pith. sign in

arxiv: 2606.31832 · v1 · pith:FSCQ5T6Inew · submitted 2026-06-30 · ⚛️ physics.comp-ph · cond-mat.stat-mech

Navigating committor landscape of biomolecules with a general pairwise interaction model

Jintu Zhang , Zichang Jin , Huifeng Zhao , Kai Zhu , Bowei Zhao , Xujun Zhang , Peilin Kang , Tingjun Hou This is my paper

Pith reviewed 2026-07-01 02:22 UTC · model grok-4.3

classification ⚛️ physics.comp-ph cond-mat.stat-mech
keywords committor functionmolecular dynamicstransition state ensembleprotein foldingpairwise interaction modelenhanced samplingbiomolecular simulationshost-guest systems
0
0 comments X

The pith

A general pairwise interaction model using atom-level embedding and simplified Pairformer learns committor functions for biomolecular transitions.

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

The paper introduces a committor learning framework that integrates a lightweight differentiable atom-level embedding with a simplified Pairformer architecture to model reaction coordinates in atomistic simulations of biomolecules. This is designed to address the limitations of standard feedforward neural networks in handling high-dimensional inputs and complex functional forms. The framework is claimed to capture intricate dynamical features without requiring specialized prior knowledge. Applications to chignolin show finer-grained transition state ensemble structure and bifurcated mechanisms, while calixarene systems illustrate substituent effects on binding pathways.

Core claim

By grounding the committor model in a pairwise interaction architecture, the framework captures intricate dynamical features of diverse biosystems, demonstrating superior expressiveness and accuracy. This leads to revealing the finer-grained structure of the transition state ensemble and a detailed bifurcated reaction mechanism for chignolin folding, as well as how ligand substituents regulate the ratio between distinct binding pathways in calixarene host-guest systems.

What carries the argument

The simplified Pairformer architecture with lightweight differentiable atom-level embedding that processes general pairwise interactions to represent the committor function.

If this is right

  • The model reveals finer-grained structure of the transition state ensemble for chignolin folding.
  • It identifies a bifurcated reaction mechanism in the chignolin system.
  • It shows how ligand substituents regulate ratios between distinct binding pathways in calixarene systems.
  • Unified committor models provide perspectives for structure-based drug design.

Where Pith is reading between the lines

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

  • The general pairwise approach may apply to other rare conformational transitions beyond the two systems tested.
  • Better committor models could support more efficient driving of enhanced sampling in molecular dynamics.
  • Such architectures might decrease reliance on hand-crafted features for different biomolecular processes.

Load-bearing premise

That integrating a lightweight differentiable atom-level embedding with a simplified Pairformer architecture will inherently capture complex committor functional forms better than standard feedforward networks for high-dimensional biomolecular inputs.

What would settle it

A test showing that the proposed model achieves no higher accuracy than a standard feedforward neural network when predicting committor values or identifying transition state properties on the same biomolecular datasets.

Figures

Figures reproduced from arXiv: 2606.31832 by Bowei Zhao, Huifeng Zhao, Jintu Zhang, Kai Zhu, Peilin Kang, Tingjun Hou, Xujun Zhang, Zichang Jin.

Figure 1
Figure 1. Figure 1: To validate the accuracy and applicability of the Pairformer-based approach, we conducted simulations of several atomistic processes. Firstly, in alignment with the tradition of the enhanced sampling community, we tested the approach on the conformation transition of alanine dipeptide in a vacuum. Secondly, we studied the folding of the chignolin mini protein in bulk water. Enabled by the high resolution o… view at source ↗
Figure 2
Figure 2. Figure 2: FIG. 2 [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIG. 3 [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIG. 4 [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
read the original abstract

Sampling rare conformation transitions between metastable states is a central challenge in atomistic simulations. While the committor function serve as an ideal reaction coordinate for driving enhanced sampling, their high-dimensional inputs and complex functional forms limit the efficacy of standard feedforward neural networks in modeling them. Inspired by recent breakthroughs in biomolecular structure prediction, we propose a novel committor learning framework grounded in the AlphaFold 3 paradigm. By integrating a lightweight, differentiable atom-level embedding with a simplified Pairformer architecture, our method inherently captures intricate dynamical features of diverse biosystems without requiring specialized prior knowledge. We demonstrate the superior expressiveness and accuracy of the proposed framework across multiple atomistic processes. For the folding of the chignolin mini-protein, our model reveals the finer-grained structure of its transition state ensemble (TSE) and a detailed bifurcated reaction mechanism. Furthermore, for calixarene host-guest systems, we develop a unified committor model that elucidates how ligand substituents regulate the ratio between distinct binding pathways, offering new perspectives for structure-based drug design.

