arxiv: 2604.25244 · v1 · submitted 2026-04-28 · 🧬 q-bio.BM · cs.LG

Recognition: unknown

Learning Structure, Energy, and Dynamics: A Survey of Artificial Intelligence for Protein Dynamics

Haocheng Tang, Jian Tang, Jiarui Lu, Liang Shi, Xixian Liu, Ya-Shi Zhang

Authors on Pith no claims yet

Pith reviewed 2026-05-07 14:08 UTC · model grok-4.3

classification 🧬 q-bio.BM cs.LG

keywords protein dynamicsartificial intelligencemachine learningmolecular dynamicsBoltzmann generatorsconformation generationcoarse-grained modelingcollective variables

0 comments

The pith

Artificial intelligence for protein dynamics organizes into three perspectives: learning structures and trajectories, incorporating energy signals, and accelerating simulations.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This survey organizes recent AI techniques applied to the movements of proteins that drive biological functions. It groups the methods by whether they learn from collections of protein shapes and time series, respect physical energy rules, or speed up the underlying simulations. A reader would care because direct computation of these dynamics is often too expensive and data on moving proteins is scarce. The paper also covers available datasets and flags persistent problems such as scaling the methods, keeping them consistent with thermodynamics, and matching real kinetic behavior.

Core claim

The paper states that advances in AI for protein dynamics fall into three perspectives—learning from structural ensembles and trajectories, learning from physical energy signals, and learning to accelerate molecular simulations—and reviews representative techniques including conformation ensemble generation, trajectory generation, Boltzmann generators, physics-aware adaptation, machine learning potentials, coarse-grained modeling, and collective variable discovery, while discussing datasets and open challenges in scalability, thermodynamic consistency, kinetic fidelity, and experimental integration.

What carries the argument

The three-perspective classification that sorts AI methods according to their primary focus on structural data, energy landscapes, or simulation speedup.

If this is right

Better generation of structural ensembles and trajectories would let researchers identify functional protein states that are hard to observe directly.
Energy-aware methods would produce predictions that automatically follow physical laws and reduce unphysical artifacts.
AI-driven acceleration of simulations would extend the reachable time scales to those relevant for many biological processes.
Resolving the listed challenges would make it easier to combine these computational tools with actual experimental measurements.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

This grouping could help practitioners pick the most suitable AI approach for a given protein system or question.
Future models might blend all three perspectives into single frameworks that handle structure, energy, and speed at once.
The highlighted challenges could serve as a short list of priorities for new method development.

Load-bearing premise

The chosen examples and challenges together give a complete view of current AI work on protein dynamics with no important omissions.

What would settle it

Locating a widely used AI method for protein movements that fits none of the three perspectives or uncovering a major practical barrier the survey does not mention would show the overview is incomplete.

Figures

Figures reproduced from arXiv: 2604.25244 by Haocheng Tang, Jian Tang, Jiarui Lu, Liang Shi, Xixian Liu, Ya-Shi Zhang.

**Figure 1.** Figure 1: Taxonomy of methods and representative works for each direction. view at source ↗

**Figure 2.** Figure 2: Examples of biomolecular conformational dynamics. This figure illustrates diverse dynamic phe view at source ↗

**Figure 3.** Figure 3: Generative modeling of protein structural dynamics from structural data. (A) Conformation ensemble generation. Generative models learn a distribution over protein structures from structural data. By sampling independent conformations from the learned distribution, the model produces multiple structural realizations that collectively form a conformational ensemble. (B) Trajectory generation. Existing appr… view at source ↗

**Figure 4.** Figure 4: Overview of data–energy–model interactions and Boltzmann generator sampling. Top: Structural information from MD trajectories and conformational ensembles provides a structure signal for training generative models, which then sample new structures. Potential energies and force fields can provide a training or inference signal through energy-based losses or guidance, which can also be incorporated during ge… view at source ↗

