Accurate prediction of protein structures and interactions using a 3-track network
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 13 of the 36 sources its claims cite were checked for support.
Abstract
DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research. One-Sentence Summary: Accurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.
Overview
CoChat Summary
TL;DR
RoseTTAFold is a 3-track neural network that integrates 1D sequence, 2D distance-map, and 3D coordinate information to predict protein structures and interactions. It approaches AlphaFold2 accuracy in CASP14, solves challenging crystallography and cryo-EM modeling problems, and generates protein-complex models directly from sequence.
Key findings
- In CASP14, the 3-track RoseTTAFold outperformed the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), the BAKER human group, and the authors’ 2-track models, though its performance was still not as good as AlphaFold2.
- On CAMEO, over 69 medium and hard targets released May 15–June 19, 2021, RoseTTAFold outperformed all other evaluated servers, including Robetta, IntFold6-TS, BestSingleTemplate, and SWISS-MODEL.
- RoseTTAFold models enabled molecular-replacement solutions for four previously unsolved crystallographic datasets; for the cryo-EM p101 Gβγ binding domain, the Cα-RMSD between predicted and refined structure was 3.0 Å over the beta-sheets.
- Among 693 domains from human disease-related proteins, over one-third had predicted lDDT > 0.8, corresponding to an average Cα-RMSD of 2.6 Å on CASP14 targets; many protein-complex models had TM-score > 0.8, with complex generation taking ~30 min on a 24G TITAN RTX GPU.
Methods
- The 3-track network transforms and integrates information at the 1D sequence/MSA level, the 2D distance/orientation-map level, and the 3D backbone-coordinate level, with information flowing between tracks; training used discontinuous sequence crops spanning 260 residues.
- Final 3D structures were generated either by feeding predicted distance/orientation distributions into pyRosetta for all-atom models or by an end-to-end SE(3)-equivariant layer producing backbone coordinates directly.
- Evaluation included CASP14 targets, CAMEO blind server assessment, four X-ray molecular-replacement datasets, a cryo-EM PI3Kγ complex, GPCRs, 693 human disease-related domains, and paired-sequence complexes of known structure, using accuracy comparisons, Cα-RMSD, lDDT, TM-score, and MR/cryo-EM fit.
Limitations
- Stated: hardware memory limitations constrained model size and training; performance remained below AlphaFold2; the end-to-end version was less accurate than the pyRosetta version due to incomplete optimization and neglect of side-chain information; the accuracy predictor did not consistently identify models better than the rapid single-pass method; the network was trained on monomeric proteins, not complexes; and current RoseTTAFold uses only the top 1000 sequences due to memory limits.
- Stated: the Perceiver-based extension for using all available sequences gave promising initial results, but more training is required for rigorous comparison.
- Evident: CASP14 and CAMEO evaluations cover limited target sets and time windows, and the end-to-end model does not produce side chains.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
3 Valid · 8 Not valid · 14 Not checked · 44 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The bi-annual Critical Assessment of Structure (CASP) meetings have demonstrated that deep learning methods such as AlphaFold (1, 2) and trRosetta (3), that extract information from the large database of known protein structures in the PDB, outperform more traditional approaches that explicitly model the folding process.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Abstract
What the sources say
- Not matchedcites [1] Jumper John Evans Richard Pritzel Alexander Green Tim Figurnov Michael Tunyasuvunakool Kathryn Ronneberger Olaf Bates Russ Augustin Žídek Alex Bridgland Clemens Meyer Fourteenth Critical Assessment of Techniques for Protein Structure Prediction
Its entry has no title and year that we can search by.
