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 2,601–2,700 of 5,636
A curated rotamer library for common post-translational modifications of proteins
Zhang, O., Naik, S. A., Liu, Z. H., Forman-Kay, J. D., & Head-Gordon, T. L. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae444 · Cited by 9
Structure of calcineurin bound to PI4KA reveals dual interface in both PI4KA and FAM126A
Shaw, A. L., Suresh, S., Parson, M. A. H., Harris, N. J., Jenkins, M. L., Yip, C. K., & Burke, J. E. (2024) · Structure · doi:10.1016/j.str.2024.08.007 · Cited by 8
Self-citationKucharska, I., Ivanochko, D., Hailemariam, S., Inklaar, M. R., Kim, H. R., Teelen, K., Stoter, R., van de Vegte‐Bolmer, M., van Gemert, G., Semesi, A., et al. (2025) · Nature Structural & Molecular Biology · doi:10.1038/s41594-025-01532-6 · Cited by 8
Investigating the potential for a limited quantum speedup on protein lattice problems
Outeiral, C., Morris, G. M., Shi, J., Strahm, M., Benjamin, S. C., & Deane, C. M. (2021) · New Journal of Physics · doi:10.1088/1367-2630/ac29ff · Cited by 31
Jovine, L. (2021) · Molecular Reproduction and Development · doi:10.1002/mrd.23538 · Cited by 8
“already shown to be able to successfully predict a number of known protein complexes (Baek et al., 2021).”
BackgroundMethodResultInfluentialSynthetic Protein Circuits and Devices Based on Reversible Protein-Protein Interactions: An Overview
Rosa, S., Bertaso, C., Pesaresi, P., Masiero, S., & Tagliani, A. (2021) · Life · doi:10.3390/life11111171 · Cited by 9
Maharana, J., Maharana, D., Bej, A., Sahoo, B. R., Panda, D., Wadavrao, S. B., Vats, A., Pradhan, S. K., & De, S. (2021) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.1c06176 · Cited by 8
The Future Potential of Biosensors to Investigate the Gut-Brain Axis
Wang, J., & Childers, W. S. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2021.826479 · Cited by 11
Self-citationZhang, H., Zhang, T., Saravanan, K. M., Liao, L., Wu, H., Zhang, H., Zhang, H., Pan, Y. F., Wu, X., & Wei, Y. (2021) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm52615.2021.9669306 · Cited by 8
Wang, C., Anglès, F., & Balch, W. E. (2022) · Structure · doi:10.1016/j.str.2022.05.011 · Cited by 8
Thicker Ice Improves the Integrity and Angular Distribution of CDC48A Hexamers on Cryo-EM Grids
Huntington, B., Zhao, L., Bron, P., Hameed, U. F. S., Arold, S. T., & Qureshi, B. M. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.890390 · Cited by 8
A MademoiseLLE domain binding platform links the key RNA transporter to endosomes
Devan, S.-K., Schott-Verdugo, S., Müntjes, K., Bismar, L., Reiners, J., Hachani, E., Schmitt, L., Höppner, A., Smits, S. H., Gohlke, H., et al. (2022) · PLOS Genetics · doi:10.1371/journal.pgen.1010269 · Cited by 8
“The generated models were also verified by the current deep neural network modelling approaches AlphaFold2 and RoseTTAFold (S1B Fig) [34,35], further indicating that the C-terminal half of Rrm4 has three MLLE domains instead of the previously identified two.”
