# Interactive Molecular Discovery with Natural Language

arXiv: https://arxiv.org/abs/2306.11976 · HTML: https://mlsanity.com/paper/2306.11976/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 49 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing](https://mlsanity.com/paper/1902.07669/) (2019)
- [UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning](https://mlsanity.com/paper/2012.15409/) (2020)
- [ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction](https://mlsanity.com/paper/2106.06130/) (2021)
- [Translation between Molecules and Natural Language](https://mlsanity.com/paper/2204.11817/) (2022)
- [Dual Learning for Machine Translation](https://mlsanity.com/paper/1611.00179/) (2016)
- [A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language](https://mlsanity.com/paper/2209.05481/) (2022)
- [Pre-trained Language Models in Biomedical Domain: A Systematic Survey](https://mlsanity.com/paper/2110.05006/) (2021)
- [MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design](https://mlsanity.com/paper/2203.14500/) (2022)
- [Improving Biomedical Pretrained Language Models with Knowledge](https://mlsanity.com/paper/2104.10344/) (2021)
- [Dual Supervised Learning](https://mlsanity.com/paper/1707.00415/) (2017)
- [Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference](https://mlsanity.com/paper/2105.13456/) (2021)
- [Using Rule-Based Labels for Weak Supervised Learning: A ChemNet for Transferable Chemical Property Prediction](https://mlsanity.com/paper/1712.02734/) (2017)
- [Chemical-protein Interaction Extraction via Gaussian Probability Distribution and External Biomedical Knowledge](https://mlsanity.com/paper/1911.09487/) (2019)

## Built on by (most cited first, 5 of 5)

- [Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey](https://mlsanity.com/paper/2403.01528/) (2024)
- [Learning Multi-view Molecular Representations with Structured and Unstructured Knowledge](https://mlsanity.com/paper/2406.09841/) (2024)
- [Bioinformatics and Biomedical Informatics with ChatGPT: Year One Review](https://mlsanity.com/paper/2403.15274/) (2024)
- [Can Decision Trees Teach Large Language Models? Distilling Verbalized Knowledge for Molecular Property Prediction](https://mlsanity.com/paper/2603.12344/) (2026)
- [BiMol-Diff: A Unified Diffusion Framework for Molecular Generation and Captioning](https://mlsanity.com/paper/2604.24089/) (2026)

## Abstract (arXiv)

Natural language is expected to be a key medium for various human-machine interactions in the era of large language models. When it comes to the biochemistry field, a series of tasks around molecules (e.g., property prediction, molecule mining, etc.) are of great significance while having a high technical threshold. Bridging the molecule expressions in natural language and chemical language can not only hugely improve the interpretability and reduce the operation difficulty of these tasks, but also fuse the chemical knowledge scattered in complementary materials for a deeper comprehension of molecules. Based on these benefits, we propose the conversational molecular design, a novel task adopting natural language for describing and editing target molecules. To better accomplish this task, we design ChatMol, a knowledgeable and versatile generative pre-trained model, enhanced by injecting experimental property information, molecular spatial knowledge, and the associations between natural and chemical languages into it. Several typical solutions including large language models (e.g., ChatGPT) are evaluated, proving the challenge of conversational molecular design and the effectiveness of our knowledge enhancement method. Case observations and analysis are conducted to provide directions for further exploration of natural-language interaction in molecular discovery.