- Partly supportedcites [2] Anishchenko I Chidyausiku TM Ovchinnikov S Pellock SJ Baker D De novo protein design by deep network hallucination bioRxiv 2020 2020.07.22.211482 PMC9293396 34853475 sourceExperimental — accuracy not yet measured
The Introduction (page not provided) says deep networks improved protein-structure prediction accuracy, notes an AlphaFold observation at CASP13, and reports that trRosetta outperformed other methods in benchmark tests. The Conclusion says the network learned from native protein structures and contrasts it with physically based approaches. The paper does not establish the claimed CASP comparison in which both AlphaFold and trRosetta outperform approaches that explicitly model folding. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [3] Yang J Anishchenko I Park H Peng Z Ovchinnikov S Baker D Improved protein structure prediction using predicted interresidue orientations Proc Natl Acad Sci U S A 2020 117 1496 1503 31896580 PMC6983395 source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The RoseTTAFold CERS1 model for residues 98 to 304 (Pfam TLC domain) (29) includes six TMH that traverse the membrane in an up and down arrangement (Fig. 3E).”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Providing insights into biological function
What the sources say
- Could not verifycites [29] Cong Q Anishchenko I Ovchinnikov S Baker D Protein interaction networks revealed by proteome coevolution Science 2019 365 185 189 31296772 PMC6948103 sourceExperimental — accuracy not yet measured
The paper’s Abstract (page unavailable) describes coevolution-based protein interaction models in E. coli and M. tuberculosis, not a CERS1 model. Searches for CERS1, the Pfam TLC domain, RoseTTAFold, and six transmembrane helices found no passage in our copy addressing the cited domain identification or the stated membrane arrangement. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in the case of SLP, only a distant model covering part of the N-terminal domain (38% of the sequence) was available in the PDB”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“trRosetta failed to predict the correct fold with the same MSA input (fig. S6)”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 3-track models with attention operating at the 1D, 2D, and 3D levels and information flowing between the three levels were the best models we tested (Fig. 1B), clearly outperforming the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), BAKER human group (ranked second among all groups), and our 2-track attention models on CASP14 targets.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Network architecture development
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
33 more claims
Create a free account to see all 69 claims and to verify the 2 references still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RF has properties well suited for use in a protein design DDPM (Fig. 1a): it generates protein structures with high precision, operates on a rigid-frame representation of residues with rotational equivariance and has an architecture enabling conditioning on design specifications at the individual residue, inter-residue distance and orientation, and 3D coordinate levels.”
From De novo design of protein structure and function with RFdiffusion (2023) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“are the best and most accurate answer to the structure prediction problem to date”
From The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins (2024) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“DeepMind’s AlphaFold2 success in sequence-based protein structure prediction,4 as well as the RoseTTAFold70 open-source counterpart, and the publicly available AlphaFold2 prediction of all human proteins203 are major steps that benefit the scientific community.”
From AlphaFold, Artificial Intelligence (AI), and Allostery (2022) · cites this paper as [70]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The unprecedented accuracy of AlphaFold2,127 RosettaFold,128 and others129,130 offers, at least in principle, the opportunity to virtually screen any protein of interest with the structure-based approach, irrespective of its a priori ligandability (after AlphaFold2, the structural coverage of the human proteome increased from 48% to 76% of the total residues).131”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [128]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The programs were also shown to accurately assess their confidence at the level of individual residues and interdomain contacts (27,28,62).”
From AI-based structure prediction empowers integrative structural analysis of human nuclear pores (2022) · cites this paper as [27]
Experimental — accuracy not yet measured
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability
