NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones

Urszula Julia Komorowska, Francisco Vargas, Alessandro Rondina, Pietro Lio, Mateja Jamnik
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:31299-31321, 2025.

Abstract

Protein’s backbone flexibility is a crucial property that heavily influences its functionality. Recent work in the field of protein diffusion probabilistic modelling has leveraged Normal Mode Analysis (NMA) and, for the first time, introduced information about large scale protein motion into the generative process. However, obtaining molecules with both the desired dynamics and designable quality has proven challenging. In this work, we present NMA-tune, a new method that introduces the dynamics information to the protein design stage. NMA-tune uses a trainable component to condition the backbone generation on the lowest normal mode of oscillation. We implement NMA-tune as a plug-and-play extension to RFdiffusion, show that the proportion of samples with high quality structure and the desired dynamics is improved as compared to other methods without the trainable component, and we show the presence of the targeted modes in the Molecular Dynamics simulations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-komorowska25a, title = {{NMA}-tune: Generating Highly Designable and Dynamics Aware Protein Backbones}, author = {Komorowska, Urszula Julia and Vargas, Francisco and Rondina, Alessandro and Lio, Pietro and Jamnik, Mateja}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {31299--31321}, 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/komorowska25a/komorowska25a.pdf}, url = {https://proceedings.mlr.press/v267/komorowska25a.html}, abstract = {Protein’s backbone flexibility is a crucial property that heavily influences its functionality. Recent work in the field of protein diffusion probabilistic modelling has leveraged Normal Mode Analysis (NMA) and, for the first time, introduced information about large scale protein motion into the generative process. However, obtaining molecules with both the desired dynamics and designable quality has proven challenging. In this work, we present NMA-tune, a new method that introduces the dynamics information to the protein design stage. NMA-tune uses a trainable component to condition the backbone generation on the lowest normal mode of oscillation. We implement NMA-tune as a plug-and-play extension to RFdiffusion, show that the proportion of samples with high quality structure and the desired dynamics is improved as compared to other methods without the trainable component, and we show the presence of the targeted modes in the Molecular Dynamics simulations.} }
Endnote
%0 Conference Paper %T NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones %A Urszula Julia Komorowska %A Francisco Vargas %A Alessandro Rondina %A Pietro Lio %A Mateja Jamnik %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-komorowska25a %I PMLR %P 31299--31321 %U https://proceedings.mlr.press/v267/komorowska25a.html %V 267 %X Protein’s backbone flexibility is a crucial property that heavily influences its functionality. Recent work in the field of protein diffusion probabilistic modelling has leveraged Normal Mode Analysis (NMA) and, for the first time, introduced information about large scale protein motion into the generative process. However, obtaining molecules with both the desired dynamics and designable quality has proven challenging. In this work, we present NMA-tune, a new method that introduces the dynamics information to the protein design stage. NMA-tune uses a trainable component to condition the backbone generation on the lowest normal mode of oscillation. We implement NMA-tune as a plug-and-play extension to RFdiffusion, show that the proportion of samples with high quality structure and the desired dynamics is improved as compared to other methods without the trainable component, and we show the presence of the targeted modes in the Molecular Dynamics simulations.
APA
Komorowska, U.J., Vargas, F., Rondina, A., Lio, P. & Jamnik, M.. (2025). NMA-tune: Generating Highly Designable and Dynamics Aware Protein Backbones. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:31299-31321 Available from https://proceedings.mlr.press/v267/komorowska25a.html.

Related Material