Accurate prediction of protein structures and interactions using a 3-track network
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 13 of the 36 sources its claims cite were checked for support.
Abstract
DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research. One-Sentence Summary: Accurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.
Overview
CoChat Summary
TL;DR
RoseTTAFold is a 3-track neural network that integrates 1D sequence, 2D distance-map, and 3D coordinate information to predict protein structures and interactions. It approaches AlphaFold2 accuracy in CASP14, solves challenging crystallography and cryo-EM modeling problems, and generates protein-complex models directly from sequence.
Key findings
- In CASP14, the 3-track RoseTTAFold outperformed the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), the BAKER human group, and the authors’ 2-track models, though its performance was still not as good as AlphaFold2.
- On CAMEO, over 69 medium and hard targets released May 15–June 19, 2021, RoseTTAFold outperformed all other evaluated servers, including Robetta, IntFold6-TS, BestSingleTemplate, and SWISS-MODEL.
- RoseTTAFold models enabled molecular-replacement solutions for four previously unsolved crystallographic datasets; for the cryo-EM p101 Gβγ binding domain, the Cα-RMSD between predicted and refined structure was 3.0 Å over the beta-sheets.
- Among 693 domains from human disease-related proteins, over one-third had predicted lDDT > 0.8, corresponding to an average Cα-RMSD of 2.6 Å on CASP14 targets; many protein-complex models had TM-score > 0.8, with complex generation taking ~30 min on a 24G TITAN RTX GPU.
Methods
- The 3-track network transforms and integrates information at the 1D sequence/MSA level, the 2D distance/orientation-map level, and the 3D backbone-coordinate level, with information flowing between tracks; training used discontinuous sequence crops spanning 260 residues.
- Final 3D structures were generated either by feeding predicted distance/orientation distributions into pyRosetta for all-atom models or by an end-to-end SE(3)-equivariant layer producing backbone coordinates directly.
- Evaluation included CASP14 targets, CAMEO blind server assessment, four X-ray molecular-replacement datasets, a cryo-EM PI3Kγ complex, GPCRs, 693 human disease-related domains, and paired-sequence complexes of known structure, using accuracy comparisons, Cα-RMSD, lDDT, TM-score, and MR/cryo-EM fit.
Limitations
- Stated: hardware memory limitations constrained model size and training; performance remained below AlphaFold2; the end-to-end version was less accurate than the pyRosetta version due to incomplete optimization and neglect of side-chain information; the accuracy predictor did not consistently identify models better than the rapid single-pass method; the network was trained on monomeric proteins, not complexes; and current RoseTTAFold uses only the top 1000 sequences due to memory limits.
- Stated: the Perceiver-based extension for using all available sequences gave promising initial results, but more training is required for rigorous comparison.
- Evident: CASP14 and CAMEO evaluations cover limited target sets and time windows, and the end-to-end model does not produce side chains.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
3 Valid · 8 Not valid · 14 Not checked · 44 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The bi-annual Critical Assessment of Structure (CASP) meetings have demonstrated that deep learning methods such as AlphaFold (1, 2) and trRosetta (3), that extract information from the large database of known protein structures in the PDB, outperform more traditional approaches that explicitly model the folding process.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Abstract
What the sources say
- Not matchedcites [1] Jumper John Evans Richard Pritzel Alexander Green Tim Figurnov Michael Tunyasuvunakool Kathryn Ronneberger Olaf Bates Russ Augustin Žídek Alex Bridgland Clemens Meyer Fourteenth Critical Assessment of Techniques for Protein Structure Prediction
Its entry has no title and year that we can search by.
- Partly supportedcites [2] Anishchenko I Chidyausiku TM Ovchinnikov S Pellock SJ Baker D De novo protein design by deep network hallucination bioRxiv 2020 2020.07.22.211482 PMC9293396 34853475 sourceExperimental — accuracy not yet measured
The Introduction (page not provided) says deep networks improved protein-structure prediction accuracy, notes an AlphaFold observation at CASP13, and reports that trRosetta outperformed other methods in benchmark tests. The Conclusion says the network learned from native protein structures and contrasts it with physically based approaches. The paper does not establish the claimed CASP comparison in which both AlphaFold and trRosetta outperform approaches that explicitly model folding. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [3] Yang J Anishchenko I Park H Peng Z Ovchinnikov S Baker D Improved protein structure prediction using predicted interresidue orientations Proc Natl Acad Sci U S A 2020 117 1496 1503 31896580 PMC6983395 source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The RoseTTAFold CERS1 model for residues 98 to 304 (Pfam TLC domain) (29) includes six TMH that traverse the membrane in an up and down arrangement (Fig. 3E).”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Providing insights into biological function
What the sources say
- Could not verifycites [29] Cong Q Anishchenko I Ovchinnikov S Baker D Protein interaction networks revealed by proteome coevolution Science 2019 365 185 189 31296772 PMC6948103 sourceExperimental — accuracy not yet measured
The paper’s Abstract (page unavailable) describes coevolution-based protein interaction models in E. coli and M. tuberculosis, not a CERS1 model. Searches for CERS1, the Pfam TLC domain, RoseTTAFold, and six transmembrane helices found no passage in our copy addressing the cited domain identification or the stated membrane arrangement. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in the case of SLP, only a distant model covering part of the N-terminal domain (38% of the sequence) was available in the PDB”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“trRosetta failed to predict the correct fold with the same MSA input (fig. S6)”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 3-track models with attention operating at the 1D, 2D, and 3D levels and information flowing between the three levels were the best models we tested (Fig. 1B), clearly outperforming the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), BAKER human group (ranked second among all groups), and our 2-track attention models on CASP14 targets.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Network architecture development
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
33 more claims
Create a free account to see all 69 claims and to verify the 2 references still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RF has properties well suited for use in a protein design DDPM (Fig. 1a): it generates protein structures with high precision, operates on a rigid-frame representation of residues with rotational equivariance and has an architecture enabling conditioning on design specifications at the individual residue, inter-residue distance and orientation, and 3D coordinate levels.”
