BAnG: Bidirectional Anchored Generation for Conditional RNA Design

Roman Klypa, Alberto Bietti, Sergei Grudinin
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31020-31043, 2025.

Abstract

Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substantial amount of experimentally determined RNA sequences for each specific protein or a detailed knowledge of RNA structure, restricting their utility in practice. To address this limitation, we develop RNA-BAnG, a deep learning-based model designed to generate RNA sequences for protein interactions without these requirements. Central to our approach is a novel generative method, Bidirectional Anchored Generation (BAnG), which leverages the observation that protein-binding RNA sequences often contain functional binding motifs embedded within broader sequence contexts. We first validate our method on generic synthetic tasks involving similar localized motifs to those appearing in RNAs, demonstrating its benefits over existing generative approaches. We then evaluate our model on biological sequences, showing its effectiveness for conditional RNA sequence design given a binding protein.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-klypa25a, title = {{BA}n{G}: Bidirectional Anchored Generation for Conditional {RNA} Design}, author = {Klypa, Roman and Bietti, Alberto and Grudinin, Sergei}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {31020--31043}, 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/klypa25a/klypa25a.pdf}, url = {https://proceedings.mlr.press/v267/klypa25a.html}, abstract = {Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substantial amount of experimentally determined RNA sequences for each specific protein or a detailed knowledge of RNA structure, restricting their utility in practice. To address this limitation, we develop RNA-BAnG, a deep learning-based model designed to generate RNA sequences for protein interactions without these requirements. Central to our approach is a novel generative method, Bidirectional Anchored Generation (BAnG), which leverages the observation that protein-binding RNA sequences often contain functional binding motifs embedded within broader sequence contexts. We first validate our method on generic synthetic tasks involving similar localized motifs to those appearing in RNAs, demonstrating its benefits over existing generative approaches. We then evaluate our model on biological sequences, showing its effectiveness for conditional RNA sequence design given a binding protein.} }
Endnote
%0 Conference Paper %T BAnG: Bidirectional Anchored Generation for Conditional RNA Design %A Roman Klypa %A Alberto Bietti %A Sergei Grudinin %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-klypa25a %I PMLR %P 31020--31043 %U https://proceedings.mlr.press/v267/klypa25a.html %V 267 %X Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substantial amount of experimentally determined RNA sequences for each specific protein or a detailed knowledge of RNA structure, restricting their utility in practice. To address this limitation, we develop RNA-BAnG, a deep learning-based model designed to generate RNA sequences for protein interactions without these requirements. Central to our approach is a novel generative method, Bidirectional Anchored Generation (BAnG), which leverages the observation that protein-binding RNA sequences often contain functional binding motifs embedded within broader sequence contexts. We first validate our method on generic synthetic tasks involving similar localized motifs to those appearing in RNAs, demonstrating its benefits over existing generative approaches. We then evaluate our model on biological sequences, showing its effectiveness for conditional RNA sequence design given a binding protein.
APA
Klypa, R., Bietti, A. & Grudinin, S.. (2025). BAnG: Bidirectional Anchored Generation for Conditional RNA Design. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:31020-31043 Available from https://proceedings.mlr.press/v267/klypa25a.html.

Related Material