File size: 4,874 Bytes
2548c76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
faf2fff
1b34a4c
 
 
faf2fff
2062064
2548c76
3aff373
2062064
554cc90
2548c76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f83527e
6e92bdc
 
 
 
 
 
5d320ee
3aff373
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
import os
import gc
import random
import warnings
warnings.filterwarnings('ignore')
import numpy as np
import pandas as pd
import torch
import tokenizers
import transformers
from transformers import AutoTokenizer, EncoderDecoderModel, AutoModelForSeq2SeqLM
import sentencepiece
from rdkit import Chem
import rdkit
import streamlit as st

st.title('predictproduct-t5')
st.markdown('### At this space, you can predict the products of reactions from their inputs.')
st.markdown('### The format of the string is like "REACTANT:{reactants of the reaction}CATALYST:{catalysts of the reaction}REAGENT:{reagents of the reaction}SOLVENT:{solvent of the reaction}".')
st.markdown('### If there are no catalyst or reagent, fill the blank with a space. And if there are multiple reactants, concatenate them with "."')
display_text = 'input the reaction smiles (e.g. REACTANT:CNc1nc(SC)ncc1CO.O.O=[Cr](=O)([O-])O[Cr](=O)(=O)[O-].[Na+]CATALYST: REAGENT: SOLVENT:CC(=O)O)'

class CFG():
    uploaded_file = st.file_uploader("Choose a CSV file")
    input_data = st.text_area(display_text)
    model_name_or_path = 'sagawa/ZINC-t5-productpredicition'
    model = 't5'
    num_beams = 5
    num_return_sequences = 5
    seed = 42


device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

def seed_everything(seed=42):
    random.seed(seed)
    os.environ['PYTHONHASHSEED'] = str(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    torch.cuda.manual_seed(seed)
    torch.backends.cudnn.deterministic = True
seed_everything(seed=CFG.seed) 


tokenizer = AutoTokenizer.from_pretrained(CFG.model_name_or_path, return_tensors='pt')
    
if CFG.model == 't5':
    model = AutoModelForSeq2SeqLM.from_pretrained(CFG.model_name_or_path).to(device)
elif CFG.model == 'deberta':
    model = EncoderDecoderModel.from_pretrained(CFG.model_name_or_path).to(device)


if CFG.uploaded_file is not None:
    input_data = pd.read_csv(CFG.uploaded_file)
    outputs = []
    for idx, row in input_data.iterrows():
        input_compound = row['input']
        min_length = min(input_compound.find('CATALYST') - input_compound.find(':') - 10, 0)
        inp = tokenizer(input_compound, return_tensors='pt').to(device)
        output = model.generate(**inp, min_length=min_length, max_length=min_length+50, num_beams=CFG.num_beams, num_return_sequences=CFG.num_return_sequences, return_dict_in_generate=True, output_scores=True)
        scores = output['sequences_scores'].tolist()
        output = [tokenizer.decode(i, skip_special_tokens=True).replace('. ', '.').rstrip('.') for i in output['sequences']]
        for ith, out in enumerate(output):
            mol = Chem.MolFromSmiles(out.rstrip('.'))
            if type(mol) == rdkit.Chem.rdchem.Mol:
                output.append(out.rstrip('.'))
                scores.append(scores[ith])
                break
        if type(mol) == None:
            output.append(None)
            scores.append(None)
        output += scores
        output = [input_compound] + output
        outputs.append(output)

    output_df = pd.DataFrame(outputs, columns=['input'] + [f'{i}th' for i in range(CFG.num_beams)] + ['valid compound'] + [f'{i}th score' for i in range(CFG.num_beams)] + ['valid compound score'])
    
    @st.cache
    def convert_df(df):
        # IMPORTANT: Cache the conversion to prevent computation on every rerun
        return df.to_csv(index=False).encode('utf-8')
    
    output_df = convert_df(output_df)
    
    st.download_button(
        label="Download data as CSV",
        data=output_df,
        file_name=input_data + '_result.csv',
        mime='text/csv',
    )

else:
    input_compound = CFG.input_data
    min_length = min(input_compound.find('CATALYST') - input_compound.find(':') - 10, 0)
    inp = tokenizer(input_compound, return_tensors='pt').to(device)
    output = model.generate(**inp, min_length=min_length, max_length=min_length+50, num_beams=CFG.num_beams, num_return_sequences=CFG.num_return_sequences, return_dict_in_generate=True, output_scores=True)
    scores = output['sequences_scores'].tolist()
    output = [tokenizer.decode(i, skip_special_tokens=True).replace('. ', '.').rstrip('.') for i in output['sequences']]
    for ith, out in enumerate(output):
        mol = Chem.MolFromSmiles(out.rstrip('.'))
        if type(mol) == rdkit.Chem.rdchem.Mol:
            output.append(out.rstrip('.'))
            scores.append(scores[ith])
            break
    if type(mol) == None:
        output.append(None)
        scores.append(None)
    output += scores
    output = [input_compound] + output
    try:
        output_df = pd.DataFrame(np.array(output).reshape(1, -1), columns=['input'] + [f'{i}th' for i in range(CFG.num_beams)] + ['valid compound'] + [f'{i}th score' for i in range(CFG.num_beams)] + ['valid compound score'])
        st.table(output_df)
    except:
        pass