SMILES Featurizers

Extract SMILES embeddings from language models pre-trained with various objectives architectures.

Getting Started

pip install smiles-featurizers

Model List

Our released models are listed as following. You can import these models by using the smiles-featurizers package or using HuggingFace's Transformers.

Use SMILES Featurizers

Bert Featurizer

from smiles_featurizers import BertFeaturizer
import torch

## set device
use_gpu = True if torch.cuda.is_available() else False

featurizer = BertFeaturizer("shahrukhx01/smole-bert", use_gpu=use_gpu)
embeddings = featurizer.embed(["CCC(C)(C)Br"])

Bart (Encoder) Featurizer

from smiles_featurizers import BartFeaturizer

featurizer = BartFeaturizer("shahrukhx01/smole-bart")
embeddings = featurizer.embed(["CCC(C)(C)Br"], embedder="encoder")

Bart (Decoder) Featurizer

from smiles_featurizers import BartFeaturizer

featurizer = BartFeaturizer("shahrukhx01/smole-bart")
embeddings = featurizer.embed(["CCC(C)(C)Br"], embedder="decoder")

SimCSE Featurizer

from smiles_featurizers import SimcseFeaturizer
import torch

## set device
device = "cuda" if torch.cuda.is_available() else "cpu"

featurizer = SimcseFeaturizer("shahrukhx01/muv2x-simcse-smole-bert", device=device)
embeddings = featurizer.embed(["CCC(C)(C)Br"])

SentenceTransformer Featurizer

from smiles_featurizers import SentenceTransformersFeaturizer
import torch

## set device
device = "cuda" if torch.cuda.is_available() else "cpu"

featurizer = SentenceTransformersFeaturizer("shahrukhx01/siamese-smole-bert-muv-1x", device=device)
embeddings = featurizer.embed(["CCC(C)(C)Br"])