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 1,601–1,700 of 5,636
Liu, J., Yuan, R., Shao, W., Wang, J., Silman, I., & Sussman, J. L. (2023) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26496 · Cited by 18
“Recently, 2000 random sequences of 100 amino acids each were used to generate 3D models with RoseTTAFold (RTF).(12) These initial”
MethodSelf-citationProtein structure-based evaluation of missense variants: Resources, challenges and future directions
David, A., & Sternberg, M. J. E. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102600 · Cited by 19
Liu, H., Wei, W., Pang, Z., Gu, S., Song, W., Gao, C., Chen, X., Liu, J., Guo, L., Wu, J., et al. (2023) · Biotechnology and Bioengineering · doi:10.1002/bit.28423 · Cited by 18
“The application of fusion labels (Wang et al., 2021) and molecular chaperones (Baek et al., 2021) has preliminarily solved the solubility problem.”
BackgroundHong, X., Lv, J., Li, Z., Xiong, Y., Zhang, J., & Chen, H. (2023) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2023.125233 · Cited by 18
Features and algorithms: facilitating investigation of secreted effectors in Gram-negative bacteria
Zhao, Z., Hu, Y., Hu, Y., White, A. P., & Wang, Y. (2023) · Trends in Microbiology · doi:10.1016/j.tim.2023.05.011 · Cited by 18
Wang, W., He, B., Xiao, T., Xu, M., Liu, B., Gao, Y., Chen, Y., Li, J., Ge, B., Ma, J., et al. (2023) · Advanced Functional Materials · doi:10.1002/adfm.202209441 · Cited by 21
Wu, J., Qing, H., Ouyang, J., Zhou, J., Gao, Z., Mason, C. E., Liu, Z., & Shi, T. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad311 · Cited by 19
An odorant receptor tuned to an attractive plant volatile vanillin in Spodoptera litura
Wei, Z., Wang, J.-X., Guo, J., Liu, X., Yan, Q., Zhang, J., & Dong, S. (2023) · Pesticide Biochemistry and Physiology · doi:10.1016/j.pestbp.2023.105619 · Cited by 18
Self-citationHou, W., Wu, H., Wang, S., Wang, W., Wang, B., & Wang, H. (2023) · Frontiers in Microbiology · doi:10.3389/fmicb.2023.1264612 · Cited by 18
“The initial tertiary structure was predicted by Robetta server9 (Baek et al., 2021).”
BackgroundLiu, B., Wang, T., Liu, L., Xiao, D., Yang, Y., Lu, Y., Zhang, A., Xu, K., Liu, S., Liu, K., et al. (2023) · New Phytologist · doi:10.1111/nph.19301 · Cited by 19
Kalogeropoulos, K., Bohn, M., Jenkins, D. E., Ledergerber, J., Sørensen, C. V., Hofmann, N., Wade, J., Fryer, T., Nguyen, G. T. T., Keller, U. A. D., et al. (2023) · Toxicon · doi:10.1016/j.toxicon.2023.107559 · Cited by 20
Dual-Specificity Inhibitor Targets Enzymes of the Trehalose Biosynthesis Pathway
Chen, Y., Tang, L., Jiang, Z., Wang, S., Qi, L., Tian, X., Deng, H., Kong, Z., Gao, W., Zhang, X., et al. (2023) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.3c06946 · Cited by 18
Analysis of the Healthy Platelet Proteome Identifies a New Form of Domain-Specific O-Fucosylation
Houlahan, C. B., Kong, Y. X., Johnston, B., Cielesh, M., Chau, T. H., Fenwick, J., Coleman, P. R., Hao, H., Haltiwanger, R. S., Thaysen‐Andersen, M., et al. (2024) · Molecular & Cellular Proteomics · doi:10.1016/j.mcpro.2024.100717 · Cited by 19
“To examine the predicted 3D-structure of the MMRN1 EMI domain we used the RoseTTAfold program (56), which predicted the correct pairing of cysteine residues (57) (Fig.”