From De novo design of protein structure and function with RFdiffusion (2023) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“are the best and most accurate answer to the structure prediction problem to date”
From The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins (2024) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“DeepMind’s AlphaFold2 success in sequence-based protein structure prediction,4 as well as the RoseTTAFold70 open-source counterpart, and the publicly available AlphaFold2 prediction of all human proteins203 are major steps that benefit the scientific community.”
From AlphaFold, Artificial Intelligence (AI), and Allostery (2022) · cites this paper as [70]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The unprecedented accuracy of AlphaFold2,127 RosettaFold,128 and others129,130 offers, at least in principle, the opportunity to virtually screen any protein of interest with the structure-based approach, irrespective of its a priori ligandability (after AlphaFold2, the structural coverage of the human proteome increased from 48% to 76% of the total residues).131”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [128]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The programs were also shown to accurately assess their confidence at the level of individual residues and interdomain contacts (27,28,62).”
From AI-based structure prediction empowers integrative structural analysis of human nuclear pores (2022) · cites this paper as [27]
Experimental — accuracy not yet measured
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability
Katoh, K., & Standley, D. M. (2013) · Molecular Biology and Evolution · doi:10.1093/molbev/mst010 · Cited by 46,209
Features and development of Coot
Emsley, P., Lohkamp, B., Scott, W. G., & Cowtan, K. (2010) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910007493 · Cited by 29,915
Clustal W and Clustal X version 2.0
Larkin, M. A., Blackshields, G., Brown, N. P., Chenna, R., McGettigan, P. A., McWilliam, H., Valentin, F., Wallace, I. M., Wilm, A., Lopez, R., et al. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm404 · Cited by 28,358
Phaser crystallographic software
McCoy, A. J., Grosse-Kunstleve, R. W., Adams, P. D., Winn, M. D., Storoni, L. C., & Read, R. J. (2007) · Journal of Applied Crystallography · doi:10.1107/s0021889807021206 · Cited by 20,612
Self-citationSWISS-MODEL: homology modelling of protein structures and complexes
Waterhouse, A., Bertoni, M., Bienert, S., Studer, G., Tauriello, G., Gumienny, R., Heer, F. T., de Beer, T. A. P., Rempfer, C., Bordoli, L., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky427 · Cited by 13,067 · cited 2×
“Fortunately,theContinuousAutomated ModelEvaluation(CAMEO)experiment( 7 ) tests structure prediction servers blindly on protein structures as they are submitted to the PDB. RoseTTAFold has been evaluated since 15 May 2021 on CAMEO; over the 69 medium and hard targets released during this time (15 May 2021 to 19 June 20…”
UCSF ChimeraX: Structure visualization for researchers, educators, and developers
Pettersen, E. F., Goddard, T. D., Huang, C. C., Meng, E. C., Couch, G. S., Croll, T. I., Morris, J. H., & Ferrin, T. E. (2021) · Protein Science · doi:10.1002/pro.3943 · Cited by 9,514
Liebschner, D., Afonine, P. V., Baker, M. L., Bunkóczi, G., Chen, V. B., Croll, T. I., Hintze, B., Hung, L.-W., Jain, S., McCoy, A. J., et al. (2019) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798319011471 · Cited by 7,953
Self-citationUniProt: the Universal Protein knowledgebase
Apweiler, R. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh131 · Cited by 7,498
Towards automated crystallographic structure refinement with phenix.refine
Afonine, P. V., Grosse-Kunstleve, R. W., Echols, N., Headd, J. J., Moriarty, N. W., Mustyakimov, M., Terwilliger, T. C., Urzhumtsev, A., Zwart, P. H., & Adams, P. D. (2012) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444912001308 · Cited by 5,511
Self-citation
Research works printed but not linked: 2
- Bunkóczi G Read RJ phenix. ensembler: a tool for multiple superposition Comput Crystallogr Newsl 2011 2 8 9
- Vagin A Lebedev A ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES INT UNION CRYSTALLOGRAPHY 2 ABBEY SQ, CHESTER, CH1 2HU ENGLAND 2015 71 S19
Cited by
Items 1,001–1,100 of 5,641
Improved protein structure prediction with trRosettaX2 , AlphaFold2 , and optimized MSAs in CASP15
Peng, Z., Wang, W., Wei, H., Li, X., & Yang, J. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26570 · Cited by 34
Engineering brain-derived neurotrophic factor mRNA delivery for the treatment of Alzheimer’s disease
Li, H., Cao, Y., Ye, J., Yang, Z., Chen, Q., Liu, X., Zhang, B., Qiao, J., Tang, Q., Yang, H., et al. (2023) · Chemical Engineering Journal · doi:10.1016/j.cej.2023.143152 · Cited by 32
Varadi, M., Nair, S., Sillitoe, I., Tauriello, G., Anyango, S., Bienert, S., Borges, C., Deshpande, M., Green, T., Hassabis, D., et al. (2022) · GigaScience · doi:10.1093/gigascience/giac118 · Cited by 32
“In 2021, the field saw tremendous advances with tools such as AlphaFold and RoseTTAFold achieving much higher accuracy for de novo predictions without homologous templates than ever before [16,17].”