BackgroundLiu, F., Jiang, X., Yang, J., Tao, J., & Zhang, M. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac365 · Cited by 8
Sabharwal, A., Wishman, M. D., Cervera, R. L., Serres, M. R., Anderson, J. L., Holmberg, S. R., Kar, B., Treichel, A. J., Ichino, N., Liu, W., et al. (2022) · eLife · doi:10.7554/elife.65488 · Cited by 8
Insights from the Structure of an Active Form of Bacillus thuringiensis Cry5B
Li, J., Wang, L., Kotaka, M., Lee, M. M., & Chan, M. K. (2022) · Toxins · doi:10.3390/toxins14120823 · Cited by 8
Li, Z., Bai, F., Wang, X., Xie, C., Wan, Y., Li, Y., Liu, J., & Li, Z. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24065853 · Cited by 8
“org/, accessed on 25 October 2022) [27] and modeled by online SWISS-MODEL server with”
BackgroundMethodSpatial Layouts of Low‐Entropy Hydration Shells Guide Protein Binding
Yang, L., Guo, S., Liao, C., Hou, C., Jiang, S., Li, J., Ma, X., Shi, L., Ye, L., & He, X. (2023) · Global Challenges · doi:10.1002/gch2.202300022 · Cited by 8
Hidden Glutathione Transferases in the Human Genome
Oakley, A. J. (2023) · Biomolecules · doi:10.3390/biom13081240 · Cited by 8
“With the availability of deep learning algorithms such as AlphaFold [5] and RoseTTAfold [6], we now have tools to make reliable predictions of protein structures.”
MethodKoutsogiannis, Z., Mina, J. G., Albus, C. A., Kol, M. A., Holthuis, J. C. M., Pohl, E., & Denny, P. W. (2023) · The FASEB Journal · doi:10.1096/fj.202201603rrr · Cited by 8
“Utilizing the recently released AlphaFold2/ RosettaFold artificial intelligence programs 43,56 we established that the structure of both orthologues was canonical, seven transmembrane domains with the substituted residues found in same arrangement in both Tg CerS1 and Tg CerS2 (Figures 2 and S3).”
DeepMind’s AI for protein structure is coming to the masses
Callaway, E. (2021) · Nature · doi:10.1038/d41586-021-01968-y · Cited by 8
Liu, Y., Chen, L.-H., & Liu, H. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.18.567666 · Cited by 15
FrameDiPT: SE(3) Diffusion Model for Protein Structure InpaintingPreprint
Zhang, C., Leach, A., Makkink, T., Arbesú, M., Kadri, I., Luo, D., Mizrahi, L., Krichen, S., Lang, M., Tovchigrechko, A., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.11.21.568057 · Cited by 11
Reliable protein-protein docking with AlphaFold, Rosetta, and replica-exchangePreprint
Harmalkar, A., Lyskov, S., & Gray, J. J. (2024) · eLife · doi:10.7554/elife.94029.1 · Cited by 12
Predicting metal-protein interactions using cofolding methods: Status quoPreprint
Dürr, S., & Röthlisberger, U. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.28.596236 · Cited by 8
ProtEx: A Retrieval-Augmented Approach for Protein Function PredictionPreprint
Shaw, P., Gurram, B., Belanger, D., Gane, A., Bileschi, M. L., Colwell, L. J., Toutanova, K., & Parikh, A. P. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.30.596539 · Cited by 15
Ille, A. M., Markosian, C., Burley, S. K., Pasqualini, R., & Arap, W. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.03.663068 · Cited by 9
Haley, O. C., Tibbs‐Cortes, L. E., Hayford, R. K., Harding, S. F., Woodhouse, M. R., Cannon, E. K. S., Gardiner, J. M., Portwood, J. L., Sen, T. Z., Kim, H.-S., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.05.663230 · Cited by 12
Likelihood-based interactive local docking into cryo-EM maps in ChimeraX
(2024) · doi:10.1107/s2059798324006776 · Cited by 8
Self-citation(2022) · doi:10.1099/jgv.0.001716 · Cited by 8
“Models of VACV E2 were thus generated using two leading structure prediction packages, AlphaFold2 (AF2) [33] and RoseTTAFold (RTF) [34].”