MethodZeng, W., Yu, X., Shang, J., Zhao, P., Liu, W., Hu, J. S., & Peng, S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123525 · Cited by 18
AI in cellular engineering and reprogramming
Capponi, S., & Wang, S. (2024) · Biophysical Journal · doi:10.1016/j.bpj.2024.04.001 · Cited by 20
GalaxySagittarius-AF: Predicting Targets for Drug-Like Compounds in the Extended Human 3D Proteome
Kwon, S., Jung, N., Yang, J., & Seok, C. (2024) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168617 · Cited by 19
Rubach, P., Sikora, M., Jarmolinska, A. I., Perlinska, A. P., & Sulkowska, J. I. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae443 · Cited by 22
An outlook on structural biology after A lpha F old: tools, limits and perspectives
Rosignoli, S., Pacelli, M., Manganiello, F., & Paiardini, A. (2024) · FEBS Open Bio · doi:10.1002/2211-5463.13902 · Cited by 26
Discovering the Representation Bottleneck of Graph Neural Networks
Wu, F., Li, S., & Li, S. Z. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3446584 · Cited by 18
Prions: structure, function, evolution, and disease
Casey, C., & Sleator, R. D. (2024) · Archives of Microbiology · doi:10.1007/s00203-024-04200-3 · Cited by 36
“RoseTTAFold, in particular, harnesses deep learning algorithms to generate synthetic proteins with tailored properties, promising significant therapeutic potential (Krishna et al. 2024).”
The protein structurome of Orthornavirae and its dark matter
Mutz, P., Camargo, A. P., Sahakyan, H., Neri, U., Butković, A., Wolf, Y. I., Krupovìč, M., Dolja, V. V., & Koonin, E. V. (2024) · mBio · doi:10.1128/mbio.03200-24 · Cited by 22
Transient interactions between the fuzzy coat and the cross-β core of brain-derived Aβ42 filaments
Milanesi, M., Brotzakis, Z. F., & Vendruscolo, M. (2025) · Science Advances · doi:10.1126/sciadv.adr7008 · Cited by 18
Advancing protein structure prediction beyond AlphaFold2
Park, S., Myung, S., & Baek, M. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.102985 · Cited by 19
Self-citationHashem, S., Dougha, A., & Tufféry, P. (2025) · Molecules · doi:10.3390/molecules30051047 · Cited by 20
“…progress in accurately predicting the structure of a protein from its sequence, notably since the release of AlphaFold2 (AF2) [72], RoseTTAFold [73], and ESMFold [74], and their latest evolutions capable of modeling large molecular complexes (like AlphaFold3 (AF3) [75], RoseTTAFold All-Atom…”
AQuaRef: machine learning accelerated quantum refinement of protein structures
Zubatyuk, R. I., Biczysko, M., Ranasinghe, K. D., Moriarty, N. W., Gökcan, H., Kruse, H., Poon, B. K., Adams, P. D., Waller, M. P., Roitberg, A. E., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-64313-1 · Cited by 22
“Consequently, any nonstandard entities or interactions, such as novel ligands or covalent cross-chain links, require manual annotation and de fi nition, without which re fi nement may fail to proceed correctly or at all.”
Self-citationZhu, Z., Deng, Z., Wang, Q., Wang, Y., Zhang, D., Xu, R., Guo, L., & Wen, H. (2022) · Frontiers in Pharmacology · doi:10.3389/fphar.2022.939555 · Cited by 28
“In the advent of accurate protein structure prediction methods such as AlphaFold2 (Jumper et al., 2021) and RoseTTAFold (Baek et al., 2021), new possibilities are brought to cryo-EM structure building.”
MethodNandigrami, P., Szczepaniak, F., Boughter, C. T., Dehez, F., Chipot, C. J., & Roux, B. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c02173 · Cited by 18
Reduced B cell antigenicity of Omicron lowers host serologic response
Tubiana, J., Xiang, Y., Fan, L., Wolfson, H. J., Chen, K., Schneidman‐Duhovny, D., & Shi, Y. (2022) · Cell Reports · doi:10.1016/j.celrep.2022.111512 · Cited by 18
HProteome-BSite: predicted binding sites and ligands in human 3D proteome
Sim, J., Kwon, S., & Seok, C. (2022) · Nucleic Acids Res. · doi:10.1093/nar/gkac873 · Cited by 14
Molecular Mechanisms of Mercury-Sensitive Aquaporins
Xie, H., Ma, S., Zhao, Y., Zhou, H., Tong, Q., Chen, Y., Zhang, Z., Yu, K., Lin, Q., Kai, L., et al. (2022) · Journal of the American Chemical Society · doi:10.1021/jacs.2c10240 · Cited by 18
Computer-Aided Drug Design: An Update
Yu, W., Weber, D. J., & MacKerell, A. D. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-2855-3_7 · Cited by 21
AlphaFold2 Update and Perspectives
Tourlet, S., Radjasandirane, R., Diharce, J., & de Brevern, A. G. (2023) · BioMedInformatics · doi:10.3390/biomedinformatics3020025 · Cited by 19
“Since then, several other similar approaches have been made available, such as RoseTTAfold by Baker’s group [36] and by Meta Platforms, Inc. [37].”
