基于LSTM的分子生成入门

环境

• Ubuntu18
• RDKit2021.09.2
• Python=3.7

数据集

分子SMILES 字符串，将其转换为词汇数据，并将其转换为表示恒定字符串长度的张量。

import torch
import pandas as pd
from collections import Counter
 
class Dataset(torch.utils.data.Dataset):
    def __init__(self, url, smiles_col, sequence_length=4):
        self.url = url
        self.smiles_col = smiles_col
        self.sequence_length = sequence_length
        self.smiles = []
        self.words = self.load_words()
        self.uniq_words = self.get_uniq_words()
        self.index_to_word = {index: word for index, word in enumerate(self.uniq_words)}
        self.word_to_index = {word: index for index, word in enumerate(self.uniq_words)}
        self.words_indexes = [self.word_to_index[w] for w in sel