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 601–700 of 5,634
van Breugel, M., Rosa e Silva, I., & Andreeva, A. (2022) · Communications Biology · doi:10.1038/s42003-022-03269-0 · Cited by 55
“…by this fi eld and utilising powerful and transformative deep-learning approaches, AlphaFold2 (AF2) developed by DeepMind has recently marked a breakthrough in the accuracy of predicting protein structures that has been mirrored by equally impressive achievements by academic groups 14 – 18 .”
BackgroundCsx28 is a membrane pore that enhances CRISPR-Cas13b–dependent antiphage defense
VanderWal, A. R., Park, J.-U., Polevoda, B., Nicosia, J. K., Molina Vargas, A. M., Kellogg, E. H., & O’Connell, M. R. (2023) · Science · doi:10.1126/science.abm1184 · Cited by 55
End-to-end learning of multiple sequence alignments with differentiable Smith–Waterman
Petti, S., Bhattacharya, N., Rao, R., Dauparas, J., Thomas, N., Zhou, J., Rush, A. M., Koo, P., & Ovchinnikov, S. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btac724 · Cited by 54
Self-citation(2021) · doi:10.1371/journal.pone.0259871 · Cited by 54
“AlphaFold2 and RoseTTAFold prediction of protein structure is greatly improved by high MSA quality and depth, with high MSA coverage critical for high confidence predictions [1, 2].”
BackgroundHuman Antibodies for Viral Infections
Crowe, J. E. (2022) · Annual Review of Immunology · doi:10.1146/annurev-immunol-042718-041309 · Cited by 57
Reinforcement learning for systems pharmacology-oriented and personalized drug design
Tan, R. K., Liu, Y., & Xie, L. (2022) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2022.2072288 · Cited by 60
“Tremendous progress in protein structure predictions [15,16] and development of new methods for exploring dark chemical genomics space [17] significantly enhance our ability to deconvolute genome-wide target profiles for dark proteins that are not readily accessible by experimental methods.”
BackgroundUsing machine learning to predict the effects and consequences of mutations in proteins
Diaz, D. J., Kulikova, A. V., Ellington, A. D., & Wilke, C. O. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102518 · Cited by 52
Serverless Prediction of Peptide Properties with Recurrent Neural Networks
Ansari, M., & White, A. D. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c01317 · Cited by 56
“Popular tools, like RoseTTAFold[23], can have days-long queues.”
MethodDevelopment of a novel multi-epitope mRNA vaccine candidate to combat HMPV virus
Ma, S., Zhu, F., Xu, Y., Wen, H., Rao, M., Zhang, P., Peng, W., Cui, Y., Yang, H., Tan, C., et al. (2024) · Human Vaccines & Immunotherapeutics · doi:10.1080/21645515.2023.2293300 · Cited by 71
“28 In addition, the quality of the model can be evaluated with Procheck, ERRAT, and Pro-sa Web servers.”
MethodExploiting enzyme evolution for computational protein design
Pinto, G., Corbella, M., Demkiv, A. O., & Kamerlin, S. C. L. (2021) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2021.08.008 · Cited by 62
Advances in NMR Spectroscopy of Weakly Aligned Biomolecular Systems
Chiliveri, S. C., Robertson, A. J., Shen, Y., Torchia, D. A., & Bax, A. (2022) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00730 · Cited by 52
Integrative Structural Biology in the Era of Accurate Structure Prediction
Masrati, G., Landau, M., Ben-Tal, N., Lupas, A., Kosloff, M., & Kosinski, J. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.167127 · Cited by 53
Deep learning methods for protein function prediction
Boadu, F., Lee, A., & Cheng, J. (2025) · PROTEOMICS · doi:10.1002/pmic.202300471 · Cited by 53
“We classify these methods roughly into four main categories based on the input information used by them: (1) sequence-based methods of using only protein sequence as input, (2) structure-based methods of using protein structure as input, (3) interaction-based methods of using protein–protein…”
Orton, H. W., Qianzhu, H., Abdelkader, E. H., Habel, E., Tan, Y., Frkic, R. L., Jackson, C. J., Huber, T., & Otting, G. (2021) · Journal of the American Chemical Society · doi:10.1021/jacs.1c10104 · Cited by 53
Chaturvedi, S. S., Bím, D., Christov, C. Z., & Alexandrova, A. N. (2023) · Chemical Science · doi:10.1039/d3sc02982d · Cited by 57
Biospecific Chemistry for Covalent Linking of Biomacromolecules
Cao, L., & Wang, L. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00066 · Cited by 54
Target-Specific De Novo Peptide Binder Design with DiffPepBuilder
Wang, F., Wang, Y., Feng, L., Zhang, C., & Lai, L. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00975 · Cited by 54
“To indicate breaks between chains, we incorporated a 100-residue gap in the residue indices between each chain, following the approach in RoseTTAFold[29].”
