get_prediction_results.py

# This source code is licensed under the GPL-3.0 license found in the
# LICENSE file in the root directory of this source tree.

import os
import sys
import csv
import shutil
import pickle
import lmdb
import subprocess
import torch
import argparse
import pandas as pd
import numpy as np
from rdkit import Chem
from tqdm import tqdm
from rdkit import RDLogger
from rdkit.Chem import AllChem
from rdkit.Chem.Scaffolds import MurckoScaffold
import warnings
warnings.filterwarnings(action='ignore')
from multiprocessing import Pool
import json
import os
from functools import lru_cache
from typing import List, Optional, Tuple
import regex as re
from transformers import AddedToken, PreTrainedTokenizer
import logging
from transformers import RobertaTokenizer
logger = logging.getLogger(__name__)


VOCAB_FILES_NAMES = {
    "vocab_file": "vocab.json",
    "merges_file": "merges.txt",
}

PRETRAINED_VOCAB_FILES_MAP = {
    "vocab_file": {
        "roberta-base": "https://huggingface.co/roberta-base/resolve/main/vocab.json",
        "roberta-large": "https://huggingface.co/roberta-large/resolve/main/vocab.json",
        "roberta-large-mnli": "https://huggingface.co/roberta-large-mnli/resolve/main/vocab.json",
        "distilroberta-base": "https://huggingface.co/distilroberta-base/resolve/main/vocab.json",
        "roberta-base-openai-detector": "https://huggingface.co/roberta-base-openai-detector/resolve/main/vocab.json",
        "roberta-large-openai-detector": "https://huggingface.co/roberta-large-openai-detector/resolve/main/vocab.json",
    },
    "merges_file": {
        "roberta-base": "https://huggingface.co/roberta-base/resolve/main/merges.txt",
        "roberta-large": "https://huggingface.co/roberta-large/resolve/main/merges.txt",
        "roberta-large-mnli": "https://huggingface.co/roberta-large-mnli/resolve/main/merges.txt",
        "distilroberta-base": "https://huggingface.co/distilroberta-base/resolve/main/merges.txt",
        "roberta-base-openai-detector": "https://huggingface.co/roberta-base-openai-detector/resolve/main/merges.txt",
        "roberta-large-openai-detector": "https://huggingface.co/roberta-large-openai-detector/resolve/main/merges.txt",
    },
}

PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES = {
    "roberta-base": 512,
    "roberta-large": 512,
    "roberta-large-mnli": 512,
    "distilroberta-base": 512,
    "roberta-base-openai-detector": 512,
    "roberta-large-openai-detector": 512,
}


@lru_cache()
def bytes_to_unicode():
    """
    Returns list of utf-8 byte and a mapping to unicode strings. We specifically avoids mapping to whitespace/control
    characters the bpe code barfs on.

    The reversible bpe codes work on unicode strings. This means you need a large # of unicode characters in your vocab
    if you want to avoid UNKs. When you're at something like a 10B token dataset you end up needing around 5K for
    decent coverage. This is a significant percentage of your normal, say, 32K bpe vocab. To avoid that, we want lookup
    tables between utf-8 bytes and unicode strings.
    """
    bs = (
        list(range(ord("!"), ord("~") + 1)) + list(range(ord("¡"), ord("¬") + 1)) + list(range(ord("®"), ord("ÿ") + 1))
    )
    cs = bs[:]
    n = 0
    for b in range(2**8):
        if b not in bs:
            bs.append(b)
            cs.append(2**8 + n)
            n += 1
    cs = [chr(n) for n in cs]
    return dict(zip(bs, cs))


def get_pairs(word):
    """
    Return set of symbol pairs in a word.

    Word is represented as tuple of symbols (symbols being variable-length strings).
    """
    pairs = set()
    prev_char = word[0]
    for char in word[1:]:
        pairs.add((prev_char, char))
        prev_char = char
    return pairs


class PolymerSmilesTokenizer(PreTrainedTokenizer):
    """Adapt Roberta Tokenizer to PolymerSmilesTokenzier"""

    """
    Original Comments:
    
    Constructs a RoBERTa tokenizer, derived from the GPT-2 tokenizer, using byte-level Byte-Pair-Encoding.