MethodLearning the shape of protein microenvironments with a holographic convolutional neural network
Pun, M. N., Ivanov, A., Bellamy, Q., Montague, Z., LaMont, C., Bradley, P. H., Otwinowski, J., & Nourmohammad, A. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2300838121 · Cited by 23
Protein Folding Neural Networks Are Not RobustPreprint
Jha, S. K., Ramanathan, A., Ewetz, R., Velasquez, A., & Jha, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.04460 · Cited by 23
AlphaFold: A Special Issue and A Special Time for Protein Science
Serpell, L. C., Radford, S. E., & Otzen, D. E. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.167231 · Cited by 23
Harnessing AlphaFold to reveal hERG channel conformational state secretsPreprint
Ngo, K., Yang, P., Yarov-Yarovoy, V. M., Clancy, C. E., & Vorobyov, I. V. (2024) · eLife · doi:10.7554/elife.104901 · Cited by 24
“…advances our knowledge of the hERG channel structural dynamics and state-dependent drug binding but also sets a precedent for using AlphaFold2 or similar computational methods, such as RoseTTAFold (Baek et al., 2021) and ESMFold (Lin et al., 2023), to study other ion channels and membrane proteins.”
Gomes, D. E. B., Yang, B., Vanella, R., Nash, M. A., & Bernardi, R. C. (2024) · Journal of the American Chemical Society · doi:10.1021/jacs.4c05869 · Cited by 18
Heterologous expression of naturally evolved putative de novo proteins with chaperones
Eicholt, L. A., Aubel, M., Berk, K., Bornberg‐Bauer, E., & Lange, A. (2022) · Protein Science · doi:10.1002/pro.4371 · Cited by 18
Kahveci-Türköz, S., Bläsius, K., Wozniak, J., Rinkens, C., Seifert, A., Kasparek, P., Ohm, H., Oltzen, S., Nieszporek, M., Schwarz, N., et al. (2023) · Cellular and Molecular Life Sciences · doi:10.1007/s00018-023-04783-y · Cited by 17
“Ab initio structures of iRhom and iRhom–ADAM17 complex (without cytosolic regions) were generated with Alpha-Fold 2, AlphaFold Multimer, RoseTTAFold and TrRosetta [31–33, 47, 92] utilising ColabFold [93].”
BackgroundMethodA database of calculated solution parameters for the AlphaFold predicted protein structures
(2022) · doi:10.1038/s41598-022-10607-z · Cited by 17
Enzyme functional classification using artificial intelligence
Kim, H. R., Ji, H., Kim, G. B., & Lee, S. Y. (2025) · Trends in biotechnology · doi:10.1016/j.tibtech.2025.03.003 · Cited by 21
Phytopathogen Effector Biology in the Burgeoning AI Era
Jones, D., & Raffaele, S. (2025) · Annual Review of Phytopathology · doi:10.1146/annurev-phyto-121823-081033 · Cited by 19
Artificial intelligence-based methods for protein structure prediction: a survey
Zhan, Z., Hong, J., Li, J.-Y., Wang, C., He, L., Xu, Z., & Zhang, J. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11325-4 · Cited by 21
A streamlined base editor engineering strategy to reduce bystander editing
Valdez, I., O’Connor, I., Patel, D., Gierer, K., Harrington, J., Ellis, E., Caponetti, S. A., Sebra, R., Valley, H. C., Coote, K. J., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-63609-6 · Cited by 22
“…of our structure-guided engineering strategy, the advancement of arti fi cial intelligence-based protein structure prediction and modeling tools 49,50 , e.g., AlphaFold3 51 , will lead to high-quality structural predictions of variable base editors, thereby expanding the application scope of this…”
Computational frameworks for enhanced extracellular vesicle biomarker discovery
Kim, J., Yang, J. D., Agopian, V. G., Zhu, Y., Tseng, H., & You, S. (2026) · Experimental & Molecular Medicine · doi:10.1038/s12276-025-01622-x · Cited by 20
“In response to this need, recent breakthroughs in arti fi cial intelligence (AI), particularly in protein structure prediction and molecular interaction modeling 16 , have introduced novel avenues for biomedical research 17 – 19 .”