Nuclear Receptor Interdomain Communication is Mediated by the Hinge with Ligand Specificity
Hazarika, S., Yu, T., Biswas, A., Dube, N., Villalona, P., & Okafor, C. D. (2024) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168805 · Cited by 7
Bera, P., & Mondal, J. (2025) · The Journal of Chemical Physics · doi:10.1063/5.0279756 · Cited by 7
Lifetime of ground conformational state determines the activity of structured RNA
Thompson, R. D., Carbaugh, D. L., Nielsen, J. R., Witt, C. M., Faison, E. M., Meganck, R. M., Rangadurai, A., Zhao, B., Bonin, J. P., Nicely, N. I., et al. (2025) · Nature Chemical Biology · doi:10.1038/s41589-025-01843-1 · Cited by 7
“…importance of ground conformational states have almost exclusively focused on their three-dimensional (3D) structures and thermodynamic stabilities, which are increasingly accessible for diverse biomolecules benefiting from advances in cryo-electron microscopy and structure predictions 14,15 .”
The topological properties of the protein universe
Madsen, C. D., Barbensi, A., Zhang, S. Y., Ham, L., David, A., Pires, D. E. V., & Stumpf, M. P. H. (2025) · Nature Communications · doi:10.1038/s41467-025-61108-2 · Cited by 7
BAGEL: Protein engineering via exploration of an energy landscape
(2025) · doi:10.1371/journal.pcbi.1013774 · Cited by 7
“Over the past decade, advances in protein structure prediction - most notably deep learning-based models such as AlphaFold2 [1], RosettaFold [2] and ESMFold [3] - have transformed the field of protein design [4].”
Ligand identification in CryoEM and X-ray maps using deep learning
Karolczak, J., Przybyłowska, A., Szewczyk, K., Taisner, W., Heumann, J. M., Stowell, M. H. B., Nowicki, M., & Brzezinski, D. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae749 · Cited by 7
Unified Sampling and Ranking for Protein Docking With DFMDock
Chu, L., Sarma, S., Xu, D., & Gray, J. J. (2026) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.70160 · Cited by 7
PS4: A Next-Generation Dataset for Protein Single-Sequence Secondary Structure Prediction
Peracha, O. (2024) · BioTechniques · doi:10.2144/btn-2023-0024 · Cited by 7
Najjari, A., Jabberi, M., Chérif, S. F., Cherif, A., Ouzari, H., Linares‐Pastén, J. A., & Sghaier, H. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1440081 · Cited by 8
Mousa, W. K., Shaikh, A. Y., Ghemrawi, R., Aldulaimi, M., Ali, A., Sammani, N., Khair, M., Helal, M. I. D., Al-Marzooq, F. I., & Oueis, E. (2024) · RSC Medicinal Chemistry · doi:10.1039/d4md00383g · Cited by 7
He, X., Shi, X., Liu, H., Wang, Y., Lu, J., Zeng, H., Li, R., & Wu, D. (2025) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2025.3541566 · Cited by 7
Chen, R., You, Y., Liu, Y., Sun, X., Ma, T., Lao, X., & Zheng, H. (2025) · Microbial Biotechnology · doi:10.1111/1751-7915.70121 · Cited by 8
“The precision of virtual screening and molecular dynamic simulations has significantly increased because the accuracy of predicted structures is similar to those of experimentally measured ones such as RoseTTAFold (Baek et al. 2021) and AlphaFold2 (Tunyasuvunakool et al. 2021).”
Enhanced prediction of antigen and antibody binding interface using ESM-2 and Bi-LSTM
Li, Q., Zhao, Y., Chordia, M. D., Xia, X., Zhang, B., & Zheng, H. (2025) · Human Immunology · doi:10.1016/j.humimm.2025.111304 · Cited by 9
Enzyme miniaturization: Revolutionizing future biocatalysts
Ding, N., Jiang, Y., Lee, S., Cheng, Z., Ran, X., Ding, Y., Ge, R., Zhang, Y., & Yang, Z. J. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108598 · Cited by 9
Liu, H., Liu, N., Zhou, C., Du, A., Kapadia, M., Tai, P. W. L., Barton, E. S., Gao, G., & Wang, D. (2025) · EMBO Molecular Medicine · doi:10.1038/s44321-025-00248-w · Cited by 8
“1D) and has been shown to be amenable to mutagenesis, suggesting it may tolerate the additional residues encoded by attR (Baek et al, 2021; Jain et al, 2024).”
