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 701–800 of 5,634
Drug-target interaction/affinity prediction: Deep learning models and advances review
Vefghi, A., Rahmati, Z., & Akbari, M. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110438 · Cited by 60
Recent progress of iPSC technology in cardiac diseases
Funakoshi, S., & Yoshida, Y. (2021) · Archives of Toxicology · doi:10.1007/s00204-021-03172-3 · Cited by 52
Recent Insights and Future Perspectives on Promiscuous Hydrolases/Acyltransferases
Müller, H., Terholsen, H., Godehard, S. P., Badenhorst, C. P. S., & Bornscheuer, U. T. (2021) · ACS Catalysis · doi:10.1021/acscatal.1c04543 · Cited by 47
An analysis of protein language model embeddings for fold prediction
Villegas-Morcillo, A., Gomez, A. M., & Sanchez, V. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac142 · Cited by 46
Protein–protein interaction prediction methods: from docking-based to AI-based approaches
Tsuchiya, Y., Yamamori, Y., & Tomii, K. (2022) · Biophysical Reviews · doi:10.1007/s12551-022-01032-7 · Cited by 55
“RoseTTaFold, the first attempt to replicate AF2 before the release of the AF2 codes, confirmed that deep neural network model trained for monomer structure prediction can predict protein–protein complex models with some degree of accuracy (Baek et al. 2021).”
BackgroundWang, S., Song, X., Zhang, Y., Zhang, K., Liu, Y., Ren, C., & Pang, S. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24098326 · Cited by 47
Tertiary structure assessment at CASP15
Simpkin, A. J., Mesdaghi, S., Sánchez Rodríguez, F., Elliott, L., Murphy, D. L., Kryshtafovych, A., Keegan, R. M., & Rigden, D. J. (2023) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26593 · Cited by 47
In silico evolution of autoinhibitory domains for a PD-L1 antagonist using deep learning models
Goudy, O. J., Nallathambi, A., Kinjo, T., Randolph, N. Z., & Kuhlman, B. A. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2307371120 · Cited by 55
“Sequences cre ated with AlphaDesign have not been experimentally validated, while RoseTTAFold - based hallucination has been used to create new protein structures, assemblies, and proteins that bind tightly to helical peptides (15, 17, 18).”
MethodInfluentialMadsen, A. V., Mejias-Gomez, O., Pedersen, L. E., Preben Morth, J., Kristensen, P., Jenkins, T. P., & Goletz, S. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.11.056 · Cited by 42
“It should be noted that computational methods, such as AlphaFold2 [10] and RoseTTAFold [11], are providing increasingly high-quality models of protein complexes and their binding interfaces from sequence alone [11,12].”
MethodRecent Progress of Protein Tertiary Structure Prediction
Wuyun, Q., Chen, Y., Shen, Y., Cao, Y., Hu, G., Cui, W., Gao, J., & Zheng, W. H. (2024) · Molecules · doi:10.3390/molecules29040832 · Cited by 53
AggreProt: a web server for predicting and engineering aggregation prone regions in proteins
Planas-Iglesias, J., Borko, S., Swiatkowski, J., Elias, M., Havlásek, M., Salamon, O., Grakova, E., Kunka, A., Martinovič, T., Damborský, J., et al. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae420 · Cited by 51
Accurate prediction of protein function using statistics-informed graph networks
Jang, Y. J., Qin, Q.-Q., Huang, S., Peter, A. T. J., Ding, X., & Kornmann, B. (2024) · Nature Communications · doi:10.1038/s41467-024-50955-0 · Cited by 60
Metabolic engineering strategies for de novo biosynthesis of sterols and steroids in yeast
Gu, Y., Xue, J., Ye, L., & Yu, H. (2021) · Bioresources and Bioprocessing · doi:10.1186/s40643-021-00460-9 · Cited by 48
de la Herrán, R., Hermida, M., Rubiolo, J. A., Gómez‐Garrido, J., Cruz, F., Robles, F., Navajas‐Pérez, R., Blanco, A., Villamayor, P. R., Torres-Sabino, D., et al. (2023) · Molecular Ecology Resources · doi:10.1111/1755-0998.13750 · Cited by 55
Ouyang, R., Costa, A. R., Cassidy, C. K., Otwinowska, A., Williams, V. C. J., Latka, A., Stansfeld, P. J., Drulis-Kawa, Z., Briers, Y., Pelt, D. M., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-34972-5 · Cited by 46
“Protein structure prediction algorithms, such as AlphaFold2 and RoseTTAFold have become invaluable tools for cryo-EM based macromolecular structure elucidation.”
