⚗️ MolGen

Domain-Agnostic Molecular Generation with Chemical Feedback

📃 Paper • 🤗 Model • 🔬 Space

🔔 News

• 2024-2 We've released ChatCell, a new paradigm that leverages natural language to make single-cell analysis more accessible and intuitive. Please visit our homepage and Github page for more information.
• 2024-1 Our paper Domain-Agnostic Molecular Generation with Chemical Feedback is accepted by ICLR 2024.
• 2024-1 Our paper Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models is accepted by ICLR 2024.
• 2023-10 We open-source MolGen-7b, which now supports de novo molecule generation!
• 2023-6 We open-source KnowLM, a knowledgeable LLM framework with pre-training and instruction fine-tuning code (supports multi-machine multi-GPU setup).
• 2023-6 We release Mol-Instructions, a large-scale biomolecule instruction dataset for large language models.
• 2023-5 We propose Knowledge graph-enhanced molecular contrAstive learning with fuNctional prOmpt (KANO) on Nature Machine Intelligence, exploiting fundamental domain knowledge in both pre-training and fine-tuning.
• 2023-4 We provide a NLP for science paper-list at https://github.com/zjunlp/NLP4Science_Papers.
• 2023-3 We release our pre-trained and fine-tuned model on 🤗 Hugging Face at MolGen-large and MolGen-large-opt.
• 2023-2 We provide a demo on 🤗 Hugging Face at Space.

📕 Requirements

To run the codes, You can configure dependencies by restoring our environment:

conda env create -f MolGen/environment.yml -n $Your_env_name$

and then：

conda activate $Your_env_name$

📚 Resource Download

You can download the pre-trained and fine-tuned models via Huggingface: MolGen-large and MolGen-large-opt.

Moreover, the dataset used for downstream tasks can be found here.

The expected structure of files is:

moldata
├── checkpoint 
│   ├── molgen.pkl              # pre-trained model
│   ├── syn_qed_model.pkl       # fine-tuned model for QED optimization on synthetic data
│   ├── syn_plogp_model.pkl     # fine-tuned model for p-logP optimization on synthetic data
│   ├── np_qed_model.pkl        # fine-tuned model for QED optimization on natural product data
│   ├── np_plogp_model.pkl      # fine-tuned model for p-logP optimization on natural product data
├── finetune
│   ├── np_test.csv             # nature product test data
│   ├── np_train.csv            # nature product train data
│   ├── plogp_test.csv          # synthetic test data for plogp optimization
│   ├── qed_test.csv            # synthetic test data for plogp optimization
│   └── zinc250k.csv            # synthetic train data
├── generate                    # generate molecules
├── output                      # molecule candidates
└── vocab_list
    └── zinc.npy                # SELFIES alphabet

🚀 How to run

• Fine-tune

  • First, preprocess the finetuning dataset by generating candidate molecules using our pre-trained model. The preprocessed data will be stored in the folder output.

      cd MolGen
      bash preprocess.sh
  

  • Then utilize the self-feedback paradigm. The fine-tuned model will be stored in the folder checkpoint.

      bash finetune.sh
  

• Generate

  To generate molecules, run this script. Please specify the checkpoint_path to determine whether to use the pre-trained model or the fine-tuned model.

  cd MolGen
  bash generate.sh
  

🥽 Experiments

We conduct experiments on well-known benchmarks to confirm MolGen's optimization capabilities, encompassing penalized logP, QED, and molecular docking properties. For detailed experimental settings and analysis, please refer to our paper.

• MolGen captures real-word molecular distributions

• MolGen mitigates molecular hallucinations

Targeted molecule discovery

Constrained molecular optimization

Citation

If you use or extend our work, please cite the paper as follows:

@inproceedings{fang2023domain,
  author       = {Yin Fang and
                  Ningyu Zhang and
                  Zhuo Chen and
                  Xiaohui Fan and
                  Huajun Chen},
  title        = {Domain-Agnostic Molecular Generation with Chemical feedback},
  booktitle    = {{ICLR}},
  publisher    = {OpenReview.net},
  year         = {2024},
  url          = {https://openreview.net/pdf?id=9rPyHyjfwP}
}