Katoh, K., & Standley, D. M. (2013) · Molecular Biology and Evolution · doi:10.1093/molbev/mst010 · Cited by 46,209
Features and development of Coot
Emsley, P., Lohkamp, B., Scott, W. G., & Cowtan, K. (2010) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910007493 · Cited by 29,915
Clustal W and Clustal X version 2.0
Larkin, M. A., Blackshields, G., Brown, N. P., Chenna, R., McGettigan, P. A., McWilliam, H., Valentin, F., Wallace, I. M., Wilm, A., Lopez, R., et al. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm404 · Cited by 28,358
Phaser crystallographic software
McCoy, A. J., Grosse-Kunstleve, R. W., Adams, P. D., Winn, M. D., Storoni, L. C., & Read, R. J. (2007) · Journal of Applied Crystallography · doi:10.1107/s0021889807021206 · Cited by 20,612
Self-citationSWISS-MODEL: homology modelling of protein structures and complexes
Waterhouse, A., Bertoni, M., Bienert, S., Studer, G., Tauriello, G., Gumienny, R., Heer, F. T., de Beer, T. A. P., Rempfer, C., Bordoli, L., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky427 · Cited by 13,067 · cited 2×
“Fortunately,theContinuousAutomated ModelEvaluation(CAMEO)experiment( 7 ) tests structure prediction servers blindly on protein structures as they are submitted to the PDB. RoseTTAFold has been evaluated since 15 May 2021 on CAMEO; over the 69 medium and hard targets released during this time (15 May 2021 to 19 June 20…”
UCSF ChimeraX: Structure visualization for researchers, educators, and developers
Pettersen, E. F., Goddard, T. D., Huang, C. C., Meng, E. C., Couch, G. S., Croll, T. I., Morris, J. H., & Ferrin, T. E. (2021) · Protein Science · doi:10.1002/pro.3943 · Cited by 9,514
Liebschner, D., Afonine, P. V., Baker, M. L., Bunkóczi, G., Chen, V. B., Croll, T. I., Hintze, B., Hung, L.-W., Jain, S., McCoy, A. J., et al. (2019) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798319011471 · Cited by 7,953
Self-citationUniProt: the Universal Protein knowledgebase
Apweiler, R. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh131 · Cited by 7,498
Towards automated crystallographic structure refinement with phenix.refine
Afonine, P. V., Grosse-Kunstleve, R. W., Echols, N., Headd, J. J., Moriarty, N. W., Mustyakimov, M., Terwilliger, T. C., Urzhumtsev, A., Zwart, P. H., & Adams, P. D. (2012) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444912001308 · Cited by 5,511
Self-citation
Research works printed but not linked: 2
- Bunkóczi G Read RJ phenix. ensembler: a tool for multiple superposition Comput Crystallogr Newsl 2011 2 8 9
- Vagin A Lebedev A ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES INT UNION CRYSTALLOGRAPHY 2 ABBEY SQ, CHESTER, CH1 2HU ENGLAND 2015 71 S19
Cited by
Items 1,701–1,800 of 5,636
Thorn, A. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102368 · Cited by 16
Generative artificial intelligence performs rudimentary structural biology modeling
Ille, A. M., Markosian, C., Burley, S. K., Mathews, M. B., Pasqualini, R., & Arap, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-69021-2 · Cited by 16
Structural assembly of the bacterial essential interactome
Gómez Borrego, J., & Torrent Burgas, M. (2024) · eLife · doi:10.7554/elife.94919 · Cited by 16
Accurate prediction of CDR-H3 loop structures of antibodies with deep learning
(2024) · doi:10.7554/elife.91512.4 · Cited by 16
“…et al., 2014 ; Almagro et al., 2011 ), and as a result, alternative artificial intelligence (AI)- based approaches, such as AlphaFold2 (AF2) ( Jumper and Hassabis, 2022 ; Jumper et al., 2021 ), trRosetta ( Du et al., 2021 ), and RoseTTAFold ( Baek et al., 2021 ), are increasing in popularity.”
BackgroundArsiwala, A., Bhatt, R., van Niekerk, L., Quintero-Cadena, P., Ao, X., Rosenbaum, A., Bhatt, A., Smith, A., Yang, Y., Anderson, K., et al. (2025) · mAbs · doi:10.1080/19420862.2025.2593055 · Cited by 16
“Recent advances in machine learning (ML), in particular, protein structure prediction and generative protein design, 21–23 are positively impacting the de novo design of antibody-binding characteristics.”
Odai, R., Leemann, M., Al-Murad, T., Abdullah, M., Shyrokova, L., Tenson, T., Hauryliuk, V., Durairaj, J., Pereira, J., & Atkinson, G. C. (2025) · Science Advances · doi:10.1126/sciadv.adz8560 · Cited by 16
Self-citationMining folded proteomes in the era of accurate structure prediction
Bayly-Jones, C., & Whisstock, J. C. (2022) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1009930 · Cited by 16
(2022) · doi:10.1016/j.freeradbiomed.2022.12.001 · Cited by 16
Exploration of O-GlcNAc transferase glycosylation sites reveals a target sequence compositional bias
(2023) · doi:10.1016/j.jbc.2023.104629 · Cited by 16
“Attaining more accurate predictions will likely require incorporation of structural and steric constraints, which may be facilitated by recent advances in structure prediction (82, 83).”