BackgroundMethod(2022) · doi:10.1101/2022.03.15.484430 · Cited by 46
An end-to-end framework for the prediction of protein structure and fitness from single sequence
Chen, Y., Xu, Y., Liu, D., Xing, Y., & Gong, H. (2024) · Nature Communications · doi:10.1038/s41467-024-51776-x · Cited by 45
“Representative models, such as AlphaFold 7,8 and RoseTTAFold 9,10 , utilize evolutionary information extracted from multiple sequence alignments (MSA) to predict protein structures and attain accuracy close to experimental results.”
Roy, R. S., Quadir, F., Soltanikazemi, E., & Cheng, J. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac063 · Cited by 45
“Another interesting recent development is the application of AlphaFold2 and RoseTTAFold (Baek et al., 2021) - the two cutting-edge deep learning methods designed for prediction of tertiary structure to the prediction of the quaternary structures of several protein complexes, demonstrating the great…”
MethodTransient disorder along pathways to amyloid
Morgan, G. J. (2021) · Biophysical Chemistry · doi:10.1016/j.bpc.2021.106711 · Cited by 45
Illuminating the dark protein-protein interactome
Sharifi Tabar, M., Parsania, C., Chen, H., Su, X.-D., Bailey, C. G., & Rasko, J. E. J. (2022) · Cell Reports Methods · doi:10.1016/j.crmeth.2022.100275 · Cited by 42
“Deep learning (DL)-based algorithms such as AlphaFold2 and RoseTTAFold have claimed to predict protein structures as accurately as X-ray crystallography (Baek et al., 2021; Jumper et al., 2021).”
MethodStrategy of developing nucleic acid-based universal monkeypox vaccine candidates
Papukashvili, D., Rcheulishvili, N., Liu, C., Wang, X., He, Y., & Wang, P. G. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.1050309 · Cited by 49
Zhang, Y., Gao, S., Cai, P., Lei, Z., & Wang, Y. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110064 · Cited by 48
FRA-1 as a Regulator of EMT and Metastasis in Breast Cancer
Casalino, L., Talotta, F., Matino, I., & Verde, P. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24098307 · Cited by 46
Harren, T., Gutermuth, T., Grebner, C., Heßler, G., & Rarey, M. (2024) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1716 · Cited by 62
De novo design of transmembrane fluorescence-activating proteins
Zhu, J., Liang, M., Sun, K., Yu, W., Guo, R., Zhang, L., Shi, J., Ma, D., Hu, Q., Huang, G., et al. (2025) · Nature · doi:10.1038/s41586-025-08598-8 · Cited by 56
“The recent development of deep learning-based methods has substantially improved the accuracy of protein structure prediction 17–19 .”
Kopaç, T. (2025) · Bioengineering · doi:10.3390/bioengineering12030312 · Cited by 57
From Concepts to Inhibitors: A Blueprint for Targeting Protein–Protein Interactions
Hong, S. H., Nguyễn, T. T., Ongkingco, J. F., Nazzaro, A., & Arora, P. S. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00046 · Cited by 46
Aligning protein-generative models to experimental fitness with ProteinDPO
Widatalla, T., Borah, A. A., King, S. B., Driscoll, C. L., Rafailov, R., & Hie, B. (2026) · Nature Methods · doi:10.1038/s41592-026-03137-3 · Cited by 54
Predicting Adhesive Free Energies of Polymer–Surface Interactions with Machine Learning
Shi, J., Quevillon, M. J., Valença, P. H. A., & Whitmer, J. K. (2022) · ACS Applied Materials & Interfaces · doi:10.1021/acsami.2c08891 · Cited by 48
Wu, W., Bai, X., Shao, Y., Yang, C., Wei, J., Wei, W., & Zhang, W. (2021) · Journal of the American Chemical Society · doi:10.1021/jacs.1c06169 · Cited by 46
Fragment-Based Drug Discovery by NMR. Where Are the Successes and Where can It Be Improved?
