Computational design of target-specific linear peptide binders with TransformerBeta

Haowen Zhao, Francesco Aprile, Barbara Bravi
Proceedings of the 19th Machine Learning in Computational Biology meeting, PMLR 261:1-27, 2024.

Abstract

The computational prediction and design of peptide binders targeting specific epitopes within disordered protein regions is crucial in biological and biomedical research, yet it remains challenging due to their highly dynamic nature and the scarcity of experimentally solved binding data. To address this problem, we built an unprecedentedly large-scale library of peptide pairs within stable secondary structures (beta sheets), leveraging newly available AlphaFold predicted structures. We then developed a machine learning method based on the Transformer architecture for the design of specific linear binders, in analogy to a language translation task. Our method, TransformerBeta, accurately predicts specific beta strand interactions and samples sequences with beta-sheet-like molecular properties, while capturing interpretable physico-chemical interaction patterns. As such, it can propose specific candidate binders targeting disordered regions for experimental validation to inform protein design.

Cite this Paper

BibTeX
@InProceedings{pmlr-v261-zhao24a, title = {Computational design of target-specific linear peptide binders with TransformerBeta}, author = {Zhao, Haowen and Aprile, Francesco and Bravi, Barbara}, booktitle = {Proceedings of the 19th Machine Learning in Computational Biology meeting}, pages = {1--27}, year = {2024}, editor = {Knowles, David A and Mostafavi, Sara}, volume = {261}, series = {Proceedings of Machine Learning Research}, month = {05--06 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v261/main/assets/zhao24a/zhao24a.pdf}, url = {https://proceedings.mlr.press/v261/zhao24a.html}, abstract = {The computational prediction and design of peptide binders targeting specific epitopes within disordered protein regions is crucial in biological and biomedical research, yet it remains challenging due to their highly dynamic nature and the scarcity of experimentally solved binding data. To address this problem, we built an unprecedentedly large-scale library of peptide pairs within stable secondary structures (beta sheets), leveraging newly available AlphaFold predicted structures. We then developed a machine learning method based on the Transformer architecture for the design of specific linear binders, in analogy to a language translation task. Our method, TransformerBeta, accurately predicts specific beta strand interactions and samples sequences with beta-sheet-like molecular properties, while capturing interpretable physico-chemical interaction patterns. As such, it can propose specific candidate binders targeting disordered regions for experimental validation to inform protein design.} }
Endnote
%0 Conference Paper %T Computational design of target-specific linear peptide binders with TransformerBeta %A Haowen Zhao %A Francesco Aprile %A Barbara Bravi %B Proceedings of the 19th Machine Learning in Computational Biology meeting %C Proceedings of Machine Learning Research %D 2024 %E David A Knowles %E Sara Mostafavi %F pmlr-v261-zhao24a %I PMLR %P 1--27 %U https://proceedings.mlr.press/v261/zhao24a.html %V 261 %X The computational prediction and design of peptide binders targeting specific epitopes within disordered protein regions is crucial in biological and biomedical research, yet it remains challenging due to their highly dynamic nature and the scarcity of experimentally solved binding data. To address this problem, we built an unprecedentedly large-scale library of peptide pairs within stable secondary structures (beta sheets), leveraging newly available AlphaFold predicted structures. We then developed a machine learning method based on the Transformer architecture for the design of specific linear binders, in analogy to a language translation task. Our method, TransformerBeta, accurately predicts specific beta strand interactions and samples sequences with beta-sheet-like molecular properties, while capturing interpretable physico-chemical interaction patterns. As such, it can propose specific candidate binders targeting disordered regions for experimental validation to inform protein design.
APA
Zhao, H., Aprile, F. & Bravi, B.. (2024). Computational design of target-specific linear peptide binders with TransformerBeta. Proceedings of the 19th Machine Learning in Computational Biology meeting, in Proceedings of Machine Learning Research 261:1-27 Available from https://proceedings.mlr.press/v261/zhao24a.html.

Related Material