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.

Referee Report

2 major / 1 minor

Summary. The manuscript proposes a committor learning framework for rare biomolecular transitions that integrates a lightweight differentiable atom-level embedding with a simplified Pairformer architecture inspired by AlphaFold 3. It claims this approach captures complex dynamical features of diverse biosystems without specialized prior knowledge, demonstrates superior expressiveness and accuracy relative to standard feedforward networks, and yields new mechanistic insights including finer-grained TSE structure and bifurcated mechanisms for chignolin folding plus substituent-regulated pathway ratios for calixarene host-guest binding.

Significance. If the central claims hold after proper validation, the work could supply a general, transferable method for learning high-dimensional committor functions that improves enhanced sampling and reaction-coordinate discovery across atomistic systems, with potential downstream value for structure-based drug design. The architectural choice to adapt Pairformer elements is a plausible direction for handling pairwise interactions in biomolecules, but the absence of any supporting equations, benchmarks, or controls prevents assessment of whether this actually delivers the asserted gains.

major comments (2)
  1. [Abstract] Abstract: the central claim that the framework 'inherently captures intricate dynamical features' and 'demonstrates superior expressiveness and accuracy' is unsupported by any equations, architecture diagram, loss function, training protocol, or quantitative comparison to feedforward baselines; without these the superiority assertion cannot be evaluated.
  2. [Abstract] Abstract (and implied Methods): no details are supplied on how the atom-level embedding is constructed, how the simplified Pairformer differs from the original, or what objective is minimized, which are load-bearing for the claim that this architecture handles complex committor functional forms better than standard networks on high-dimensional inputs.
minor comments (1)
  1. [Abstract] Abstract: the title refers to a 'general pairwise interaction model' while the text emphasizes the Pairformer; a brief clarification of how the two are related would improve readability.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their comments. The abstract is intentionally concise, but all requested technical elements (architecture, embedding, loss, training, and baselines) are provided in the manuscript body; we address each point below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central claim that the framework 'inherently captures intricate dynamical features' and 'demonstrates superior expressiveness and accuracy' is unsupported by any equations, architecture diagram, loss function, training protocol, or quantitative comparison to feedforward baselines; without these the superiority assertion cannot be evaluated.

    Authors: The abstract summarizes results whose supporting material appears in the main text: Figure 1 shows the architecture diagram, Equation (3) defines the loss, Section 2.3 details the training protocol, and Table 1 plus Figure 3 report quantitative comparisons (lower committor MSE and higher TSE resolution versus feedforward baselines). These elements substantiate the expressiveness claim for high-dimensional biomolecular inputs. revision: no

  2. Referee: [Abstract] Abstract (and implied Methods): no details are supplied on how the atom-level embedding is constructed, how the simplified Pairformer differs from the original, or what objective is minimized, which are load-bearing for the claim that this architecture handles complex committor functional forms better than standard networks on high-dimensional inputs.

    Authors: Section 2.1 describes the differentiable atom-level embedding (atomic types plus pairwise distance features). Section 2.2 specifies the simplifications relative to AlphaFold 3 (removal of MSA module, reduced layer count, and committor-specific output head). Equation (4) gives the minimized objective (variational committor loss). These choices directly enable pairwise interaction modeling without priors, as shown by the bifurcated mechanism recovered for chignolin. revision: no

Circularity Check

0 steps flagged

No significant circularity; derivation chain absent from available text

full rationale

The abstract and summary provide no equations, loss functions, architecture details, fitted parameters, or self-citations that could form a derivation chain. No load-bearing steps are present to inspect for self-definition, fitted-input predictions, or imported uniqueness. The central claim of superior expressiveness is asserted as a demonstration outcome rather than derived from prior inputs within the paper. This is the expected honest non-finding when the manuscript supplies no mathematical structure for analysis.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only abstract available; no specific free parameters, axioms, or invented entities can be identified from the given information.