Mureddu, L. G., & Vuister, G. W. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.834453 · Cited by 50
Yu, M., Zhu, Y., Li, Y., Chen, Z., Li, Z., Wang, J., Li, Z., Zhang, F., & Ding, J. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.884433 · Cited by 45
Self-citationPark, S., & Seok, C. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00306 · Cited by 49
Assessing PDB macromolecular crystal structure confidence at the individual amino acid residue level
Shao, C., Bittrich, S., Wang, S., & Burley, S. K. (2022) · Structure · doi:10.1016/j.str.2022.08.004 · Cited by 47
A language model beats alphafold2 on orphans
Michaud, J. M., Madani, A., & Fraser, J. S. (2022) · Nature Biotechnology · doi:10.1038/s41587-022-01466-0 · Cited by 50
AI and the democratization of knowledge
Dessimoz, C., & Thomas, P. D. (2024) · Scientific Data · doi:10.1038/s41597-024-03099-1 · Cited by 45
Protein p K a Prediction with Machine Learning
Cai, Z., Luo, F., Wang, Y., Li, E., & Huang, Y. (2021) · ACS Omega · doi:10.1021/acsomega.1c05440 · Cited by 45
The ϕPA3 phage nucleus is enclosed by a self-assembling 2D crystalline lattice
(2023) · doi:10.1038/s41467-023-36526-9 · Cited by 45
Self-citationProtein sequence‐to‐structure learning: Is this the end(‐to‐end revolution)?
Laine, E., Eismann, S., Elofsson, A., & Grudinin, S. (2021) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26235 · Cited by 44
“combination was also leveraged in the most recent RoseTTAFold network.(148)”
BackgroundA combinatorially complete epistatic fitness landscape in an enzyme active site
Johnston, K. E., Almhjell, P. J., Watkins-Dulaney, E. J., Liu, G., Porter, N. J., Yang, J., & Arnold, F. H. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2400439121 · Cited by 44
“For each unique starting variant, 00 , all possible double substitutions, 11 , were tested such that all variants within the set of 00 , 01 , 10 , and 11 were active and an epistasis type was assigned.”
Structure of the IL-27 quaternary receptor signaling complex
(2022) · doi:10.7554/elife.78463 · Cited by 44
Self-citationEnd-to-end protein–ligand complex structure generation with diffusion-based generative models
Nakata, S., Mori, Y., & Tanaka, S. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05354-5 · Cited by 56
Zero‐shot mutation effect prediction on protein stability and function using RoseTTAFold
Mansoor, S., Baek, M., Juergens, D., Watson, J. L., & Baker, D. (2023) · Protein Science · doi:10.1002/pro.4780 · Cited by 40
Self-citationData‐Driven Protein Engineering for Improving Catalytic Activity and Selectivity
Ao, Y., Dörr, M., Menke, M. J., Born, S., Heuson, E., & Bornscheuer, U. T. (2023) · ChemBioChem · doi:10.1002/cbic.202300754 · Cited by 44
ABodyBuilder3: improved and scalable antibody structure predictions
Kenlay, H., Dreyer, F. A., Cutting, D., Nissley, D. A., & Deane, C. M. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae576 · Cited by 56
Audagnotto, M., Czechtizky, W., Maria, L. D., Käck, H., Papoian, G. A., Tornberg, L., Tyrchan, C., & Ulander, J. (2022) · Scientific Reports · doi:10.1038/s41598-022-13714-z · Cited by 50
Chen, P., Jiao, R., Liu, J., Liu, Y., & Lu, Y. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00876 · Cited by 45
Burley, S. K., Berman, H. M., Chiu, W., Dai, W., Flatt, J. W., Hudson, B. P., Kaelber, J. T., Khare, S. D., Kulczyk, A. W., Lawson, C. L., et al. (2022) · Biophysical Reviews · doi:10.1007/s12551-022-01013-w · Cited by 41
Inverse folding for antibody sequence design using deep learningPreprint
Dreyer, F. A., Cutting, D., Schneider, C., Kenlay, H., & Deane, C. M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.19513 · Cited by 62
Generative power of a protein language model trained on multiple sequence alignments
(2023) · doi:10.7554/elife.79854 · Cited by 43
“This concept differs from structure- and physics-based de novo design [3–5], and from the new possibility to use supervised deep learning models able to accurately predict protein structures [28, 73, 74] for structure-driven sequence generation [75].”