A comprehensive survey of genome language models in bioinformatics
Shu, L., Tang, J., Guan, X., & Zhang, D. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf724 · Cited by 25
Using metagenomic data to boost protein structure prediction and discovery
Hou, Q., Pucci, F., Pan, F., Xue, F., Rooman, M. J., & Feng, Q. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2021.12.030 · Cited by 20
“…or continue to fuel a series of other applications that have not been analyzed in this mini-review such as protein function prediction [124], predictions of protein–protein interactions and protein complex structures [95,125,126] and the detection and tracing of novel viral pathogens [127,128].”
BackgroundMethodPowering morphogenesis: multiscale challenges at the interface of cell adhesion and the cytoskeleton
Fernández‐González, R., & Peifer, M. A. (2022) · Molecular Biology of the Cell · doi:10.1091/mbc.e21-09-0452 · Cited by 19
“In parallel, artificial intelligence (AI)-driven approaches have revolutionized the ability to predict protein structure de novo (Baek et al., 2021; Jumper et al., 2021), and delivered databases of predicted structures of all proteins in multiple model animals including humans (Tunyasuvunakool et…”
BackgroundCMTr mediated 2′-O-ribose methylation status of cap-adjacent nucleotides across animals
Dix, T. C., Haussmann, I. U., Brivio, S., Nallasivan, M. P., Hadzhiev, Y., Müller, F., Müller, B., Pettitt, J., & Soller, M. (2022) · RNA · doi:10.1261/rna.079317.122 · Cited by 17
Kandaswamy, S., Zobel, L., John, B., Santhiya, S. T., Bogedein, J., Przemeck, G. K. H., Gailus‐Durner, V., Fuchs, H., Biel, M., de Angelis, M. H., et al. (2022) · Cell Death Discovery · doi:10.1038/s41420-022-01185-0 · Cited by 17
“Models were generated using the RoseTTAfold deep learning algorithm [19] available at https://robetta.”
MethodBae, H., & Nam, H. (2022) · Biomedicines · doi:10.3390/biomedicines11010067 · Cited by 17
“Recently, deep-learning models that predict protein structures based only on amino acid sequences have been developed [38,39].”
BackgroundStructural and biochemical insight into a modular β-1,4-galactan synthase in plants
Prabhakar, P. K., Pereira, J. H., Taujale, R., Shao, W., Bharadwaj, V. S., Chapla, D. G., Yang, J., Bomble, Y. J., Moremen, K. W., Kannan, N., et al. (2023) · Nature Plants · doi:10.1038/s41477-023-01358-4 · Cited by 22
Self-citationDey, D., Tanaka, R., & Itô, H. (2023) · Journal of Molecular Evolution · doi:10.1007/s00239-023-10100-9 · Cited by 18
PSAC-PDB: Analysis and classification of protein structures
Nawaz, M. S., Fournier‐Viger, P., He, Y., & Zhang, Q. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.106814 · Cited by 18
“Protein structural classification and prediction is an important research topic and the recent use of deep learning methods [20, 21] to accurately predict protein structures has greatly increased the scope of comparative structural studies that was constrained in the past by the labor and cost…”
Boyer, N., Tokmina‐Lukaszewska, M., Batista, M. B., Mus, F., Dixon, R. A., Bothner, B. B., & Peters, J. W. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2302732120 · Cited by 17
Oda, T. (2023) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26551 · Cited by 17
Generative design of therapeutics that bind and modulate protein states
Chen, T., Hong, L., Yudistyra, V., Vincoff, S., & Chatterjee, P. (2023) · Current Opinion in Biomedical Engineering · doi:10.1016/j.cobme.2023.100496 · Cited by 20
DiIorio, M. C., & Kulczyk, A. (2023) · Micromachines · doi:10.3390/mi14091674 · Cited by 19
“The field of protein structure prediction has been transformed by significant developments in DL algorithms, exemplified by AlphaFold2 [68], RoseTTaFold [166], ESM-Fold [167], and I-TASSER-MTD [168].”