**Figure 5.** Figure 5: Machine Learning Potentials (MLPs) and Collective Variables (CVs) for Molecular Dynamics. view at source ↗

read the original abstract

Protein dynamics underlie many biological functions, yet remain difficult to characterize due to the high computational cost of molecular dynamics simulations and the scarcity of dynamic structural data. This survey reviews recent advances in artificial intelligence for protein dynamics from three perspectives: learning from structural ensembles and trajectories, learning from physical energy signals, and learning to accelerate molecular simulations. We summarize representative methods for conformation ensemble generation, trajectory generation, Boltzmann generators, physics-aware adaptation, machine learning potentials, coarse-grained modeling, and collective variable discovery. We further discuss available datasets and key open challenges, such as scalability, thermodynamic consistency, kinetic fidelity, and integration with experimental constraints.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

This is a standard survey that organizes AI methods for protein dynamics into three categories but adds no new methods or results.

read the letter

This paper is a survey that reviews AI methods for protein dynamics by breaking them down into three perspectives: learning from structural ensembles and trajectories, learning from physical energy signals, and learning to accelerate molecular simulations. It summarizes methods for things like generating conformation ensembles, creating trajectories, using Boltzmann generators, adapting physics-aware models, machine learning potentials, coarse-grained modeling, and finding collective variables. It also covers datasets and highlights challenges including scalability, thermodynamic consistency, kinetic fidelity, and tying into experimental constraints.

Referee Report

0 major / 3 minor

Summary. The manuscript is a survey of artificial intelligence methods for modeling protein dynamics. It organizes recent advances into three perspectives: learning from structural ensembles and trajectories (covering conformation ensemble generation and trajectory generation), learning from physical energy signals (covering Boltzmann generators, physics-aware adaptation, and machine learning potentials), and learning to accelerate molecular simulations (covering coarse-grained modeling and collective variable discovery). The paper also reviews available datasets and identifies open challenges including scalability, thermodynamic consistency, kinetic fidelity, and integration with experimental constraints.

Significance. If the coverage is accurate and reasonably complete, the survey would provide a useful organizational framework for a rapidly evolving interdisciplinary area at the intersection of AI and biophysics. The three-perspective structure helps clarify how data-driven methods can complement or replace traditional molecular dynamics, and the explicit listing of challenges (thermodynamic consistency, kinetic fidelity) could usefully direct future work. The paper does not introduce new methods or proofs, so its value lies in synthesis rather than novel claims.

minor comments (3)

The abstract states that the survey summarizes 'representative methods' for seven categories, but the main text should include a brief table or explicit list (perhaps in §2 or §4) mapping each cited paper to its primary perspective and method category to improve navigability for readers.
In the discussion of open challenges, the distinction between thermodynamic consistency and kinetic fidelity is conceptually important but would benefit from one or two concrete examples of how a method can satisfy one while failing the other (e.g., a Boltzmann generator that matches equilibrium distributions but not transition rates).
The paper mentions 'available datasets' but does not appear to provide a consolidated table of commonly used benchmarks (e.g., specific protein systems, trajectory lengths, or experimental references); adding such a table in the datasets section would strengthen the survey's utility.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of our survey and for recommending minor revision. The referee's summary accurately captures the manuscript's organization into three perspectives on AI for protein dynamics, the covered methods, datasets, and open challenges. Since no specific major comments were provided in the report, we have no point-by-point responses to offer at this stage.

Circularity Check

0 steps flagged

No circularity: pure survey with no derivations or predictions

full rationale

This is a review paper that organizes and summarizes existing literature on AI methods for protein dynamics across three perspectives (structural ensembles/trajectories, energy signals, simulation acceleration). It presents no original equations, fitted parameters, predictions, or theoretical derivations. All content is descriptive citation of prior work, with no self-referential steps that reduce claims to inputs by construction. The central claim is organizational rather than falsifiable or load-bearing, so no circularity analysis applies.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey the paper introduces no new free parameters, axioms, or invented entities. It reviews methods and challenges already present in the cited literature.

pith-pipeline@v0.9.0 · 5414 in / 1000 out tokens · 75329 ms · 2026-05-07T14:08:19.254699+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