Alagesan, K., Nagarajan, H., Ramachandran, B., Vetrivel, U., Pandian, C. J., & Jeyaraman, J. (2025) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2025.2507812 · Cited by 7
“Robetta has generated five models of TetR-FTRs; it uses RoseTTAFold to predict the structure by ab initio , and the best model was selected based on their C score (Confidence score).”
InfluentialBrookes, E., Curtis, J. E., Householder, A., & Rocco, M. (2025) · Journal of Applied Crystallography · doi:10.1107/s1600576725003590 · Cited by 8
The AI drug revolution needs a revolution
Jacobson, R. D. (2025) · npj Drug Discovery. · doi:10.1038/s44386-025-00013-6 · Cited by 7
Artificial intelligence in therapeutic antibody design: Advances and future prospects
Park, S., Jeong, W., Kim, Y., Lee, C., & Seok, C. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103084 · Cited by 10
Upgrading microalgae for petroleum alternatives: CO2 upcycling for photosynthesis-based society
Lee, J. S., Tsang, Y. F., Kwon, E. E., & Sim, S. J. (2025) · Renewable and Sustainable Energy Reviews · doi:10.1016/j.rser.2025.116025 · Cited by 8
Protein Engineering Paving the Way for Next-Generation Therapies in Cancer
Naderiyan, Z., & Shoari, A. (2025) · International Journal of Translational Medicine · doi:10.3390/ijtm5030028 · Cited by 8
“Notably, AlphaFold2, developed by DeepMind, and RoseTTAFold (Figure 2), developed by the Baker Lab, have demonstrated that AI can reliably infer atomic-level protein structures, rivaling experimental techniques such as X-ray crystallography and cryo-electron microscopy in many cases [76,77].”
The path to biotechnological singularity: Current breakthroughs and outlook
Wen, Z., Yang, D., Yang, Y., Hu, J., Parviainen, A., Chen, X., Li, Q., VanDeusen, E. A., Ma, J., & Tay, F. R. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108667 · Cited by 8
From “Information” to Configuration and Meaning: In Living Systems, the Structure Is the Function
Renati, P., & Madl, P. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26157319 · Cited by 7
“A fleet of experts has been working on protbots, like «Alphafold» [82] and «Rosettafold» [83], which have been fed with huge amounts of data (predominantly from the gigantic Uniprot database [84]) to facilitate protein folding simulations.”
Wang, Y. X., Wang, F., Feng, L., Zhang, C., & Lai, L. (2025) · Protein Science · doi:10.1002/pro.70338 · Cited by 9
“End-to-end protein structure prediction methods, such as AlphaFold2 (AF2) (Jumper et al., 2021) and RoseT-TAFold (Baek et al., 2021), have demonstrated atom-level accuracy in modeling protein monomers.”