    This tokenizer has been trained to treat spaces like parts of the tokens (a bit like sentencepiece) so a word will
    be encoded differently whether it is at the beginning of the sentence (without space) or not:

    ```
    #>>> from transformers import RobertaTokenizer
    #>>> tokenizer = RobertaTokenizer.from_pretrained("roberta-base")
    #>>> tokenizer("Hello world")['input_ids']
    [0, 31414, 232, 328, 2]
    #>>> tokenizer(" Hello world")['input_ids']
    [0, 20920, 232, 2]
    ```

    You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer or when you
    call it on some text, but since the model was not pretrained this way, it might yield a decrease in performance.

    <Tip>

    When used with `is_split_into_words=True`, this tokenizer will add a space before each word (even the first one).

    </Tip>

    This tokenizer inherits from [`PreTrainedTokenizer`] which contains most of the main methods. Users should refer to
    this superclass for more information regarding those methods.

    Args:
        vocab_file (`str`):
            Path to the vocabulary file.
        merges_file (`str`):
            Path to the merges file.
        errors (`str`, *optional*, defaults to `"replace"`):
            Paradigm to follow when decoding bytes to UTF-8. See
            [bytes.decode](https://docs.python.org/3/library/stdtypes.html#bytes.decode) for more information.
        bos_token (`str`, *optional*, defaults to `"<s>"`):
            The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.

            <Tip>

            When building a sequence using special tokens, this is not the token that is used for the beginning of
            sequence. The token used is the `cls_token`.

            </Tip>

        eos_token (`str`, *optional*, defaults to `"</s>"`):
            The end of sequence token.

            <Tip>

            When building a sequence using special tokens, this is not the token that is used for the end of sequence.
            The token used is the `sep_token`.

            </Tip>

        sep_token (`str`, *optional*, defaults to `"</s>"`):
            The separator token, which is used when building a sequence from multiple sequences, e.g. two sequences for
            sequence classification or for a text and a question for question answering. It is also used as the last
            token of a sequence built with special tokens.
        cls_token (`str`, *optional*, defaults to `"<s>"`):
            The classifier token which is used when doing sequence classification (classification of the whole sequence
            instead of per-token classification). It is the first token of the sequence when built with special tokens.
        unk_token (`str`, *optional*, defaults to `"<unk>"`):
            The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
            token instead.
        pad_token (`str`, *optional*, defaults to `"<pad>"`):
            The token used for padding, for example when batching sequences of different lengths.
        mask_token (`str`, *optional*, defaults to `"<mask>"`):
            The token used for masking values. This is the token used when training this model with masked language
            modeling. This is the token which the model will try to predict.
        add_prefix_space (`bool`, *optional*, defaults to `False`):
            Whether or not to add an initial space to the input. This allows to treat the leading word just as any
            other word. (RoBERTa tokenizer detect beginning of words by the preceding space).
    """

    vocab_files_names = VOCAB_FILES_NAMES
    pretrained_vocab_files_map = PRETRAINED_VOCAB_FILES_MAP
    max_model_input_sizes = PRETRAINED_POSITIONAL_EMBEDDINGS_SIZES
    model_input_names = ["input_ids", "attention_mask"]

    def __init__(
        self,
        vocab_file,
        merges_file,
        errors="replace",
        bos_token="<s>",
        eos_token="</s>",
        sep_token="</s>",
        cls_token="<s>",
        unk_token="<unk>",
        pad_token="<pad>",
        mask_token="<mask>",
        add_prefix_space=False,
        **kwargs
    ):
        bos_token = AddedToken(bos_token, lstrip=False, rstrip=False) if isinstance(bos_token, str) else bos_token
        eos_token = AddedToken(eos_token, lstrip=False, rstrip=False) if isinstance(eos_token, str) else eos_token
        sep_token = AddedToken(sep_token, lstrip=False, rstrip=False) if isinstance(sep_token, str) else sep_token
        cls_token = AddedToken(cls_token, lstrip=False, rstrip=False) if isinstance(cls_token, str) else cls_token
        unk_token = AddedToken(unk_token, lstrip=False, rstrip=False) if isinstance(unk_token, str) else unk_token
        pad_token = AddedToken(pad_token, lstrip=False, rstrip=False) if isinstance(pad_token, str) else pad_token