39 extracted references · 29 canonical work pages · 1 internal anchor

[1]

AlphaFold meets flow matching for generating protein ensembles

Bowen Jing, Bonnie Berger, and Tommi Jaakkola. AlphaFold meets flow matching for generating protein ensembles. In Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp, editors,Proceedings of the 41st International Conference on Machine Learning, volume 235 ofProceedings of Machine Learni...

work page arXiv 2025
[2]

Tan, Joey Bose, Chen Lin, Leon Klein, Michael M

Charlie B. Tan, Joey Bose, Chen Lin, Leon Klein, Michael M. Bronstein, and Alexander Tong. Scalable equilibrium sampling with sequential boltzmann generators. InForty-second International Conference on Machine Learning, 2025a. URLhttps://openreview.net/forum?id=U7eMoRDIGihttps://openreview.net/forum?id=U7eMoRDIGi. Charlie B. Tan, Majdi Hassan, Leon Klein,...

work page arXiv
[3]

URL https://www.biorxiv.org/content/early/2026/02/11/2026.02.10.704873https://www.biorxiv.org/content/early/2026/02/11/2026.02.10.704873

doi: 10.64898/2026.02.10.70487310.64898/2026.02.10.704873. URL https://www.biorxiv.org/content/early/2026/02/11/2026.02.10.704873https://www.biorxiv.org/content/early/2026/02/11/2026.02.10.704873. Tong Wang, Xinheng He, Mingyu Li, Yatao Li, Ran Bi, Yusong Wang, Chaoran Cheng, Xiangzhen Shen, Jiawei Meng, He Zhang, Haiguang Liu, Zun Wang, Shaoning Li, Bin ...

work page doi:10.64898/2026.02.10.70487310.64898/2026.02.10.704873 2026
[4]

Ferguson

Wei Chen and Andrew L. Ferguson. Molecular enhanced sampling with autoencoders: On-the-fly collective variable discovery and accelerated free energy landscape exploration.Journal of Computational Chemistry, 39(25):2079–2102, 9

2079
[5]

Exploring the conformational ensembles of protein–protein complex with transformer-based generative model.Journal of Chemical Theory and Computation, 20(11):4469– 4480, 2024c

Jianmin Wang, Xun Wang, Yanyi Chu, Chunyan Li, Xue Li, Xiangyu Meng, Yitian Fang, Kyoung Tai No, Jiashun Mao, and Xiangxiang Zeng. Exploring the conformational ensembles of protein–protein complex with transformer-based generative model.Journal of Chemical Theory and Computation, 20(11):4469– 4480, 2024c. Yusong Wang, Youjun Xu, Wentao Li, Haoyu Yu, Wenju...

2026
[6]

Sarah Lewis, Tim Hempel, José Jiménez-Luna, Michael Gastegger, Yu Xie, Andrew YK Foong, Victor García Satorras, Osama Abdin, Bastiaan S Veeling, Iryna Zaporozhets, et al

URLhttps://arxiv.org/abs/2603.17633https://arxiv.org/abs/2603.17633. Sarah Lewis, Tim Hempel, José Jiménez-Luna, Michael Gastegger, Yu Xie, Andrew YK Foong, Victor García Satorras, Osama Abdin, Bastiaan S Veeling, Iryna Zaporozhets, et al. Scalable emulation of protein equilibrium ensembles with generative deep learning.Science, 389(6761):eadv9817,

work page arXiv
[7]

Physically grounded generative modeling of all-atom biomolecular dynamics.bioRxiv, pages 2026–02, 2026b

Bin Feng, Jiying Zhang, Xinni Zhang, Ming Zhang, Patrick Barth, Zijing Liu, and Yu Li. Physically grounded generative modeling of all-atom biomolecular dynamics.bioRxiv, pages 2026–02, 2026b. Saro Passaro, Gabriele Corso, Jeremy Wohlwend, Mateo Reveiz, Stephan Thaler, Vignesh Ram Somnath, Noah Getz, Tally Portnoi, Julien Roy, Hannes Stark, et al. Boltz-2:...

