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 401–500 of 5,634
A metagenomic ‘dark matter’ enzyme catalyses oxidative cellulose conversion
Santos, C. A., Morais, M. A. B., Mandelli, F., de Lima, E. A., Miyamoto, R. Y., Higasi, P. M. R., de Araújo, E. A., Paixão, D. A. A., Martins, J., Motta, M. L. L., et al. (2025) · Nature · doi:10.1038/s41586-024-08553-z · Cited by 88
Enhanced Protein-Protein Interaction Discovery via AlphaFold-Multimer
Kim, A.-R., Hu, Y., Comjean, A., Rodiger, J., Mohr, S. E., & Perrimon, N. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.19.580970 · Cited by 70
Cicconardi, F., Milanetti, E., Pinheiro de Castro, E. C., Mazo-Vargas, A., Van Belleghem, S. M., Ruggieri, A. A., Rastas, P., Hanly, J., Evans, E., Jiggins, C. D., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-41412-5 · Cited by 81
“1.0 171 to predict three-dimensional structures, building fi ve models per sequence using default parameters.”
InfluentialGao, M., Ren, J., Gong, Y., Fang, M., Yang, J., & Li, Z. (2023) · Aggregate · doi:10.1002/agt2.462 · Cited by 79
Theranostics - a sure cure for cancer after 100 years?
Song, Y., Zou, J., Castellanos, E., Matsuura, N., Ronald, J. A., Shuhendler, A. J., Weber, W., Gilad, A. A., Müller, C., Witney, T. H., et al. (2024) · Theranostics · doi:10.7150/thno.96675 · Cited by 83
Xu, Y., Huang, H., Lu, H., Wu, M., Lin, M., Zhang, C., Zhao, Z., Li, W., Zhang, C., Li, X., et al. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2021.820380 · Cited by 77
Fonin, A. V., Antifeeva, I. A., Kuznetsova, I. М., Константинович, Т. К., Zaslavsky, B. Y., Kulkarni, P., & Uversky, V. N. (2022) · Essays in Biochemistry · doi:10.1042/ebc20220052 · Cited by 80
Metabolic engineering for sustainability and health
Kim, G. B., Choi, S. Y., Cho, I., Ahn, D., & Lee, S. Y. (2023) · Trends in biotechnology · doi:10.1016/j.tibtech.2022.12.014 · Cited by 83
From byte to bench to bedside: molecular dynamics simulations and drug discovery
Ahmed, M., Maldonado, A. M., & Durrant, J. D. (2023) · BMC Biology · doi:10.1186/s12915-023-01791-z · Cited by 94
The origin and structural evolution of de novo genes in Drosophila
Peng, J., & Zhao, L. (2024) · Nature Communications · doi:10.1038/s41467-024-45028-1 · Cited by 71
A De Novo Metalloenzyme for Cerium Photoredox Catalysis
(2024) · doi:10.1021/jacs.4c04618 · Cited by 76
De Novo Peptide and Protein Design Using Generative Adversarial Networks: An Update
Lin, E., Lin, C., & Lane, H. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01361 · Cited by 83
Deep learning for protein structure prediction and design—progress and applications
Jänes, J., & Beltrão, P. (2024) · Molecular Systems Biology · doi:10.1038/s44320-024-00016-x · Cited by 84
“RoseTTAFold has been adapted to predict protein-nucleic acid complexes (Baek et al, 2024).”