Efficient generation of protein pockets with PocketGen
Zhang, Z., Shen, W. X., Liu, Q., & Zitnik, M. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00920-9 · Cited by 32
“For instance, RFdiffu-sion 26 leverages denoising diffusion probabilistic models 27 alongside RoseTTAFold 28 for de novo protein structure generation.”
CryoEM structure of the outer membrane secretin channel pIV from the f1 filamentous bacteriophage
Conners, R., McLaren, M., Łapińska, U., Sanders, K., Stone, M. R. L., Blaskovich, M. A. T., Pagliara, S., Daum, B., Rakonjac, J., & Gold, V. A. M. (2021) · Nature Communications · doi:10.1038/s41467-021-26610-3 · Cited by 32
A 3D structural SARS-CoV-2–human interactome to explore genetic and drug perturbations
Wierbowski, S. D., Liang, S., Liu, Y., Chen, Y., Gupta, S., Andre, N. M., Lipkin, S. M., Whittaker, G. R., & Yu, H. (2021) · Nature Methods · doi:10.1038/s41592-021-01318-w · Cited by 32
“Recent advances in protein-folding predictions 91–93 may ameliorate this restriction in the future.”
BackgroundProtein–protein contact prediction by geometric triangle-aware protein language models
Lin, P., Tao, H., Li, H., & Huang, S. (2023) · Nature Machine Intelligence · doi:10.1038/s42256-023-00741-2 · Cited by 37
“We then use the radial basis function to convert the intra-protein distance as follows 52 : where d is the intra-protein distance, and d k is a hyperparameter, which ranges from 2 to 22 Å and is divided into 64 bins with variance σ = 0.3125 Å .”
MethodInfluentialRaffele, D. D., & Ilie, I. M. (2024) · Chemical Communications · doi:10.1039/d3cc04630c · Cited by 38
The PDLIM family of actin-associated proteins and their emerging role in membrane trafficking
Healy, M. D., & Collins, B. M. (2023) · Biochemical Society Transactions · doi:10.1042/bst20220804 · Cited by 34
Advanced computational approaches to understand protein aggregation
Ghosh, D., Biswas, A., & Radhakrishna, M. (2024) · Biophysics Reviews · doi:10.1063/5.0180691 · Cited by 32
Conceição, C. J. F., Moe, E., Ribeiro, P. A., & Raposo, M. (2025) · Biochimica et Biophysica Acta (BBA) - Reviews on Cancer · doi:10.1016/j.bbcan.2025.189282 · Cited by 43
Harnessing hyperaccumulator plants to recover technology‐critical metals: where are we at?
Rylott, E. L., & van der Ent, A. (2025) · New Phytologist · doi:10.1111/nph.20449 · Cited by 35
“R OSE TTAF OLD (Baek et al ., 2021) and, recently upgraded, AlphaFold3 (Abramson et al ., 2024) can be used to optimise protein structure, and the resultant synthetic proteins can be expressed, purified, and tested.”
Intracellular protein editing enables incorporation of noncanonical residues in endogenous proteins
Beyer, J. N., Serebrenik, Y. V., Toy, K., Najar, M. A., Feierman, E. R., Raniszewski, N. R., Korb, E., Shalem, O., & Burslem, G. M. (2025) · Science · doi:10.1126/science.adr5499 · Cited by 38
Marciano, C. L., de Lima, J. V. F., Rosa, M. S. D. C., do Nascimento, R. A., Ferraz, A. D. O., da Silva, I. C., Chrysostomo-Massaro, T. N., da Rosa-Garzon, N. G., & Cabral, H. (2025) · Antibiotics · doi:10.3390/antibiotics14111115 · Cited by 39
“Computational tools such as AlphaFold [178], RoseTTAFold [179,180] and PEP-FOLD [47] can be employed to predict AMP secondary and tertiary structures.”
Machine learning interatomic potentials at the centennial crossroads of quantum mechanics
Kalita, B., Gökcan, H., & Isayev, O. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00930-6 · Cited by 54
“…Geoffrey Hinton for ‘foundational discoveries and inventions that enable machine learning with artificial neural networks’ 24,25 , and Demis Hassabis and John Jumper shared the 2024 Chemistry Nobel Prize with David Baker for ‘protein structure prediction and computational protein design’ 26,27 .”
Álvarez‐García, G., Davidson, R. K., Jokelainen, P., Klevar, S., Spano, F., & Seeber, F. (2021) · Microorganisms · doi:10.3390/microorganisms9112346 · Cited by 32
Conformational snapshots of the bacitracin sensing and resistance transporter BceAB
George, N. L., Schilmiller, A. L., & Orlando, B. J. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2123268119 · Cited by 33
Chatzigoulas, A., & Cournia, Z. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbab518 · Cited by 32
Principles of Alternating Access in LeuT-fold Transporters: Commonalities and Divergences
del Alamo, D., Meiler, J., & Mchaourab, H. S. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2022.167746 · Cited by 33
“Although formidable, the task of determining alternating access mechanisms of LeuT-fold transporters will almost certainly benefit from the recent development of high accuracy de novo structure prediction tools, particularly for families lacking representatives in the Protein Data Bank[83,154,155].”