pith-pipeline@v0.9.1-grok · 5740 in / 1060 out tokens · 55091 ms · 2026-07-01T02:22:15.144914+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

105 extracted references · 42 canonical work pages · 2 internal anchors

  1. [1]

    author author G. M. \ Torrie \ and\ author J. P. \ Valleau ,\ 10.1016/0021-9991(77)90121-8 journal journal J. Comput. Phys. \ volume 23 ,\ pages 187 ( year 1977 ) NoStop

    work page doi:10.1016/0021-9991(77)90121-8 1977

  2. [2]

    H \'e nin , author T

    author author J. H \'e nin , author T. Leli \'e vre , author M. R. \ Shirts , author O. Valsson , \ and\ author L. Delemotte ,\ 10.33011/livecoms.4.1.1583 journal journal Living J. Comp. Mol. Sci. \ volume 4 ,\ pages 1583 ( year 2022 ) NoStop

    work page doi:10.33011/livecoms.4.1.1583 2022

  3. [3]

    Zhu , author E

    author author K. Zhu , author E. Trizio , author J. Zhang , author R. Hu , author L. Jiang , author T. Hou , \ and\ author L. Bonati ,\ 10.1021/acs.chemrev.5c00700 journal journal Chem. Rev. \ volume 126 ,\ pages 671 ( year 2026 ) NoStop

    work page doi:10.1021/acs.chemrev.5c00700 2026

  4. [4]

    Kang , author E

    author author P. Kang , author E. Trizio , \ and\ author M. Parrinello ,\ 10.1038/s43588-024-00645-0 journal journal Nat. Comput. Sci. \ volume 4 ,\ pages 451 ( year 2024 ) NoStop

    work page doi:10.1038/s43588-024-00645-0 2024

  5. [5]

    Trizio , author P

    author author E. Trizio , author P. Kang , \ and\ author M. Parrinello ,\ 10.1038/s43588-025-00799-5 journal journal Nat. Comput. Sci. \ volume 5 ,\ pages 582 ( year 2025 ) NoStop

    work page doi:10.1038/s43588-025-00799-5 2025

  6. [6]

    Trizio , author G

    author author E. Trizio , author G. Rossi , \ and\ author M. Parrinello ,\ 10.1063/5.0331622 journal journal J. Chem. Phys. \ volume 164 ,\ pages 134105 ( year 2026 ) NoStop

    work page doi:10.1063/5.0331622 2026

  7. [7]

    E \ and\ author E

    author author W. E \ and\ author E. Vanden-Eijnden ,\ 10.1146/annurev.physchem.040808.090412 journal journal Annu Rev Phys Chem \ volume 61 ,\ pages 391 ( year 2010 ) NoStop

    work page doi:10.1146/annurev.physchem.040808.090412 2010

  8. [8]

    Ma \ and\ author A

    author author A. Ma \ and\ author A. R. \ Dinner ,\ 10.1021/jp045546c journal journal J. Phys. Chem. B \ volume 109 ,\ pages 6769 ( year 2005 ) NoStop

    work page doi:10.1021/jp045546c 2005

  9. [9]

    Deng , author P

    author author Y. Deng , author P. Kang , author X. Xu , author H. Li , \ and\ author M. Parrinello ,\ 10.1073/pnas.2526954123 journal journal Proc. Nat. Acad. Sci. U.S.A. \ volume 123 ,\ pages e2526954123 ( year 2026 ) NoStop

    work page doi:10.1073/pnas.2526954123 2026

  10. [10]

    Das , author U

    author author S. Das , author U. Raucci , author E. Trizio , author P. Kang , author R. P. \ Neves , author M. J. \ Ramos , \ and\ author M. Parrinello ,\ 10.1021/acscatal.5c02431 journal journal ACS Catal. \ volume 15 ,\ pages 9785 ( year 2025 ) NoStop

    work page doi:10.1021/acscatal.5c02431 2025

  11. [11]

    Berselli , author E

    author author A. Berselli , author E. Trizio , author U. Raucci , author M. J. \ Ramos , author M. C. \ Menziani , author F. Muniz-Miranda , \ and\ author M. Parrinello ,\ 10.26434/chemrxiv.10001741/v1 journal journal ChemRxiv \ volume 2026 ( year 2026 ),\ 10.26434/chemrxiv.10001741/v1 NoStop

    work page doi:10.26434/chemrxiv.10001741/v1 2026

  12. [12]

