+
+tokenizer = AutoTokenizer.from_pretrained(a_model_name)
+d_tokenizer = AutoTokenizer.from_pretrained(d_model_name)
+
+#--biomarker Model
+##-- hyper param config file Load --##
+config = load_hparams('config/predict.json')
+config = DictX(config)
+model = markerModel(config.d_model_name, config.p_model_name,
+                              config.lr, config.dropout, config.layer_features, config.loss_fn, config.layer_limit, config.pretrained['chem'], config.pretrained['prot'])
+ 
+model = markerModel.load_from_checkpoint(config.load_checkpoint,strict=False)
+model.eval()
+model.freeze()
+    
+if device_biomarker.type == 'cuda':
+    model = torch.nn.DataParallel(model)
+    
+def get_marker(drug_inputs, prot_inputs):
+    output_preds = model(drug_inputs, prot_inputs)
+   
+    predict = torch.squeeze( (output_preds)).tolist()
+
+    # output_preds = torch.relu(output_preds)
+    # predict = torch.tanh(output_preds)
+    # predict = predict.squeeze(dim=1).tolist()
+
+    return predict
+
+
+def marker_prediction(smiles, aas):
+    try:
+        aas_input = []
+        for ass_data in aas:
+            aas_input.append(' '.join(list(ass_data)))
+    
+        a_inputs = tokenizer(smiles, padding='max_length', max_length=510, truncation=True, return_tensors="pt")
+        # d_inputs = tokenizer(smiles, truncation=True, return_tensors="pt")
+        a_input_ids = a_inputs['input_ids'].to(device)
+        a_attention_mask = a_inputs['attention_mask'].to(device)
+        a_inputs = {'input_ids': a_input_ids, 'attention_mask': a_attention_mask}
+
+        d_inputs = d_tokenizer(aas_input, padding='max_length', max_length=510, truncation=True, return_tensors="pt")
+        # p_inputs = prot_tokenizer(aas_input, truncation=True, return_tensors="pt")
+        d_input_ids = d_inputs['input_ids'].to(device)
+        d_attention_mask = d_inputs['attention_mask'].to(device)
+        d_inputs = {'input_ids': d_input_ids, 'attention_mask': d_attention_mask}
+ 
+        output_list = get_marker(a_inputs, d_inputs)
+        
+      
+        return output_list
+
+    except Exception as e:
+        print(e)
+        return {'Error_message': e}
+
+
+def smiles_aas_test(smile_acc,smile_don):
+    
+    mola =  Chem.MolFromSmiles(smile_acc) 
+    smile_acc = Chem.MolToSmiles(mola,   canonical=True)
+    mold =  Chem.MolFromSmiles(smile_don)  
+    smile_don = Chem.MolToSmiles(mold, canonical=True)
+
+    batch_size = 1
+ 
+    datas = []
+    marker_list = []
+    marker_datas = []
+
+    
+     
+    marker_datas.append([smile_acc,smile_don])
+    if len(marker_datas) == batch_size:
+            marker_list.append(list(marker_datas))
+            marker_datas.clear()
+
+    if len(marker_datas) != 0:
+        marker_list.append(list(marker_datas))
+        marker_datas.clear()
+        
+    for marker_datas in tqdm(marker_list, total=len(marker_list)):
+        smiles_d , smiles_a  = zip(*marker_datas)
+        output_pred = marker_prediction(list(smiles_d), list(smiles_a) )
+        if len(datas) == 0:
+            datas = output_pred
+        else:
+            datas = datas + output_pred
+    
+    # ## -- Export result data to csv -- ##
+    # df = pd.DataFrame(datas)
+    # df.to_csv('./results/predictData_nontonon_bindingdb_test.csv', index=None)
+
+    # print(df)
+    return datas
+        
+ 
+
+if __name__ == '__main__':
+    
+    a = smiles_aas_test('CCCCCCCCCCCC1=C(/C=C2\C(=O)C3=C(C=C(F)C(F)=C3)C2=C(C#N)C#N)SC2=C1SC1=C2N(CC(CC)CCCC)C2=C1C1=NSN=C1C1=C2N(CC(CC)CCCC)C2=C1SC1=C2SC(/C=C2\C(=O)C3=C(C=C(F)C(F)=C3)C2=C(C#N)C#N)=C1CCCCCCCCCCC','CCCCCCC(CCCC)CC1=C(C)SC(C2=CC3=C(S2)C2=C(C=C(C4=CC(CC(CCCC)CCCCCC)=C(C5=CC6=C(C7=CC=C(CC(CC)CCCC)S7)C7=C(C=C(C)S7)C(C7=CC=C(CC(CC)CCCC)S7)=C6S5)S4)S2)C2=NSN=C23)=C1')                         
+    

screen.py

@@ -0,0 +1,120 @@
+import os
+import pandas as pd
+
+import torch
+from torch.nn import functional as F
+from transformers import AutoTokenizer
+
+from util.utils import *
+
+from tqdm import tqdm