BackgroundMethodInfluentialApplication of Transformers in Cheminformatics
Luong, K.-D., & Singh, A. K. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c02070 · Cited by 85
Transformers for Molecular Property Prediction: Lessons Learned from the Past Five Years
Sultan, A., Sieg, J., Mathea, M., & Volkamer, A. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00747 · Cited by 91
AI Methods for Antimicrobial Peptides: Progress and Challenges
Brizuela, C. A., Liu, G., Stokes, J. M., & de la Fuente‐Núñez, C. (2025) · Microbial Biotechnology · doi:10.1111/1751-7915.70072 · Cited by 88
Building structural models of a whole mycoplasma cell
Maritan, M., Autin, L., Karr, J., Covert, M. W., Olson, A. J., & Goodsell, D. S. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.167351 · Cited by 75
Geometric deep learning of protein–DNA binding specificity
Mitra, R., Li, J., Sagendorf, J. M., Jiang, Y., Cohen, A. S., Chiu, T.-P., Glasscock, C. J., & Rohs, R. (2024) · Nature Methods · doi:10.1038/s41592-024-02372-w · Cited by 75
“The rapid advancement of protein structure prediction meth-ods, including AlphaFold 26 , OpenFold 27 and RoseTTAFold 28 , along with protein–DNA complex modelers, such as RoseTTAFoldNA (RFNA) 29 , RoseTTAFold All-Atom 30 , MELD-DNA 31 and AlphaFold3 (ref.”
BackgroundMethodAccurate protein structure prediction: what comes next?
Seok, C., Baek, M., Steinegger, M., Park, H., Lee, G. R., & Won, J. (2021) · Korean Society for Structural Biology · doi:10.34184/kssb.2021.9.3.47 · Cited by 87
Self-citationOmics-based interdisciplinarity is accelerating plant breeding
Shen, Y., Zhou, G., Liang, C., & Tian, Z. (2022) · Current Opinion in Plant Biology · doi:10.1016/j.pbi.2021.102167 · Cited by 75
Stable and Functionally Diverse Versatile Peroxidases Designed Directly from Sequences
Barber-Zucker, S., Mindel, V., Garcia‐Ruiz, E., Weinstein, J. J., Alcalde, M., & Fleishman, S. J. (2022) · Journal of the American Chemical Society · doi:10.1021/jacs.1c12433 · Cited by 84
Tsai, Y.-X., Chang, N.-E., Reuter, K., Chang, H., Yang, T., von Bülow, S., Sehrawat, V., Zerrouki, N., Tuffery, M., Gecht, M., et al. (2024) · Cell · doi:10.1016/j.cell.2024.01.034 · Cited by 78
Dematteis, G., Tapella, L., Casali, C., Talmon, M., Tonelli, E., Reano, S., Ariotti, A., Pessolano, E., Malecka, J., Chrostek, G., et al. (2024) · Communications Biology · doi:10.1038/s42003-024-06933-9 · Cited by 86
“Structural prediction, using Robetta service 18 , was used to select the correct number of amino acids resulting in the desired ruler lengths.”
Leveraging network pharmacology for drug discovery: Integrative approaches and emerging insights
Li, L., & Kar, S. (2025) · Medicine in Drug Discovery · doi:10.1016/j.medidd.2025.100220 · Cited by 91
Regulatory perspectives of combination products
Tian, J., Song, X., Wang, Y., Cheng, M., Lu, S., Xu, W., Gao, G., Sun, L., Tang, Z., Wang, M., et al. (2021) · Bioactive Materials · doi:10.1016/j.bioactmat.2021.09.002 · Cited by 102
Structural and biochemical insights into lipid transport by VPS13 proteins
Adlakha, J., Hong, Z., Li, P., & Reinisch, K. M. (2022) · Journal of Cell Biology · doi:10.1083/jcb.202202030 · Cited by 74
Biochemistry and Biotechnology of Lipid Accumulation in the Microalga Nannochloropsis oceanica
Xu, Y. (2022) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.2c05309 · Cited by 78
Critical Assessment of Methods for Predicting the 3D Structure of Proteins and Protein Complexes
Wodak, S. J., Vajda, S., Lensink, M. F., Kozakov, D., & Bates, P. A. (2023) · Annual Review of Biophysics · doi:10.1146/annurev-biophys-102622-084607 · Cited by 67
Porebski, B. T., Balmforth, M., Browne, G., Riley, A., Jamali, K., Fürst, M. J. L. J., Velic, M., Buchanan, A., Minter, R., Vaughan, T., et al. (2023) · Nature Biomedical Engineering · doi:10.1038/s41551-023-01093-3 · Cited by 72
Ghafouri, H., Lazar, T., Del Conte, A., Tenorio Ku, L. G., PED Consortium, Aspromonte, M. C., Bernadó, P., Chaves-Arquero, B., Chemes, L. B., Clementel, D., et al. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkad947 · Cited by 73
“More-over, the advent of AlphaFold2 ( 9 ), RoseTTAFold ( 10 ) and the advancements in machine learning approaches have fostered the development of various pipelines aimed at effectively modeling multiple conformational states or predicting conformational ensembles ( 11–13 ).”