BackgroundAttSec: protein secondary structure prediction by capturing local patterns from attention map
(2023) · doi:10.1186/s12859-023-05310-3 · Cited by 16
“Many recent studies aim to predict this tertiary structure because several unique properties of protein can be derived from this structure [1–3].”
BackgroundGPCR molecular dynamics forecasting using recurrent neural networks
López-Correa, J. M., König, C., & Vellido, A. (2023) · Scientific Reports · doi:10.1038/s41598-023-48346-4 · Cited by 16
Uncertainty-Aware Graph Neural Networks: A Multihop Evidence Fusion Approach
Chen, Q., Li, S., Liu, Y., Pan, S., Webb, G. I., & Zhang, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3581083 · Cited by 40
Nature‐inspired hierarchical materials
Fu, Q., Baino, F., Saiz, E., Bai, H., & Mauro, J. C. (2025) · Journal of the American Ceramic Society · doi:10.1111/jace.70156 · Cited by 18
“278,279,291,292 Using the DL-based model AlphaFold 2, Demis Hassabis and John Jumper further optimized the accuracy of protein structure prediction to about 1 Å. 279,291 These advancements in protein structure prediction and engineering have significant implications for various fields, including…”
Multi-dimensional metagenomics
Peng, H., Ruiz-Moreno, A. J., & Fu, J. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00346-x · Cited by 21
“AI-driven tools like AlphaFold 76 , RoseTTAFold 77 , DeepARG 68 and ESMFold 78 use deep learning models trained on large datasets of known protein structures to predict the 3D conformations of both known and unknown proteins.”
Artificial intelligence for nanomedicine
Song, X., Gao, X., Wang, H., Yu, F., Qin, M., Li, Y., Liu, Y., Feng, W., Zhou, C., Chukavin, N. N., et al. (2025) · Science China Chemistry · doi:10.1007/s11426-025-2942-5 · Cited by 21
Computational design of transmembrane proteins
Zhu, J., & Lu, P. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102381 · Cited by 18
Neuromuscular disorders: finding the missing genetic diagnoses
Koczwara, K. E., Lake, N. J., DeSimone, A. M., & Lek, M. (2022) · Trends in Genetics · doi:10.1016/j.tig.2022.07.001 · Cited by 19
Ubiquitin and ubiquitin-like conjugation systems in trypanosomatids
Burge, R. J., Mottram, J. C., & Wilkinson, A. J. (2022) · Current Opinion in Microbiology · doi:10.1016/j.mib.2022.102202 · Cited by 16
Kwon, S., & Seok, C. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.11.047 · Cited by 16
“Despite the huge leap in protein structure prediction using deep learning [2,3,6], computational prediction of protein-compound complex structure, called protein–ligand docking, is still an unsolved problem [7,8].”
BackgroundSun, Y.-Y., Liu, K., Zhang, C., Ni, Z., Zhu, Y., Bao, H., Chen, L., Ye, W., Huo, S.-X., Huo, S.-X., et al. (2023) · Antiviral Research · doi:10.1016/j.antiviral.2023.105548 · Cited by 16
Malaga, W., Payros, D., Meunier, E., Frigui, W., Sayes, F., Pawlik, A., Orgeur, M., Berrone, C., Moreau, F., Mazères, S., et al. (2023) · PLoS Pathogens · doi:10.1371/journal.ppat.1011437 · Cited by 16
“To further outline the 3D architecture of PhoR, the PhoR amino acid sequence was submitted to RoseTTAFold [27] at https://robetta.bakerlab.org/ and the resulted prediction was compared to the prediction retrieved from the AlphaFold Protein Structure Database [28] at https://alphafold.ebi.ac.uk/entry/P71815.”
MethodRcheulishvili, N., Mao, J., Papukashvili, D., Feng, S., Liu, C., Wang, X., He, Y., & Wang, P. G. (2023) · Frontiers in Microbiology · doi:10.3389/fmicb.2023.1203355 · Cited by 17
“The 3D structure of the designed vaccine was constructed via RoseTTAFold (Baek et al., 2021).”