Lesbon, J. C. C., Poleti, M., Mattos, E. C., Patané, J. S. L., Clemente, L. G., Viala, V. L., Ribeiro, G. D. C., Giovanetti, M., de Alcantara, L., Teixeira, O., et al. (2021) · Viruses · doi:10.3390/v13122474 · Cited by 43
“The default parameters were used to produce predicted models using the simultaneous processing of sequence, distance, and coordinate information by the three-track architecture implemented in the RoseTTAfold method [1].”
MethodPhenol-soluble modulins PSMα3 and PSMβ2 form nanotubes that are cross-α amyloids
Kreutzberger, M. A. B., Wang, S., Beltrán, L. C., Tuachi, A., Zuo, X., Egelman, E. H., & Conticello, V. P. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2121586119 · Cited by 45
“Notably, the computational algorithm RoseTTAFold (59) predicted a structural model from the sequence of PSMβ2 that closely resembled that observed for the individual subunits in the atomic model of the PSMβ2 nanotube (SI Appendix, Fig.”
BackgroundMolecular Modeling Insights into the Structure and Behavior of Integrins: A Review
Tvaroška, I., Kozmon, S., & Kóňa, J. (2023) · Cells · doi:10.3390/cells12020324 · Cited by 49
Latent generative landscapes as maps of functional diversity in protein sequence space
Ziegler, C., Martin, J., Sinner, C., & Morcos, F. (2023) · Nature Communications · doi:10.1038/s41467-023-37958-z · Cited by 42
The application of artificial intelligence to accelerate G protein‐coupled receptor drug discovery
Nguyen, A. T. N., Nguyen, D. T. N., Koh, H. Y., Toskov, J., MacLean, W., Xu, A., Zhang, D., Webb, G. I., May, L. T., & Halls, M. L. (2023) · British Journal of Pharmacology · doi:10.1111/bph.16140 · Cited by 54
Genomic basis of environmental adaptation in the widespread poly-extremophilic Exiguobacterium group
Shen, L., Liu, Y., Chen, L., Lei, T., Ren, P., Ji, M., Song, W., Lin, H., Su, W., Wang, S., et al. (2024) · The ISME Journal · doi:10.1093/ismejo/wrad020 · Cited by 48
Microsecond time-resolved cryo-electron microscopy
Lorenz, U. J. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102840 · Cited by 46
“[2,3] In contrast, our understanding of protein function is lagging behind, since it is not routinely possible to observe proteins as they perform their tasks.”
BackgroundBuller, R., Damborský, J., Hilvert, D., & Bornscheuer, U. T. (2024) · Angewandte Chemie International Edition · doi:10.1002/anie.202421686 · Cited by 46
A survey on deep learning-based algorithms for the traveling salesman problem
Sui, J., Ding, S., Huang, X., Yu, Y., Liu, R., Xia, B., Ding, Z., Xu, L., Zhang, H., Yu, C., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40490-y · Cited by 54
Lu, Y., Huang, W., Li, Y., Xu, Y., Wei, Q., Sha, C., & Guo, P. (2025) · npj Precision Oncology · doi:10.1038/s41698-025-01159-2 · Cited by 56
“Recent breakthroughs in deep learning have yielded highly accurate structure prediction tools, including AlphaFold2 50,51 and RoseTTAFold 52 , capable of modeling complete antibody structures, particularly the complementarity-determining regions (CDRs), with high precision.”
Could AlphaFold revolutionize chemical therapeutics?