BackgroundThe Potential Applications of Artificial Intelligence in Drug Discovery and Development
Farghali, H., Kutinová Canová, N., & Arora, M. (2021) · Physiological Research · doi:10.33549/physiolres.934765 · Cited by 72
Novel machine learning approaches revolutionize protein knowledge
Bordin, N., Dallago, C., Heinzinger, M., Kim, S., Littmann, M., Rauer, C., Steinegger, M., Rost, B., & Orengo, C. (2023) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2022.11.001 · Cited by 72
“DeepMind ’ s AF2 outperformed others in CASP14 [26], and reports suggest that high-quality models can be comparable to crystallographic structures, with competing methods reproducing DeepMind ’ s results [24,27,28].”
MethodResultLeveraging transformers‐based language models in proteome bioinformatics
Le, N. Q. K. (2023) · PROTEOMICS · doi:10.1002/pmic.202300011 · Cited by 81
Computer-Aided Drug Discovery for Undruggable Targets
Sun, Q., Wang, H., Xie, J., Wang, L., Mu, J., Li, J., Ren, Y., & Lai, L. (2025) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00969 · Cited by 82
Generalized biological foundation model with unified nucleic acid and protein language
He, Y., Fang, P., Shan, Y., Pan, Y., Wei, Y., Chen, Y., Chen, Y., Liu, Y., Zeng, Z., Zhou, Z. M., et al. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01044-4 · Cited by 104
“In life science, substantial efforts have been put into adopting such language models, especially in protein tasks (ProTrans[8], ProteinBERT[9], ESM2[10], Ankh[11]), such as structure prediction[10, 12] and function annotation[13, 14].”
Accurate modeling of peptide-MHC structures with AlphaFold
Mikhaylov, V., Brambley, C. A., Keller, G. L. J., Arbuiso, A. G., Weiss, L. I., Baker, B. M., & Levine, A. J. (2024) · Structure · doi:10.1016/j.str.2023.11.011 · Cited by 72
Accurate modeling of peptide-MHC structures with AlphaFold
Mikhaylov, V., & Levine, A. J. (2023) · doi:10.1101/2023.03.06.531396 · Cited by 72
GPU-accelerated homology search with MMseqs2
(2025) · doi:10.1038/s41592-025-02819-8 · Cited by 71
Hasanzadeh, A., Hamblin, M. R., Kiani, J., Noori, H., Hardie, J. M., Karimi, M., & Shafiee, H. (2022) · Nano Today · doi:10.1016/j.nantod.2022.101665 · Cited by 74
Structure‐Based Drug Discovery with Deep Learning**
Özçelik, R., van Tilborg, D., Jiménez-Luna, J., & Grisoni, F. (2023) · ChemBioChem · doi:10.1002/cbic.202200776 · Cited by 88
One bead per residue can describe all-atom protein structures
Heo, L., & Feig, M. (2024) · Structure · doi:10.1016/j.str.2023.10.013 · Cited by 62
Cordoves‐Delgado, G., & García‐Jacas, C. R. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c02061 · Cited by 80
The protein-folding problem: Not yet solved
Moore, P. B., Hendrickson, W. A., Henderson, R., & Brunger, A. T. (2022) · Science · doi:10.1126/science.abn9422 · Cited by 74
Engineering Acetogenic Bacteria for Efficient One-Carbon Utilization
Lee, H., Bae, J., Jin, S., Kang, S., & Cho, B. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.865168 · Cited by 75
Casadevall, G., Duran, C., & Osuna, S. (2023) · JACS Au · doi:10.1021/jacsau.3c00188 · Cited by 65
Adaptive Sampling Methods for Molecular Dynamics in the Era of Machine Learning
Kleiman, D. E., Nadeem, H., & Shukla, D. (2023) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.3c04843 · Cited by 71
FoldScript: a web server for the efficient analysis of AI-generated 3D protein models
Robert, X., Guillon, C., & Gouet, P. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf326 · Cited by 85
“…discoveries and inventions that enable machine learning with artificial neural networks’, while the Prize in Chemistry was jointly awarded to RoseTTAFold [ 2 ] and AlphaFold (AF) [ 3 , 4 ] for their pioneering use of AI ‘for computational protein design and protein structure prediction’.”