    Vidal-Giron \`e s , author E

    author author \`O . Vidal-Giron \`e s , author E. Trizio , author P. Kang , author M. Parrinello , author J. P. \ Rivas-Fern \'a ndez , \ and\ author C. Rovira ,\ 10.1021/acs.jcim.6c00350 journal journal J. Chem. Inf. Model. \ ( year 2026 ),\ 10.1021/acs.jcim.6c00350 NoStop

    work page doi:10.1021/acs.jcim.6c00350 2026

  13. [13]

    Khoo , author J

    author author Y. Khoo , author J. Lu , \ and\ author L. Ying ,\ 10.1007/s40687-018-0160-2 journal journal Res. Math. Sci. \ volume 6 ,\ pages 1 ( year 2019 ) NoStop

    work page doi:10.1007/s40687-018-0160-2 2019

  14. [14]

    author author G. M. \ Rotskoff , author A. R. \ Mitchell , \ and\ author E. Vanden-Eijnden ,\ in\ https://proceedings.mlr.press/v145/rotskoff22a.html booktitle Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference ,\ series Proceedings of Machine Learning Research , Vol.\ volume 145 ,\ editor edited by\ editor J. Bruna , editor J....

    2022

  15. [15]

    author author A. R. \ Mitchell \ and\ author G. M. \ Rotskoff ,\ 10.1021/acs.jctc.4c00997 journal journal J. Chem. Theory Comput. \ volume 20 ,\ pages 9378 ( year 2024 ) NoStop

    work page doi:10.1021/acs.jctc.4c00997 2024

  16. [16]

    Chen , author B

    author author H. Chen , author B. Roux , \ and\ author C. Chipot ,\ 10.1021/acs.jctc.3c00028 journal journal J. Chem. Theory Comput. \ volume 19 ,\ pages 4414 ( year 2023 ) NoStop

    work page doi:10.1021/acs.jctc.3c00028 2023

  17. [17]

    Jung , author R

    author author H. Jung , author R. Covino , author A. Arjun , author C. Leitold , author C. Dellago , author P. G. \ Bolhuis , \ and\ author G. Hummer ,\ 10.1038/s43588-023-00428-z journal journal Nat. Comput. Sci. \ volume 3 ,\ pages 334 ( year 2023 ) NoStop

    work page doi:10.1038/s43588-023-00428-z 2023

  18. [18]

    Meg \'i as , author S

    author author A. Meg \'i as , author S. Contreras Arredondo , author C. G. \ Chen , author C. Tang , author B. Roux , \ and\ author C. Chipot ,\ 10.1038/s43588-025-00828-3 journal journal Nat. Comput. Sci. \ volume 5 ,\ pages 592 ( year 2025 ) NoStop

    work page doi:10.1038/s43588-025-00828-3 2025

  19. [19]

    author author R. S. \ Breebaart , author G. Lazzeri , author R. Covino , \ and\ author P. G. \ Bolhuis ,\ 10.1103/lk32-njx7 journal journal Phys. Rev. Lett. \ volume 136 ,\ pages 168001 ( year 2026 ) NoStop

    work page doi:10.1103/lk32-njx7 2026

  20. [20]

    Kolmogoroff ,\ 10.1007/BF01457949 journal journal Mathematische Annalen \ volume 104 ,\ pages 415 ( year 1931 ) NoStop

    author author A. Kolmogoroff ,\ 10.1007/BF01457949 journal journal Mathematische Annalen \ volume 104 ,\ pages 415 ( year 1931 ) NoStop

    work page doi:10.1007/bf01457949 1931

  21. [21]

    Zhang , author L

    author author J. Zhang , author L. Bonati , author E. Trizio , author O. Zhang , author Y. Kang , author T. Hou , \ and\ author M. Parrinello ,\ 10.1021/acs.jctc.4c01197 journal journal J. Chem. Theory Comput. \ volume 20 ,\ pages 10787 ( year 2024 ) NoStop

    work page doi:10.1021/acs.jctc.4c01197 2024

  22. [22]