2026
[8]

arXiv preprint arXiv:2509.13294 (2025)

Allan dos Santos Costa, Manvitha Ponnapati, Dana Rubin, Tess Smidt, and Joseph Jacobson. Accelerating protein molecular dynamics simulation with deepjump.arXiv preprint arXiv:2509.13294,

work page arXiv
[9]

Dynafold: A latent diffusion based generative framework for protein dynamic trajectory.bioRxiv, 2025a

Zirui Fan, Junjie Zhu, and Hai-Feng Chen. Dynafold: A latent diffusion based generative framework for protein dynamic trajectory.bioRxiv, 2025a. Wei Lu, Jixian Zhang, Weifeng Huang, Ziqiao Zhang, Xiangyu Jia, Zhenyu Wang, Leilei Shi, Chengtao Li, Peter G Wolynes, and Shuangjia Zheng. Dynamicbind: predicting ligand-specific protein-ligand complex structure...

work page arXiv
[10]

F3low: Frame-to-frame coarse-grained molecular dynamics with se (3) guided flow matching.arXiv preprint arXiv:2405.00751,

Shaoning Li, Yusong Wang, Mingyu Li, Jian Zhang, Bin Shao, Nanning Zheng, and Jian Tang. F3low: Frame-to-frame coarse-grained molecular dynamics with se (3) guided flow matching.arXiv preprint arXiv:2405.00751,

work page arXiv
[11]

Yaowei Jin, Qi Huang, Ziyang Song, Mingyue Zheng, Dan Teng, and Qian Shi

URLhttps://arxiv.org/abs/2508.03709https://arxiv.org/abs/2508.03709. Yaowei Jin, Qi Huang, Ziyang Song, Mingyue Zheng, Dan Teng, and Qian Shi. P2dflow: A protein ensemble generative model with se(3) flow matching.Journal of Chemical Theory and Computation, 21(6):3288– 3296,

work page arXiv
[12]

Yuyang Wang, Jiarui Lu, Navdeep Jaitly, Josh Susskind, and Miguel Angel Bautista

URL https://openreview.net/forum?id=PtRLxAAKzKhttps://openreview.net/forum?id=PtRLxAAKzK. Yuyang Wang, Jiarui Lu, Navdeep Jaitly, Josh Susskind, and Miguel Angel Bautista. Simplefold: Folding proteins is simpler than you think.arXiv preprint arXiv:2509.18480, 2025a. Nima Shoghi, Yuxuan Liu, Yuning Shen, Rob Brekelmans, Pan Li, and Quanquan Gu. Scalable sp...

work page arXiv
[13]

Joseph C Kim, David Bloore, Karan Kapoor, Jun Feng, Ming-Hong Hao, and Mengdi Wang

URLhttps://openreview.net/forum?id=XCTVFJwS9LJhttps://openreview.net/forum?id=XCTVFJwS9LJ. Joseph C Kim, David Bloore, Karan Kapoor, Jun Feng, Ming-Hong Hao, and Mengdi Wang. Scalable normalizing flows enable boltzmann generators for macromolecules.arXiv preprint arXiv:2401.04246,

work page arXiv
[14]

arXiv preprint arXiv:2409.09787 , year=

URLhttps://arxiv.org/abs/2409.09787https://arxiv.org/abs/2409.09787. Tara Akhound-Sadegh, Jungyoon Lee, Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein, Dominique Beaini, Siamak Ravanbakhsh, Kirill Neklyudov, and Alexander Tong. Pro- gressive inference-time annealing of diffusion models for sampling from boltzmann densities. In The Thi...

work page arXiv
[15]

Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling

URLhttps://arxiv.org/abs/2509.03726https://arxiv.org/abs/2509.03726. Christopher von Klitzing, Denis Blessing, Henrik Schopmans, Pascal Friederich, and Gerhard Neumann. Learning boltzmann generators via constrained mass transport. InThe Fourteenth International Confer- ence on Learning Representations,

work page internal anchor Pith review Pith/arXiv arXiv
[16]