MethodUnmasking AlphaFold to integrate experiments and predictions in multimeric complexes
Mirabello, C., Wallner, B., Nystedt, B., Azinas, S., & Carroni, M. (2024) · Nature Communications · doi:10.1038/s41467-024-52951-w · Cited by 46
“The idea was later generalised to directly fi lling in gaps in 3D structures in RF joint 51 , a modi fi ed version of RoseTTAFold 52 weremaskingfragmentsofproteinsequence/structure pairs allows to predict native-like structures while generating novel sequences in the masked regions.”
BackgroundAdvancing time-resolved structural biology: latest strategies in cryo-EM and X-ray crystallography
Banari, A., Samanta, A. K., Munke, A., Laugks, T., Bajt, S., Grünewald, K., Marlovits, T. C., Küpper, J., Maia, F. R. N. C., Chapman, H. N., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02659-6 · Cited by 68
“14) and RoseTTAFold 15 , have achieved high-accuracy protein structure predictions and assist in ligand design.”
Peptide-based drug design using generative AI
Ekambaram, S., & Dokholyan, N. V. (2026) · Chemical Communications · doi:10.1039/d5cc04998a · Cited by 59
Balasubramaniam, D., Schroeder, O., Russell, A. M., Fitchett, J. R., Austin, A. K., Beyer, T. P., Chen, Y., Day, J. W., Ehsani, M. E., Heng, A. R., et al. (2022) · Journal of Lipid Research · doi:10.1016/j.jlr.2022.100198 · Cited by 56
Barbarin-Bocahu, I., & Graille, M. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322002157 · Cited by 52
Contriving multi-epitope vaccine ensemble for monkeypox disease using an immunoinformatics approach
Aziz, S., Almajhdi, F. N., Waqas, M. S., Ullah, I., Salim, M. A., Khan, N. A., & Ali, A. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.1004804 · Cited by 57
“Modeling, re fi nement, and quality validation of tertiary structure I-TASSER (41) and RoseTTAFold (42) servers were used to predict the tertiary structures of the designed vaccines.”
MethodPrediction of DNA origami shape using graph neural network
Truong-Quoc, C., Lee, J. Y., Kim, K. S., & Kim, D. (2024) · Nature Materials · doi:10.1038/s41563-024-01846-8 · Cited by 57
Protein Ensemble Generation Through Variational Autoencoder Latent Space Sampling
Mansoor, S., Baek, M., Park, H., Lee, G. R., & Baker, D. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c01057 · Cited by 51
“The comparison with AF2 is vital as it showcases the current state-of-the-art in single-state structure prediction; AF2 generates diverse structures for each target by incorporating variations in input structural templates and input MSA features (Table S5, ″ 1.12.1 Training procedure, ″ in the…”
InfluentialSelf-citationLiu, Y., Wang, S., Dong, J., Chen, L.-H., Wang, X., Wang, L., Li, F., Wang, C., Zhang, J., Wang, Y., et al. (2024) · Nature Methods · doi:10.1038/s41592-024-02437-w · Cited by 61
“While matching the performance of the pretrained RoseTTAFold-based RFdiffusion in generating experimentally realizable protein structures, SCUBA-D readily generates protein structures with not-yet-observed overall folds that are different from those predictable with RoseTTAFold.”