MethodFusionNeoAntigen: a resource of fusion gene-specific neoantigens
Kumar, H., Luo, R., Wen, J., Yang, C., Zhou, X., & Kim, P. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad922 · Cited by 19
“Using RoseTTAFold ( 20 ), we predicted the 3D structures of these cell surface fusion proteins.”
BackgroundMethodMultiparametric domain insertional profiling of adeno-associated virus VP1
Hoffmann, M. D., Zdechlik, A. C., He, Y., Nedrud, D. M., Aslanidi, G., Gordon, W. R., & Schmidt, D. (2023) · Molecular Therapy — Methods & Clinical Development · doi:10.1016/j.omtm.2023.101143 · Cited by 18
Segura, J., Rose, Y., Bi, C., Duarte, J. M., Burley, S. K., & Bittrich, S. (2023) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2023.1311287 · Cited by 19
Advances in ligand-specific biosensing for structurally similar molecules
Xi, C., Diao, J., & Moon, T. S. (2023) · Cell Systems · doi:10.1016/j.cels.2023.10.009 · Cited by 19
Atxabal, U., Nycholat, C. M., Pröpster, J. M., Fernández, A., Oyenarte, I., Lenza, M. P., Franconetti, A., Soares, C. O., Coelho, H., Marcelo, F., et al. (2024) · ACS Chemical Biology · doi:10.1021/acschembio.3c00664 · Cited by 18
Fine-tuning activation specificity of G-protein-coupled receptors via automated path searching
Ti, R., Pang, B., Yu, L., Gan, B., Ma, W., Warshel, A., Ren, R., & Zhu, L. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2317893121 · Cited by 17
“Given the abundance of resolved inactive and active forms of various GPCRs (29) and the tremendous progress in structure prediction by AlphaFold2 (30) or RosettaFold (31), path methods are particularly suitable for dissecting the activation process between the two states.”
Lactylation prediction models based on protein sequence and structural feature fusion
Yang, Y., Yang, J., & Liu, J.-F. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbad539 · Cited by 19
Ge, J., Jiang, D., Sun, H., Kang, Y., Pan, P., Deng, Y., Hsieh, C., & Hou, T. (2024) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2024.101980 · Cited by 20
Rational modification of melatonin for broad‐spectrum antifungal agents discovery
Cai, H., Li, R., Chen, Y., Bi, R., Fang, X., Wu, P., Xu, W., Bao, L., Liu, Z., Li, J., et al. (2024) · Journal of Pineal Research · doi:10.1111/jpi.12960 · Cited by 17
von Ehr, J., Oberstrass, L., Yazgan, E., Schnaubelt, L. I., Blümel, N., McNicoll, F., Weigand, J. E., Zarnack, K., Müller-McNicoll, M., Korn, S. M., et al. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.107457 · Cited by 18
“Five structural models of Arid5a were generated ab initio with RoseTTAfold (75) using residues 37 to 183 from the sequence deposited in Uniprot (76) under ID Q03989 (see Fig.”
MethodRaisinghani, N., Alshahrani, M., Gupta, G., Tian, H., Xiao, S., Tao, P., & Verkhivker, G. M. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c00222 · Cited by 17
Soleymani, F., Paquet, E., Viktor, H. L., & Michalowski, W. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.06.021 · Cited by 19
“The emergence of artificial intelligence/machine learning methods, such as AlphaFold 2 [11] and RoseTTAFold [20], has revolutionized structural bioinformatics, enabling accurate prediction of protein 3-”
MethodInfluentialExpanding insights from in situ cryo-EM
Hutchings, J., & Villa, E. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102885 · Cited by 18
Luo, D., Zhang, Y., Li, Y., Liu, Z., Wu, H., & Xue, W. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c03731 · Cited by 17
Ochoa, S., Hsu, A. P., Oler, A. J., Kumar, D., Chauss, D., van Hamburg, J. P., van Laar, G. G., Oikonomou, V., Ganesan, S., Ferré, E. M. N., et al. (2024) · Science Translational Medicine · doi:10.1126/scitranslmed.adk0845 · Cited by 20
“Because the complete crystal structure of AIRE has not yet been solved and there are now no available templates for the C-terminal region of AIRE, we performed ab initio modeling using AlphaFold and RoseTTAFold ( 32 , 33 ).”