Park, H., Pritchard, B. P., & Wang, L. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01540 · Cited by 8
Self-citationDe Novo Design of Peptide Masks Enables Rapid Generation of Conditionally-Active Miniprotein Binders
Escobar-Rosales, M., Montaner, C., Expòsit, M., Lucchi, R., Díaz‐Perlas, C., Baker, D. A., & Oller‐Salvia, B. (2025) · Journal of the American Chemical Society · doi:10.1021/jacs.5c16108 · Cited by 8
Self-citationComputational Modeling of PROTAC Ternary Complexes as Ensembles Using SILCS-xTAC
Nordquist, E. B., Zhao, M., Yu, W., & MacKerell, A. D. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02045 · Cited by 8
A Comprehensive Review of Transformer-Based Language Models for Protein Sequence Analysis and Design
Ghosh, N., Santoni, D., Nawn, D., Ottaviani, E., & Felici, G. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3631454 · Cited by 10
Li, J., Wan, B., & Song, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113489 · Cited by 8
Approaches for accelerating microbial gene function discovery using artificial intelligence
Palsson, B. Ø., Lee, S. Y., & Kim, G. B. (2026) · Nature Microbiology · doi:10.1038/s41564-025-02214-1 · Cited by 10
Protein foundation models: a comprehensive survey
Xu, H., Li, L., Pan, S., Cheng, P., Wang, Y., Rong, Z., Feng, L., Huang, X., Wang, S., & Shu, W. (2026) · Science China Life Sciences · doi:10.1007/s11427-025-3147-2 · Cited by 10
Liu, Q., Wang, T., Nian, B., Ma, F., Zhao, S., Vásquez, A. F., Guo, L., Ding, C., & Davari, M. D. (2026) · Biotechnology Advances · doi:10.1016/j.biotechadv.2026.108803 · Cited by 12
Generating Dynamic Structures Through Physics‐Based Sampling of Predicted Inter‐Residue Geometries
Xiang, C., Wang, W., Peng, Z., & Yang, J. (2026) · Advanced Science · doi:10.1002/advs.202518469 · Cited by 11
“While deep learning approaches, such as AlphaFold2 (AF2) [ 3 ], RoseTTAFold [ 4 ], trRosetta [ 5– 8 ], and ESMFold [ 9 ], have revolutionized static protein structure prediction, accurately modeling alternative conformations of proteins remains a significant challenge.”
Nam, K. H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27031370 · Cited by 7
“RoseTTAFold (RF), developed by the Baker lab, provides accurate and fast predictions through a three-track network architecture [22].”
InfluentialMulti-scale structural similarity embedding search across entire proteomes
Segura, J., Sánchez-García, R., Bittrich, S., Rose, Y., Burley, S. K., & Duarte, J. M. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag058 · Cited by 7
Wang, Y., Lv, J., Xia, Y., Xu, J., Meng, Y., Cui, F., Wei, L., Zou, Q., & Zhang, Z. (2026) · Biotechnology Advances · doi:10.1016/j.biotechadv.2026.108843 · Cited by 10
Niazi, S. K. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27104349 · Cited by 8
“AlphaFold2, RoseTTAFold, and ESMFold have established deep learning as the dominant paradigm for monomeric protein structure prediction [1,2,6].”
Development and Applications of Antifreeze Materials: From Nature to Design
Zhang, X., Tian, Y., Yang, H., Jiang, X., Li, Y. T., Huang, X., Yang, J., & Zhang, L. (2026) · Advanced Materials · doi:10.1002/adma.73293 · Cited by 9
Hu, W., Sun, Y., Li, T., Williamson, M., Hu, X., & Wang, M. (2026) · The Innovation Drug Discovery · doi:10.59717/j.xinn-drugdisc.2026.100009 · Cited by 8
Curse and Blessing of Non‐Proteinogenic Parts in Computational Enzyme Engineering
Korbeld, K. T., & Fürst, M. J. L. J. (2023) · ChemBioChem · doi:10.1002/cbic.202300192 · Cited by 8
A Review of Drug-related Associations Prediction Based on Artificial Intelligence Methods
Ma, M., Lei, X., & Zhang, Y. (2023) · Current Bioinformatics · doi:10.2174/1574893618666230707123817 · Cited by 7
Genetically encoded phosphatidylserine biosensor for in vitro, ex vivo and in vivo labelling
Dirvelytė-Valauskė, E., Bujanauskienė, D., Jankaitytė, E., Daugelaviciene, N., Kisieliute, U., Nagula, I., Budvytytė, R., & Neniškytė, U. (2023) · Cellular & Molecular Biology Letters · doi:10.1186/s11658-023-00472-7 · Cited by 8
Yang, Z., Wang, R. S., Cheng, B. Y., Ruan, V., Yang, P., Liang, C.-H., & Shen, C. R. (2023) · Biochemical Engineering Journal · doi:10.1016/j.bej.2023.109064 · Cited by 7
Protein structures unravel the signatures and patterns of deep time evolution
Harish, A. (2024) · QRB Discovery · doi:10.1017/qrd.2024.4 · Cited by 8
Next-generation direct reprogramming
Keshri, R., Detraux, D., Phal, A., McCurdy, C., Jhajharia, S., Chan, T. C., Mathieu, J., & Ruohola‐Baker, H. (2024) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2024.1343106 · Cited by 8
Du, C., Yin, H., Xie, A., Yu, J., Wang, Y., Yao, F., Zhang, S., Zhang, Y., Liu, L., Wang, P., et al. (2024) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2024.2331101 · Cited by 7
“…from DeepMind and the RoseTTAFold from David Baker’s lab were released, both of which were trained using the coevo-lutionary information for protein and structure from Protein Structure Database (RCSB PDB) to obtain precise structures at the atomic level (Baek et al., 2021; Jumper et al., 2021).”