InfluentialProtein structure prediction via deep learning: an in-depth review
Meng, Y., Zhang, Z., Zhou, C., Tang, X., Hu, X., Tian, G., Yang, J., & Yao, Y. (2025) · Frontiers in Pharmacology · doi:10.3389/fphar.2025.1498662 · Cited by 54
“Although AlphaFold2 and alternative models such as RoseTTAFold Baek et al. (2021), ESMFold Lin et al. (2022), and OmegaFold (Wu et al., 2022) are widely considered to have successfully addressed the challenge of predicting protein structures from sequences, their effectiveness is primarily limited…”
InfluentialProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
Hong, L., Li, M., Ma, X., Ouyang, W., Tan, P., Tan, Y., Yu, H., Zhong, B., Zhou, B., & Zhou, Z. (2024) · Advances in Neural Information Processing Systems 37 · doi:10.52202/079017-1126 · Cited by 44
Yu, C., Chen, W., Chiang, Y.-H., Guo, K., Martín‐Moldes, Z., Kaplan, D. L., & Buehler, M. J. (2022) · ACS Biomaterials Science & Engineering · doi:10.1021/acsbiomaterials.1c01343 · Cited by 54
Ford, C. T., Jacob Machado, D., & Janies, D. A. (2022) · Frontiers in Virology · doi:10.3389/fviro.2022.830202 · Cited by 52
“RoseTTAFold is a similar neural network-based system by the Institute for Protein Design at the University ofWashington (12).”
MethodKæstel-Hansen, J., de Sautu, M., Saminathan, A., Scanavachi, G., Bango Da Cunha Correia, R. F., Juma Nielsen, A., Bleshøy, S. V., Tsolakidis, K., Boomsma, W., Kirchhausen, T., et al. (2025) · Nature Methods · doi:10.1038/s41592-025-02665-8 · Cited by 51
HADDOCK3: A Modular and Versatile Platform for Integrative Modeling of Biomolecular Complexes
Giulini, M., Reys, V., Teixeira, J. M. C., Jiménez-García, B., V. Honorato, R., Kravchenko, A., Xu, X., Versini, R., Engel, A., Verhoeven, S., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00969 · Cited by 51
Design of Cyclic Peptides Targeting Protein–Protein Interactions Using AlphaFold
(2023) · doi:10.3390/ijms241713257 · Cited by 51
Ozden, B., Kryshtafovych, A., & Karaca, E. (2023) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26598 · Cited by 51
“13,14 The CAPRI blind docking competition has been evaluating the state-of-the-art in assembly modeling since 2002.”
BackgroundThe Zip4 protein directly couples meiotic crossover formation to synaptonemal complex assembly
Pyatnitskaya, A., Andreani, J., Guérois, R., De Muyt, A., & Borde, V. (2022) · Genes & Development · doi:10.1101/gad.348973.121 · Cited by 51
“A 3D model of Zip4 was generated using the latest version of the RoseTTAFold server combining coevolution and deep learning approaches for the prediction of 3D monomeric structures (Baek et al., 2021).”
MethodProtein–Protein Docking: Past, Present, and Future
Sunny, S., & Jayaraj, P. B. (2021) · The Protein Journal · doi:10.1007/s10930-021-10031-8 · Cited by 54
“Baek et al. [115] used a three-track network that uses the sequence data, distance map, and 3D coordinate information to elucidate the working of AlphaFold.”
MethodIdentification and function analysis of bHLH genes in response to cold stress in sweetpotato
Jin, R., Kim, H. S., Yu, T., Zhang, A., Yang, Y., Liu, M., Yu, W., Zhao, P., Zhang, Q., Cao, Q., et al. (2021) · Plant Physiology and Biochemistry · doi:10.1016/j.plaphy.2021.11.027 · Cited by 51
Methods for Cryo-EM Single Particle Reconstruction of Macromolecules Having Continuous Heterogeneity
Toader, B., Sigworth, F. J., & Lederman, R. R. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.168020 · Cited by 70
“Finally, we have we witnessed in recent years the immense success of protein structure prediction algorithms such as AlphaFold [90] and RoseTTAfold [91].”