MethodCrystal Structure of de Novo Designed Coiled-Coil Protein Origami Triangle
Satler, T., Hadži, S., & Jerala, R. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.3c05531 · Cited by 16
Machine Learning Enables Prediction of Pyrrolysyl-tRNA Synthetase Substrate Specificity
Zhang, Q., Zheng, W., Song, Z., Zhang, Q., Yang, L., Wu, J., Lin, J., Xu, G., & Yu, H. (2023) · ACS Synthetic Biology · doi:10.1021/acssynbio.3c00225 · Cited by 18
Choi, W.-Y., Wu, H., Yserentant, K., Huang, B., & Cheng, Y. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2302471120 · Cited by 19
Yu, Q., Feng, C., Liang, S., Benjakul, S., Tan, Y., Luo, Y., & Hong, H. (2023) · Food Hydrocolloids · doi:10.1016/j.foodhyd.2023.109117 · Cited by 17
Liu, X., Shi, L., Khashaveh, A., Shan, S., Lv, B., Gu, S., & Zhang, Y. (2023) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.3c04247 · Cited by 16
Stuart, D. D., Guzman-Perez, A., Brooijmans, N., Jackson, E. L., Kryukov, G. V., Friedman, A. A., & Hoos, A. (2023) · Cancer Discovery · doi:10.1158/2159-8290.cd-23-0280 · Cited by 22
Maurer, S. K., Mayer, M. P., Ward, S. J., Boudjema, S., Halawa, M. R., Zhang, J., Caulton, S. G., Emsley, J., & Dreveny, I. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.105300 · Cited by 17
“…large loops and insertions are common in many proteins and can be ever better predicted using ab initio folding and homology modeling methods (43, 52), this approach will 32)) structure in complex with a Lys 6 -linked diubiquitin substrate ( wheat color ) highlighting that the triple glycine in…”
BackgroundNicastro, G. G., Burroughs, A. M., Iyer, L. M., & Aravind, L. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad879 · Cited by 17
Drug Repurposing: Insights into Current Advances and Future Applications
Bhatia, T., & Sharma, S. (2023) · Current Medicinal Chemistry · doi:10.2174/0109298673266470231023110841 · Cited by 19
Arragain, B., Pelosse, M., Thompson, A., & Cusack, S. (2023) · Nature Communications · doi:10.1038/s41467-023-44044-x · Cited by 16
“In addition, the uniqueness of the putative TiLV encoded proteins, apart from a recognisable polymerase PB1-like subunit, precludes hypotheses as to protein function based on sequence homology or structure prediction using Alphafold 11 or RoseTTAfold 12 .”
Bastos, L. L., Mariano, D., Lemos, R. P., Bialves, T. S., Oliveira, C. J. F., & de Melo-Minardi, R. C. (2024) · Immuno · doi:10.3390/immuno4010002 · Cited by 17
“AlphaFold can potentially accelerate drug discovery, enhancing our comprehension of diseases at a molecular level and helping the development of novel treatments and therapies [105,109,110].”
BackgroundZeng, W., Lv, D., Liu, X., Chen, G., Liu, W., & Peng, S. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385509 · Cited by 17
“Despite recent breakthroughs in the field of protein structure prediction by AlphaFold2 [21] and RoseTTAFold [22], the accuracy of predicted 3D structure cannot be fully trusted, especially on orphan proteins that lack high-quality MSA information.”