CEMIP ( HYBID , KIAA1199 ): structure, function and expression in health and disease
Spataro, S., Guerra, C., Cavalli, A., Sgrignani, J., Sleeman, J. P., Poulain, L., Boland, A., Scapozza, L., Moll, S., & Prunotto, M. (2022) · FEBS Journal · doi:10.1111/febs.16600 · Cited by 35
Xu, D., Liu, B., Wang, J., & Zhang, Z. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.998298 · Cited by 38
“In recent years, several major research developments have been achieved, including the AI-mediated prediction of protein structure, which was breakthrough of the year in 2021 (Baek et al., 2021).”
BackgroundSelf-citationGarvicin Q: characterization of biosynthesis and mode of action
Desiderato, C. K., Hasenauer, K. M., Reich, S. J., Goldbeck, O., Holivololona, L., Ovchinnikov, K. V., Reiter, A., Oldiges, M., Diep, D. B., Eikmanns, B. J., et al. (2022) · Microbial Cell Factories · doi:10.1186/s12934-022-01952-9 · Cited by 33
“To gain structural insights, deep learning modelling method RoseTTAFold of Robetta [54] was used for tertiary structure prediction.”
Smorodina, E., Diankin, I. D., Tao, F., Qing, R., Yang, S., & Zhang, S. (2022) · Scientific Reports · doi:10.1038/s41598-022-23764-y · Cited by 33
Gong, Y., Wei, X., Zheng, Y., Li, Y., Yu, Q. C., Li, P., & Zhu, B. (2023) · Journal of Virology · doi:10.1128/jvi.00050-23 · Cited by 35
The Impact of Supervised Learning Methods in Ultralarge High-Throughput Docking
Cavasotto, C. N., & Filippo, J. I. D. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c01471 · Cited by 34
Reķēna, A., Pinheiro, M. J., Bonturi, N., Belouah, I., Tammekivi, E., Herodes, K., Kerkhoven, E. J., & Lahtvee, P. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011009 · Cited by 35
Is Protein BLAST a thing of the past?
Al-Fatlawi, A., Menzel, M., & Schroeder, M. (2023) · Nature Communications · doi:10.1038/s41467-023-44082-5 · Cited by 31
Histones and histone variant families in prokaryotes
Schwab, S., Hu, Y., van Erp, B., Cajili, M. K. M., Hartmann, M. D., Alvarez, B. H., Alva, V., Boyle, A. L., & Dame, R. T. (2024) · Nature Communications · doi:10.1038/s41467-024-52337-y · Cited by 33
“Withthereleaseof AlphaFold2 and RoseTTAFold, we are now able to reliably predict monomeric and multimeric structures with atomic accuracy 27 – 29 .”
Old Moats for New Models: Openness, Control, and Competition in Generative AI
Azoulay, P., Krieger, J., & Nagaraj, A. (2024) · National Bureau of Economic Research · doi:10.3386/w32474 · Cited by 62
Crowdsourced Protein Design: Lessons From the Adaptyv EGFR Binder CompetitionPreprint
Cotet, T., Krawczuk, I., Stocco, F., Ferruz, N., Gitter, A., Kurumida, Y., Machado, L. D. A., Paesani, F., Calia, C. N., Challacombe, C. A., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.17.648362 · Cited by 46
CryoEM structure of the outer membrane secretin channel pIV from the f1 filamentous bacteriophage
(2021) · doi:10.1101/2021.07.20.453082 · Cited by 32
Computed cancer interactome explains the effects of somatic mutations in cancers
Zhang, J., Pei, J., Durham, J., Bos, T., & Cong, Q. (2022) · Protein Science · doi:10.1002/pro.4479 · Cited by 31
“RoseTTAFold [33] and AlphaFold (AF) [34], can be used to identify”
BackgroundSelf-citationPairing interacting protein sequences using masked language modeling
Lupo, U., Sgarbossa, D., & Bitbol, A.-F. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2311887121 · Cited by 31
“A major advance in protein structure prediction was achieved by AlphaFold [2] and other deep learning approaches [3–5].”
BackgroundCarbery, A., Buttenschoen, M., Skyner, R., von Delft, F., & Deane, C. M. (2024) · Journal of Cheminformatics · doi:10.1186/s13321-024-00821-4 · Cited by 35
“Since mid-2021, highly accurate structure predictions for many proteins have been available, first from AlphaFold [3], and later from others, including RosettaFold [5], OmegaFold [6] and ESMFold [4].”
MethodOpportunities and challenges of graph neural networks in electrical engineering
Chien, E., Li, M., Aportela, A., Ding, K., Jia, S., Maji, S., Zhao, Z., Duarte, J. M., Fung, V., Hao, C., et al. (2024) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-024-00076-z · Cited by 36
“Besides the use of GNNs in strictly related electrical engineering applications, GNNs can also be used in other domains such as physics 24–26 , materials science 27,28 and biology 29–31 .”