Tong, A. B., Burch, J. D., McKay, D., Bustamante, C., Crackower, M. A., & Wu, H. (2021) · Nature Structural & Molecular Biology · doi:10.1038/s41594-021-00670-x · Cited by 44
Key Enzymes in Fatty Acid Synthesis Pathway for Bioactive Lipids Biosynthesis
Zhuang, X., Zhang, Y., Xiao, A., Zhang, A., & Fang, B. (2022) · Frontiers in Nutrition · doi:10.3389/fnut.2022.851402 · Cited by 55
Evseev, P. V., Lukianova, A. A., Tarakanov, R. I., Tokmakova, A. D., Shneider, M. M., Ignatov, A. N., & Анатольевич, М. К. (2022) · Current Issues in Molecular Biology · doi:10.3390/cimb44020060 · Cited by 48
EnzyHTP: A High-Throughput Computational Platform for Enzyme Modeling
Shao, Q., Jiang, Y., & Yang, Z. J. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01424 · Cited by 43
Zheng, W. H., Wuyun, Q., Zhou, X., Li, Y., Freddolino, L., & Zhang, Y. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac248 · Cited by 49
“For this reason, TBM is still contained as a necessary module in many state-of-the-art deep learning approaches and shows important effects on improving the accuracy of final models based on such pipelines (4,5,12).”
Kinase-independent synthesis of 3-phosphorylated phosphoinositides by a phosphotransferase
Walpole, G. F. W., Pacheco, J. E., Chauhan, N., Clark, J. P., Anderson, K. E., Abbas, Y. M., Brabant-Kirwan, D., Montaño-Rendón, F., Liu, Z., Zhu, H., et al. (2022) · Nature Cell Biology · doi:10.1038/s41556-022-00895-y · Cited by 45
PANDORA: A Fast, Anchor-Restrained Modelling Protocol for Peptide: MHC Complexes
Marzella, D. F., Parizi, F. M., Tilborg, D. V., Renaud, N., Sybrandi, D., Buzatu, R., Rademaker, D. T., ‘t Hoen, P. A. C., & Xue, L. C. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.878762 · Cited by 44
“More recently, AlphaFold2 (41) and RoseTTAfold (42) have demonstrated outstanding performance in single-chain protein structure prediction.”
BackgroundDeep Learning in RNA Structure Studies
Yu, H., Qi, Y., & Ding, Y. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.869601 · Cited by 45
“Based on this hard-earned data, deep learning models such as Alphafold2 and RoseTTAFold can predict protein structures from amino acid sequences that are remarkably close to those determined experimentally (Baek et al., 2021; Jumper et al., 2021).”
MethodThe 3D mutational constraint on amino acid sites in the human proteome
Li, B., Roden, D. M., & Capra, J. A. (2022) · Nature Communications · doi:10.1038/s41467-022-30936-x · Cited by 37
Engineering the biosynthesis of fungal nonribosomal peptides
Zhang, L., Wang, C., Chen, K., Zhong, W., Xu, Y., & Molnár, I. (2023) · Natural Product Reports · doi:10.1039/d2np00036a · Cited by 45
Li, S., Wu, S., Wang, L., Li, F., Jiang, H., & Bai, F. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102344 · Cited by 42
Rapid and automated design of two-component protein nanomaterials using ProteinMPNN
de Haas, R. J., Brunette, N., Goodson, A., Dauparas, J., Yi, S. Y., Yang, E. C., Dowling, Q., Nguyen, H., Kang, A., Bera, A. K., et al. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2314646121 · Cited by 42
Self-citationHAP2-Mediated Gamete Fusion: Lessons From the World of Unicellular Eukaryotes
Pinello, J. F., & Clark, T. G. (2022) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2021.807313 · Cited by 43
“2018); a RosettaFold model protein structure of a Tetrahymena HAP2 monomer (Baek et al., 2021); a single protomer from the trimeric crystal structure of the Semliki”
BackgroundInfluentialComputer-Aided Drug Design towards New Psychotropic and Neurological Drugs
Dorahy, G., Chen, Z., & Balle, T. (2023) · Molecules · doi:10.3390/molecules28031324 · Cited by 45
“Furthermore, the completion of the Human Genome Project and use of artificial intelligencebased structure prediction tools such as AlphaFold2 [42] and RoseTTAFold [43] allow for prediction of structures of proteins from sequence alone.”
