Machine learned coarse-grained protein force-fields: Are we there yet?
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
The successful recent application of machine learning methods to scientific problems includes the learning of flexible and accurate atomic-level force-fields for materials and biomolecules from quantum chemical data. In parallel, the machine learning of force-fields at coarser resolutions is rapidly gaining relevance, as an efficient way to represent the higher-body interactions needed in coarse-grained force-fields to compensate for the omitted degrees of freedom. Coarse-grained models are important for the study of systems at time and length scales exceeding those of atomistic simulations. However, the development of transferable coarse-grained models via machine learning still presents significant challenges. Here we discuss recent developments in this field and current efforts to address the remaining challenges.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Dropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471 · cited 1×
“However, recent advances have started to enable estimates of uncertainty [76,77].”
UCSF ChimeraX: Meeting modern challenges in visualization and analysis
Goddard, T. D., Huang, C. C., Meng, E. C., Pettersen, E. F., Couch, G. S., Morris, J. H., & Ferrin, T. E. (2018) · Protein Science · doi:10.1002/pro.3235 · Cited by 5,267
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010
Training Products of Experts by Minimizing Contrastive Divergence
Hinton, G. E. (2002) · Neural Computation · doi:10.1162/089976602760128018 · Cited by 4,879 · cited 1×
“This is called relative entropy minimization in the coarse-graining literature [49,50,47] and maximum likelihood estimation in the ML energy-based model community [51].”
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
Lakshminarayanan, B., Pritzel, A., & Blundell, C. (2016) · arXiv · doi:10.48550/arxiv.1612.01474 · Cited by 3,666 · cited 1×
“However, recent advances have started to enable estimates of uncertainty [76,77].”
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
Bartók, A. P., Payne, M. C., Kondor, R., & Csányi, G. (2010) · Physical Review Letters · doi:10.1103/physrevlett.104.136403 · Cited by 3,242 · cited 1×
“Indeed, thanks to the flexibility of ML algorithms, some frameworks developed for the atomistic resolution [32,33] have been transferred to the CG resolution [34 e 37].”
SchNet – A deep learning architecture for molecules and materials
Schütt, K. T., Sauceda, H. E., Kindermans, P.-J., Tkatchenko, A., & Müller, K.-R. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5019779 · Cited by 2,217 · cited 1×
“Indeed, thanks to the flexibility of ML algorithms, some frameworks developed for the atomistic resolution [32,33] have been transferred to the CG resolution [34 e 37].”
THEORY OF PROTEIN FOLDING: The Energy Landscape Perspective
Onuchic, J. N., Luthey-Schulten, Z., & Wolynes, P. G. (1997) · Annual Review of Physical Chemistry · doi:10.1146/annurev.physchem.48.1.545 · Cited by 2,210
How fast-folding proteins fold
Lindorff-Larsen, K., Piana, S., Dror, R. O., & Shaw, D. E. (2011) · Science · doi:10.1126/science.1208351 · Cited by 1,980 · cited 2×
“By employing special-purpose super-computers [23] or distributed simulation combined with Markov State Models [24,21,25], the dynamics of small solvated proteins can be simulated over milli-second timescales [20].”
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
Smith, J. S., Isayev, O., & Roitberg, A. E. (2017) · Chemical Science · doi:10.1039/c6sc05720a · Cited by 1,921
Cited by
Deep learning–guided design of dynamic proteins
Guo, A. B., Akpinaroglu, D., Stephens, C. A., Grabe, M., Smith, C. A., Kelly, M. J. S., & Kortemme, T. (2025) · Science · doi:10.1126/science.adr7094 · Cited by 67
Transferable deep generative modeling of intrinsically disordered protein conformations
Janson, G., & Feig, M. (2024) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1012144 · Cited by 62
Schuhmann, F., Akkaya, K. C., Puchkov, D., Hohensee, S., Lehmann, M., Liu, F., & Pezeshkian, W. (2025) · Angewandte Chemie International Edition · doi:10.1002/anie.202417804 · Cited by 18
Deep learning guided design of dynamic proteins
Guo, A. B., Akpinaroglu, D., Kelly, M. J. S., & Kortemme, T. (2024) · doi:10.1101/2024.07.17.603962 · Cited by 9
Chromatin structures from integrated AI and polymer physics model
Schultz, E. R., Kyhl, S., Willett, R., & de Pablo, J. J. (2025) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1012912 · Cited by 6
Metadata
- Authors
- Durumeric, A. E. P., Charron, N. E., Templeton, C., Musil, F., Bonneau, K., Pasos-Trejo, A. S., Chen, Y., Kelkar, A., Noé, F., & Clementi, C.
- Venue
- Current Opinion in Structural Biology
- Publisher
- Elsevier BV
- Published
- 2023-04
- Volume
- 79
- Pages
- 102533
- ISSN
- 0959-440X (ISSN-L)
- OpenAlex
- W4318681889
- Cited by
- 81
- References
- 17
- FWCI
- 2.02
- Type
- journal article
- Language
- en
- Open access
- bronze
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Machine learned coarse-grained protein force-fields: Are we there yet? https://app.cochat.ai/papers/10.1016/j.sbi.2023.102533
- The paper
- Durumeric, A. E. P., Charron, N. E., Templeton, C., Musil, F., Bonneau, K., Pasos-Trejo, A. S., Chen, Y., Kelkar, A., Noé, F., & Clementi, C. (2023). Machine learned coarse-grained protein force-fields: Are we there yet? Current Opinion in Structural Biology. https://doi.org/10.1016/j.sbi.2023.102533
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.