---
OA_place: publisher
OA_type: hybrid
PlanS_conform: '1'
_id: '22268'
abstract:
- lang: eng
text: AlphaFold3 predicts highly accurate protein structures from sequence but tends
to collapse to a single dominant conformation, even when the underlying structure
is inherently heterogeneous. Moreover, its predictions are oblivious to experimental
conditions that can alter local sequence conformation. In this work, we show that
AlphaFold3 can be guided to match data obtained by nuclear magnetic resonance
(NMR) spectroscopy, X-ray crystallography and cryogenic electron microscopy (cryo-EM)
experiments and combinations thereof. Our approach can also incorporate data that
explicitly report on dynamics, such as site-resolved order parameters. We demonstrate
that this methodology generates compact structural ensembles whose ensemble-averaged
observables agree with experiment, with fewer distance restraint violations than
traditionally resolved NMR structures and with unmodeled alternate conformations
uncovered in electron density. This methodology paves the way for experimentally
aware predictive models that generate structural ensembles consistent with the
measurements, potentially over multiple modalities, and that can be further refined
toward thermodynamically grounded ensembles by incorporating energetics.
acknowledgement: A. Marx acknowledges the financial support of the Helmsley Fellowships
Program for Sustainability and Health. A.M.B. and P.S. are supported by the Institute
of Science and Technology Austria Internal Project Call grant Generative Protein
NMR. S.V. was supported in part by funding from the Eric and Wendy Schmidt Center
at the Broad Institute of MIT and Harvard. Open access funding provided by Institute
of Science and Technology (IST Austria).
article_processing_charge: Yes (via OA deal)
article_type: original
author:
- first_name: Sai A
full_name: Maddipatla, Sai A
id: e957f5e5-91c9-11f0-a95f-e090f66ecb4d
last_name: Maddipatla
- first_name: Nadav E
full_name: Sellam, Nadav E
id: ef280fe0-91c9-11f0-a95f-8dea3f5bc513
last_name: Sellam
- first_name: Meital I
full_name: Bojan, Meital I
id: 11d88cf5-91ca-11f0-a95f-edf9f08f47b7
last_name: Bojan
- first_name: Vova
full_name: Masalitin, Vova
id: ff7958eb-91c9-11f0-a95f-f3bf65828cf6
last_name: Masalitin
- first_name: Sanketh
full_name: Vedula, Sanketh
last_name: Vedula
- first_name: Paul
full_name: Schanda, Paul
id: 7B541462-FAF6-11E9-A490-E8DFE5697425
last_name: Schanda
orcid: 0000-0002-9350-7606
- first_name: Ailie
full_name: Marx, Ailie
last_name: Marx
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: Maddipatla SA, Sellam NE, Bojan MI, et al. Experiment-guided AlphaFold3 resolves
measurement-consistent protein ensembles. Nature Biotechnology. 2026. doi:10.1038/s41587-026-03166-5
apa: Maddipatla, S. A., Sellam, N. E., Bojan, M. I., Masalitin, V., Vedula, S.,
Schanda, P., … Bronstein, A. M. (2026). Experiment-guided AlphaFold3 resolves
measurement-consistent protein ensembles. Nature Biotechnology. Springer
Nature. https://doi.org/10.1038/s41587-026-03166-5
chicago: Maddipatla, Sai A, Nadav E Sellam, Meital I Bojan, Vova Masalitin, Sanketh
Vedula, Paul Schanda, Ailie Marx, and Alex M. Bronstein. “Experiment-Guided AlphaFold3
Resolves Measurement-Consistent Protein Ensembles.” Nature Biotechnology.