MethodThe LightDock Server: Artificial Intelligence-powered modeling of macromolecular interactions
Jiménez‐García, B., Roel‐Touris, J., & Barradas‐Bautista, D. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad327 · Cited by 51
The current role and evolution of X-ray crystallography in drug discovery and development
Bijak, V., Szczygiel, M., Lenkiewicz, J., Gucwa, M., Cooper, D. R., Murzyn, K., & Minor, W. (2023) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2023.2246881 · Cited by 55
Tackling Undruggable Targets with Designer Peptidomimetics and Synthetic Biologics
Swenson, C., Mandava, G., Thomas, D. M., & Moellering, R. E. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00423 · Cited by 63
Roadmap on machine learning glassy dynamics
Jung, G., Alkemade, R. M., Bapst, V., Coslovich, D., Filion, L., Landes, F. P., Liu, A. J., Pezzicoli, F. S., Shiba, H., Volpe, G., et al. (2025) · Nature Reviews Physics · doi:10.1038/s42254-024-00791-4 · Cited by 73
“Salient examples of successful applications of attention are AlphaFold v2 and RoseTTAFold [143, 144], which both use a rotation-equivariant attention-based trans-former to predict the three-dimensional structure of proteins.”
Molecular machineries shaping the mitochondrial inner membrane
Daumke, O., & van der Laan, M. (2025) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-025-00854-z · Cited by 60
“Recently, structural insights into some of the key factors governing MIM architecture have been experimentally obtained and artificial intelligence-based approaches 27,28 have allowed accurate predictions of complexes so far not amenable to structural studies.”
Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence
Duran-Frigola, M., Cigler, M., & Winter, G. E. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.2c11098 · Cited by 50
Livesey, B. J., & Marsh, J. A. (2025) · Genome Biology · doi:10.1186/s13059-025-03575-w · Cited by 50
“Thus, given the recent availability of computational structural models for all human proteins [36, 62], the inclusion of structural information may now becoming more important for variant effect prediction.”
Conformational changes and CO2-induced channel gating in connexin26
Brotherton, D. H., Savva, C. G., Ragan, T. J., Dale, N., & Cameron, A. D. (2022) · Structure · doi:10.1016/j.str.2022.02.010 · Cited by 51
Can Drug Repurposing Accelerate Precision Oncology?
Schipper, L. J., Zeverijn, L. J., Garnett, M. J., & Voest, E. E. (2022) · Cancer Discovery · doi:10.1158/2159-8290.cd-21-0612 · Cited by 46
DSDP: A Blind Docking Strategy Accelerated by GPUs
Huang, Y., Zhang, H., Jiang, S., Yue, D., Lin, X., Zhang, J., & Gao, Y. Q. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00519 · Cited by 53
Wu, X., Lin, H., Bai, R., & Duan, H. (2024) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2024.116262 · Cited by 59
Modeling protein–ligand interactions for drug discovery in the era of deep learning
Wang, Y., Li, Y., Chen, J., & Lai, L. (2025) · Chemical Society Reviews · doi:10.1039/d5cs00415b · Cited by 53
AlphaBridge: Tools for the analysis of predicted biomolecular complexes
Salmoral, D. Á., Borza, R., Maiella, C., Kwee, B. P. Y., Xie, R., Joosten, R. P., Hekkelman, M. L., & Perrakis, A. (2026) · Structure · doi:10.1016/j.str.2026.08.011 · Cited by 54
Gorgulla, C., Jayaraj, A., Fackeldey, K., & Arthanari, H. (2022) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2022.102156 · Cited by 52
Rhodopsin-bestrophin fusion proteins from unicellular algae form gigantic pentameric ion channels
Rozenberg, A., Kaczmarczyk, I., Matzov, D., Vierock, J., Nagata, T., Sugiura, M., Katayama, K., Kawasaki, Y., Konno, M., Nagasaka, Y., et al. (2022) · Nature Structural & Molecular Biology · doi:10.1038/s41594-022-00783-x · Cited by 54
A recipe for cracking the quantum scaling limit with machine learned electron densities
Rackers, J. A., Tecot, L., Geiger, M., & Smidt, T. (2023) · Machine Learning Science and Technology · doi:10.1088/2632-2153/acb314 · Cited by 80
Huang, Y. J., Zhang, N., Bersch, B., Fidelis, K., Inouye, M., Ishida, Y., Kryshtafovych, A., Kobayashi, N., Kuroda, Y., Liu, G., et al. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26246 · Cited by 49
Predicting antibody binders and generating synthetic antibodies using deep learning
Lim, Y. W., Adler, A. S., & Johnson, D. S. (2022) · mAbs · doi:10.1080/19420862.2022.2069075 · Cited by 49
Zeng, W., Dou, Y., Pan, L., Xu, L., & Peng, S. (2024) · Nature Communications · doi:10.1038/s41467-024-52293-7 · Cited by 49
“This particular structure-coloring and MCC need to be recalculated.”