DeepMineLys: Deep mining of phage lysins from human microbiome
Fu, Y., Yu, S., Li, J., Lao, Z., Yang, X., & Lin, Z. (2024) · Cell Reports · doi:10.1016/j.celrep.2024.114583 · Cited by 36
NMR investigations of glycan conformation, dynamics, and interactions
Angulo, J., Ardá, A., Bertuzzi, S., Canales, Á., Ereño‐Orbea, J., Gimeno, A., Gómez‐Redondo, M., Muñoz-García, J. C., Oquist-Phillips, P., Monaco, S., et al. (2024) · Progress in Nuclear Magnetic Resonance Spectroscopy · doi:10.1016/j.pnmrs.2024.10.002 · Cited by 36
Deep learning and its applications in nuclear magnetic resonance spectroscopy
Luo, Y., Zheng, X., Qiu, M., Gou, Y., Yang, Z., Qu, X., Chen, Z., & Lin, Y. (2025) · Progress in Nuclear Magnetic Resonance Spectroscopy · doi:10.1016/j.pnmrs.2024.101556 · Cited by 44
Structural bioinformatics for rational drug design
Mozaffari, S., Moen, A., Ng, C. Y., Nicolaes, G. A. F., & Wichapong, K. (2025) · Research and Practice in Thrombosis and Haemostasis · doi:10.1016/j.rpth.2025.102691 · Cited by 37
TCR catch bonds nonlinearly control CD8 cooperation to shape T cell specificity
Qin, R., Zhang, Y., Shi, J., Wu, P., An, C., Li, Z., Liu, N., Wan, Z., Hua, T., Li, X., et al. (2025) · Cell Research · doi:10.1038/s41422-025-01077-9 · Cited by 35
Emerging frontiers in protein structure prediction following the AlphaFold revolution
Rennie, M. L., & Oliver, M. R. (2025) · Journal of The Royal Society Interface · doi:10.1098/rsif.2024.0886 · Cited by 40
“It is worth noting that RoseTTAFold from the Baker group was subsequently developed and produces predictions approaching the accuracy of AF2 [38].”
Malik, A., Subramaniyam, S., Kim, C.-B., & Manavalan, B. (2021) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.12.014 · Cited by 33
Computational Advances in Protein Engineering and Enzyme Design
Derat, É., & Kamerlin, S. C. L. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c01198 · Cited by 31
Goulet, A., & Cambillau, C. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.907452 · Cited by 33
“The breakthrough of AlphaFold2, and certainly that of other publicly and freely available deep-learning based prediction methods like RoseTTAFold of the Rosetta suite (Baek et al., 2021), requires us to revisit our way of doing structural biology.”
BackgroundStructure of the TnsB transposase-DNA complex of type V-K CRISPR-associated transposon
Tenjo-Castaño, F., Sofos, N., Mendez, B. L., Stutzke, L. S., Fuglsang, A., Stella, S., & Montoya, G. (2022) · Nature Communications · doi:10.1038/s41467-022-33504-5 · Cited by 32
Computationally Guided Enzymatic Studies on Schizochytrium-Sourced Malonyl-CoA:ACP Transacylase
Chi, G., Cao, X., Li, Q., Yao, C., Lu, F., Liu, Y., Cao, M., & He, N. (2022) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.2c05447 · Cited by 31
Zhao, J., Chen, Y., Ding, Z., Zhou, Y., Bi, R., Qin, Z., Yang, L., Sun, P., Sun, Q., Chen, G., et al. (2023) · Plant Communications · doi:10.1016/j.xplc.2023.100679 · Cited by 31
Sequence‐Tunable Phase Behavior and Intrinsic Fluorescence in Dynamically Interacting Peptides
Sementa, D., Dave, D. R., Fisher, R. S., Wang, T., Elbaum‐Garfinkle, S., & Ulijn, R. V. (2023) · Angewandte Chemie International Edition · doi:10.1002/anie.202311479 · Cited by 32
Ansell, T. B., Song, W., Coupland, C. E., Carrique, L., Corey, R. A., Duncan, A. L., Cassidy, C. K., Geurts, M. M. G., Rasmussen, T., Ward, A. B., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-43392-y · Cited by 35
Databases of ligand-binding pockets and protein-ligand interactions
Carpenter, K. A., & Altman, R. B. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.03.015 · Cited by 36
Language models can identify enzymatic binding sites in protein sequences
Teukam, Y. G. N., Dassi, L. K., Manica, M., Probst, D., Schwaller, P., & Laino, T. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.04.012 · Cited by 36
“The identification of binding and active site residues and the characterization of the corresponding protein function [31–33] pose a significant scientific challenge, particularly following groundbreaking research on protein structure prediction [20,34].”
InfluentialCREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning
Grambow, C. A., Weir, H., Cunningham, C. N., Biancalani, T., & Chuang, K. V. (2024) · Scientific Data · doi:10.1038/s41597-024-03698-y · Cited by 22
Language models for materials discovery and sustainability: Progress, challenges, and opportunities
Pei, Z., Yin, J., & Zhang, J. (2025) · Progress in Materials Science · doi:10.1016/j.pmatsci.2025.101495 · Cited by 30
Peptide design through binding interface mimicry with PepMimic
(2025) · doi:10.1038/s41551-025-01507-4 · Cited by 30
Accurate and robust protein sequence design with CarbonDesign
Ren, M., Yu, C., Bu, D., & Zhang, H. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00838-2 · Cited by 30
“These proteins pose a significant challenge for existing structure prediction methods due to the scarcity of evolutionary information 16,17,20,30,31 .”
Cryo-EM structure and B-factor refinement with ensemble representation
Beton, J. G., Mulvaney, T., Cragnolini, T., & Topf, M. (2024) · Nature Communications · doi:10.1038/s41467-023-44593-1 · Cited by 30
“Finally, we show that our re fi nement protocol can take advantage of recent developments in the fi eld of structureprediction 51,52 .”