Beyond static structures: protein dynamic conformations modeling in the post-AlphaFold era
Cui, X., Ge, L., Chen, X., Lv, Z., Wang, S., Zhou, X., & Zhang, G. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf340 · Cited by 84
Structure-informed Language Models Are Protein Designers
Zheng, Z., Deng, Y., Xue, D., Zhou, Y., Ye, F., & Gu, Q. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.03.526917 · Cited by 62
Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
Steiner, M., & Reiher, M. (2022) · Topics in Catalysis · doi:10.1007/s11244-021-01543-9 · Cited by 87
“The situation will then be similar to that of the prediction of a most stable protein fold, which is a conformational sampling problem at its core and for which specific knowledge-based approaches are advantageous [378, 379].”
BackgroundMarchand, A., Van Hall-Beauvais, A. K., & Correia, B. E. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102370 · Cited by 65
Automated optimisation of solubility and conformational stability of antibodies and proteins
Rosace, A., Bennett, A., Oeller, M., Mortensen, M. M., Sakhnini, L. I., Lorenzen, N., Poulsen, C., & Sormanni, P. (2023) · Nature Communications · doi:10.1038/s41467-023-37668-6 · Cited by 80
“While an experimentally determined structure may not always be available, great advances have been made in the de novo modelling of proteins (74, 75) and unbound antibody structures (76–79).”
BackgroundComputational discovery of microstructured composites with optimal stiffness-toughness trade-offs
Li, B., Deng, B., Shou, W., Oh, T.-H., Hu, Y., Luo, Y., Shi, L., & Matusik, W. (2024) · Science Advances · doi:10.1126/sciadv.adk4284 · Cited by 84
“…pipeline is readily applicable to various trade-off problems well beyond the field of solid mechanics, especially where simulation struggles to match reality, such as polymer chemistry ( 43 ), computational biology ( 44, 45 ), fluid dynamics ( 46, 47 ), meteorology ( 48, 49 ), and robotics ( 50 ).”
BackgroundDiaz, D. J., Gong, C., Ouyang-Zhang, J., Loy, J. M., Wells, J., Yang, D., Ellington, A. D., Dimakis, A. G., & Klivans, A. R. (2024) · Nature Communications · doi:10.1038/s41467-024-49780-2 · Cited by 60
“Deep learning is currently revolutionizing many physical and biological disciplines 17 – 21 , with AlphaFoldV2 leading the way as the scienti fi c breakthrough of the year in 2021 22,23 and sparking an entire waveofdeeplearningstructurepredictiontools 24,25 .”
Improved Docking of Protein Models by a Combination of Alphafold2 and ClusPro
Ghani, U., Desta, I., Jindal, A., Khan, O., Jones, G., Hashemi, N., Kotelnikov, S., Padhorny, D., Vajda, S., & Kozakov, D. (2021) · doi:10.1101/2021.09.07.459290 · Cited by 68
Evolutionary diversification of methanotrophic ANME-1 archaea and their expansive virome
Laso-Pérez, R., Wu, F., Crémière, A., Speth, D. R., Magyar, J. S., Zhao, K., Krupovic, M., & Orphan, V. J. (2023) · Nature Microbiology · doi:10.1038/s41564-022-01297-4 · Cited by 68
“38) and RoseTTAFold v.1.1.0 (ref.”