Phosphorylation control of PIN auxin transporters
Bassukas, A. E. L., Xiao, Y., & Schwechheimer, C. (2021) · Current Opinion in Plant Biology · doi:10.1016/j.pbi.2021.102146 · Cited by 56
Uman-type neurofilament light antibodies are effective reagents for the imaging of neurodegeneration
Shaw, G., Madorsky, I., Li, Y., Wang, Y.-S., Jorgensen, M., Rana, S. D., & Fuller, D. D. (2023) · Brain Communications · doi:10.1093/braincomms/fcad067 · Cited by 52
Li, P., & Liu, Z.-P. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad288 · Cited by 50
Harnessing the power of artificial intelligence to advance cell therapy
Capponi, S., & Daniels, K. G. (2023) · Immunological Reviews · doi:10.1111/imr.13236 · Cited by 54
“RoseTTAFold was developed and published in 2021 61 to improve the accuracy of protein structure prediction for protein design purposes.”
BackgroundLi, J., Kang, G., Wang, J., Yuan, H., Wu, Y., Meng, S., Wang, P., Zhang, M., Wang, Y., Feng, Y., et al. (2023) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2023.125733 · Cited by 55
Self-citationLucas, B. A., Himes, B. A., & Grigorieff, N. (2023) · eLife · doi:10.7554/elife.90486 · Cited by 49
A review of machine learning-based methods for predicting drug–target interactions
Shi, W., Yang, H. T., Xie, L., Yin, X.-X., & Zhang, Y. (2024) · Health Information Science and Systems · doi:10.1007/s13755-024-00287-6 · Cited by 61
“These advances in protein structure prediction, such as AlphaFold2 [96] and RoseTTA [97], may accelerate research at various stages of the drug discovery process.”
Jung, J., Yagi, K., Tan, C., Oshima, H., Mori, T., Yu, I., Matsunaga, Y., Kobayashi, C., Ito, S., Torre, D. U. L., et al. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c02096 · Cited by 55
“Combining Machine Learning with MD. Alpha-Fold 176 and RoseTTAFold 177 have marked significant advancements in predicting biomolecular structures through deep learning algorithms.”
Xiong, D., Qiu, Y., Zhao, J., Zhou, Y., Lee, D., Gupta, S., Torres, M., Lü, W., Liang, S., Kang, J. J., et al. (2024) · Nature Biotechnology · doi:10.1038/s41587-024-02428-4 · Cited by 61
Berman, H. M., & Burley, S. K. (2025) · Quarterly Reviews of Biophysics · doi:10.1017/s0033583525000034 · Cited by 72
Structures of highly flexible intracellular domain of human α7 nicotinic acetylcholine receptor
Bondarenko, V., Wells, M. M., Chen, Q., Tillman, T. S., Singewald, K., Lawless, M. J., Caporoso, J., Brandon, N. R., Coleman, J. A., Saxena, S., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-28400-x · Cited by 51
Xlink Mapping and AnalySis (XMAS) - Smooth Integrative Modeling in ChimeraX
Lagerwaard, I. M., Albanese, P., Jankevics, A., & Scheltema, R. A. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.21.489026 · Cited by 52
Predicting RNA structures and functions by artificial intelligence.
Zhang, J., Lang, M., Zhou, Y., & Zhang, Y. (2024) · Trends in Genetics · doi:10.1016/j.tig.2023.10.001 · Cited by 48
Protein Design with Deep Learning
Defresne, M., Barbe, S., & Schiex, T. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222111741 · Cited by 44
“Currently, top methods [8,26] can sometimes reach atomic accuracy on single chains, and can even deal with multimers [27].”
Functional metagenomic screening identifies an unexpected β-glucuronidase
Neun, S., Brear, P., Campbell, E. C., Tryfona, T., Omari, K. E., Wagner, A., Dupree, P., Hyvönen, M., & Hollfelder, F. (2022) · Nature Chemical Biology · doi:10.1038/s41589-022-01071-x · Cited by 53
Fast and accurate Ab Initio Protein structure prediction using deep learning potentials
Pearce, R., Li, Y., Omenn, G. S., & Zhang, Y. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010539 · Cited by 51
“These data demonstrate that the DeepFold knowledge-based force field and DeepPotential contact and Cα distance restraints may improve the results obtained by RosettaFold.”
