Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages

Michael Sun, Weize Yuan, Gang Liu, Wojciech Matusik, Jie Chen
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:57886-57937, 2025.

Abstract

Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic inference. We propose Foundation Molecular Grammar (FMG), which leverages multi-modal foundation models (MMFMs) to induce an interpretable molecular language. By exploiting the chemical knowledge of an MMFM, FMG renders molecules as images, describes them as text, and aligns information across modalities using prompt learning. FMG can be used as a drop-in replacement for the prior grammar learning approaches in molecular generation and property prediction. We show that FMG not only excels in synthesizability, diversity, and data efficiency but also offers built-in chemical interpretability for automated molecular discovery workflows. Code is available at https://github.com/shiningsunnyday/induction.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-sun25aa, title = {Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages}, author = {Sun, Michael and Yuan, Weize and Liu, Gang and Matusik, Wojciech and Chen, Jie}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {57886--57937}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/sun25aa/sun25aa.pdf}, url = {https://proceedings.mlr.press/v267/sun25aa.html}, abstract = {Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic inference. We propose Foundation Molecular Grammar (FMG), which leverages multi-modal foundation models (MMFMs) to induce an interpretable molecular language. By exploiting the chemical knowledge of an MMFM, FMG renders molecules as images, describes them as text, and aligns information across modalities using prompt learning. FMG can be used as a drop-in replacement for the prior grammar learning approaches in molecular generation and property prediction. We show that FMG not only excels in synthesizability, diversity, and data efficiency but also offers built-in chemical interpretability for automated molecular discovery workflows. Code is available at https://github.com/shiningsunnyday/induction.} }
Endnote
%0 Conference Paper %T Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages %A Michael Sun %A Weize Yuan %A Gang Liu %A Wojciech Matusik %A Jie Chen %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-sun25aa %I PMLR %P 57886--57937 %U https://proceedings.mlr.press/v267/sun25aa.html %V 267 %X Recent data-efficient molecular generation approaches exploit graph grammars to introduce interpretability into the generative models. However, grammar learning therein relies on expert annotation or unreliable heuristics for algorithmic inference. We propose Foundation Molecular Grammar (FMG), which leverages multi-modal foundation models (MMFMs) to induce an interpretable molecular language. By exploiting the chemical knowledge of an MMFM, FMG renders molecules as images, describes them as text, and aligns information across modalities using prompt learning. FMG can be used as a drop-in replacement for the prior grammar learning approaches in molecular generation and property prediction. We show that FMG not only excels in synthesizability, diversity, and data efficiency but also offers built-in chemical interpretability for automated molecular discovery workflows. Code is available at https://github.com/shiningsunnyday/induction.
APA
Sun, M., Yuan, W., Liu, G., Matusik, W. & Chen, J.. (2025). Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:57886-57937 Available from https://proceedings.mlr.press/v267/sun25aa.html.

Related Material