        # Mask token behave like a normal word, i.e. include the space before it
        mask_token = AddedToken(mask_token, lstrip=True, rstrip=False) if isinstance(mask_token, str) else mask_token

        super().__init__(
            errors=errors,
            bos_token=bos_token,
            eos_token=eos_token,
            unk_token=unk_token,
            sep_token=sep_token,
            cls_token=cls_token,
            pad_token=pad_token,
            mask_token=mask_token,
            add_prefix_space=add_prefix_space,
            **kwargs,
        )

        with open(vocab_file, encoding="utf-8") as vocab_handle:
            self.encoder = json.load(vocab_handle)
        self.decoder = {v: k for k, v in self.encoder.items()}
        self.errors = errors  # how to handle errors in decoding
        self.byte_encoder = bytes_to_unicode()
        self.byte_decoder = {v: k for k, v in self.byte_encoder.items()}
        with open(merges_file, encoding="utf-8") as merges_handle:
            bpe_merges = merges_handle.read().split("\n")[1:-1]
        bpe_merges = [tuple(merge.split()) for merge in bpe_merges]
        self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges))))
        self.cache = {}
        self.add_prefix_space = add_prefix_space

        # Should have added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions
        """Regex for SMILES"""
        smi_regex_pattern = r"(\-?[0-9]+\.?[0-9]*|\[|\]|SELF|Li|Be|Na|Mg|Al|K|Ca|Co|Zn|Ga|Ge|As|Se|Sn|Te|N|O|P|H|I|b|c|n|o|s|p|Br?|Cl?|Fe?|Ni?|Si?|\||\(|\)|\^|=|#|-|\+|\\|\/|@|\*|\.|\%|\$)"
        self.pat = re.compile(smi_regex_pattern)

    @property
    def vocab_size(self):
        return len(self.encoder)

    def get_vocab(self):
        return dict(self.encoder, **self.added_tokens_encoder)

    def bpe(self, token):
        if token in self.cache:
            return self.cache[token]
        word = tuple(token)
        pairs = get_pairs(word)

        if not pairs:
            return token

        while True:
            bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float("inf")))
            if bigram not in self.bpe_ranks:
                break
            first, second = bigram
            new_word = []
            i = 0
            while i < len(word):
                try:
                    j = word.index(first, i)
                except ValueError:
                    new_word.extend(word[i:])
                    break
                else:
                    new_word.extend(word[i:j])
                    i = j

                if word[i] == first and i < len(word) - 1 and word[i + 1] == second:
                    new_word.append(first + second)
                    i += 2
                else:
                    new_word.append(word[i])
                    i += 1
            new_word = tuple(new_word)
            word = new_word
            if len(word) == 1:
                break
            else:
                pairs = get_pairs(word)
        word = " ".join(word)
        self.cache[token] = word
        return word

    def _tokenize(self, text):
        """Tokenize a string."""
        bpe_tokens = []
        for token in re.findall(self.pat, text):
            token = "".join(
                self.byte_encoder[b] for b in token.encode("utf-8")
            )  # Maps all our bytes to unicode strings, avoiding control tokens of the BPE (spaces in our case)
            bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(" "))
        return bpe_tokens

    def _convert_token_to_id(self, token):
        """Converts a token (str) in an id using the vocab."""
        return self.encoder.get(token, self.encoder.get(self.unk_token))

    def _convert_id_to_token(self, index):
        """Converts an index (integer) in a token (str) using the vocab."""
        return self.decoder.get(index)

    def convert_tokens_to_string(self, tokens):
        """Converts a sequence of tokens (string) in a single string."""
        text = "".join(tokens)
        text = bytearray([self.byte_decoder[c] for c in text]).decode("utf-8", errors=self.errors)
        return text

    def save_vocabulary(self, save_directory: str, filename_prefix: Optional[str] = None) -> Tuple[str]:
        if not os.path.isdir(save_directory):
            logger.error(f"Vocabulary path ({save_directory}) should be a directory")
            return
        vocab_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["vocab_file"]
        )
        merge_file = os.path.join(
            save_directory, (filename_prefix + "-" if filename_prefix else "") + VOCAB_FILES_NAMES["merges_file"]
        )

        with open(vocab_file, "w", encoding="utf-8") as f:
            f.write(json.dumps(self.encoder, ensure_ascii=False))

        index = 0
        with open(merge_file, "w", encoding="utf-8") as writer:
            writer.write("#version: 0.2\n")
            for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]):
                if index != token_index:
                    logger.warning(
                        f"Saving vocabulary to {merge_file}: BPE merge indices are not consecutive."
                        " Please check that the tokenizer is not corrupted!"
                    )
                    index = token_index
                writer.write(" ".join(bpe_tokens) + "\n")
                index += 1

        return vocab_file, merge_file

    def build_inputs_with_special_tokens(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and
        adding special tokens. A RoBERTa sequence has the following format:

        - single sequence: `<s> X </s>`
        - pair of sequences: `<s> A </s></s> B </s>`

        Args:
            token_ids_0 (`List[int]`):
                List of IDs to which the special tokens will be added.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of [input IDs](../glossary#input-ids) with the appropriate special tokens.
        """
        if token_ids_1 is None:
            return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]
        cls = [self.cls_token_id]
        sep = [self.sep_token_id]
        return cls + token_ids_0 + sep + sep + token_ids_1 + sep

    def get_special_tokens_mask(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None, already_has_special_tokens: bool = False
    ) -> List[int]:
        """
        Retrieve sequence ids from a token list that has no special tokens added. This method is called when adding
        special tokens using the tokenizer `prepare_for_model` method.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.
            already_has_special_tokens (`bool`, *optional*, defaults to `False`):
                Whether or not the token list is already formatted with special tokens for the model.

        Returns:
            `List[int]`: A list of integers in the range [0, 1]: 1 for a special token, 0 for a sequence token.
        """
        if already_has_special_tokens:
            return super().get_special_tokens_mask(
                token_ids_0=token_ids_0, token_ids_1=token_ids_1, already_has_special_tokens=True
            )

        if token_ids_1 is None:
            return [1] + ([0] * len(token_ids_0)) + [1]
        return [1] + ([0] * len(token_ids_0)) + [1, 1] + ([0] * len(token_ids_1)) + [1]

    def create_token_type_ids_from_sequences(
        self, token_ids_0: List[int], token_ids_1: Optional[List[int]] = None
    ) -> List[int]:
        """
        Create a mask from the two sequences passed to be used in a sequence-pair classification task. RoBERTa does not
        make use of token type ids, therefore a list of zeros is returned.

        Args:
            token_ids_0 (`List[int]`):
                List of IDs.
            token_ids_1 (`List[int]`, *optional*):
                Optional second list of IDs for sequence pairs.

        Returns:
            `List[int]`: List of zeros.
        """
        sep = [self.sep_token_id]
        cls = [self.cls_token_id]

        if token_ids_1 is None:
            return len(cls + token_ids_0 + sep) * [0]
        return len(cls + token_ids_0 + sep + sep + token_ids_1 + sep) * [0]

    def prepare_for_tokenization(self, text, is_split_into_words=False, **kwargs):
        add_prefix_space = kwargs.pop("add_prefix_space", self.add_prefix_space)
        if (is_split_into_words or add_prefix_space) and (len(text) > 0 and not text[0].isspace()):
            text = " " + text
        return (text, kwargs)


def smi2scaffold(smi):
    try:
        return MurckoScaffold.MurckoScaffoldSmiles(
            smiles=smi, includeChirality=True)
    except:
        print("failed to generate scaffold with smiles: {}".format(smi))
        return smi


def smi2_2Dcoords(smi):
    mol = Chem.MolFromSmiles(smi)
    mol = AllChem.AddHs(mol)
    AllChem.Compute2DCoords(mol)
    coordinates = mol.GetConformer().GetPositions().astype(np.float32)
    len(mol.GetAtoms()) == len(coordinates), "2D coordinates shape is not align with {}".format(smi)
    return coordinates


def smi2_3Dcoords(smi,cnt):
    mol = Chem.MolFromSmiles(smi)
    mol = AllChem.AddHs(mol)
    coordinate_list=[]
    for seed in range(cnt):
        try:
            res = AllChem.EmbedMolecule(mol, randomSeed=seed)  # will random generate conformer with seed equal to -1. else fixed random seed.
            if res == 0:
                try:
                    AllChem.MMFFOptimizeMolecule(mol)       # some conformer can not use MMFF optimize
                    coordinates = mol.GetConformer().GetPositions()
                except:
                    print("Failed to generate 3D, replace with 2D")
                    coordinates = smi2_2Dcoords(smi)            
                    