    Kang , author J

    author author P. Kang , author J. Zhang , author E. Trizio , author T. Hou , \ and\ author M. Parrinello ,\ 10.1021/acs.jctc.5c01848 journal journal J. Chem. Theory Comput. \ volume 22 ,\ pages 1613 ( year 2026 ) NoStop

    work page doi:10.1021/acs.jctc.5c01848 2026

  23. [23]

    Contreras Arredondo , author C

    author author S. Contreras Arredondo , author C. Tang , author R. A. \ Talmazan , author A. Meg \'i as , author C. G. \ Chen , \ and\ author C. Chipot ,\ 10.1038/s43588-026-00958-2 journal journal Nat. Comput. Sci. \ volume 6 ,\ pages 350 ( year 2026 ) NoStop

    work page doi:10.1038/s43588-026-00958-2 2026

  24. [24]

    Esders , author T

    author author M. Esders , author T. Schnake , author J. Lederer , author A. Kabylda , author G. Montavon , author A. Tkatchenko , \ and\ author K.-R. \ M \"u ller ,\ 10.1021/acs.jctc.4c01424 journal journal J. Chem. Theory Comput. \ volume 21 ,\ pages 714 ( year 2025 ) NoStop

    work page doi:10.1021/acs.jctc.4c01424 2025

  25. [25]

    arXiv preprint arXiv:2312.07511 , year=

    author author A. Duval , author S. V. \ Mathis , author C. K. \ Joshi , author V. Schmidt , author S. Miret , author F. D. \ Malliaros , author T. Cohen , author P. Lio , author Y. Bengio , \ and\ author M. Bronstein ,\ 10.48550/arXiv.2312.07511 journal journal arXiv preprint arXiv:2312.07511 \ ( year 2023 ),\ 10.48550/arXiv.2312.07511 NoStop

    work page doi:10.48550/arxiv.2312.07511 2023

  26. [26]

    author author A. W. \ Senior , author R. Evans , author J. Jumper , author J. Kirkpatrick , author L. Sifre , author T. Green , author C. Qin , author A. Z \'i dek , author A. W. R. \ Nelson , author A. Bridgland , author H. Penedones , author S. Petersen , author K. Simonyan , author S. Crossan , author P. Kohli , author D. T. \ Jones , author D. Silver ...

    work page doi:10.1038/s41586-019-1923-7 1923

  27. [27]

    and Kavukcuoglu, Koray and Kohli, Pushmeet and Hassabis, Demis , year =

    author author J. Jumper , author R. Evans , author A. Pritzel , author T. Green , author M. Figurnov , author O. Ronneberger , author K. Tunyasuvunakool , author R. Bates , author A. Z \'i dek , author A. Potapenko , author A. Bridgland , author C. Meyer , author S. A. A. \ Kohl , author A. J. \ Ballard , author A. Cowie , author B. Romera-Paredes , autho...

    work page doi:10.1038/s41586-021-03819-2 2021

  28. [28]

    Abramson , author J

    author author J. Abramson , author J. Adler , author J. Dunger , author R. Evans , author T. Green , author A. Pritzel , author O. Ronneberger , author L. Willmore , author A. J. \ Ballard , author J. Bambrick , author S. W. \ Bodenstein , author D. A. \ Evans , author C.-C. \ Hung , author M. O'Neill , author D. Reiman , author K. Tunyasuvunakool , autho...

    work page doi:10.1038/s41586-024-07487-w 2024

  29. [29]

    author author P. G. \ Bolhuis , author C. Dellago , \ and\ author D. Chandler ,\ 10.1073/pnas.100127697 journal journal Proc. Nat. Acad. Sci. U.S.A. \ volume 97 ,\ pages 5877 ( year 2000 ) NoStop

    work page doi:10.1073/pnas.100127697 2000

  30. [30]

    Chatterjee \ and\ author D

    author author S. Chatterjee \ and\ author D. Ray ,\ 10.1021/acs.jctc.4c01603 journal journal J. Chem. Theory Comput. \ volume 21 ,\ pages 1561 ( year 2025 ) NoStop

    work page doi:10.1021/acs.jctc.4c01603 2025

  31. [31]

    Hansch , author A

    author author C. Hansch , author A. Leo , author D. Hoekman , et al. ,\ @noop title Exploring QSAR: hydrophobic, electronic, and steric constants ,\ Vol. volume 2 \ ( publisher American Chemical Society Washington, DC ,\ year 1995 ) NoStop