Knots and θ-Curves Identification in Polymeric Chains and Native Proteins Using Neural Networks
da Silva, F. B., Gabrovšek, B., Korpacz, M., Łuczkiewicz, K., Niewieczerzał, S., Sikora, M., & Sulkowska, J. I. (2024) · Macromolecules · doi:10.1021/acs.macromol.3c02479 · Cited by 7
RhoMax: Computational Prediction of Rhodopsin Absorption Maxima Using Geometric Deep Learning
Sela, M., Church, J. R., Schapiro, I., & Schneidman‐Duhovny, D. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00467 · Cited by 11
Factors affecting macromolecule orientations in thin films formed in cryo-EM
Yadav, S., & Vinothkumar, K. R. (2024) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798324005229 · Cited by 7
Üresin, D., Schulte, J., Morgner, N., & Soppa, J. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25137166 · Cited by 7
Zhu, C., Zhang, C., Shang, T., Zhang, C., Zhai, S., Cao, L., Xu, Z., Su, Z., Song, Y., Su, A., et al. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae297 · Cited by 8
Shimanovich, U., & Hartl, F. U. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2411135121 · Cited by 7
“Since its development, AlphaFold and related approaches such as RoseTTAfold (6) have already made tre - mendous contributions to the life sciences by accurately predicting the structures of proteins involved in cancer development, neurodegeneration, and infectious diseases, including research on Covid - 19, to name on…”
MethodWang, B., & Li, W. (2024) · Genes · doi:10.3390/genes15081090 · Cited by 11
“For example, in the structure prediction competition CASP 14 [29], AlphaFold2 [30], and RoseTTAFold [31] made a major breakthrough in protein tertiary structure prediction, providing raw structural data for large-scale PNBP as a reliable alternative to experimental methods.”
Deep Learning Approaches for the Prediction of Protein Functional Sites
Pitarch, B., & Pazos, F. (2025) · Molecules · doi:10.3390/molecules30020214 · Cited by 9
“In fact, deep learning-based AlphaFold [7] or RosettaFold [8] are successful in predicting accurate three-dimensional (3D) structures, which are comparable to experimental structures.”
Probing Biomolecular Interactions with Paramagnetic Nuclear Magnetic Resonance Spectroscopy
Busch, H., Ateeque, M. Y., Taube, F., Wiegand, T., Corzilius, B., & Kuenze, G. (2025) · ChemBioChem · doi:10.1002/cbic.202400903 · Cited by 8
MELD in Action: Harnessing Data to Accelerate Molecular Dynamics
Gaza, J. T., Brini, E., MacCallum, J. L., Dill, K. A., & Pérez, A. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02108 · Cited by 8
Surfactant-like peptide gels are based on cross-β amyloid fibrils
Das, A. K., Gnewou, O. M., Zuo, X., Wang, F., & Conticello, V. P. (2025) · Faraday Discussions · doi:10.1039/d4fd00190g · Cited by 7
Slice'N'Dice : maximizing the value of predicted models for structural biologists
Simpkin, A. J., Elliott, L. G., Joseph, A. P., Burnley, B. T., Stevenson, K., Rodríguez, F. S., Fando, M. S., Krissinel, E., McNicholas, S. J., Rigden, D. J., et al. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325001251 · Cited by 12
Kim, D., Kim, J.-S., Bai, X., Zhang, J., Park, M., Lee, U., Lee, J., Bahn, Y., Xu, Y., & Ha, N. (2025) · Journal of Microbiology and Biotechnology · doi:10.4014/jmb.2411.11076 · Cited by 9
Hu, L., Wainman, A., Andreeva, A. E., Apizi, M., Alvarez‐Rodrigo, I., Wong, S., Saurya, S., Sheppard, D., Cottee, M. A., Johnson, S., et al. (2025) · Science Advances · doi:10.1126/sciadv.adr5744 · Cited by 7
A unique mechanism of snRNP core assembly
Wang, Y., Chen, X., Kong, X., Chen, Y., Xiang, Z., Xiang, Y., Hu, Y., Hou, Y., Zhou, S., Shen, C., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-58461-7 · Cited by 7
“Recently, more accurate structure prediction programs based on arti fi cial intelligence (AI) such as AF and RosettaFold (RF) have been developed 42,43 .”