MethodZhang, O., Haghighatlari, M., Li, J., Liu, Z. H., Namini, A., Teixeira, J. M. C., Forman-Kay, J. D., & Head-Gordon, T. (2023) · The Journal of Chemical Physics · doi:10.1063/5.0141474 · Cited by 38
Plant virus movement proteins originated from jelly-roll capsid proteins
Butković, A., Dolja, V. V., Koonin, E. V., & Krupovìč, M. (2023) · PLoS Biology · doi:10.1371/journal.pbio.3002157 · Cited by 46
“The quality of the RoseTTAFold models was assessed using residue-wise CA-lDDT implemented in the end-to-end version of RoseTTAFold.”
InfluentialMaciejewska, B., Squeglia, F., Łątka, A., Privitera, M., Olejniczak, S., Switala, P., Ruggiero, A., Marasco, D., Kramarska, E., Drulis‐Kawa, Z., et al. (2023) · mBio · doi:10.1128/mbio.01329-23 · Cited by 44
“In this latter case, modeling was performed using RoseTTAFold (51).”
MethodAntigen spacing on protein nanoparticles influences antibody responses to vaccination
Ellis, D., Dosey, A. M., Boyoglu-Barnum, S., Park, Y., Gillespie, R. A., Syeda, H., Hutchinson, G. B., Tsybovsky, Y., Murphy, M., Pettie, D., et al. (2023) · Cell Reports · doi:10.1016/j.celrep.2023.113552 · Cited by 43
McMaster, B., Thorpe, C. J., Ogg, G. S., Deane, C. M., & Koohy, H. (2024) · Nature Methods · doi:10.1038/s41592-024-02240-7 · Cited by 50
“Inspired by the success of AlphaFold in general protein structure prediction, other comparable models have been developed: namely RoseTTAFold 34 (or the newly updated RoseTTAFold2 (ref.”
Feng, S., Chen, Z., Zhang, C., Xie, Y., Ovchinnikov, S., Gao, Y. Q., & Liu, S. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00873-z · Cited by 46
Self-citationControl of lysogeny and antiphage defense by a prophage-encoded kinase-phosphatase module
Guo, Y., Tang, K., Sit, B., Gu, J., Chen, R., Shao, X., Lin, S., Huang, Z., Nie, Z., Lin, J., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-51617-x · Cited by 50
Animal and bacterial viruses share conserved mechanisms of immune evasion
Hobbs, S. J., Nomburg, J., Doudna, J. A., & Kranzusch, P. J. (2024) · Cell · doi:10.1016/j.cell.2024.07.057 · Cited by 46
Singh, A., Tanwar, M., Singh, T. P., Sharma, S., & Sharma, P. K. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.135253 · Cited by 53
The future of machine learning for small-molecule drug discovery will be driven by data
Durant, G., Boyles, F., Birchall, K., & Deane, C. M. (2024) · Nature Computational Science · doi:10.1038/s43588-024-00699-0 · Cited by 49
“AlphaFold 2 and other protein structure prediction tools 13,68,69 leveraged the far larger corpus of publicly available protein sequence data 70,71 to help overcome the relative paucity of experimentally determined protein structures (of the order of hundreds of thousands).”
Liu, J., Wu, L., Xie, A., Liu, W. L., Zhao, H., Wan, Y., & Mao, W. (2025) · Journal of Nanobiotechnology · doi:10.1186/s12951-025-03169-5 · Cited by 50
“Alpha-Fold2 utilizes multiple sequence alignment (MSA), residue pairing information, and structural templates for modeling [178], while RoseTTAFold employs a three-track neural network to simultaneously refine MSAs, inter-residue contacts, and 3D structures [209].”
