CoChat
Sign Up
PreprintCited by 5Protein Structure and DynamicsComputational Drug Discovery MethodsMachine Learning in Bioinformatics

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Conditional Diffusion with Locality-Aware Modal Alignment for Generating Diverse Protein Conformational Ensembles

Open access
Wang, Baoli, Wang, Chenglin, Chen, Jingyang, Liu, Danlin, Sun, Changzhi, Zhang, Jie, Zhang, Kai, Li, Honglin·2025·Nature Machine Intelligence
DOI 10.1101/2025.02.21.639488

Preprint — published as 10.1038/s42256-026-01198-9 · Paper page

Open this paper in CoChat — free account

Abstract

Recent advances in AI have enabled the accurate prediction of a single stable protein structure solely based on its amino acid sequence. However, capturing the complete conformational landscape of a protein and its dynamic flexibility remains challenging. In this work, we developed Modal-aligned conditional Diffusion (Mac-Diff), a score based diffusion model for generating the conformational ensembles for unseen proteins. Central to Mac-Diff is an innovative attention module that enforces a delicate, locality-aware alignment between the conditional view (protein sequence) and the target view (residue pair geometry) to compute highly contextualized features for effective structural denoising. Furthermore, Mac-Diff leverages semantically rich sequence embedding from Protein Language Models like ESM-2 in enforcing the protein sequence condition that captures evolutionary, structural and functional information. This compensates for protein structural heterogeneity more effectively than embeddings from structure prediction models that are possibly biased to the dominant conformation. Mac-Diff showed promising results in generating realistic and diverse protein structures. It successfully recovered conformational distributions of fast folding proteins, captured multiple meta-stable conformations that were only observed in long MD simulation trajectories and efficiently predicted alternative conformations for allosteric proteins. We believe that Mac-Diff offers a useful tool to improve understanding of protein dynamics and structural variability, with broad implications for structural biology, drug discovery, and protein engineering.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2025.02.21.639488