InfluentialAlong the allostery stream: Recent advances in computational methods for allosteric drug discovery
Ni, D., Chai, Z., Wang, Y., Li, M., Yu, Z., Liu, Y., Lu, S., & Zhang, J. (2022) · WIREs Computational Molecular Science · doi:10.1002/wcms.1585 · Cited by 68
Enabling technology and core theory of synthetic biology
Zhang, X., Liu, C., Dai, J., Yuan, Y., Gao, C., Feng, Y. F., Wu, B., Wei, P., You, C., Wang, X., et al. (2023) · Science China Life Sciences · doi:10.1007/s11427-022-2214-2 · Cited by 75
“Notably, recent developments in AI algorithms should play a vital role in future protein engineering (Baek et al., 2021).”
BackgroundStructural basis for ATG9A recruitment to the ULK1 complex in mitophagy initiation
Ren, X., Nguyen, T. N., Lam, W. K., Buffalo, C. Z., Lazarou, M., Yokom, A. L., & Hurley, J. H. (2023) · Science Advances · doi:10.1126/sciadv.adg2997 · Cited by 68
“Our truncation data limited the primary sequence for the ATG9A component to be modeled on the ATG13:ATG101 dimer, making AF2 prediction of the complex feasible.”
BackgroundDirected Biosynthesis of Mitragynine Stereoisomers
Schotte, C., Jiang, Y., Grzech, D., Dang, T. T., Laforest, L. C., León, F., Mottinelli, M., Nadakuduti, S. S., McCurdy, C. R., & O'Connor, S. E. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.2c13644 · Cited by 68
Protein dynamics: The future is bright and complicated!
Nam, K., & Wolf‐Watz, M. (2023) · Structural Dynamics · doi:10.1063/4.0000179 · Cited by 73
Han, Y., Kim, D. H., & Pack, S. P. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms262211121 · Cited by 83
“Although fully validated end-to-end studies are still emerging, evidence suggests that generative strategies expand the accessible design space and support faster clinical translation of nanomedicines [89–92].”
Protein language models trained on multiple sequence alignments learn phylogenetic relationships
Lupo, U., Sgarbossa, D., & Bitbol, A.-F. (2022) · Nature Communications · doi:10.1038/s41467-022-34032-y · Cited by 67
“Neural network architectures based on attention are also employed in the Evoformer blocks in AlphaFold [12], as well as in RoseTTAFold [13] and RGN2 [14], and they contributed to the recent breakthrough in the supervised prediction of protein structure.”
MethodYuan, Q., Chen, S., Wang, Y., Zhao, H., & Yang, Y. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac444 · Cited by 68
He, H., Chen, G., & Chen, C. Y. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad355 · Cited by 67
Braxton, J. R., & Southworth, D. R. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.105182 · Cited by 70
A Perspective on Protein Structure Prediction Using Quantum Computers
Doğa, H., Raubenolt, B. A., Cumbo, F., Joshi, J., DiFilippo, F. P., Qin, J., Blankenberg, D. J., & Shehab, O. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c00067 · Cited by 81
“Over the years, there have been many works that utilize some type of neural network based architecture to achieve this [124–127].”
