汇总药用数据库(Pubchem,bingdingDB,Chembl,ExcapeDB)数据

记载一下如何汇总4大数据库的数据
上代码:

# -*- coding: utf-8 -*-
"""
Created on Fri Mar 26 19:41:40 2021

@author: recherHE
@Email:recherHE.@163.COM
"""
import pandas as pd
import os,sys




def read_big_csv(input_path):
    """
    

    Parameters
    ----------
    input_path : str
        csc file path

    Returns
    -------
    res_df : pandas.DataFrame
        
    """
    
    df_chunk=pd.read_csv(input_path,chunksize=10000)
    res_chunk=[]
    
    for chunk in df_chunk:
        res_chunk.append(chunk)
    res_df=pd.concat(res_chunk)

    return res_df

def pubchem(pubchem_folder):
    """
    summary pubchem asssay infomation of the folder
    
    Parameters
    ----------
    pubchem_folder : str
        pubchem folder path

    Returns
    -------
    None.

    """
    df_all = pd.DataFrame()
    
    files = os.listdir(pubchem_folder)
    for file in files: 
        try:
            df = pd.read_csv(os.path.join(pubchem_folder,file))
            df.dropna(subset=['SMILES'],inplace=True)              
            df["DB"] = "PUBCHEM"
            df["TYPE"] = df["Standard Type"] 
            if "Standard Value" in df.columns:  
                order = ["PUBCHEM_CID", "DB", "SMILES", "Standard Value","Standard Units", "TYPE"]
                df = df[order]
                
                df_all = pd.concat([df_all,df],ignore_index=True)
                print(f"{file} finished")
        except:
            print(f"{file} failed")

        
    df_all.columns = ["ID", "DB", "SMILES", "ACTIVITY","UNITS", "TYPE"]
    df_all.dropna(inplace=True)
    df_all.to_csv(os.path.join(pubchem_folder,"PUCHEM_SUMMARY.csv"),index =False)
        

def data_summary(Chembl_file,Excape_file,Binding_DB_file,pubchem_folder,outfile):
    """
    summary data of 4 database(Chembl,Excape,Binding_DB,pubchem)

    Parameters
    ----------
    Chembl_file : str
        chembl file path
    Excape_file : str
        Excape file path
    Binding_DB_file : str
        Binding_DB file path
    pubchem_folder : str
        pubchem folder path
    outfile : str
        output file path(csv)

    Returns
    -------
    None.

    """
    
    df_exspace = read_big_csv(Excape_file)
    df_chembl = read_big_csv(Chembl_file)
    df_bindingDB = read_big_csv(Binding_DB_file)
    df_PUBCHEM = read_big_csv(os.path.join(pubchem_folder,"PUCHEM_SUMMARY.csv"))
    
    summary_columns = ["ID", "DB", "SMILES", "ACTIVITY", "UNITS", "TYPE"]
    
    order = ["Original_Entry_ID","DB","SMILES","pXC50"]
    df_exspace = df_exspace[order]
    df_exspace["pXC50"] = df_exspace["pXC50"].map(lambda x: '%.1f' %(10**-x * 10**9))
    df_exspace["UNITS"] = "nM"
    df_exspace["TYPE"] = "IC50"
    df_exspace.columns =  summary_columns
    
    
    
    order_1 = ['monomerid', 'smile', 'affinity', 'affinity_type']
    df_bindingDB = df_bindingDB[order_1]
    df_bindingDB.columns = ["ID","SMILES","ACTIVITY","TYPE"]
    df_bindingDB["DB"] = "BindingDB"
    df_bindingDB["UNITS"] = "nM"
    df_bindingDB["ACTIVITY"] = df_bindingDB["ACTIVITY"].str.replace("<|>", "")
    df_bindingDB.columns =  ["ID", "SMILES", "ACTIVITY", "TYPE", "DB", "UNITS"]
    
    
    order_2 = ['molecule_chembl_id', 'canonical_smiles', 'value', 'units', 'type']
    df_chembl = df_chembl[order_2]
    df_chembl.columns = ["ID", "SMILES", "ACTIVITY", "UNITS" ,"TYPE"]
    df_chembl["DB"] = "CHEMBL"
    df_chembl.columns =  ["ID", "SMILES", "ACTIVITY", "UNITS", "TYPE", "DB"]
    
    df_all = pd.concat([df_exspace,df_bindingDB,df_chembl,df_PUBCHEM],ignore_index=True)   
    df_all.dropna(subset=["SMILES", "ACTIVITY"], inplace=True)
    df_all = df_all.to_csv(outfile,index =False)


def main(argv=[__name__]):
    
    pubchem_folder = sys.argv[1]
    Chembl_file = sys.argv[2]
    Excape_file = sys.argv[3]
    Binding_DB_file = sys.argv[4]
    outfile = sys.argv[5]
    
    pubchem(pubchem_folder)
    data_summary(Chembl_file,Excape_file,Binding_DB_file,pubchem_folder,outfile)
  

if __name__ == '__main__':
    print("""
    ==========================================================================================================================
    Please enter in order {puhcme_folder path} {Chembl file path} {Excape file path} {Binding_DB_file path} {outfile path}
    ==========================================================================================================================
    """)
    
    sys.exit(main(sys.argv))
    

输出结果展示: