Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space

Minji Lee, Luiz Felipe Vecchietti, Hyunkyu Jung, Hyun Joo Ro, Meeyoung Cha, Ho Min Kim
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:26976-26990, 2024.

Abstract

Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-lee24x, title = {Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space}, author = {Lee, Minji and Vecchietti, Luiz Felipe and Jung, Hyunkyu and Ro, Hyun Joo and Cha, Meeyoung and Kim, Ho Min}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {26976--26990}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/lee24x/lee24x.pdf}, url = {https://proceedings.mlr.press/v235/lee24x.html}, abstract = {Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.} }
Endnote
%0 Conference Paper %T Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space %A Minji Lee %A Luiz Felipe Vecchietti %A Hyunkyu Jung %A Hyun Joo Ro %A Meeyoung Cha %A Ho Min Kim %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-lee24x %I PMLR %P 26976--26990 %U https://proceedings.mlr.press/v235/lee24x.html %V 235 %X Proteins are complex molecules responsible for different functions in nature. Enhancing the functionality of proteins and cellular fitness can significantly impact various industries. However, protein optimization using computational methods remains challenging, especially when starting from low-fitness sequences. We propose LatProtRL, an optimization method to efficiently traverse a latent space learned by an encoder-decoder leveraging a large protein language model. To escape local optima, our optimization is modeled as a Markov decision process using reinforcement learning acting directly in latent space. We evaluate our approach on two important fitness optimization tasks, demonstrating its ability to achieve comparable or superior fitness over baseline methods. Our findings and in vitro evaluation show that the generated sequences can reach high-fitness regions, suggesting a substantial potential of LatProtRL in lab-in-the-loop scenarios.
APA
Lee, M., Vecchietti, L.F., Jung, H., Ro, H.J., Cha, M. & Kim, H.M.. (2024). Robust Optimization in Protein Fitness Landscapes Using Reinforcement Learning in Latent Space. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:26976-26990 Available from https://proceedings.mlr.press/v235/lee24x.html.

Related Material