BackgroundDesign of Functional Globular β‐Sheet Miniproteins
Pham, T. L., & Thomas, F. (2024) · ChemBioChem · doi:10.1002/cbic.202300745 · Cited by 16
Identifying virulence factors using graph transformer autoencoder with ESMFold-predicted structures
Li, G., Bai, P., Chen, J., & Liang, C. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108062 · Cited by 17
Attenuation of phytofungal pathogenicity of Ascomycota by autophagy modulators
Woo, J., Jung, S., Kim, S., Li, Y., Chung, H., Roubtsova, T. V., Zhang, H., Caseys, C., Kliebenstein, D. J., Kim, K., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45839-2 · Cited by 19
Promoter regulatory mode evolution enhances the high multidrug resistance of tmexCD1-toprJ1
Wang, C.-Z., Yang, J., Xu, Z., Lv, L., Chen, S., Hong, M., & Liu, J. (2024) · mBio · doi:10.1128/mbio.00218-24 · Cited by 16
Computational and bioinformatics tools for understanding disease mechanisms
Athar, M., Manhas, A., Rana, N., & Irfan, A. (2024) · Biocell · doi:10.32604/biocell.2024.049891 · Cited by 19
Generative adversarial networks in protein and ligand structure generation: a case study
Faizi, S. A. A., Singh, N. K., Kamal, A., & Raza, K. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-22299-3.00014-1 · Cited by 22
Data hazards in synthetic biology
Zelenka, N., Cara, N. H. D., Sharma, K., Sarvaharman, S., Ghataora, J. S., Parmeggiani, F., Nivala, J., Abdallah, Z. S., Marucci, L., & Gorochowski, T. E. (2024) · Synthetic Biology · doi:10.1093/synbio/ysae010 · Cited by 18
Resource analysis of quantum algorithms for coarse-grained protein folding models
Linn, H., Lyngfelt, I., García-Álvarez, L., & Johansson, G. (2024) · Physical Review Research · doi:10.1103/physrevresearch.6.033112 · Cited by 18
Structural prediction of GluN3 NMDA receptors
Liu, Y., Shao, D., Lou, S., & Kou, Z. (2024) · Frontiers in Physiology · doi:10.3389/fphys.2024.1446459 · Cited by 17
Xu, L., Jang, H., & Nussinov, R. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01392 · Cited by 16
Conditioned Protein Structure Prediction
(2024) · doi:10.1103/prxlife.2.043001 · Cited by 16
Applying Spatiotemporal Modeling of Cell Dynamics to Accelerate Drug Development
Chen, X., Xu, S., Chu, B., Guo, J., Zhang, H.-K., Sun, S.-Y., Song, L., & Feng, X. (2024) · ACS Nano · doi:10.1021/acsnano.4c12599 · Cited by 18
Song, J., Ha, J., Lee, J., Ko, J., & Shin, W. (2024) · Scientific Reports · doi:10.1038/s41598-024-75400-6 · Cited by 24
Vergalli, J., Réfrégiers, M., Ruggerone, P., Winterhalter, M., & Pagès, J. (2024) · Communications Biology · doi:10.1038/s42003-024-07168-4 · Cited by 19
PDB-IHM: A System for Deposition, Curation, Validation, and Dissemination of Integrative Structures
Vallat, B. K., Webb, B., Zalevsky, A. O., Tangmunarunkit, H., Sekharan, M. R., Voinea, S., Shafaeibejestan, A., Sagendorf, J. M., Hoch, J. C., Kurisu, G., et al. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.168963 · Cited by 18
Yao, Y., Chen, F., Wu, C., Chang, X., Cheng, W., Wang, Q., Deng, Z., Liu, T., & Lü, L. (2025) · Plant Biotechnology Journal · doi:10.1111/pbi.70002 · Cited by 18
“The advanced artificial intelligence-driven accurate prediction of protein structures, such as AlphaFold2 and RoseTTAFold, presents great potential in precise virtual screening.”
InfluentialToward deep learning sequence–structure co-generation for protein design
Wang, C., Alamdari, S., Domingo-Enrich, C., Amini, A. P., & Yang, K. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103018 · Cited by 24
Cheng, S., Chen, Y., Cao, Y. H., Huang, X., Liu, B., Liu, M., Jiang, S., & Jiang, L. (2025) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2025.105216 · Cited by 17
Predicting the structural impact of human alternative splicing
Song, Y., Zhang, C., Omenn, G. S., O’Meara, M. J., & Welch, J. D. (2025) · Genome biology · doi:10.1186/s13059-025-03744-x · Cited by 22
“Most recently, neural network approaches such as AlphaFold2 and RoseTTAFold have enabled high-precision protein structure prediction [16, 17].”