Rehman, O

URL https://arxiv.org/abs/2506.01158https://arxiv.org/abs/2506.01158. 27 Henrik Schopmans, Christopher von Klitzing, and Pascal Friederich. Efficient training of boltzmann gener- ators using off-policy log-dispersion regularization,

work page arXiv
[17]

Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio

URLhttps://arxiv.org/abs/2602.03729https://arxiv.org/abs/2602.03729. Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. Density estimation using real nvp.arXiv preprint arXiv:1605.08803,

work page arXiv
[18]

Chan, Lester Hedges, Meritxell Malagarriga, Rolf David, Miguel de la Puente, Damien Laage, Iñaki Tuñón, Marc W

Valentin Gradisteanu, Elliot W. Chan, Lester Hedges, Meritxell Malagarriga, Rolf David, Miguel de la Puente, Damien Laage, Iñaki Tuñón, Marc W. van der Kamp, and Kir- ill Zinovjev. Simulating enzyme catalysis with electrostatically embedded machine learn- ing potentials.ChemRxiv, 2025(0707),

2025
[19]

URL https://chemrxiv.org/doi/abs/10.26434/chemrxiv-2025-nw9lthttps://chemrxiv.org/doi/abs/10.26434/chemrxiv-2025-nw9lt

doi: 10.26434/chemrxiv-2025-nw9lt10.26434/chemrxiv-2025-nw9lt. URL https://chemrxiv.org/doi/abs/10.26434/chemrxiv-2025-nw9lthttps://chemrxiv.org/doi/abs/10.26434/chemrxiv-2025-nw9lt. Xujian Wang, Haocheng Tang, Xiongwu Wu, Bernard Brooks, Junmei Wang, and Wan- Lu Li. Redefining computational enzymology with multiscale machine learning/molecular mechanics ...

work page doi:10.26434/chemrxiv-2025-nw9lt10.26434/chemrxiv-2025-nw9lt 2025
[20]

Yang et al., MatterSim: A Deep Learning Atomistic Model Across Elements, Temperatures and Pressures

ISSN 2052-4463. Han Yang, Chenxi Hu, Yichi Zhou, Xixian Liu, Yu Shi, Jielan Li, Guanzhi Li, Zekun Chen, Shuizhou Chen, Claudio Zeni, et al. Mattersim: A deep learning atomistic model across elements, temperatures and pressures.arXiv preprint arXiv:2405.04967, 2024a. Haokai Hong, Wanyu Lin, Zhang Chusong, and KC Tan. Geometric graph neural diffusion for st...

work page arXiv 2052
[21]

29 MohammadM.SultanandVijayS.Pande

URLhttps://arxiv.org/abs/2601.22123https://arxiv.org/abs/2601.22123. 29 MohammadM.SultanandVijayS.Pande. Automateddesignofcollectivevariablesusingsupervisedmachine learning.The Journal of Chemical Physics, 149(9), 9

work page arXiv
[22]

Learning collective variables from time-lagged generation

Seonghyun Park, Kiyoung Seong, Soojung Yang, Rafael Gomez-Bombarelli, and Sungsoo Ahn. Learning collective variables from time-lagged generation. InICML 2025 Generative AI and Biology (GenBio) Workshop,

2025
[23]

Adrià Pérez, Pablo Herrera-Nieto, Stefan Doerr, and Gianni De Fabritiis

doi:10.1109/DLS49591.2019.0000710.1109/DLS49591.2019.00007. Adrià Pérez, Pablo Herrera-Nieto, Stefan Doerr, and Gianni De Fabritiis. Adaptivebandit: A multi-armed bandit framework for adaptive sampling in molecular simulations.Journal of Chemical Theory and Com- putation, 16(7):4685–4693,

work page doi:10.1109/dls49591.2019.0000710.1109/dls49591.2019.00007 2019
[24]

arXiv preprint arXiv:2507.17700 (2025)