Springer Nature, 2026. https://doi.org/10.1038/s41587-026-03166-5.
ieee: S. A. Maddipatla et al., “Experiment-guided AlphaFold3 resolves measurement-consistent
protein ensembles,” Nature Biotechnology. Springer Nature, 2026.
ista: Maddipatla SA, Sellam NE, Bojan MI, Masalitin V, Vedula S, Schanda P, Marx
A, Bronstein AM. 2026. Experiment-guided AlphaFold3 resolves measurement-consistent
protein ensembles. Nature Biotechnology.
mla: Maddipatla, Sai A., et al. “Experiment-Guided AlphaFold3 Resolves Measurement-Consistent
Protein Ensembles.” Nature Biotechnology, Springer Nature, 2026, doi:10.1038/s41587-026-03166-5.
short: S.A. Maddipatla, N.E. Sellam, M.I. Bojan, V. Masalitin, S. Vedula, P. Schanda,
A. Marx, A.M. Bronstein, Nature Biotechnology (2026).
corr_author: '1'
das_tickbox: '1'
dataavailabilitystatement: All structures and metrics reported in this paper are openly
available on Harvard Dataverse - https://doi.org/10.7910/DVN/PLYUHN. All code is
openly available on GitHub (https://github.com/sai-advaith/guided_alphafold); the
version used for this paper (version 0.9.1) is permanently archived on Zenodo https://doi.org/10.5281/zenodo.17307005
date_created: 2026-07-12T22:02:19Z
date_published: 2026-06-29T00:00:00Z
date_updated: 2026-08-04T09:25:18Z
day: '29'
ddc:
- '570'
department:
- _id: PaSc
- _id: AlBr
- _id: GradSch
doi: 10.1038/s41587-026-03166-5
external_id:
pmid:
- '42374114'
has_accepted_license: '1'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://doi.org/10.1038/s41587-026-03166-5
month: '06'
oa: 1
oa_version: Published Version
pmid: 1
publication: Nature Biotechnology
publication_identifier:
eissn:
- 1546-1696
issn:
- 1087-0156
publication_status: epub_ahead
publisher: Springer Nature
quality_controlled: '1'
related_material:
link:
- description: News on ISTA website
relation: press_release
url: https://ista.ac.at/en/news/toward-experiment-guided-alphafold/
researchdata_availability: yes
scopus_import: '1'
status: public
supplementarymaterial: yes
title: Experiment-guided AlphaFold3 resolves measurement-consistent protein ensembles
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: journal_article
user_id: ba8df636-2132-11f1-aed0-ed93e2281fdd
year: '2026'
...
---
OA_place: publisher
OA_type: gold
_id: '22722'
abstract:
- lang: eng
text: "The local structure of a protein strongly impacts its function and interactions\r\nwith
other molecules. Representing local biomolecular environments remains a\r\nkey
challenge while applying machine learning approaches over protein structures.
The structural and chemical variability of these environments makes them\r\nchallenging
to model, and performing representation learning on these objects\r\nremains largely
under-explored. In this work, we propose representations for\r\nlocal protein
environments that leverage intermediate features from machine learning force fields
(MLFFs). We extensively benchmark state-of-the-art MLFFs,\r\ncomparing their performance
across latent spaces and downstream tasks, and\r\nshow that their embeddings capture
local structural (e.g., secondary motifs) and\r\nchemical features (e.g., amino
acid identity and protonation state), organizing\r\nprotein environments into
a structured manifold. We show that these representations enable zero-shot generalization
and transfer across diverse downstream\r\ntasks. As a case study, we build a physics-informed,
uncertainty-aware chemical shift predictor that achieves state-of-the-art accuracy
in biomolecular NMR\r\nspectroscopy. Our results establish MLFFs as general-purpose,
reusable representation learners for protein modeling, opening new directions
in representation learning for structured physical systems. Code and data are
available at\r\nhttps://github.com/mb012/MLFF_representation.\r\n"
acknowledged_ssus:
- _id: ScienComp
acknowledgement: "This work was supported by the Institute of Science and Technology
Austria (ISTA) through the IPC\r\ngrant “Generative Protein NMR” and by the Israeli
Science Foundation (ISF) under grant number\r\n1834/24. This research used resources
of the Institute of Science and Technology Austria’s scientific\r\ncomputing cluster.