InfluentialMalhotra, Y., John, J., Yadav, D., Sharma, D., Vanshika, Rawal, K., Mishra, V., & Chaturvedi, N. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.109842 · Cited by 44
Artificial intelligence powers protein-folding predictions
Eisenstein, M. S. (2021) · Nature · doi:10.1038/d41586-021-03499-y · Cited by 50
Harnessing Reversed Allosteric Communication: A Novel Strategy for Allosteric Drug Discovery
Fan, J., Liu, Y., Kong, R., Ni, D., Yu, Z., Lu, S., & Zhang, J. (2021) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.1c01695 · Cited by 48
Supramolecular assembly of protein building blocks: from folding to function
Kim, N. H., Choi, H., Shahzad, Z. M., Ki, H., Lee, J., Chae, H., & Kim, Y. H. (2022) · Nano Convergence · doi:10.1186/s40580-021-00294-3 · Cited by 44
“Recently, as protein folding prediction using artificial intelligence, such as Alphafold [249] and RoseTTAFold [250], and computational tools have become very sophisticated, it is possible to make folding units with more diverse structures.”
MethodSymmetry-Based Representations for Artificial and Biological General Intelligence
Higgins, I., Racanière, S., & Rezende, D. J. (2022) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2022.836498 · Cited by 62
“, 2020), protein folding (Fuchs et al., 2020; Baek et al., 2021), or quantum chemistry (Pfau et al.”
BackgroundAlphaKnot: server to analyze entanglement in structures predicted by AlphaFold methods
Niemyska, W., Rubach, P., Gren, B. A., Nguyen, M. L., Garstka, W., da Silva, F. B., Rawdon, E. J., & Sulkowska, J. I. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac388 · Cited by 42
Caswell, R. C., Gunning, A. C., Owens, M., Ellard, S., & Wright, C. F. (2022) · Genome Medicine · doi:10.1186/s13073-022-01082-2 · Cited by 46
Morales-Martínez, A., Martínez-Gómez, P. A., Martínez‐Fong, D., Villegas-Rojas, M. M., Pérez‐Severiano, F., Toro-Colín, M. A. D., Delgado-Minjares, K. M., Blanco-Álvarez, V. M., León‐Chávez, B. A., Aparicio‐Trejo, O. E., et al. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms231911394 · Cited by 42
“For this reason, the homology prediction of the complete sequence structures was carried out in the Rosetta software [81,82], and the identity of the templates with the rat sequence of each protein was confirmed in the Swiss Model server (https://swissmodel.”
MethodGomes, P. S. F. C., Gomes, D. E. B., & Bernardi, R. C. (2022) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2022.983306 · Cited by 38
“The success of AlphaFold, and the analog RoseTTAFold approach (Baek et al., 2021) that appeared a few months later, is partially due to their open-source nature, which makes them readily and freely available to anyone who is interested in trying these software.”
BackgroundLee, S., Kim, S., Lee, G. R., Kwon, S., Woo, H., Seok, C., & Park, H. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.11.057 · Cited by 42
“Deep learning (DL) has revolutionized protein structure prediction [1,2] and started to have a large impact on structure-based drug design (SBDD) [3,4].”
BackgroundSelf-citationMeller, A., Ward, M. D., Borowsky, J. H., Lotthammer, J. M., Kshirsagar, M., Oviedo, F., Ferres, J. L., & Bowman, G. R. (2023) · Biophysical Journal · doi:10.1016/j.bpj.2022.11.2400 · Cited by 47
Effective Molecular Dynamics from Neural Network-Based Structure Prediction Models
Jussupow, A., & Kaila, V. R. I. (2023) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.2c01027 · Cited by 42
Rapid and automated design of two-component protein nanomaterials using ProteinMPNN
de Haas, R. J., Brunette, N., Goodson, A., Dauparas, J., Yi, S. Y., Yang, E. C., Dowling, Q., Nguyen, H., Kang, A., Bera, A. K., et al. (2023) · doi:10.1101/2023.08.04.551935 · Cited by 42
Self-citationMedium-sized protein language models perform well at transfer learning on realistic datasets
Vieira, L. C., Handojo, M. L., & Wilke, C. O. (2025) · Scientific Reports · doi:10.1038/s41598-025-05674-x · Cited by 41
Evolutionary selection of proteins with two folds
(2023) · doi:10.1038/s41467-023-41237-2 · Cited by 41
“Although state-of-the-art predictive algorithms have revolutionized protein structure prediction 1,2,60 , they systematically fail to predict protein fold switching 17,20 .”
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.