URL https://arxiv.org/abs/2507.17700https://arxiv.org/abs/2507.17700. Haochuan Chen, Benoît Roux, and Christophe Chipot. Discovering reaction pathways, slow variables, and committor probabilities with machine learning.Journal of Chemical Theory and Computation, 19(14): 4414–4426,

work page arXiv
[25]

doi:10.1038/s43588-025-00828-310.1038/s43588-025-00828-3

ISSN 2662-8457. doi:10.1038/s43588-025-00828-310.1038/s43588-025-00828-3. Bojun Liu, Jordan G Boysen, Ilona Christy Unarta, Xuefeng Du, Yixuan Li, and Xuhui Huang. Exploring transition states of protein conformational changes via out-of-distribution detection in the hyperspherical latent space.Nature communications, 16(1):349, 1

work page doi:10.1038/s43588-025-00828-310.1038/s43588-025-00828-3
[26]

doi:10.1038/s41467-024-55228-410.1038/s41467-024-55228-4

ISSN 2041-1723. doi:10.1038/s41467-024-55228-410.1038/s41467-024-55228-4. Stephan Thaler, Zhiyi Wu, William G. Glass, Richard T. Bradshaw, Gail Bartlett, Prudencio Tossou, and Geoffrey P. F. Wood. Boltz-abfe: Free energy perturbation without crystal structures.Journal of Chemical Theory and Computation, 22(4):1823–1833,

work page doi:10.1038/s41467-024-55228-410.1038/s41467-024-55228-4 2041
[27]

Sam Giannakoulias, John Ferrie, and Andrew Apicello

doi:10.1021/acs.jctc.5c0145110.1021/acs.jctc.5c01451. Sam Giannakoulias, John Ferrie, and Andrew Apicello. Fepω: The end of parameter tuning.ChemRxiv, 2025(1023),

work page doi:10.1021/acs.jctc.5c0145110.1021/acs.jctc.5c01451 2025
[28]

Donald J

doi:10.26434/chemrxiv-2025-bg1t910.26434/chemrxiv-2025-bg1t9. Donald J. M. van P and Willem Jespers. Integrating machine learning into free energy per- turbation workflows.Journal of Chemical Information and Modeling, 65(19):9856–9864,

work page doi:10.26434/chemrxiv-2025-bg1t910.26434/chemrxiv-2025-bg1t9 2025
[29]

31 Helen M Berman, John Westbrook, Zukang Feng, Gary Gilliland, Talapady N Bhat, Helge Weissig, Ilya N Shindyalov, and Philip E Bourne

doi:10.1021/acs.jcim.5c0144910.1021/acs.jcim.5c01449. 31 Helen M Berman, John Westbrook, Zukang Feng, Gary Gilliland, Talapady N Bhat, Helge Weissig, Ilya N Shindyalov, and Philip E Bourne. The protein data bank.Nucleic acids research, 28(1):235–242,

work page doi:10.1021/acs.jcim.5c0144910.1021/acs.jcim.5c01449
[30]

Alphafold protein structure database in 2024: providing structure coverage for over 214 million protein sequences.Nucleic acids research, 52(D1):D368–D375,

Mihaly Varadi, Damian Bertoni, Paulyna Magana, Urmila Paramval, Ivanna Pidruchna, Malarvizhi Rad- hakrishnan, Maxim Tsenkov, Sreenath Nair, Milot Mirdita, Jingi Yeo, et al. Alphafold protein structure database in 2024: providing structure coverage for over 214 million protein sequences.Nucleic acids research, 52(D1):D368–D375,

2024
[31]

Metagenomic-scale analysis of the predicted protein structure universe.bioRxiv, pages 2025–04,

Jingi Yeo, Yewon Han, Nicola Bordin, Andy M Lau, Shaun M Kandathil, Hyunbin Kim, Eli Levy Karin, Milot Mirdita, David T Jones, Christine Orengo, et al. Metagenomic-scale analysis of the predicted protein structure universe.bioRxiv, pages 2025–04,

2025
[32]

Consistent synthetic sequences unlock struc- tural diversity in fully atomistic de novo protein design.arXiv preprint arXiv:2512.01976,