S.V. was supported in part by funding from the Eric and Wendy Schmidt Center at\r\nthe
Broad Institute of MIT and Harvard."
article_processing_charge: No
arxiv: 1
author:
- first_name: Meital I
full_name: Bojan, Meital I
id: 11d88cf5-91ca-11f0-a95f-edf9f08f47b7
last_name: Bojan
- first_name: Sanketh
full_name: Vedula, Sanketh
last_name: Vedula
- first_name: Sai A
full_name: Maddipatla, Sai A
id: e957f5e5-91c9-11f0-a95f-e090f66ecb4d
last_name: Maddipatla
- first_name: Nadav E
full_name: Sellam, Nadav E
id: ef280fe0-91c9-11f0-a95f-8dea3f5bc513
last_name: Sellam
- first_name: Anar
full_name: Rzayev, Anar
id: 2cd60677-9acd-11f1-ae1a-a85ae1c4dd35
last_name: Rzayev
- first_name: Federico
full_name: Napoli, Federico
id: d42e08e7-f4fc-11eb-af0a-d71e26138f1b
last_name: Napoli
orcid: 0000-0002-9043-136X
- first_name: Paul
full_name: Schanda, Paul
id: 7B541462-FAF6-11E9-A490-E8DFE5697425
last_name: Schanda
orcid: 0000-0002-9350-7606
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Bojan MI, Vedula S, Maddipatla SA, et al. Representing local protein environments
with machine learning force fields. In: 14th International Conference on Learning
Representations. Vol 2026. ; 2026:100760-100799.'
apa: Bojan, M. I., Vedula, S., Maddipatla, S. A., Sellam, N. E., Rzayev, A., Napoli,
F., … Bronstein, A. M. (2026). Representing local protein environments with machine
learning force fields. In 14th International Conference on Learning Representations
(Vol. 2026, pp. 100760–100799). Rio de Janeiro, Brazil.
chicago: Bojan, Meital I, Sanketh Vedula, Sai A Maddipatla, Nadav E Sellam, Anar
Rzayev, Federico Napoli, Paul Schanda, and Alex M. Bronstein. “Representing Local
Protein Environments with Machine Learning Force Fields.” In 14th International
Conference on Learning Representations, 2026:100760–99, 2026.
ieee: M. I. Bojan et al., “Representing local protein environments with machine
learning force fields,” in 14th International Conference on Learning Representations,
Rio de Janeiro, Brazil, 2026, vol. 2026, pp. 100760–100799.
ista: 'Bojan MI, Vedula S, Maddipatla SA, Sellam NE, Rzayev A, Napoli F, Schanda
P, Bronstein AM. 2026. Representing local protein environments with machine learning
force fields. 14th International Conference on Learning Representations. ICLR:
International Conference on Learning Representations vol. 2026, 100760–100799.'
mla: Bojan, Meital I., et al. “Representing Local Protein Environments with Machine
Learning Force Fields.” 14th International Conference on Learning Representations,
vol. 2026, 2026, pp. 100760–99.
short: M.I. Bojan, S. Vedula, S.A. Maddipatla, N.E. Sellam, A. Rzayev, F. Napoli,
P. Schanda, A.M. Bronstein, in:, 14th International Conference on Learning Representations,
2026, pp. 100760–100799.
conference:
end_date: 2026-04-27
location: Rio de Janeiro, Brazil
name: 'ICLR: International Conference on Learning Representations'
start_date: 2026-04-23
corr_author: '1'
das_tickbox: '1'
dataavailabilitystatement: "The code, trained models, and data-processing scripts
are publicly available at https://github.\r\ncom/mb012/MLFF_representation. In addition,
complete details of the models and optimization parameters are provided in Appendix
G.3. The hardware resources used to produce the\r\nresults are specified in Appendix
I.4. The loss functions, evaluation metrics, and details regarding\r\nablation studies
are specified in Appendix G. These details ensure that all results reported in the
paper\r\ncan be independently verified."
