Physics‐based protein structure refinement in the era of artificial intelligence
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Protein structure refinement is the last step in protein structure prediction pipelines. Physics‐based refinement via molecular dynamics (MD) simulations has made significant progress during recent years. During CASP14, we tested a new refinement protocol based on an improved sampling strategy via MD simulations. MD simulations were carried out at an elevated temperature (360 K). An optimized use of biasing restraints and the use of multiple starting models led to enhanced sampling. The new protocol generally improved the model quality. In comparison with our previous protocols, the CASP14 protocol showed clear improvements. Our approach was successful with most initial models, many based on deep learning methods. However, we found that our approach was not able to refine machine‐learning models from the AlphaFold2 group, often decreasing already high initial qualities. To better understand the role of refinement given new types of models based on machine‐learning, a detailed analysis via MD simulations and Markov state modeling is presented here. We continue to find that MD‐based refinement has the potential to improve AI predictions. We also identified several practical issues that make it difficult to realize that potential. Increasingly important is the consideration of inter‐domain and oligomeric contacts in simulations; the presence of large kinetic barriers in refinement pathways also continues to present challenges. Finally, we provide a perspective on how physics‐based refinement could continue to play a role in the future for improving initial predictions based on machine learning‐based methods.
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
TM-align: a protein structure alignment algorithm based on the TM-score
Zhang, Y. (2005) · Nucleic Acids Research · doi:10.1093/nar/gki524 · Cited by 3,774
Improved protein structure prediction using potentials from deep learning
Senior, A. W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., Qin, C., Žídek, A., Nelson, A. W. R., Bridgland, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1923-7 · Cited by 3,378
Comparative Protein Structure Modeling of Genes and Genomes
Martí-Renom, M. A., Stuart, A. C., Fiser, A., Sánchez, R., Melo, F., & Šali, A. (2000) · Annual Review of Biophysics and Biomolecular Structure · doi:10.1146/annurev.biophys.29.1.291 · Cited by 3,169 · cited 1×
“Template-based modeling became the first successful approach with the growth of protein structure databases by relying on homologous protein structures.(3) In the meantime, the number of protein sequences has exploded as sequencing techniques advanced.”
MethodHHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment
Remmert, M., Biegert, A., Hauser, A., & Söding, J. (2012) · Nature Methods · doi:10.1038/nmeth.1818 · Cited by 2,288
Protein Structure Prediction and Structural Genomics
Baker, D., & Sali, A. (2001) · Science · doi:10.1126/science.1065659 · Cited by 1,587
HH-suite3 for fast remote homology detection and deep protein annotation
Steinegger, M., Meier, M., Mirdita, M., Vöhringer, H., Haunsberger, S. J., & Söding, J. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-3019-7 · Cited by 1,145
Protein 3D Structure Computed from Evolutionary Sequence Variation
Marks, D. S., Colwell, L. J., Sheridan, R., Hopf, T. A., Pagnani, A., Zecchina, R., & Sander, C. (2011) · PLoS ONE · doi:10.1371/journal.pone.0028766 · Cited by 1,144 · cited 1×
“This progress enabled the identification of co-evolutionary relationships between residues from multiple sequence alignments of protein homologs.(5) At the beginning, co-evolutionary information was”
BackgroundMariani, V., Biasini, M., Barbato, A., & Schwede, T. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt473 · Cited by 1,138
LGA: a method for finding 3D similarities in protein structures
Zemla, A. (2003) · Nucleic Acids Research · doi:10.1093/nar/gkg571 · Cited by 1,069 · cited 1×
“…performance by FEIG-S (server predictor) and FEIG (human predictor) is summarized in Figures 2, S2, and For 37 regular refinement targets, which excludes the CASP-COVID and the extended time targets, FEIG-S improved GDT-HA 57 and IDDT 58 scores on average by + 1.67 and + 1.16%, respectively.”
BackgroundInfluentialIdentification of slow molecular order parameters for Markov model construction
Pérez-Hernández, G., Paul, F., Giorgino, T., De Fabritiis, G., & Noé, F. (2013) · The Journal of Chemical Physics · doi:10.1063/1.4811489 · Cited by 990 · cited 1×
“Time-lagged independent components analysis (tICA) 53 was employed to reduce the dimensionality of these input features and k-means clustering was then used to cluster the MD snapshots in the tICA space.”
Method
Cited by
Ins and outs of AlphaFold2 transmembrane protein structure predictions
Hegedűs, T., Geisler, M., Lukács, G. L., & Farkas, B. (2022) · Cellular and Molecular Life Sciences · doi:10.1007/s00018-021-04112-1 · Cited by 127
Assessing the utility of CASP14 models for molecular replacement
Millán, C., Keegan, R. M., Pereira, J., Sammito, M. D., Simpkin, A. J., McCoy, A. J., Lupas, A. N., Hartmann, M. D., Rigden, D. J., & Read, R. J. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26214 · Cited by 62
“Some consideration of potential future changes can be found elsewhere in this issue.(30,31) In conclusion, we have shown that the reLLG is a useful addition to the assessment metrics for CASP and should replace the metrics based on dLLG used in previous rounds.”
MethodInfluentialEvaluation of model refinement in CASP14
Simpkin, A. J., Sánchez Rodríguez, F., Mesdaghi, S., Kryshtafovych, A., & Rigden, D. J. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26185 · Cited by 28
Exploring the Alternative Conformation of a Known Protein Structure Based on Contact Map Prediction
(2023) · doi:10.1021/acs.jcim.3c01381 · Cited by 21
A-Prot: protein structure modeling using MSA transformer
Hong, Y., Lee, J., & Ko, J. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-04628-8 · Cited by 19
Metadata
- Authors
- Heo, L., Janson, G., & Feig, M.
- Venue
- Proteins: Structure, Function, and Bioinformatics
- Publisher
- Wiley
- Published
- 2021-06-29
- Volume
- 89
- Issue
- 12
- Pages
- 1870-1887
- ISSN
- 0887-3585 (ISSN-L)
- 1097-0134
- OpenAlex
- W3175014854
- Cited by
- 31
- References
- 18
- FWCI
- 1.54
- Type
- journal article
- Language
- en
- Open access
- green
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: Physics‐based protein structure refinement in the era of artificial intelligence. https://app.cochat.ai/papers/10.1002/prot.26161
- The paper
- Heo, L., Janson, G., & Feig, M. (2021). Physics‐based protein structure refinement in the era of artificial intelligence. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.26161
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.