Systemic evolutionary chemical space exploration for drug discovery
Lu, C., Liu, S., Shi, W., Yu, J., Zhou, Z., Zhang, X., Lu, X., Cai, F., Xia, N., & Wang, Y. (2022) · Journal of Cheminformatics · doi:10.1186/s13321-022-00598-4 · Cited by 30
Structure-informed protein language models are robust predictors for variant effects
(2024) · doi:10.1007/s00439-024-02695-w · Cited by 30
Computational Design of Peptide Assemblies
Min, J., Rong, X., Zhang, J., Su, R., Wang, Y., & Qi, W. D. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c01054 · Cited by 32
The time revolution in macromolecular crystallography
Khusainov, G., Standfuss, J., & Weinert, T. (2024) · Structural Dynamics · doi:10.1063/4.0000247 · Cited by 31
Dynamic interactions drive early spliceosome assembly
Martínez‐Lumbreras, S., Morguet, C., & Sattler, M. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102907 · Cited by 35
Mukherjee, S., Moafinejad, S. N., Badepally, N. G., Merdas, K., & Bujnicki, J. M. (2024) · Structure · doi:10.1016/j.str.2024.08.015 · Cited by 33
Unveiling the frontiers of deep learning: Innovations shaping diverse domains
Ahmed, S. F., Alam, M. S. B., Kabir, M., Afrin, S., Rafa, S. J., Mehjabin, A., & Gandomi, A. H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06259-x · Cited by 39
Recent advances in the pharmacology of voltage-gated ion channels
Mateos, D. L., Harris, B. J., Hernández-González, A., Yarov-Yarovoy, V. M., & Wulff, H. (2025) · Pharmacological Reviews · doi:10.1016/j.pharmr.2025.100090 · Cited by 31
Hierarchical deep reinforcement learning reveals a modular mechanism of cell movement
Wang, Z., Xu, Y., Wang, D., Yang, J., & Bao, Z. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-021-00431-x · Cited by 35
(2022) · doi:10.1126/sciadv.abo1126 · Cited by 30
Structural basis of mRNA maturation: Time to put it together
Vorländer, M. K., Pacheco-Fiallos, B., & Plaschka, C. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102431 · Cited by 32
Applications of machine learning in computer-aided drug discovery
Turzo, S. B. A., Hantz, E. R., & Lindert, S. (2022) · QRB Discovery · doi:10.1017/qrd.2022.12 · Cited by 34
Protein Function Analysis through Machine Learning
Avery, C., Patterson, J., Grear, T. J., Frater, T. D., & Jacobs, D. J. (2022) · Biomolecules · doi:10.3390/biom12091246 · Cited by 31
“OpenFold is a recreation of AlphaFold using pytorch and RoseTTAfold is a “three track” neural network [93,94].”
BackgroundMethodHigh-throughput biochemistry in RNA sequence space: predicting structure and function
Marklund, E., Ke, Y., & Greenleaf, W. J. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-022-00567-5 · Cited by 31
“Accurate prediction of protein structure enabled by deep learning algorithms such as AlphaFold 78 and RoseTTAFold 79 represents a major breakthrough in structural biology.”
Advances in the discovery of new chemotypes through ultra-large library docking
Potlitz, F., Link, A., & Schulig, L. (2023) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2023.2171984 · Cited by 32
“Alternatively, the target structures can be predicted based on their sequence via homology modeling and more recent tools such as AlphaFold2 [46] or RoseTTAFold [47].”
MethodJin, Y., Fayyaz, A., Liaqat, A., Khan, A., Alshammari, A., Wang, Y., Gu, R., & Wei, D. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106893 · Cited by 31
Tetorya, M., Li, H., Djami‐Tchatchou, A. T., Buchko, G. W., Czymmek, K. J., & Shah, D. M. (2023) · Molecular Plant Pathology · doi:10.1111/mpp.13336 · Cited by 31
“Similarly, ab initio structure prediction using the Rosetta protein structure modeling package (Baek et al., 2021) did not predict any consistent fold or high-confidence secondary structure elements (data not shown).”
MethodWu, T., Guo, Z., & Cheng, J. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad298 · Cited by 35
Yang, D., Eun, H., & Prabowo, C. P. S. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24108923 · Cited by 30
“In addition, the rapidly advancing machine learning-assisted accurate prediction of proteins using AlphaFold [60] or RoseTTAFold [61] will allow better understanding of the complex polyketide biosynthesis machinery, thus allowing the creation of PKSs for the production of tailor-made aromatic…”
BackgroundBritton, B. M., Yovanno, R. A., Costa, S. F., McCausland, J. W., Lau, A. Y., Xiao, J., & Hensel, Z. (2023) · Nature Communications · doi:10.1038/s41467-023-39921-4 · Cited by 34
Structures of the mumps virus polymerase complex via cryo-electron microscopy
Li, T., Liu, M., Gu, Z., Su, X., Liu, Y., Lin, J., Zhang, Y., & Shen, Q.-T. (2024) · Nature Communications · doi:10.1038/s41467-024-48389-9 · Cited by 30
“We followed the reviewer’s advice and rephrased the statement to “P is required for RNA synthesis in most nsNSVs”.”
Modeling of protein conformational changes with Rosetta guided by limited experimental data
Sala, D., del Alamo, D., Mchaourab, H. S., & Meiler, J. (2022) · Structure · doi:10.1016/j.str.2022.04.013 · Cited by 30
Varadi, M., Bordin, N., Orengo, C., & Velankar, S. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102543 · Cited by 29
“The unprecedented quality of models predicted by Alpha-Fold 2.0 during the 14th Critical Assessment of Structure Prediction competition, followed by the release of an improved version of RoseTTAFold, made accurate protein structure prediction tools available to the broad scientific community [6 e 8].”
