compute_descript.py

def compute_descript(smile, walltime=1):
    """                                                                                                                                                                                                                                        
    import random                                                                                                                                                                                                                              
    import time                                                                                                                                                                                                                                
    if random.randint(0,8) == 0:                                                                                                                                                                                                               
        time.sleep(1)                                                                                                                                                                                                                          
    """
    from mordred import Calculator, descriptors
    from rdkit import Chem
    import numpy as np
    import pickle

    calc = Calculator(descriptors, ignore_3D=True) # this object doesn't need to be created everytime. Can make global I think?                                                                                                                

    #read smiles                                                                                                                                                                                                                               
    mol = Chem.MolFromSmiles(smile)
    if mol is None:
        print("Error processing mol")
        return pickle.dumps(None)

    descs = calc(mol)

    data = np.array(descs).flatten().astype(np.float32) #could run in FP16 UNO , something to think about                                                                                                                                      
    # data = descs                                                                                                                                                                                                                             
    return pickle.dumps(data) # We do this to avoid a bug in the serialization routines that Parsl                                                                                                                                             
    # return data                                                                                                                                                                                                                              

if mol is None or len(mol.GetAtoms()) > 100:

try that to filter out biologics