Prix Nobel de chimie 2024: David Baker, Demis Hassabis et John M. Jumper
Aguero, S., Bettler, E., & Gouet, P. (2025) · médecine/sciences · doi:10.1051/medsci/2025060 · Cited by 9
Cheng, L., Lu, W., Xia, Y., Lu, Y., Shen, J., Hui, Z., Xu, Y., Wu, H., Chen, J., Fu, Q., et al. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108429 · Cited by 7
Suneesh, N. S., Dhotre, K., Mahajan, P., Dass, D., Banerjee, A., Siddiqi, N. J., Malik, A., Joshi, M., Khan, A. A., Nema, V., et al. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1586271 · Cited by 7
Interplay Between tRNA Modifications and Processing
Peschek, J., & Tuorto, F. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169198 · Cited by 7
Morando, M. A., D’Alessandro, V., Spinello, A., Sollazzo, M., Monaca, E., Sabbatella, R., Volpe, M. C., Gervaso, F., Polini, A., Mizielinska, S., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-02035-6 · Cited by 10
“54 This was necessary because the only available experimental structure of TDP-43 RRMs is in complex with UG-rich RNA (PDB 4bs2).”
Hou, Y., Guan, A., Fan, X., & Qin, J. (2025) · Synthetic and Systems Biotechnology · doi:10.1016/j.synbio.2025.08.005 · Cited by 7
“Emerging artificial intelligence (AI) tools like AlphaFold [70,71] now enable rational protein design, exemplified by its use in modeling aminase structures to classify cytidine deaminases more accurately [72].”
An adaptive autoregressive diffusion approach to design active humanized antibodies and nanobodies
Ma, J., Wu, F., Xu, T., Xu, S., Liu, W., Yan, L., Qu, M., Yang, X., Bai, Q., Xiao, J., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01120-9 · Cited by 9
Congenital heart disease diagnosis using machine learning: a systematic literature review
Khan, K., Syed, I., Ullah, F., & Khan, R. U. (2026) · Frontiers in Medicine · doi:10.3389/fmed.2026.1757468 · Cited by 10
“Through techniques like Doppler echo, clinicians can assess the direction and velocity of blood flow, helping to identify abnormalities such as septal defects, valve malformations, or improper circulation often associated with CHD. Multiview CHD-echo (44) comprises a total of 1,308 children.”
Myosin light chain proteins cooperatively promote sarcomere growth in fast-twitch muscle
Adekeye, T. E., Hupper, T., Easterbrooks, T., Teets, E. M., Tomak, E. A., Waterman, S., Sprague, K., White, A., Coffin, M., Tanaka, D. K., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-73861-z · Cited by 8
George, K., Mateos, D. L., El‐Aziz, T. M. A., Xiao, Y., Kline, J. T., Bao, H., Raza, S. A., Stockand, J. D., Cummins, T., Fornelli, L., et al. (2022) · Frontiers in Pharmacology · doi:10.3389/fphar.2022.846992 · Cited by 11
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.