+from train import markerModel
+
+os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"] = '0 '
+
+device_count = torch.cuda.device_count()
+device_biomarker = torch.device('cuda' if torch.cuda.is_available() else "cpu")
+
+device = torch.device('cpu')
+a_model_name = 'DeepChem/ChemBERTa-10M-MLM'
+d_model_name = 'DeepChem/ChemBERTa-10M-MTR'
+
+tokenizer = AutoTokenizer.from_pretrained(a_model_name)
+d_tokenizer = AutoTokenizer.from_pretrained(d_model_name)
+
+#--biomarker Model
+##-- hyper param config file Load --##
+config = load_hparams('config/predict.json')
+config = DictX(config)
+model = markerModel(config.d_model_name, config.p_model_name,
+                              config.lr, config.dropout, config.layer_features, config.loss_fn, config.layer_limit, config.pretrained['chem'], config.pretrained['prot'])
+ 
+model = markerModel.load_from_checkpoint(config.load_checkpoint,strict=False)
+model.eval()
+model.freeze()
+    
+if device_biomarker.type == 'cuda':
+    model = torch.nn.DataParallel(model)
+    
+def get_marker(drug_inputs, prot_inputs):
+    output_preds = model(drug_inputs, prot_inputs)
+   
+    predict = torch.squeeze( (output_preds)).tolist()
+
+    # output_preds = torch.relu(output_preds)
+    # predict = torch.tanh(output_preds)
+    # predict = predict.squeeze(dim=1).tolist()
+
+    return predict
+
+
+def marker_prediction(smiles, aas):
+    try:
+        aas_input = []
+        for ass_data in aas:
+            aas_input.append(' '.join(list(ass_data)))
+    
+        a_inputs = tokenizer(smiles, padding='max_length', max_length=510, truncation=True, return_tensors="pt")
+        # d_inputs = tokenizer(smiles, truncation=True, return_tensors="pt")
+        a_input_ids = a_inputs['input_ids'].to(device)
+        a_attention_mask = a_inputs['attention_mask'].to(device)
+        a_inputs = {'input_ids': a_input_ids, 'attention_mask': a_attention_mask}
+
+        d_inputs = d_tokenizer(aas_input, padding='max_length', max_length=510, truncation=True, return_tensors="pt")
+        # p_inputs = prot_tokenizer(aas_input, truncation=True, return_tensors="pt")
+        d_input_ids = d_inputs['input_ids'].to(device)
+        d_attention_mask = d_inputs['attention_mask'].to(device)
+        d_inputs = {'input_ids': d_input_ids, 'attention_mask': d_attention_mask}
+ 
+        output_predict = get_marker(a_inputs, d_inputs)
+        
+        output_list = [{'acceptor': smiles[i], 'donor': aas[i], 'predict': output_predict[i]} for i in range(0,len(aas))]
+
+        return output_list
+
+    except Exception as e:
+        print(e)
+        return {'Error_message': e}
+
+
+def smiles_aas_test(file):
+     
+    batch_size = 80
+    try:
+        datas = []
+        marker_list = []
+        marker_datas = []
+
+        smiles_aas = pd.read_csv(file)
+        
+        ## -- 1 to 1 pair predict check -- ##
+        for data in smiles_aas.values:
+            mola =  Chem.MolFromSmiles(data[2]) 
+            data[2] = Chem.MolToSmiles(mola,   canonical=True)
+            mola =  Chem.MolFromSmiles(data[1]) 
+            data[1] = Chem.MolToSmiles(mola,   canonical=True)                        
+            marker_datas.append([data[2], data[1]])
+            if len(marker_datas) == batch_size:
+                marker_list.append(list(marker_datas))
+                marker_datas.clear()
+
+        if len(marker_datas) != 0:
+            marker_list.append(list(marker_datas))
+            marker_datas.clear()
+            
+        for marker_datas in tqdm(marker_list, total=len(marker_list)):
+            smiles_d , smiles_a  = zip(*marker_datas)
+            output_pred = marker_prediction(list(smiles_d), list(smiles_a) )
+            if len(datas) == 0:
+                datas = output_pred
+            else:
+                datas = datas + output_pred
+        datas = pd.DataFrame(datas)
+ 
+        return datas
+        
+    except Exception as e:
+        print(e)
+        return {'Error_message': e}
+