Uni-Fold: An Open-Source Platform for Developing Protein Folding Models beyond AlphaFold
Li, Z., Liu, X., Chen, W., Shen, F., Bi, H., Ke, G., & Zhang, L. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.08.04.502811 · Cited by 59
Protein design via deep learning
Ding, W., Nakai, K., & Gong, H. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac102 · Cited by 66
Sequence-Defined Synthetic Polymers for New-Generation Functional Biomaterials
Deng, Z., Shi, Q., Tan, J., Hu, J., & Liu, S. (2021) · ACS Materials Letters · doi:10.1021/acsmaterialslett.1c00358 · Cited by 72
Method of the Year: protein structure prediction
Marx, V. (2022) · Nature Methods · doi:10.1038/s41592-021-01359-1 · Cited by 78
Design of a multi-epitope vaccine candidate against Brucella melitensis
Li, M., Zhu, Y., Niu, C., Xie, X., Haimiti, G., Guo, W., Yu, M., Chen, Z., Ding, J., & Zhang, F. (2022) · Scientific Reports · doi:10.1038/s41598-022-14427-z · Cited by 75
Modelling peptide–protein complexes: docking, simulations and machine learning
Mondal, A., Chang, L., & Pérez, A. (2022) · QRB Discovery · doi:10.1017/qrd.2022.14 · Cited by 73
Underexplored viral auxiliary metabolic genes in soil: Diversity and eco‐evolutionary significance
Sun, M., Yuan, S., Xia, R. M., Ye, M., & Balcázar, J. L. (2022) · Environmental Microbiology · doi:10.1111/1462-2920.16329 · Cited by 66
Keskin Karakoyun, H., Yüksel, Ş. K., Amanoglu, I., Naserikhojasteh, L., Yeşilyurt, A., Yakıcıer, C., Timuçin, E., & Akyerli, C. B. (2023) · Frontiers in Genetics · doi:10.3389/fgene.2023.1052383 · Cited by 58
“Furthermore, RCSB Protein Data Bank (RCSB PDB) has presented more than 1 million computed structural models including AF2 predictions (Baek et al., 2021; Burley and Berman, 2021; Jumper et al., 2021; Tunyasuvunakool et al., 2021).”
MethodFragment-based drug discovery supports drugging ‘undruggable’ protein–protein interactions
Wang, Z.-Z., Shi, X.-X., Huang, G.-Y., Hao, G., & Yang, G. (2023) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2023.01.008 · Cited by 68
Data-Driven Elucidation of Flavor Chemistry
Kou, X., Shi, P., Gao, C., Ma, P., Xing, H., Ke, Q., & Zhang, D. (2023) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.3c00909 · Cited by 66
Theoretical and Data-Driven Approaches for Biomolecular Condensates
Saar, K. L., Qian, D., Good, L. L., Morgunov, A. S., Collepardo‐Guevara, R., Best, R. B., & Knowles, T. P. J. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.2c00586 · Cited by 76
The Effects of Codon Usage on Protein Structure and Folding
Moss, M. J., Chamness, L. M., & Clark, P. L. (2023) · Annual Review of Biophysics · doi:10.1146/annurev-biophys-030722-020555 · Cited by 75
AI for targeted polypharmacology: The next frontier in drug discovery
Cichońska, A., Ravikumar, B., & Rahman, R. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102771 · Cited by 73
Targeting DCAF5 suppresses SMARCB1-mutant cancer by stabilizing SWI/SNF
Radko-Juettner, S., Yue, H., Myers, J., Carter, R. D., Robertson, A. N., Mittal, P., Zhu, Z., Hansen, B. S., Donovan, K. A., Hunkeler, M., et al. (2024) · Nature · doi:10.1038/s41586-024-07250-1 · Cited by 75
Visualizing RNA conformational and architectural heterogeneity in solution
Ding, J., Lee, Y.-T., Bhandari, Y., Schwieters, C. D., Fan, L., Yu, P., Tarosov, S. G., Stagno, J. R., Ma, B., Nussinov, R., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-36184-x · Cited by 66
iCn3D: From Web-Based 3D Viewer to Structural Analysis Tool in Batch Mode
Wang, J., Youkharibache, P., Marchler-Bauer, A., Lanczycki, C., Zhang, D., Lu, S., Madej, T., Marchler, G. H., Cheng, T., Chong, L. C., et al. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.831740 · Cited by 65
“With the release of more and more AlphaFold (Jumper et al., 2021) or RoseTTAFold (Baek et al., 2021) predicted structures and experimentally determined structures, it is important to be able to do structural analysis in batch mode.”
BackgroundSelf-citationBoeckaerts, D., Stock, M., De Baets, B., & Briers, Y. (2022) · Viruses · doi:10.3390/v14061329 · Cited by 58
From structure to function – Ligand recognition by myeloid C-type lectin receptors
Fischer, S., Stegmann, F., Gnanapragassam, V. S., & Lepenies, B. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.10.019 · Cited by 72
“Another approach is the primary amino acid sequence based three-dimensional structure prediction, by using Alpha Fold 2 [74] and RoseTTA Fold [75].”