    1995

  32. [32]

    Yin , author N

    author author J. Yin , author N. M. \ Henriksen , author D. R. \ Slochower , author M. R. \ Shirts , author M. W. \ Chiu , author D. L. \ Mobley , \ and\ author M. K. \ Gilson ,\ 10.1007/s10822-016-9974-4 journal journal J. Comput. Aided Mol. Des. \ volume 31 ,\ pages 1 ( year 2017 ) NoStop

    work page doi:10.1007/s10822-016-9974-4 2017

  33. [34]

    Invernizzi \ and\ author M

    author author M. Invernizzi \ and\ author M. Parrinello ,\ 10.1021/acs.jpclett.0c00497 journal journal J. Phys. Chem. Lett. \ volume 11 ,\ pages 2731 ( year 2020 ) NoStop

    work page doi:10.1021/acs.jpclett.0c00497 2020

  34. [35]

    Vaswani , author N

    author author A. Vaswani , author N. Shazeer , author N. Parmar , author J. Uszkoreit , author L. Jones , author A. N. \ Gomez , author L. u. \ Kaiser , \ and\ author I. Polosukhin ,\ in\ https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf booktitle Advances in Neural Information Processing Systems ,\ Vol....

    2017

  35. [36]

    La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

    author author T. Geffner , author K. Didi , author Z. Cao , author D. Reidenbach , author Z. Zhang , author C. Dallago , author E. Kucukbenli , author K. Kreis , \ and\ author A. Vahdat ,\ 10.48550/arXiv.2507.09466 journal journal arXiv preprint arXiv:2507.09466 \ ( year 2025 ),\ 10.48550/arXiv.2507.09466 NoStop

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2507.09466 2025

  36. [37]

    Gasteiger, J

    author author J. Gasteiger , author J. Gro , \ and\ author S. G \"u nnemann ,\ 10.48550/arXiv.2003.03123 journal journal arXiv preprint arXiv:2003.03123 \ ( year 2022 ),\ 10.48550/arXiv.2003.03123 NoStop

    work page doi:10.48550/arxiv.2003.03123 2003

  37. [38]

    Rizzi , author L

    author author V. Rizzi , author L. Bonati , author N. Ansari , \ and\ author M. Parrinello ,\ 10.1038/s41467-020-20310-0 journal journal Nat. Commun. \ volume 12 ,\ pages 93 ( year 2021 ) NoStop

    work page doi:10.1038/s41467-020-20310-0 2021

  38. [39]

    Ansari , author V

    author author N. Ansari , author V. Rizzi , \ and\ author M. Parrinello ,\ 10.1038/s41467-022-33104-3 journal journal Nat. Commun. \ volume 13 ,\ pages 5438 ( year 2022 ) NoStop

    work page doi:10.1038/s41467-022-33104-3 2022

  39. [40]

    Novelli , author L

    author author P. Novelli , author L. Bonati , author M. Pontil , \ and\ author M. Parrinello ,\ 10.1021/acs.jctc.2c00393 journal journal J. Chem. Theory Comput. \ volume 18 ,\ pages 5195 ( year 2022 ) NoStop

    work page doi:10.1021/acs.jctc.2c00393 2022

  40. [41]

    Tibshirani ,\ 10.1111/j.2517-6161.1996.tb02080.x journal journal J

    author author R. Tibshirani ,\ 10.1111/j.2517-6161.1996.tb02080.x journal journal J. Roy. Stat. Soc. B. \ volume 58 ,\ pages 267 ( year 1996 ) NoStop

    work page doi:10.1111/j.2517-6161.1996.tb02080.x 1996

  41. [42]

    Bonati , author E

    author author L. Bonati , author E. Trizio , author A. Rizzi , \ and\ author M. Parrinello ,\ 10.1063/5.0156343 journal journal J. Chem. Phys. \ volume 159 ,\ pages 014801 ( year 2023 ) NoStop

    work page doi:10.1063/5.0156343 2023

  42. [43]

    Living J

    Enhanced Sampling Methods for Molecular Dynamics Simulations , volume=. Living J. Comp. Mol. Sci. , author=. 2022 , pages=

    2022

  43. [44]

    Zhu, Kai and Trizio, Enrico and Zhang, Jintu and Hu, Renling and Jiang, Linlong and Hou, Tingjun and Bonati, Luigi , title =. Chem. Rev. , volume =. 2026 , doi =