InfluentialProtein multiple conformations prediction using multi-objective evolution algorithm
Hou, M.-H., Jin, S.-R., Cui, X.-Y., Peng, C.-X., Zhao, K.-L., Song, L., & Zhang, G.-J. (2023) · doi:10.1101/2023.04.21.537776 · Cited by 29
Integrating Computational Design and Experimental Approaches for Next-Generation Biologics
Son, A., Park, J., Kim, W., Lee, W., Yoon, Y., Ji, J., & Kim, H. (2024) · Biomolecules · doi:10.3390/biom14091073 · Cited by 29
“The success of AlphaFold has inspired the development of other AI-powered tools for protein structure prediction and design, such as RoseTTAFold and ESMFold, further expanding the toolkit available to researchers [27,28].”
MethodProtein Multiple Conformation Prediction Using Multi-Objective Evolution Algorithm
(2024) · doi:10.1007/s12539-023-00597-5 · Cited by 29
“For example, consider RoseTTAFold [9], which employs an end-to-end prediction method to generate models using a three-track network.”
AI-assisted food enzymes design and engineering: a critical review
Wang, X., Yang, P., Zhao, B., & Liu, S. (2022) · Systems Microbiology and Biomanufacturing · doi:10.1007/s43393-022-00138-z · Cited by 30
“Generally, a protein with approximately 300 amino acids can be predicted its structure by RF within 30 min using an Nvidia 3080Ti GPU [37].”
MethodApproaching Optimal pH Enzyme Prediction with Large Language Models
Zaretckii, M., Buslaev, P., Kozlovskii, I., Morozov, A., & Popov, P. A. (2024) · ACS Synthetic Biology · doi:10.1021/acssynbio.4c00465 · Cited by 34
SPOT: A machine learning model that predicts specific substrates for transport proteins
Kroll, A., Niebuhr, N., Butler, G., & Lercher, M. J. (2024) · PLoS Biology · doi:10.1371/journal.pbio.3002807 · Cited by 30
DenAdel, A., Hughes, M., Thoutam, A., Gupta, A., Navia, A. W., Fusi, N., Raghavan, S., Winter, P. S., Amini, A. P., & Crawford, L. A. (2026) · Nature Methods · doi:10.1038/s41592-026-03120-y · Cited by 52
Advances in the Simulations of Enzyme Reactivity in the Dawn of the Artificial Intelligence Age
Świderek, K., Bertrán, J., Zinovjev, K., Tuñón, I., & Moliner, V. (2025) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70003 · Cited by 34
“Nowadays, the problem of determining the structure of a protein from its sequence is considered to be almost solved thanks to computational approaches such as AlphaFold [41, 42] or RoseTTAFold [43].”
Artificial intelligence methods for protein folding and design
Zhang, Z., Ou, C., Cho, Y., Akiyama, Y., & Ovchinnikov, S. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103066 · Cited by 31
Self-citationCheng, H., Yang, C., Wang, J., Liu, H., Zhang, K., Wu, R., Li, J., Fang, Y., Hu, R., Jeong, H., et al. (2025) · Chem · doi:10.1016/j.chempr.2025.102624 · Cited by 31
Self-citationArtificial intelligence-driven computational methods for antibody design and optimization
Vecchietti, L. F., Wijaya, B. N., Armanuly, A., Hangeldiyev, B., Jung, H., Lee, S., Cha, M., & Kim, H. M. (2025) · mAbs · doi:10.1080/19420862.2025.2528902 · Cited by 37
Generative AI for the Design of Molecules: Advances and Challenges
Sun, Y., Chen, L., Jing, Z., Li, Y. Y., Kim, D., Gao, J.-Y., Noroozi, R., Yi, G. Y., Feugmo, C. G. T., Klinkova, A., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02234 · Cited by 39
Lam, J. H., & Katritch, V. (2025) · npj Drug Discovery. · doi:10.1038/s44386-025-00031-4 · Cited by 40
Target identification and assessment in the era of AI
Pun, F. W., Podolskiy, D. I., Izumchenko, E., Mortlock, A. A., Oprea, T. I., Scheibye‐Knudsen, M., Fortney, K., Morgen, E. K., Ren, F., & Zhavoronkov, A. A. (2026) · Nature Reviews Drug Discovery · doi:10.1038/s41573-026-01412-8 · Cited by 40
“Concurrently, RoseTTAFold emerged as another major deep learning framework for structure prediction 159 .”
Reframing the Protein Folding Problem: Entropy as Organizer
Rose, G. D. (2021) · Biochemistry · doi:10.1021/acs.biochem.1c00687 · Cited by 29
From systems to structure — using genetic data to model protein structures
Braberg, H., Echeverria, I., Kaake, R. M., Šali, A., & Krogan, N. J. (2022) · Nature Reviews Genetics · doi:10.1038/s41576-021-00441-w · Cited by 35
“The accuracy of RoseTTAFold is generally somewhat lower than that of AlphaFold, but the predictions are faster and require less computational power 60 .”
BackgroundMethodInfluentialRecent Developments in Positron Emission Tomography Tracers for Proteinopathies Imaging in Dementia
Ni, R., & Nitsch, R. M. (2022) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.751897 · Cited by 30
“In addition, deep learning-based drug development such as using AlphaFold or RoseTTaFold and on-chip pharmacokinetics may speed up the development and optimization of imaging tracers (Schneider, 2018; Bhhatarai et al., 2019; Baek et al., 2021; Jumper et al., 2021).”