Golinelli‐Pimpaneau, B. (2021) · Inorganics · doi:10.3390/inorganics10010002 · Cited by 16
“In addition, Baker’s group developed a related three-track network named RoseTTAFold that integrates information at the one-dimensional (sequence), twodimensional (distance between pairs of amino acids) and three-dimensional (coordinate) levels to produce structure predictions with accuracies approaching those of Deep…”
BackgroundParasitology meets cryo-electron tomography – exciting prospects await
Theveny, L. M., Mageswaran, S. K., Chen, W. D., Martinez, M. P., Guérin, A., & Chang, Y. (2022) · Trends in Parasitology · doi:10.1016/j.pt.2022.01.006 · Cited by 16
Peptide Toxins as Biothreats and the Potential for AI Systems to Enhance Biosecurity
Lee, Y.-C. J., Cowan, A. J., & Tankard, A. (2022) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2022.860390 · Cited by 16
“Further iterations of BAIN with expanded computing resources may predict peptide and protein structures as well as potentially concerning peptide or protein interactions of all synthesis orders by integrating with existing programs such as RoseTTAFold and DeepMind ’ s AlphaFold2 (Baek et al., 2021; Jumper et al., 2021…”
MethodDeep Learning-Powered Prediction of Human-Virus Protein-Protein Interactions
Yang, X., Yang, S., Ren, P., Wuchty, S., & Zhang, Z. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.842976 · Cited by 20
“Indeed, Baek et al. (2021) have taken the initiative to employ two DL-based structure prediction methods (i.e., RoseTTAFold and AlphaFold2) to systematically detect PPIs and construct accurate 3D models of protein complexes within the yeast proteome (Humphreys et al., 2021), which will be used for…”
MethodActivity-based annotation: the emergence of systems biochemistry
Rhee, K. Y., Jansen, R. S., & Grundner, C. (2022) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2022.03.017 · Cited by 16
An ancient function of PGR5 in iron delivery?
Leister, D., Marino, G., Minagawa, J., & Dann, M. (2022) · Trends in Plant Science · doi:10.1016/j.tplants.2022.04.006 · Cited by 17
(2022) · doi:10.1021/acssynbio.2c00176 · Cited by 16
Chen, H., Zhong, L., Zhou, H., Sun, T., Zhong, G., Tu, Q., Zhuang, Y., Bai, X., Wang, X., Xu, J., et al. (2022) · Angewandte Chemie International Edition · doi:10.1002/anie.202203591 · Cited by 16
Receptor control by membrane-tethered ubiquitin ligases in development and tissue homeostasis
Lebensohn, A. M., Bazán, J. F., & Rohatgi, R. (2022) · Current topics in developmental biology/Current Topics in Developmental Biology · doi:10.1016/bs.ctdb.2022.03.003 · Cited by 19
Trifan, A., Gorgun, D., Salim, M., Brace, A., Zvyagin, M., Ma, H., Clyde, A., Clark, D., Salim, M., Hardy, D. J., et al. (2022) · The International Journal of High Performance Computing Applications · doi:10.1177/10943420221113513 · Cited by 22
Guo, S., Li, Y., Chen, P., Zhang, G., Wang, H., Jiang, H.-M., Liu, W., Xu, J.-P., Ding, X., Fu, P., et al. (2022) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2022.102440 · Cited by 19
“predict protein structure based on the amino acid sequence of a protein, particularly template-free modeling (61) using artificial intelligence (AI) deep machine learning algorithms such as Robetta (62) and AlphaFold (63).”