    2026

  44. [45]

    Kang, Peilin and Trizio, Enrico and Parrinello, Michele , title=. Nat. Comput. Sci. , year=

  45. [46]

    Trizio, Enrico and Kang, Peilin and Parrinello, Michele , title=. Nat. Comput. Sci. , year=

  46. [47]

    Bonati, Luigi and Trizio, Enrico and Rizzi, Andrea and Parrinello, Michele , title =. J. Chem. Phys. , volume =. 2023 , doi =

    2023

  47. [48]

    Annu Rev Phys Chem , year =

    E, Weinan and Vanden-Eijnden, Eric , title =. Annu Rev Phys Chem , year =

  48. [49]

    and Ramos, Maria J

    Das, Sudip and Raucci, Umberto and Trizio, Enrico and Kang, Peilin and Neves, Rui P.P. and Ramos, Maria J. and Parrinello, Michele , title =. ACS Catal. , volume =. 2025 , doi =

    2025

  49. [50]

    Yuanpeng Deng and Peilin Kang and Xiang Xu and Hui Li and Michele Parrinello , title =. Proc. Nat. Acad. Sci. U.S.A. , volume =. 2026 , doi =

    2026

  50. [51]

    ChemRxiv , volume =

    Alessandro Berselli and Enrico Trizio and Umberto Raucci and Maria J Ramos and Maria Cristina Menziani and Francesco Muniz-Miranda and Michele Parrinello , title =. ChemRxiv , volume =. 2026 , doi =

    2026

  51. [52]

    Enzyme Reset: Water-Mediated Tautomerization Restores the Catalytic Asparagine in Protein O-Fucosyltransferase 1 , journal =

    Vidal-Giron. Enzyme Reset: Water-Mediated Tautomerization Restores the Catalytic Asparagine in Protein O-Fucosyltransferase 1 , journal =. 2026 , doi =

    2026

  52. [53]

    Automatic method for identifying reaction coordinates in complex systems , author=. J. Phys. Chem. B , volume=. 2005 , publisher=

    2005

  53. [54]

    and Rotskoff, Grant M

    Mitchell, Andrew R. and Rotskoff, Grant M. , title =. J. Chem. Theory Comput. , volume =. 2024 , doi =

    2024

  54. [55]

    Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference , pages =

    Active Importance Sampling for Variational Objectives Dominated by Rare Events: Consequences for Optimization and Generalization , author =. Proceedings of the 2nd Mathematical and Scientific Machine Learning Conference , pages =. 2022 , editor =

    2022

  55. [56]

    Discovering Reaction Pathways, Slow Variables, and Committor Probabilities with Machine Learning , journal=

    Chen, Haochuan and Roux, Beno. Discovering Reaction Pathways, Slow Variables, and Committor Probabilities with Machine Learning , journal=. 2023 , doi =

    2023

  56. [57]

    Li, Qianxiao and Lin, Bo and Ren, Weiqing , title =. J. Chem. Phys. , volume =. 2019 , doi =

    2019

  57. [58]

    Understanding Mechanisms of Molecular Rare Events from Start to Finish , author =. Phys. Rev. Lett. , volume =. 2026 , doi =

    2026

  58. [59]

    and Leitold, Christian and Dellago, Christoph and Bolhuis, Peter G

    Jung, Hendrik and Covino, Roberto and Arjun, A. and Leitold, Christian and Dellago, Christoph and Bolhuis, Peter G. and Hummer, Gerhard , title=. Nat. Comput. Sci. , year=

  59. [60]

    Solving for high-dimensional committor functions using artificial neural networks , author=. Res. Math. Sci. , volume=. 2019 , doi=

    2019

  60. [61]

    1931 , doi=

    Kolmogoroff, Andrei , journal=. 1931 , doi=

    1931

  61. [62]

    Zhang, Jintu and Bonati, Luigi and Trizio, Enrico and Zhang, Odin and Kang, Yu and Hou, TingJun and Parrinello, Michele , title =. J. Chem. Theory Comput. , volume =. 2024 , doi =

    2024

  62. [63]

    Contreras Arredondo, Sergio and Tang, Chenyu and Talmazan, Radu A. and Meg. Learning the committor without collective variables , journal=. 2026 , volume=