ResultInfluentialXia, Y., Zhao, K., Liu, D., Zhou, X., & Zhang, G. (2023) · Communications Biology · doi:10.1038/s42003-023-05610-7 · Cited by 47
“The three-track network of the end-to-end version of RoseTTAFold 5 generates protein-protein complex structure models by combining features from discontinuous crops of the protein sequence.”
InfluentialHigh-Speed Atomic Force Microscopy for Filming Protein Molecules in Dynamic Action
Ando, T., Fukuda, S., Ngo, K. X., & Flechsig, H. (2023) · Annual Review of Biophysics · doi:10.1146/annurev-biophys-030722-113353 · Cited by 55
Fragment-to-Lead Medicinal Chemistry Publications in 2022
Woodhead, A., Erlanson, D. A., de Esch, I. J. P., Holvey, R. S., Jahnke, W., & Pathuri, P. (2024) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.3c02070 · Cited by 52
High-throughput reprogramming of an NRPS condensation domain
Folger, I. B., Frota, N., Pistofidis, A., Niquille, D. L., Hansen, D. A., Schmeing, T. M., & Hilvert, D. (2024) · Nature Chemical Biology · doi:10.1038/s41589-023-01532-x · Cited by 48
Ni, B., Kaplan, D. L., & Buehler, M. J. (2024) · Science Advances · doi:10.1126/sciadv.adl4000 · Cited by 39
“For forward problems focused on structure identification, deep learning-based tools such as AlphaFold2 ( 20 ) and RoseTTAFold ( 21 ) represents a breakthrough in achieving competitive accuracy with experimental methods in predicting 3D folded structures based on protein sequences at a much reduced…”
Protein interactions in human pathogens revealed through deep learning
Humphreys, I. R., Zhang, J., Baek, M., Wang, Y., Krishnakumar, A., Pei, J., Anishchenko, I., Tower, C. A., Jackson, B. A., Warrier, T., et al. (2024) · Nature Microbiology · doi:10.1038/s41564-024-01791-x · Cited by 44
“We revised the original RoseTTAFold network by introducing architectural improvements to increase accuracy while reducing the number of layers to enable the rapid computation necessary for large-scale screens (Fig.”
MethodSelf-citationCesaro, G., Nagai, J. S., Nicolò, G., Chiodi, A., Tussardi, G., Klöker, V., Musumarra, C. V., Mosca, E., Costa, I. G., Camillo, B. D., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf280 · Cited by 60
AI-generated MLH1 small binder improves prime editing efficiency
Park, J.-C., Uhm, H., Kim, Y. W., Oh, Y. E., Lee, J., Yang, J., Kim, K., & Bae, S. (2025) · Cell · doi:10.1016/j.cell.2025.07.010 · Cited by 53
Peng, C., Ni, W., Liu, Q., Hu, G., & Zheng, W. H. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf616 · Cited by 55
Kandathil, S. M., Greener, J. G., Lau, A. M., & Jones, D. T. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2113348119 · Cited by 38
Cryo-electron Microscopy of Adeno-associated Virus
Stagg, S. M., Yoshioka, C., Davulcu, O., & Chapman, M. S. (2022) · Chemical Reviews · doi:10.1021/acs.chemrev.1c00936 · Cited by 50
A closed Candidatus Odinarchaeum chromosome exposes Asgard archaeal viruses
Tamarit, D., Caceres, E. F., Krupovic, M., Nijland, R., Eme, L., Robinson, N. P., & Ettema, T. J. G. (2022) · Nature Microbiology · doi:10.1038/s41564-022-01122-y · Cited by 47
NMR hawk‐eyed view of AlphaFold2 structures
Zweckstetter, M. (2021) · Protein Science · doi:10.1002/pro.4175 · Cited by 47
“Since the CASP14 announcement, the Rosetta software was also greatly improved.(2) In addition, AlphaFold2 was used to predict the 3D structure of 98.”
