MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning

Peter Eckmann, Dongxia Wu, Germano Heinzelmann, Michael K Gilson, Rose Yu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:14972-14988, 2025.

Abstract

Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show real-world experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning (MF-LAL), a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. Using active learning, we train a surrogate model for each oracle and use these surrogates to guide generation of compounds with high predicted activity. Unlike previous approaches that separately learn the surrogate model and generative model, MF-LAL combines the generative and multi-fidelity surrogate models into a single framework, allowing for more accurate activity prediction and higher quality samples. Our experiments on two disease-relevant proteins show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches ( 50% improvement in mean binding free energy score). The code is available at https://github.com/Rose-STL-Lab/MF-LAL.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-eckmann25a, title = {{MF}-{LAL}: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning}, author = {Eckmann, Peter and Wu, Dongxia and Heinzelmann, Germano and Gilson, Michael K and Yu, Rose}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {14972--14988}, 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/eckmann25a/eckmann25a.pdf}, url = {https://proceedings.mlr.press/v267/eckmann25a.html}, abstract = {Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show real-world experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning (MF-LAL), a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. Using active learning, we train a surrogate model for each oracle and use these surrogates to guide generation of compounds with high predicted activity. Unlike previous approaches that separately learn the surrogate model and generative model, MF-LAL combines the generative and multi-fidelity surrogate models into a single framework, allowing for more accurate activity prediction and higher quality samples. Our experiments on two disease-relevant proteins show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches ( 50% improvement in mean binding free energy score). The code is available at https://github.com/Rose-STL-Lab/MF-LAL.} }
Endnote
%0 Conference Paper %T MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning %A Peter Eckmann %A Dongxia Wu %A Germano Heinzelmann %A Michael K Gilson %A Rose Yu %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-eckmann25a %I PMLR %P 14972--14988 %U https://proceedings.mlr.press/v267/eckmann25a.html %V 267 %X Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do not consistently show real-world experimental activity. More accurate methods for activity prediction exist, such as molecular dynamics based binding free energy calculations, but they are too computationally expensive to use in a generative model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning (MF-LAL), a generative modeling framework that integrates a set of oracles with varying cost-accuracy tradeoffs. Using active learning, we train a surrogate model for each oracle and use these surrogates to guide generation of compounds with high predicted activity. Unlike previous approaches that separately learn the surrogate model and generative model, MF-LAL combines the generative and multi-fidelity surrogate models into a single framework, allowing for more accurate activity prediction and higher quality samples. Our experiments on two disease-relevant proteins show that MF-LAL produces compounds with significantly better binding free energy scores than other single and multi-fidelity approaches ( 50% improvement in mean binding free energy score). The code is available at https://github.com/Rose-STL-Lab/MF-LAL.
APA
Eckmann, P., Wu, D., Heinzelmann, G., Gilson, M.K. & Yu, R.. (2025). MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:14972-14988 Available from https://proceedings.mlr.press/v267/eckmann25a.html.

Related Material