date_created: 2026-08-17T12:03:24Z
date_published: 2026-05-01T00:00:00Z
date_updated: 2026-08-18T06:36:55Z
day: '01'
ddc:
- '000'
- '570'
department:
- _id: GradSch
- _id: PaSc
- _id: AlBr
external_id:
arxiv:
- '2505.23354'
file:
- access_level: open_access
checksum: 9f43f5469443388ec55388d95c4cf243
content_type: application/pdf
creator: dernst
date_created: 2026-08-18T06:33:14Z
date_updated: 2026-08-18T06:33:14Z
file_id: '22723'
file_name: 2026_ICLR_Bojan.pdf
file_size: 8534339
relation: main_file
success: 1
file_date_updated: 2026-08-18T06:33:14Z
has_accepted_license: '1'
intvolume: ' 2026'
language:
- iso: eng
month: '05'
oa: 1
oa_version: Published Version
page: 100760-100799
publication: 14th International Conference on Learning Representations
publication_status: published
quality_controlled: '1'
related_material:
link:
- relation: software
url: https://github.com/mb012/MLFF_representation
researchdata_availability: yes
status: public
supplementarymaterial: yes
title: Representing local protein environments with machine learning force fields
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 2026
year: '2026'
...
---
OA_place: publisher
OA_type: gold
_id: '21327'
abstract:
- lang: eng
text: Proteins exist as a dynamic ensemble of multiple conformations, and these
motions are often crucial for their functions. However, current structure prediction
methods predominantly yield a single conformation, overlooking the conformational
heterogeneity revealed by diverse experimental modalities. Here, we present a
framework for building experiment-grounded protein structure generative models
that infer conformational ensembles consistent with measured experimental data.
The key idea is to treat stateof-the-art protein structure predictors (e.g., AlphaFold3)
as sequence-conditioned structural priors, and cast ensemble modeling as posterior
inference of protein structures given experimental measurements. Through extensive
real-data experiments, we demonstrate the generality of our method to incorporate
a variety of experimental measurements. In particular, our framework uncovers
previously unmodeled conformational heterogeneity from crystallographic densities,
and generates high-accuracy NMR ensembles orders of magnitude faster than the
status quo. Notably, we demonstrate that our ensembles outperform AlphaFold3 (Abramson
et al., 2024) and sometimes better fit experimental data than publicly deposited
structures to the Protein Data Bank (PDB, Burley et al. (2017)). We believe that
this approach will unlock building predictive models that fully embrace experimentally
observed conformational diversity.
acknowledged_ssus:
- _id: ScienComp
acknowledgement: 'This work was supported by the Israeli Science Foundation (ISF)
grant number 1834/24. We acknowledge support from the Austrian Science Fund (FWF,
grant numbers I5812-B and I6223) and the financial support of the Helmsley Fellowships
Program for Sustainability and Health. This research uses resources of the Institute
of Science and Technology Austria’s scientific computing cluster. '
alternative_title:
- PMLR
article_processing_charge: No
arxiv: 1
author:
- first_name: Sai A
full_name: Maddipatla, Sai A
id: e957f5e5-91c9-11f0-a95f-e090f66ecb4d
last_name: Maddipatla
- first_name: Nadav E
full_name: Sellam, Nadav E
id: ef280fe0-91c9-11f0-a95f-8dea3f5bc513
last_name: Sellam
- first_name: Meital I
full_name: Bojan, Meital I
id: 11d88cf5-91ca-11f0-a95f-edf9f08f47b7
last_name: Bojan
- first_name: Sanketh
full_name: Vedula, Sanketh
id: 94f2fe44-70fa-11f0-b76b-92922c09452b
last_name: Vedula
- first_name: Paul
full_name: Schanda, Paul
id: 7B541462-FAF6-11E9-A490-E8DFE5697425
last_name: Schanda
orcid: 0000-0002-9350-7606
- first_name: Ailie
full_name: Marx, Ailie
last_name: Marx
- first_name: Alexander
full_name: Bronstein, Alexander
id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
last_name: Bronstein
orcid: 0000-0001-9699-8730
citation:
ama: 'Maddipatla SA, Sellam NE, Bojan MI, et al. Inverse problems with experiment-guided
AlphaFold. In: Proceedings of the 42nd International Conference on Machine
Learning. Vol 267. ML Research Press; 2025:42366-42393.'
apa: 'Maddipatla, S. A., Sellam, N. E., Bojan, M. I., Vedula, S., Schanda, P., Marx,
A., & Bronstein, A. M. (2025). Inverse problems with experiment-guided AlphaFold.