MethodDrug repurposing in silico screening platforms
Mullins, J. G. L. (2022) · Biochemical Society Transactions · doi:10.1042/bst20200967 · Cited by 34
Lemaire, O. N., & Wagner, T. (2022) · Biochemistry · doi:10.1021/acs.biochem.2c00135 · Cited by 32
QuasAr Odyssey: the origin of fluorescence and its voltage sensitivity in microbial rhodopsins
Silapētere, A., Hwang, S., Hontani, Y., Lahore, R. G. F., Balke, J., Escobar, F. V., Tros, M., Konold, P. E., Matis, R., Croce, R., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-33084-4 · Cited by 31
The impact of AlphaFold2 on experimental structure solution
Edich, M., Briggs, D. C., Kippes, O., Gao, Y., & Thorn, A. (2022) · Faraday Discussions · doi:10.1039/d2fd00072e · Cited by 29
Metadata
- Authors
- Baek, M., DiMaio, F., Anishchenko, I., Dauparas, J., Ovchinnikov, S., Lee, G. R., Wang, J., Cong, Q., Kinch, L. N., Schaeffer, R. D., Millán, C., Park, H., Adams, C., Glassman, C. R., DeGiovanni, A., Pereira, J. H., Rodrigues, A. V., van Dijk, A. A., Ebrecht, A. C., Opperman, D. J., Sagmeister, T., Buhlheller, C., Pavkov-Keller, T., Rathinaswamy, M. K., Dalwadi, U., Yip, C. K., Burke, J. E., Garcia, K. C., Grishin, N. V., Adams, P. D., Read, R. J., & Baker, D.
- Affiliations
- University of Washington (US)
- Harvard University (US)
- The University of Texas Southwestern Medical Center (US)
- Howard Hughes Medical Institute (US)
- University of Cambridge (GB)
- Stanford Medicine (US)
- Lawrence Berkeley National Laboratory (US)
- North-West University (ZA)
- University of the Free State (ZA)
- University of Graz (AT)
- University of Victoria (CA)
- University of British Columbia (CA)
- Corresponding author
- Baker, David
- ORCID
- Baek, Minkyung
- DiMaio, Frank
- Anishchenko, Ivan
- Dauparas, Justas
- Ovchinnikov, Sergey
- Lee, Gyu Rie
- Wang, Jue
- Cong, Qian
- Kinch, Lisa N.
- Schaeffer, R. Dustin
- Millán, Claudia
- Park, Hahnbeom
- Adams, Carson
- Glassman, Caleb R.
- Pereira, Jose H.
- Rodrigues, Andria V.
- van Dijk, Alberdina A.
- Ebrecht, Ana C.
- Opperman, Diederik J.
- Sagmeister, Theo
- Buhlheller, Christoph
- Rathinaswamy, Manoj K
- Dalwadi, Udit
- Yip, Calvin K
- Burke, John E
- Grishin, Nick V.
- Adams, Paul D.
- Read, Randy J.
- Baker, David
- Venue
- Science
- Publisher
- openRxiv
- Published
- 2021-06-15
- Volume
- 373
- Issue
- 6557
- Pages
- 871-876
- ISSN
- 0036-8075 (ISSN-L)
- PMC
- PMC7612213
- OpenAlex
- W3186179742
- Semantic Scholar
- 51362860fb8ad08255660303550ed4bc345535fc
- Cited by
- 5,549
- References
- 85
- Citations by year
- 2026: 912 · 2025: 1108 · 2024: 1165 · 2023: 1144 · 2022: 982 · 2021: 227
- FWCI
- 247.22
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Science (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (submittedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion, cc-by)
- DESY Publication Database (PUBDB) (Deutsches Elektronen-Synchrotron) (submittedVersion)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Apollo (cc-by)
- Funders
- National Science Foundation (GM127390, 1937533)
- Welch Foundation (I‐1505)
- Washington Research Foundation
- Microsoft
- TU Graz, Internationale Beziehungen und Mobilitätsprogramme
- Wellcome Trust (Z/17/Z, 209407/Z/17/Z, 209407)
- G. Harold and Leila Y. Mathers Foundation
- Diamond Light Source
- Open Philanthropy Project
- Global Challenges Research Fund (ST/R002754/1)
- Schmidt Family Foundation
- European Synchrotron Radiation Facility
- Austrian Science Fund (P 29432, DOC 50)
- National Institutes of Health (DP5OD026389, RO1-AI51321)
- Canadian Institutes of Health Research (168998, 168907)
- Science and Technology Facilities Council (ST/R002754/1)
- Deutsches Elektronen-Synchrotron
- National Institute of General Medical Sciences (P01GM063210, R35GM127390, R01GM123089)
- National Institute of Allergy and Infectious Diseases (R01AI051321)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Structural Biology › Enzyme Structure and Function
- Keywords
- protein structure prediction, protein-protein complex prediction, distance maps, sequence-based structure prediction, CASP14, protein function prediction
- MeSH terms
- Deep Learning, Amino Acid Sequence, Computer Simulation, Membrane Proteins, Models, Molecular, Protein Conformation, Proteins, Neural Networks, Computer, Protein Folding, Crystallography, X-Ray, Cryoelectron Microscopy, Protein Subunits, Databases, Protein, Receptors, G-Protein-Coupled, Multiprotein Complexes, Sphingosine N-Acyltransferase, ADAM Proteins
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
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.