Proximal Exploration for Model-guided Protein Sequence Design

Zhizhou Ren, Jiahan Li, Fan Ding, Yuan Zhou, Jianzhu Ma, Jian Peng
Proceedings of the 39th International Conference on Machine Learning, PMLR 162:18520-18536, 2022.

Abstract

Designing protein sequences with a particular biological function is a long-lasting challenge for protein engineering. Recent advances in machine-learning-guided approaches focus on building a surrogate sequence-function model to reduce the burden of expensive in-lab experiments. In this paper, we study the exploration mechanism of model-guided sequence design. We leverage a natural property of protein fitness landscape that a concise set of mutations upon the wild-type sequence are usually sufficient to enhance the desired function. By utilizing this property, we propose Proximal Exploration (PEX) algorithm that prioritizes the evolutionary search for high-fitness mutants with low mutation counts. In addition, we develop a specialized model architecture, called Mutation Factorization Network (MuFacNet), to predict low-order mutational effects, which further improves the sample efficiency of model-guided evolution. In experiments, we extensively evaluate our method on a suite of in-silico protein sequence design tasks and demonstrate substantial improvement over baseline algorithms.

Cite this Paper

BibTeX
@InProceedings{pmlr-v162-ren22a, title = {Proximal Exploration for Model-guided Protein Sequence Design}, author = {Ren, Zhizhou and Li, Jiahan and Ding, Fan and Zhou, Yuan and Ma, Jianzhu and Peng, Jian}, booktitle = {Proceedings of the 39th International Conference on Machine Learning}, pages = {18520--18536}, year = {2022}, editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan}, volume = {162}, series = {Proceedings of Machine Learning Research}, month = {17--23 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v162/ren22a/ren22a.pdf}, url = {https://proceedings.mlr.press/v162/ren22a.html}, abstract = {Designing protein sequences with a particular biological function is a long-lasting challenge for protein engineering. Recent advances in machine-learning-guided approaches focus on building a surrogate sequence-function model to reduce the burden of expensive in-lab experiments. In this paper, we study the exploration mechanism of model-guided sequence design. We leverage a natural property of protein fitness landscape that a concise set of mutations upon the wild-type sequence are usually sufficient to enhance the desired function. By utilizing this property, we propose Proximal Exploration (PEX) algorithm that prioritizes the evolutionary search for high-fitness mutants with low mutation counts. In addition, we develop a specialized model architecture, called Mutation Factorization Network (MuFacNet), to predict low-order mutational effects, which further improves the sample efficiency of model-guided evolution. In experiments, we extensively evaluate our method on a suite of in-silico protein sequence design tasks and demonstrate substantial improvement over baseline algorithms.} }
Endnote
%0 Conference Paper %T Proximal Exploration for Model-guided Protein Sequence Design %A Zhizhou Ren %A Jiahan Li %A Fan Ding %A Yuan Zhou %A Jianzhu Ma %A Jian Peng %B Proceedings of the 39th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2022 %E Kamalika Chaudhuri %E Stefanie Jegelka %E Le Song %E Csaba Szepesvari %E Gang Niu %E Sivan Sabato %F pmlr-v162-ren22a %I PMLR %P 18520--18536 %U https://proceedings.mlr.press/v162/ren22a.html %V 162 %X Designing protein sequences with a particular biological function is a long-lasting challenge for protein engineering. Recent advances in machine-learning-guided approaches focus on building a surrogate sequence-function model to reduce the burden of expensive in-lab experiments. In this paper, we study the exploration mechanism of model-guided sequence design. We leverage a natural property of protein fitness landscape that a concise set of mutations upon the wild-type sequence are usually sufficient to enhance the desired function. By utilizing this property, we propose Proximal Exploration (PEX) algorithm that prioritizes the evolutionary search for high-fitness mutants with low mutation counts. In addition, we develop a specialized model architecture, called Mutation Factorization Network (MuFacNet), to predict low-order mutational effects, which further improves the sample efficiency of model-guided evolution. In experiments, we extensively evaluate our method on a suite of in-silico protein sequence design tasks and demonstrate substantial improvement over baseline algorithms.
APA
Ren, Z., Li, J., Ding, F., Zhou, Y., Ma, J. & Peng, J.. (2022). Proximal Exploration for Model-guided Protein Sequence Design. Proceedings of the 39th International Conference on Machine Learning, in Proceedings of Machine Learning Research 162:18520-18536 Available from https://proceedings.mlr.press/v162/ren22a.html.

Related Material