MethodRock, scissors, paper: How RNA structure informs function
Assmann, S. M., Chou, H., & Bevilacqua, P. C. (2023) · The Plant Cell · doi:10.1093/plcell/koad026 · Cited by 68
Recent progress in the synthesis of advanced biofuel and bioproducts
Pfleger, B. F., & Takors, R. (2023) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2023.102913 · Cited by 69
Li, N., Quan, A., Li, D., Pan, J., Ren, H., Hoeltzel, G. D., de Val, N., Ashworth, D., Ni, W., Zhou, J., et al. (2023) · Nature Communications · doi:10.1038/s41467-023-37616-4 · Cited by 69
Using AlphaFold Predictions in Viral Research
Gutnik, D., Evseev, P. V., Анатольевич, М. К., & Shneider, M. M. (2023) · Current Issues in Molecular Biology · doi:10.3390/cimb45040240 · Cited by 67
DTI-LM: language model powered drug–target interaction prediction
Ahmed, K. T., Ansari, M. I., & Zhang, W. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae533 · Cited by 69
AlphaDesign: A de novo protein design framework based on AlphaFold
Jendrusch, M., Korbel, J. O., & Sadiq, S. K. (2021) · doi:10.1101/2021.10.11.463937 · Cited by 65
AAV capsid design: A Goldilocks challenge
Zolotukhin, S., & Vandenberghe, L. H. (2022) · Trends in Molecular Medicine · doi:10.1016/j.molmed.2022.01.003 · Cited by 64
(2022) · doi:10.1016/j.chempr.2022.07.012 · Cited by 64
Quality Assessment of Selected Protein Structures Derived from Homology Modeling and AlphaFold
Binbay, F. A., Rathod, D., George, A. A. P., & Imhof, D. (2023) · Pharmaceuticals · doi:10.3390/ph16121662 · Cited by 72
“The absence of a long loop region might have contributed these two proteins In addition, the development of not only AF but also different AI-based methods such as ESMFold [45] and RoseTTAFold [46] are among the factors triggering competition in this field.”
MethodComputational drug development for membrane protein targets
Li, H., Sun, X., Cui, W., Xu, M., Dong, J., Ekundayo, B., Ni, D., Rao, Z., Guo, L., Stahlberg, H., et al. (2024) · Nature Biotechnology · doi:10.1038/s41587-023-01987-2 · Cited by 70
“In particular, artificial intelligence (AI)-based methods have substantially improved protein folding prediction 9–11 and predict different structural levels of membrane proteins.”
Burley, S. K., Piehl, D. W., Vallat, B. K., & Zardecki, C. (2024) · IUCrJ · doi:10.1107/s2052252524002604 · Cited by 72
Chen, J.-Y., Wang, J.-F., Hu, Y., Li, X.-H., Qian, Y.-R., & Song, C.-L. (2025) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2025.1506508 · Cited by 49
“The breakthroughs in 3D structure prediction made by models such as AlphaFold and RosettaFold have made it possible to obtain a large number of protein structures from sequence data (Jumper et al., 2021; Baek et al., 2021).”
Self-citationDNA-guided transcription factor interactions extend human gene regulatory code
Xie, Z., Sokolov, I., Osmala, M., Xue, Y., Bower, G., Pett, J. P., Chen, Y., Wang, K., Cavga, A. D., Popov, A. N., et al. (2025) · Nature · doi:10.1038/s41586-025-08844-z · Cited by 74
Barnes, A. C., Rodríguez-Zapata, F., Juárez-Núñez, K. A., Gates, D. J., Janzen, G. M., Kur, A., Wang, L., Jensen, S. E., Estévez-Palmas, J. M., Crow, T. M., et al. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2100036119 · Cited by 67
Putting AlphaFold models to work with phenix.process_predicted_model and ISOLDE
Oeffner, R. D., Croll, T. I., Millán, C., Poon, B. K., Schlicksup, C. J., Read, R. J., & Terwilliger, T. C. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322010026 · Cited by 63
Self-citation
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.