            elif res == -1:
                mol_tmp = Chem.MolFromSmiles(smi)
                AllChem.EmbedMolecule(mol_tmp, maxAttempts=5000, randomSeed=seed)
                mol_tmp = AllChem.AddHs(mol_tmp, addCoords=True)
                try:
                    AllChem.MMFFOptimizeMolecule(mol_tmp)       # some conformer can not use MMFF optimize
                    coordinates = mol_tmp.GetConformer().GetPositions()
                except:
                    print("Failed to generate 3D, replace with 2D")
                    coordinates = smi2_2Dcoords(smi) 
        except:
            print("Failed to generate 3D, replace with 2D")
            coordinates = smi2_2Dcoords(smi) 

        assert len(mol.GetAtoms()) == len(coordinates), "3D coordinates shape is not align with {}".format(smi)
        coordinate_list.append(coordinates.astype(np.float32))
    return coordinate_list


def inner_smi2coords(content):  
    smi = content
    target = -999
    
    mol = Chem.MolFromSmiles(smi)
    atoms = [atom.GetSymbol() for atom in mol.GetAtoms()]
    
    assert 'H' not in atoms
    
    star_atoms_id = []
    for idx, atom_symbol in enumerate(atoms):
        if atom_symbol == '*':
            star_atoms_id.append(idx)
    assert len(star_atoms_id) == 2, "Error star num"
    
    star_pair_list = []
    for star_id in star_atoms_id:
        star_pair_list.append(star_id)
        star_atom = mol.GetAtomWithIdx(star_id)
        neighbors = star_atom.GetNeighbors()
        assert len(neighbors) == 1, "Error star neighbors num"    
        for neighbor in neighbors:
            star_pair_list.append(neighbor.GetIdx())
    
    pair_1_star = star_pair_list[0]
    pair_1 = star_pair_list[3]
    atom = mol.GetAtomWithIdx(pair_1_star)
    atom.SetAtomicNum(mol.GetAtomWithIdx(pair_1).GetAtomicNum())
    
    pair_2_star = star_pair_list[2]
    pair_2 = star_pair_list[1]
    atom = mol.GetAtomWithIdx(pair_2_star)
    atom.SetAtomicNum(mol.GetAtomWithIdx(pair_2).GetAtomicNum())
    
    smi = Chem.MolToSmiles(mol)
    
    cnt = 10
    scaffold = smi2scaffold(smi)
    
    if len(mol.GetAtoms()) > 400:
        coordinate_list =  [smi2_2Dcoords(smi)] * (cnt+1)
        print("atom num > 400, use 2D coords",smi)
    else:
        coordinate_list = smi2_3Dcoords(smi, cnt)
        coordinate_list.append(smi2_2Dcoords(smi).astype(np.float32))
    
    mol = Chem.MolFromSmiles(smi)
    mol = AllChem.AddHs(mol)
    
    atoms = [atom.GetSymbol() for atom in mol.GetAtoms()]
    
    origin_smi = content
    origin_mol = Chem.MolFromSmiles(origin_smi)
    origin_atoms = [atom.GetSymbol() for atom in origin_mol.GetAtoms()]
    
    assert origin_atoms[pair_1_star] == '*'
    assert origin_atoms[pair_2_star] == '*'
    
    atoms[pair_1_star] = '*'
    atoms[pair_2_star] = '*'
    
    return {'atoms': atoms, 
    'coordinates': coordinate_list, 
    'mol':mol, 'smi': content, 'origin_smi': content, 'star_pair': star_pair_list, 'scaffold': scaffold, 'target': target}


def smi2coords(content):
    try:
        return inner_smi2coords(content)
    except:
        print("failed psmiles: {}".format(content))
        return None


if __name__ == "__main__":
    os.environ['MKL_THREADING_LAYER'] = 'GNU' 
    
    parser = argparse.ArgumentParser()
    
    parser.add_argument("--input_data", help="PSMILES or CSV file")
    parser.add_argument("--property", help="which property to predict", default='all')
    
    parser.add_argument('--outputs_path', default='outputs') 
    parser.add_argument('--cache_path', default='cache')  
        
    args = parser.parse_args()
        
    if os.path.exists(args.outputs_path):
        shutil.rmtree(args.outputs_path)
    os.mkdir(args.outputs_path)
    
    if os.path.exists(args.cache_path):
        shutil.rmtree(args.cache_path)
    os.mkdir(args.cache_path)
    