MethodBanico, E. C., Sira, E. M. J. S., Fajardo, L. E., Dulay, A. N. G., Odchimar, N. M. O., Simbulan, A. M., & Orosco, F. L. (2024) · PLoS ONE · doi:10.1371/journal.pone.0310703 · Cited by 22
Hu, Y., Yang, H., Li, M., Zhong, Z., Zhou, Y., Bai, F., & Wang, Q. (2024) · Advanced Science · doi:10.1002/advs.202400884 · Cited by 22
Evolving CRISPR/Cas system for food safety monitoring across the food supply chain
Shen, J., Zhang, D., He, Y., Shen, Y., Duan, M., Zhao, Y., Liu, Z., & Jia, F. (2024) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2024.118050 · Cited by 19
Exploration of the hierarchical assembly space of collagen-like peptides beyond the triple helix
Yu, L. T., Kreutzberger, M. A. B., Bui, T. H., Hancu, M. C., Farsheed, A. C., Egelman, E. H., & Hartgerink, J. D. (2024) · Nature Communications · doi:10.1038/s41467-024-54560-z · Cited by 17
Crosslinking intermodular condensation in non-ribosomal peptide biosynthesis
Heberlig, G. W., Clair, J. J. L., & Burkart, M. D. (2024) · Nature · doi:10.1038/s41586-024-08306-y · Cited by 17
“The initial molecular models for TycA-M1 and TycB-M2 were generated using the Robetta server 42 (https://robetta.bakerlab.org/) and were fit into the map on a domain-by-domain basis.”
Reprogramming pretrained language models for protein sequence representation learning
Vinod, R., Chen, P., & Das, P. (2025) · Digital Discovery · doi:10.1039/d4dd00195h · Cited by 18
The continuous evolution of biomolecular force fields
Lu, X., Chen, J., & Huang, J. (2025) · Structure · doi:10.1016/j.str.2025.05.013 · Cited by 21
Retargeted serine integrases for one-step, precise integration of large DNA sequences in human cells
Fauser, F., Arangundy‐Franklin, S., Davis, J. E., Liu, L., Schmidt, N., Rodriguez, L., Xia, D. F., Nguyen, N., Zhou, Y., Scarlott, N. A., et al. (2026) · Nature Biotechnology · doi:10.1038/s41587-026-03186-1 · Cited by 17
Pan, L., Hoffmeister, P., Turkiewicz, A., Huynh, N., Große-Berkenbusch, A., Knippschild, U., Gebhardt, J. C. M., Baumann, B., Borggrefe, T., & Oswald, F. (2021) · Cancers · doi:10.3390/cancers13195027 · Cited by 19
How to strike a conformational balance in protein force fields for molecular dynamics simulations?
Kang, W., Jiang, F., & Wu, Y. (2021) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1578 · Cited by 18
“…given the impressive progress made in the field of “ static ” protein structure prediction by deep-learning models (Alphafold2, 258 RoseTTAFold, 259 etc.), there is an ever-pressing need for reliable protein FFs that can give not only accurate conformational balances but also realistic protein…”
Background3DFI: a pipeline to infer protein function using structural homology
Julian, A. T., dos Santos, A. C. M., & Pombert, J. (2021) · Bioinformatics Advances · doi:10.1093/bioadv/vbab030 · Cited by 17
Computational methods to assist in the discovery of pharmacological chaperones for rare diseases
Scafuri, B., Verdino, A., D’Arminio, N., & Marabotti, A. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac198 · Cited by 19
Phillips, E., Bulka, O., Picott, K. J., Kümmel, S., Edwards, E. A., Nijenhuis, I., Gehre, M., Dworatzek, S. M., Webb, J., & Lollar, B. S. (2022) · FEMS Microbiology Ecology · doi:10.1093/femsec/fiac072 · Cited by 18
Laveglia, V., Giachetti, A., Sala, D., Andreini, C., & Rosato, A. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00522 · Cited by 18
Starch-Binding Domain Modulates the Specificity of Maltopentaose Production at Moderate Temperatures
Ding, N., Zhao, B., Han, X., Li, C., Gu, Z., & Li, Z. (2022) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.2c03031 · Cited by 17
Iglesias, R., Russo, R., Landi, N., Valletta, M., Chambery, A., Maro, A. D., Bolognesi, A., Ferreras, J. M., & Citores, L. (2022) · Toxins · doi:10.3390/toxins14090611 · Cited by 17
“The recent emergence of programs that predict the structure of proteins at the atomic level [23,64] has allowed us to conduct in silico experiments to predict how galactose and lactose bind to these proteins.”