MethodQuantum computing algorithms: getting closer to critical problems in computational biology
Marchetti, L., Nifosì, R., Martelli, P. L., Da Pozzo, E., Cappello, V., Banterle, F., Trincavelli, M. L., Martini, C., & D’Elia, M. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac437 · Cited by 47
Smith, Z., Strobel, M., Vani, B. P., & Tiwary, P. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c01698 · Cited by 47
Turzo, S. B. A., Seffernick, J. T., Rolland, A. D., Donor, M. T., Heinze, S., Prell, J. S., Wysocki, V. H., & Lindert, S. (2022) · Nature Communications · doi:10.1038/s41467-022-32075-9 · Cited by 47
“AlphaFold2 (v.2.0.0) 98 and RoseTTAFold (v.1.1.0) 99 (protocols detailed in the Supplementary Methods) were also benchmarked (with and without templates) for both the datasets to further assess the effectiveness of IM data.”
MethodInfluentialCourrol, D. D. S., da Silva, C. C. F., Prado, L. G., Chura‐Chambi, R. M., Morganti, L., de Souza, G. O., Heinemann, M. B., Isaac, L., Conte, F. D. P., Portaro, F. C. V., et al. (2022) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2022.966370 · Cited by 49
“org; accessed on 10 October 2021) (Kim et al., 2004; Baek et al., 2021), based on the full-length amino acid sequence of the protein (Uniprot ID Q72LV9) excluding its signal peptide (1-22).”
BackgroundWaqas, M. S., Aziz, S., Lió, P., Khan, Y., Ali, A., Iqbal, A., Khan, F., & Almajhdi, F. N. (2023) · Frontiers in Immunology · doi:10.3389/fimmu.2023.1091941 · Cited by 56
“To predict the multi-epitope vaccine’s three-dimensional (3D) structure, we used the RoseTTAFold server (49).”
MethodZhao, K., Xia, Y., Zhang, F., Zhou, X., Li, S. Z., & Zhang, G. (2023) · Communications Biology · doi:10.1038/s42003-023-04605-8 · Cited by 48
“In end-to-end deep learning methods, such as AlphaFold2 3 , RoseTTAFold 12 and RGN2 13 , template information is used explicitly or implicitly for deep learning models.”
MethodWard, J. A., Perez‐Lopez, C., & Mayor‐Ruiz, C. (2023) · ChemBioChem · doi:10.1002/cbic.202300163 · Cited by 47
Rational design of functional amyloid fibrillar assemblies
Wang, X., Zhang, S., Zhang, J., Wang, Y., Jiang, X., Tao, Y., Li, D., Zhong, C., & Liu, C. (2023) · Chemical Society Reviews · doi:10.1039/d2cs00756h · Cited by 48
Structural biology: A golden era
Carugo, O., & Djinović-Carugo, K. (2023) · PLOS Biology · doi:10.1371/journal.pbio.3002187 · Cited by 39
“In 2021, AlphaFold2 and RoseTTAFold were the first to use deep learning approaches [4,5] for protein modelling.”
BackgroundCheminformatics and artificial intelligence for accelerating agrochemical discovery
Djoumbou-Feunang, Y., Wilmot, J. T., Kinney, J., Chanda, P., Yu, P., Sader, C. A., Sharifi, M., Smith, S., Ou, J., Hu, J. K., et al. (2023) · Frontiers in Chemistry · doi:10.3389/fchem.2023.1292027 · Cited by 53
Electrostatics as a Guiding Principle in Understanding and Designing Enzymes
Ruiz‐Pernía, J. J., Świderek, K., Bertrán, J., Moliner, V., & Tuñón, I. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c01395 · Cited by 48
Nuñez, L. F. S., Barrera-Ocampo, A. A., Caicedo, P. A., Cortés, N., Osorio, E. H., Villegas-Torres, M. F., & Barrios, A. F. G. (2024) · Metabolites · doi:10.3390/metabo14030154 · Cited by 50
“This approach allows for the use of multiple sources of information and the capture of complex protein features [57].”
BackgroundGenerative artificial intelligence for enzyme design: Recent advances in models and applications
Wen, S., Zheng, W., Bornscheuer, U. T., & Wu, S. (2025) · Current Opinion in Green and Sustainable Chemistry · doi:10.1016/j.cogsc.2025.101010 · Cited by 61
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.