Danny Reidenbach, Zhonglin Cao, Zuobai Zhang, Kieran Didi, Tomas Geffner, Guoqing Zhou, Jian Tang, Christian Dallago, Arash Vahdat, Emine Kucukbenli, et al. Consistent synthetic sequences unlock struc- tural diversity in fully atomistic de novo protein design.arXiv preprint arXiv:2512.01976,

work page arXiv
[33]

Dynamic pdb: A new dataset and a se (3) model extension by integrating dynamic behaviors and physical properties in protein structures.arXiv preprint arXiv:2408.12413,

Ce Liu, Jun Wang, Zhiqiang Cai, Yingxu Wang, Huizhen Kuang, Kaihui Cheng, Liwei Zhang, Qingkun Su, Yining Tang, Fenglei Cao, et al. Dynamic pdb: A new dataset and a se (3) model extension by integrating dynamic behaviors and physical properties in protein structures.arXiv preprint arXiv:2408.12413,

work page arXiv
[34]

Af-calvados: Alphafold-guided simulations of multi-domain proteins at the proteome level.bioRxiv, pages 2025–10,

Sören von Bülow, Kristoffer E Johansson, and Kresten Lindorff-Larsen. Af-calvados: Alphafold-guided simulations of multi-domain proteins at the proteome level.bioRxiv, pages 2025–10,

2025
[35]

Enhanced sampling, public dataset and generative model for drug-protein dissociation dynamics

Maodong Li, Jiying Zhang, Bin Feng, Wenqi Zeng, Dechin Chen, Zhijun Pan, Yu Li, Zijing Liu, and Yi Isaac Yang. Enhanced sampling, public dataset and generative model for drug-protein dissociation dynamics. arXiv preprint arXiv:2504.18367,

work page arXiv
[36]

Mobidb in 2025: inte- grating ensemble properties and function annotations for intrinsically disordered proteins.Nucleic Acids Research, 53(D1):D495–D503,

Damiano Piovesan, Alessio Del Conte, Mahta Mehdiabadi, Maria Cristina Aspromonte, Matthias Blum, Giulio Tesei, Sören von Bülow, Kresten Lindorff-Larsen, and Silvio CE Tosatto. Mobidb in 2025: inte- grating ensemble properties and function annotations for intrinsically disordered proteins.Nucleic Acids Research, 53(D1):D495–D503,

2025
[37]

Uniprot: the universal protein knowledgebase in 2025.Nucleic Acids Research, 53(D1):D609–D617, November

Alex Bateman, Maria-Jesus Martin, Sandra Orchard, Michele Magrane, Aduragbemi Adesina, Shadab Ah- mad, Emily H Bowler-Barnett, Hema Bye-A-Jee, David Carpentier, Paul Denny, Jun Fan, Penelope Garmiri, Leonardo Jose da Costa Gonzales, Abdulrahman Hussein, Alexandr Ignatchenko, Giuseppe In- sana, Rizwan Ishtiaq, Vishal Joshi, Dushyanth Jyothi, Swaathi Kandas...

2025
[38]

doi:10.1093/nar/gkae101010.1093/nar/gkae1010

ISSN 1362-4962. doi:10.1093/nar/gkae101010.1093/nar/gkae1010. URL http://dx.doi.org/10.1093/nar/gkae1010http://dx.doi.org/10.1093/nar/gkae1010. Rommie E. Amaro, Johan Åqvist, Ivet Bahar, Federica Battistini, Adam Bellaiche, Daniel Beltran, Philip C. Biggin, Massimiliano Bonomi, Gregory R. Bowman, Richard A. Bryce, Giovanni Bussi, Paolo Carloni, DavidA.Cas...

work page doi:10.1093/nar/gkae101010.1093/nar/gkae1010
[39]

doi: 10.1063/5.003652210.1063/5.0036522

ISSN 1089-7690. doi: 10.1063/5.003652210.1063/5.0036522. URL http://dx.doi.org/10.1063/5.0036522http://dx.doi.org/10.1063/5.0036522. 34

work page doi:10.1063/5.003652210.1063/5.0036522