BackgroundRefinement of AlphaFold2 models against experimental and hybrid cryo-EM density maps
Alshammari, M., Wriggers, W. R., Sun, J., & He, J. J. (2022) · QRB Discovery · doi:10.1017/qrd.2022.13 · Cited by 21
Rcheulishvili, N., Papukashvili, D., Liu, C., Ji, Y., He, Y., & Wang, P. G. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.1025884 · Cited by 20
Advances in antibody discovery from human BCR repertoires
Xu, Z., Ismanto, H. S., Zhou, H., Saputri, D. S., Sugihara, F., & Standley, D. M. (2022) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2022.1044975 · Cited by 19
“Protein structure prediction is one of the areas of computational biology that has progressed most rapidly in recent years, owing to breakthroughs in Deep learning (Baek et al., 2021; Jumper et al., 2021).”
BackgroundApplying deep reinforcement learning to the HP model for protein structure prediction
Yang, K., Huang, H., Vandans, O., Murali, A., Tian, F., Yap, R. H. C., & Dai, L. (2022) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2022.128395 · Cited by 19
“We highlight that the HP model represents the ab initio paradigm heavily rooted in biophysics, which is di ff erent from the AlphaFold [10, 11] and the academia counterpart ‘RoseTTaFold’ [12] methods that rely heavily on protein structure data.”
MethodPrecord, T. W., Ramesh, S., Dommaraju, S. R., Harris, L. A., Kille, B. L., & Mitchell, D. A. (2023) · ACS Bio & Med Chem Au · doi:10.1021/acsbiomedchemau.2c00085 · Cited by 17
AI-Predicted Protein Deformation Encodes Energy Landscape Perturbation
McBride, J. M., & Tlusty, T. (2024) · Physical Review Letters · doi:10.1103/physrevlett.133.098401 · Cited by 17
Protein-Protein Interaction Prediction is Achievable with Large Language ModelsPreprint
Hallee, L., & Gleghorn, J. P. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.07.544109 · Cited by 26
Comparative Structure Analysis of the Multi-Domain, Cell Envelope Proteases of Lactic Acid Bacteria
Christensen, L. F., Høie, M. H., Bang-Berthelsen, C. H., Marcatili, P., & Hansen, E. B. (2023) · Microorganisms · doi:10.3390/microorganisms11092256 · Cited by 17
“This structural fold corresponded to the structure of other SlpA-domains, where the two β -sheet regions were divided by a spacer region with a reduced sequence identity compared to the two tandem regions [46,47].”
Neprosin belongs to a new family of glutamic peptidase based on in silico evidence
Ting, T.-Y., Baharin, A., Ramzi, A. B., Ng, C.-L., & Goh, H.-H. (2022) · Plant Physiology and Biochemistry · doi:10.1016/j.plaphy.2022.04.027 · Cited by 17
Ching, W.-Y., Adhikari, P., Jawad, B., & Podgornik, R. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms231710091 · Cited by 17
“More recently, there was a flurry of research activity [44, 45] based on artificial intelligence (AI) and machine learning (ML) techniques, such as AlphaFold [46] and RoseTTAFold [47].”
BackgroundApplication of artificial scaffold systems in microbial metabolic engineering
Liu, N., Dong, W., Yang, H., Li, J.-H., & Chiu, T.-Y. (2023) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2023.1328141 · Cited by 16
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.