In Proceedings of the 42nd International Conference on Machine Learning
(Vol. 267, pp. 42366–42393). Vancouver, Canada: ML Research Press.'
chicago: Maddipatla, Sai A, Nadav E Sellam, Meital I Bojan, Sanketh Vedula, Paul
Schanda, Ailie Marx, and Alex M. Bronstein. “Inverse Problems with Experiment-Guided
AlphaFold.” In Proceedings of the 42nd International Conference on Machine
Learning, 267:42366–93. ML Research Press, 2025.
ieee: S. A. Maddipatla et al., “Inverse problems with experiment-guided AlphaFold,”
in Proceedings of the 42nd International Conference on Machine Learning,
Vancouver, Canada, 2025, vol. 267, pp. 42366–42393.
ista: 'Maddipatla SA, Sellam NE, Bojan MI, Vedula S, Schanda P, Marx A, Bronstein
AM. 2025. Inverse problems with experiment-guided AlphaFold. Proceedings of the
42nd International Conference on Machine Learning. ICML: International Conference
on Machine Learning, PMLR, vol. 267, 42366–42393.'
mla: Maddipatla, Sai A., et al. “Inverse Problems with Experiment-Guided AlphaFold.”
Proceedings of the 42nd International Conference on Machine Learning, vol.
267, ML Research Press, 2025, pp. 42366–93.
short: S.A. Maddipatla, N.E. Sellam, M.I. Bojan, S. Vedula, P. Schanda, A. Marx,
A.M. Bronstein, in:, Proceedings of the 42nd International Conference on Machine
Learning, ML Research Press, 2025, pp. 42366–42393.
conference:
end_date: 2025-07-19
location: Vancouver, Canada
name: 'ICML: International Conference on Machine Learning'
start_date: 2025-07-13
corr_author: '1'
date_created: 2026-02-18T12:11:17Z
date_published: 2025-07-30T00:00:00Z
date_updated: 2026-02-19T08:56:43Z
day: '30'
ddc:
- '000'
- '540'
department:
- _id: PaSc
- _id: AlBr
- _id: GradSch
external_id:
arxiv:
- '2502.09372'
file:
- access_level: open_access
checksum: f33230a6d59b7978d4cd72795e4e9059
content_type: application/pdf
creator: dernst
date_created: 2026-02-19T08:56:10Z
date_updated: 2026-02-19T08:56:10Z
file_id: '21338'
file_name: 2025_ICML_Maddipatla.pdf
file_size: 1924177
relation: main_file
success: 1
file_date_updated: 2026-02-19T08:56:10Z
has_accepted_license: '1'
intvolume: ' 267'
language:
- iso: eng
month: '07'
oa: 1
oa_version: Published Version
page: 42366 - 42393
project:
- _id: eb9c82eb-77a9-11ec-83b8-aadd536561cf
grant_number: I05812
name: AlloSpace. The emergence and mechanisms of allostery
- _id: bdb9578d-d553-11ed-ba76-ed5d39fce6f0
grant_number: I06223
name: Structure and mechanism of the mitochondrial MIM insertase
publication: Proceedings of the 42nd International Conference on Machine Learning
publication_identifier:
eissn:
- 2640-3498
publication_status: published
publisher: ML Research Press
quality_controlled: '1'
status: public
title: Inverse problems with experiment-guided AlphaFold
tmp:
image: /images/cc_by.png
legal_code_url: https://creativecommons.org/licenses/by/4.0/legalcode
name: Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)
short: CC BY (4.0)
type: conference
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 267
year: '2025'
...