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 64

  1. 10.1021/acs.jpcb.2c04346 · DOI · Paper page
  2. 10.1126/science.abc2754 · DOI · Paper page
  3. 10.1146/annurev.biophys.093008.131258 · DOI · Paper page
  4. 10.1126/science.1219021 · DOI · Paper page
  5. 10.1021/cr040426m · DOI
  6. Shaw, D. E. , Grossman, J. , Bank, J. A. , Batson, B. , Butts, J. A. , Chao, J. C. , Deneroff, M. M. , Dror, R. O. , Even, A. , Fenton, C. H. et al. Anton 2: raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer. In SC’14: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, 41–53 (IEEE, 2014). · DOI
  7. Yang, Y. I. , Shao, Q. , Zhang, J. , Yang, L. & Gao, Y. Q . Enhanced sampling in molecular dynamics. The J . chemical physics 151 (2019). · DOI
  8. 10.3389/fmolb.2022.832847 · DOI
  9. 10.1093/bioinformatics/btac202 · DOI · Paper page
  10. 10.1038/s41592-023-02087-4 · DOI · Paper page
  11. 10.1038/s41467-024-46715-9 · DOI · Paper page
  12. 10.1371/journal.pcbi.1010483 · DOI · Paper page
  13. 10.1002/prot.26382 · DOI · Paper page
  14. 10.1021/acs.jctc.3c00290 · DOI
  15. 10.1021/jacsau.3c00188 · DOI
  16. 10.1016/j.sbi.2023.102645 · DOI · Paper page
  17. 10.1038/s41592-021-01357-3 · DOI
  18. 10.1038/s41467-023-36443-x · DOI · Paper page
  19. 10.1021/acs.jctc.3c01057 · DOI
  20. 10.3389/fmolb.2021.781635 · DOI · Paper page
  21. Sohl-Dickstein, J. , Weiss, E. , Maheswaranathan, N. & Ganguli, S. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning, 2256–2265 (PMLR, 2015).
  22. 10.1038/s41467-024-45051-2 · DOI
  23. Lu, J. , Zhong, B. , Zhang, Z. & Tang, J . Str2str: A score-based framework for zero-shot protein conformation sampling. In The Twelfth International Conference on Learning Representations (2024).
  24. Jing, B. , Erives, E. , Pao-Huang, P. , Corso, G. , Berger, B. & Jaakkola, T. S . Eigenfold: Generative protein structure prediction with diffusion models. In ICLR 2023-Machine Learning for Drug Discovery workshop (2023).
  25. YanWang , Wang, L. , Shen, Y. , Wang, Y. , Yuan, H. , Wu, Y. & Gu, Q. Protein conformation generation via force-guided SE(3) diffusion models. In Forty-first International Conference on Machine Learning (2024).
  26. Jing, B. , Berger, B. & Jaakkola, T . Alphafold meets flow matching for generating protein ensembles. In Forty-first International Conference on Machine Learning (2024).
  27. 10.1371/journal.pcbi.1012144 · DOI · Paper page
  28. Lisanza, S. L. , Gershon, J. M. , Tipps, S. W. , Sims, J. N. , Arnoldt, L. , Hendel, S. J. , Simma, M. K. , Liu, G. , Yase, M. , Wu, H. et al. Multistate and functional protein design using rosettafold sequence space diffusion. Nat . biotechnology 1–11 (2024). · DOI
  29. 10.1038/s41586-023-06415-8 · DOI · Paper page
  30. 10.1038/s41586-023-06728-8 · DOI · Paper page
  31. 2024, Diffusion models in bioinformatics and computational biology, Nat. reviews bioengineering, 2, 136
  32. 10.1126/science.ade2574 · DOI · Paper page
  33. Wu, R. , Ding, F. , Wang, R. , Shen, R. , Zhang, X. , Luo, S. , Su, C. , Wu, Z. , Xie, Q. , Berger, B. et al. High-resolution de novo structure prediction from primary sequence. BioRxiv 2022–07 (2022).
  34. Yim, J. , Trippe, B. L. , De Bortoli, V. , Mathieu, E. , Doucet, A. , Barzilay, R. & Jaakkola, T. Se (3) diffusion model with application to protein backbone generation. In International Conference on Machine Learning, 40001–40039 (PMLR, 2023).
  35. 10.1038/s41467-024-51801-z · DOI · Paper page
  36. Rombach, R. , Blattmann, A. , Lorenz, D. , Esser, P. & Ommer, B . High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 10684–10695 (2022). · DOI · Paper page
  37. 10.1021/acs.jctc.3c00702 · DOI
  38. 10.1038/s41467-024-51507-2 · DOI · Paper page
  39. 10.1038/s41592-020-0884-y · DOI
  40. 10.1093/nar/gkad1084 · DOI
  41. 10.1126/science.1208351 · DOI · Paper page
  42. Naritomi, Y. & Fuchigami, S . Slow dynamics in protein fluctuations revealed by time-structure based independent component analysis: the case of domain motions. The J . chemical physics 134 (2011). · DOI
  43. 10.1371/journal.pcbi.1005324 · DOI · Paper page
  44. 10.1093/bioinformatics/bts598 · DOI
  45. 10.1126/science.1187409 · DOI · Paper page
  46. Scott, D. W. Multivariate density estimation: theory, practice, and visualization (John Wiley & Sons, 2015). · DOI · Paper page
  47. Chakraborty, S. , Venkatramani, R. , Rao, B. J. , Asgeirsson, B. & Dandekar, A. M . Protein structure quality assessment based on the distance profiles of consecutive backbone cα atoms. F1000Research 2 (2013). · DOI
  48. 10.1016/S0022-2836(63)80023-6 · DOI
  49. 10.1002/prot.20264 · DOI · Paper page
  50. 10.1093/bioinformatics/btl158 · DOI
  51. 10.1016/j.str.2008.04.013 · DOI
  52. 10.1074/jbc.M707632200 · DOI
  53. 10.3390/ijms10041729 · DOI
  54. Kim, G. , Lee, S. , Levy Karin, E. , Kim, H. , Moriwaki, Y. , Ovchinnikov, S. , Steinegger, M. & Mirdita, M . Easy and accurate protein structure prediction using colabfold. Nat. Protoc. 1–23 (2024). · DOI
  55. Peebles, W. & Xie, S . Scalable diffusion models with transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 4195–4205 (2023). · DOI · Paper page
  56. Lipman, Y. , Chen, R. T. , Ben-Hamu, H. , Nickel, M. & Le, M. Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022). · arXiv
  57. Ingraham, J. , Riesselman, A. , Sander, C. & Marks, D . Learning protein structure with a differentiable simulator. In International conference on learning representations (2018).
  58. 2023, Openmm 8: molecular dynamics simulation with machine learning potentials, The J. Phys. Chem. B, 128, 109
  59. Xue, S. , Yi, M. , Luo, W. , Zhang, S. , Sun, J. , Li, Z. & Ma, Z.-M . Sa-solver: Stochastic adams solver for fast sampling of diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024).
  60. Gonzalez, M. , Fernandez Pinto, N. , Tran, T. , Hajri, H. , Masmoudi, N. et al. Seeds: Exponential sde solvers for fast high-quality sampling from diffusion models. Adv. Neural Inf. Process. Syst. 36 (2024). · DOI
  61. 2022, Elucidating the design space of diffusion-based generative models, Adv. neural information processing systems, 35, 26565
  62. Rao, R. M. , Liu, J. , Verkuil, R. , Meier, J. , Canny, J. , Abbeel, P. , Sercu, T. & Rives, A. Msa transformer. In International Conference on Machine Learning, 8844–8856 (PMLR, 2021). · DOI · Paper page
  63. 2022, Elucidating the design space of diffusion-based generative models, Adv. neural information processing systems, 35, 26565
  64. 10.1126/science.aaw1147 · DOI

Metadata

Authors
Wang, B., Wang, C., Chen, J., Liu, D., Sun, C., Zhang, J., Zhang, K., & Li, H.
Affiliations
  • East China University of Science and Technology (CN)
  • East China Normal University (CN)
  • Shanghai Medical College of Fudan University (CN)
ORCID
Venue
Nature Machine Intelligence
Publisher
openRxiv
Published
2025-02-27
Volume
8
Issue
3
Pages
415-434
ISSN
2522-5839 (ISSN-L)
DOI
10.1101/2025.02.21.639488
OpenAlex
W7131351614
Cited by
5
References
8
Citations by year
2026: 4 · 2025: 1
FWCI
8.37
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Machine Intelligence (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion)
Funders
  • National Natural Science Foundation of China (82173690, 2022YFC3400501, 82 425 104, 62276099)
  • National Key Research and Development Program of China (82173690, 2022YFC3400501)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
Keywords
conditional diffusion models, protein conformational ensembles, modal alignment, protein structure generation, protein flexibility, structural heterogeneity

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review