    
    # data pre
    content_list = []
    if args.input_data.endswith('.csv'):
        with open(args.input_data, newline='', encoding='utf-8') as csvfile:
            csvreader = csv.reader(csvfile)
            headers = next(csvreader)
            for row in csvreader:
                psmi = row[0]
                content_list.append(psmi)  
    else:    
        psmi = args.input_data
        content_list.append(psmi)
    
    outputfilename = os.path.join(args.cache_path, 'test.lmdb')
    env = lmdb.open(
        outputfilename,
        subdir=False,
        readonly=False,
        lock=False,
        readahead=False,
        meminit=False,
        max_readers=1,
        map_size=int(1000e9),
    )
    txn = env.begin(write=True)
    
    index = 0
    tokenizer = PolymerSmilesTokenizer.from_pretrained("./MMPolymer/models/roberta-base", max_len=411)
    
    for content in tqdm(content_list):
        data_info = smi2coords(content)
        if data_info == None:
            continue
        
        encoding = tokenizer(
                    str(data_info['origin_smi']),
                    add_special_tokens=True,
                    max_length=411,
                    return_token_type_ids=False,
                    padding="max_length",
                    truncation=True,
                    return_attention_mask=True,
                    return_tensors='pt',
                    )

        data_info["input_ids"] = encoding["input_ids"].flatten()
        data_info["attention_mask"] = encoding["attention_mask"].flatten()
        
        assert data_info["input_ids"].shape[0] == 411
        assert data_info["attention_mask"].shape[0] == 411
                
        txn.put(f'{index}'.encode("ascii"), pickle.dumps(data_info, protocol=-1))
        index += 1
        
    txn.commit()
    env.close() 
    
    
    # model run
    if args.property != 'all':
        property_list = [args.property]
    else:
        property_list = ['Egc', 'Egb', 'Eea', 'Ei', 'Xc', 'EPS', 'Nc', 'Eat']
        
    
    total_psmi_list = []
    total_pred_list = []
    
    
    for property_name in property_list:
        weight_path = f'./ckpt/${property_name}/checkpoint_best.pt'
        cmd1 = f"python ./MMPolymer/infer.py --user-dir ./MMPolymer ./ --task-name {args.cache_path} --valid-subset test --results-path {args.cache_path} --num-workers 1 --ddp-backend=c10d --batch-size 128 --task MMPolymer_finetune --loss MMPolymer_finetune --arch MMPolymer_base --classification-head-name {args.cache_path} --num-classes 1 --dict-name dict.txt --conf-size 11 --only-polar 0  --path {weight_path}  --fp16 --fp16-init-scale 4 --fp16-scale-window 256 --log-interval 50 --log-format simple"
        process1 = subprocess.Popen(cmd1, shell=True)
        process1.wait()

        predict_result_path = f'./cache/{property_name}_test_cpu.out.pkl'
        predict_outputs = pd.read_pickle(predict_result_path)

        pred_list = []
        psmi_list = []
        for epoch in range(len(predict_outputs)):
            predict_output = predict_outputs[epoch]
            pred_list.append(predict_output['predict'])
            psmi_list.extend(predict_output['smi_name'])
        pred_list = torch.cat(pred_list, dim=0).float()
        
        psmi_list = psmi_list[::11]
        pred_list = pred_list.view(-1, 11).numpy().mean(axis=1)
        pred_list = np.round(pred_list, 2)
        
        total_psmi_list.append(psmi_list)
        total_pred_list.append(pred_list)
    
    transposed_total_pred_list = list(map(list, zip(*total_pred_list)))
    results_data = transposed_total_pred_list
    result_pd = pd.DataFrame(results_data, columns=property_list)
    result_pd.insert(0, 'psmile', total_psmi_list[0])
    
    predict_result_save_path = os.path.join(args.outputs_path, "predict_result.csv")
    print(f'The final prediction result is saved in {predict_result_save_path}')
    result_pd.to_csv(predict_result_save_path, index=None)