    2026

  63. [64]

    Kang, Peilin and Zhang, Jintu and Trizio, Enrico and Hou, TingJun and Parrinello, Michele , title =. J. Chem. Theory Comput. , volume =. 2026 , doi =

    2026

  64. [65]

    Analyzing Atomic Interactions in Molecules as Learned by Neural Networks , journal =

    Esders, Malte and Schnake, Thomas and Lederer, Jonas and Kabylda, Adil and Montavon, Gr. Analyzing Atomic Interactions in Molecules as Learned by Neural Networks , journal =. 2025 , doi =

    2025

  65. [66]

    arXiv preprint arXiv:2312.07511 , year=

    A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems , author=. arXiv preprint arXiv:2312.07511 , year=

    work page arXiv

  66. [67]

    Proceedings of the 40th International Conference on Machine Learning , pages =

    Ewald-based Long-Range Message Passing for Molecular Graphs , author =. Proceedings of the 40th International Conference on Machine Learning , pages =. 2023 , editor =

    2023

  67. [68]

    npj Comput

    Cheng, Bingqing , title=. npj Comput. Mater. , year=

  68. [69]

    Extending the range of graph neural networks with global encodings , journal=

    Caruso, Alessandro and Venturin, Jacopo and Giambagli, Lorenzo and Rolando, Edoardo and El-Machachi, Zakariya and No. Extending the range of graph neural networks with global encodings , journal=. 2026 , volume=

    2026

  69. [70]

    2026 , journal=

    MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry , author=. 2026 , journal=

    2026

  70. [71]

    and Evans, Richard and Jumper, John and Kirkpatrick, James and Sifre, Laurent and Green, Tim and Qin, Chongli and

    Senior, Andrew W. and Evans, Richard and Jumper, John and Kirkpatrick, James and Sifre, Laurent and Green, Tim and Qin, Chongli and. Improved protein structure prediction using potentials from deep learning , journal=. 2020 , volume=

    2020

  71. [72]

    Highly accurate protein structure prediction with AlphaFold , journal=

    Jumper, John and Evans, Richard and Pritzel, Alexander and Green, Tim and Figurnov, Michael and Ronneberger, Olaf and Tunyasuvunakool, Kathryn and Bates, Russ and. Highly accurate protein structure prediction with AlphaFold , journal=. 2021 , volume=

    2021

  72. [73]

    and Bambrick, Joshua and Bodenstein, Sebastian W

    Abramson, Josh and Adler, Jonas and Dunger, Jack and Evans, Richard and Green, Tim and Pritzel, Alexander and Ronneberger, Olaf and Willmore, Lindsay and Ballard, Andrew J. and Bambrick, Joshua and Bodenstein, Sebastian W. and Evans, David A. and Hung, Chia-Chun and O'Neill, Michael and Reiman, David and Tunyasuvunakool, Kathryn and Wu, Zachary and. Accur...

    2024

  73. [74]

    Attention is All you Need , volume =

    Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, ukasz and Polosukhin, Illia , booktitle =. Attention is All you Need , volume =. 2017 , url =

    2017

  74. [75]

    Invernizzi, Michele and Parrinello, Michele , title =. J. Phys. Chem. Lett. , volume =. 2020 , doi =

    2020

  75. [76]

    La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching

    La-Proteina: Atomistic Protein Generation via Partially Latent Flow Matching , author=. arXiv preprint arXiv:2507.09466 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  76. [77]

    Gasteiger, J

    Directional Message Passing for Molecular Graphs , author=. arXiv preprint arXiv:2003.03123 , year=

    work page arXiv 2003

  77. [78]

    Rizzi, Valerio and Bonati, Luigi and Ansari, Narjes and Parrinello, Michele , title=. Nat. Commun. , year=

  78. [79]

    Ansari, Narjes and Rizzi, Valerio and Parrinello, Michele , title=. Nat. Commun. , year=

  79. [80]

    Novelli, Pietro and Bonati, Luigi and Pontil, Massimiliano and Parrinello, Michele , title =. J. Chem. Theory Comput. , volume =. 2022 , doi =

    2022

  80. [81]

    Regression shrinkage and selection via the lasso , author =. J. Roy. Stat. Soc. B. , volume =. 1996 , doi=

    1996

Showing first 80 references.