BackgroundMethodInfluentialde Abreu, V. A. C., Alves, R. M., Silva, S. R., Ferro, J. A., Domingues, D. S., Miranda, V. F. O., & Varani, A. M. (2022) · Gene · doi:10.1016/j.gene.2022.146904 · Cited by 16
Analytic modeling of inhomogeneous-resolution maps in cryo-electron microscopy and crystallography
Urzhumtsev, A., & Lunin, V. Y. (2022) · IUCrJ · doi:10.1107/s2052252522008260 · Cited by 16
Structural Basis of Activation and Antagonism of Receptor Signaling Mediated by Interleukin-27
Składanowska, K., Bloch, Y., Strand, J., White, K., Hua, J., Aldridge, D. L., Welin, M., Logan, D. T., Soete, A., Merceron, R., et al. (2022) · Cell Reports · doi:10.1016/j.celrep.2022.111490 · Cited by 16
New opportunities in integrative structural modeling
Ziemianowicz, D. S., & Kosiński, J. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102488 · Cited by 20
A subclass of archaeal U8-tRNA sulfurases requires a [4Fe–4S] cluster for catalysis
He, N., Zhou, J., Bimaï, O., Oltmanns, J., Ravanat, J., Velours, C., Schünemann, V., Fontecave, M., & Golinelli‐Pimpaneau, B. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac1156 · Cited by 16
Bioinformatic Approaches for Characterizing Molecular Structure and Function of Food Proteins
Helmick, H. D. B., Jain, A., Terashi, G., Liceaga, A. M., Bhunia, A. K., Kihara, D., & Kokini, J. L. (2023) · Annual Review of Food Science and Technology · doi:10.1146/annurev-food-060721-022222 · Cited by 19
EFMC: Trends in Medicinal Chemistry and Chemical Biology
Auberson, Y. P., Arimondo, P. B., Duca, M., Essig, S., Grether, U., Rufer, A. C., Sbardella, G., Schopfer, U., Torrens, A., van der Stelt, M., et al. (2023) · ChemBioChem · doi:10.1002/cbic.202200690 · Cited by 18
Yang, T., Chen, Y., Xu, Y., Liu, X., Yang, M., & Mao, C. (2023) · Materials Science and Engineering R Reports · doi:10.1016/j.mser.2023.100715 · Cited by 18
Citores, L., Ragucci, S., Russo, R., Gay, C. C., Chambery, A., Maro, A. D., Iglesias, R., & Ferreras, J. M. (2023) · Protein Science · doi:10.1002/pro.4621 · Cited by 16
Rush, K. W., Eastman, K. A. S., Kincannon, W. M., Blackburn, N. J., & Bandarian, V. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.3c00831 · Cited by 16
Alfonso‐Prieto, M., & Capelli, R. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00380 · Cited by 18
Mei, Y., Chen, H., Yang, B. K., Zhao, J., Zhang, H., & Chen, W. (2023) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.3c00857 · Cited by 16
GraphGPSM: a global scoring model for protein structure using graph neural networks
He, G., Liu, J., Liu, D., & Zhang, G. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad219 · Cited by 16
Exploring new horizons: Empowering computer-assisted drug design with few-shot learning
Mendonça, S. S., Vitória, A. R. S., de Lima, T. W., Filho, A. R. G., & Andrade, C. H. (2023) · Artificial Intelligence in the Life Sciences · doi:10.1016/j.ailsci.2023.100086 · Cited by 19
CASP15 cryo‐EM protein and RNA targets: Refinement and analysis using experimental maps
Mulvaney, T., Kretsch, R. C., Elliott, L., Beton, J. G., Kryshtafovych, A., Rigden, D. J., Das, R., & Topf, M. (2023) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26644 · Cited by 15
Challenges and frontiers of computational modelling of biomolecular recognition
Wang, J., Bhattarai, A., Do, H. N., & Miao, Y. (2022) · QRB Discovery · doi:10.1017/qrd.2022.11 · Cited by 16
Self-citationTM-Vec: template modeling vectors for fast homology detection and alignment
Hamamsy, T., Morton, J. T., Berenberg, D., Carriero, N., Gligorijevic, V., Blackwell, R., Strauss, C. E. M., Leman, J. K., Cho, K., & Bonneau, R. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.07.25.501437 · Cited by 17
Microphase separation produces interfacial environment within diblock biomolecular condensatesPreprint
Latham, A. P., Zhu, L., Sharon, D. A., Ye, S., Willard, A. P., Zhang, X., & Zhang, B. (2025) · eLife · doi:10.7554/elife.90750 · Cited by 23
“These simulations began from RoseTTAFold predictions of the peptide structure ( Baek et al., 2021 ; Bonneau et al., 2001 ) and lasted for 1 μs in the NPT ensemble.”
Proteus: Exploring Protein Structure Generation for Enhanced Designability and EfficiencyPreprint
Wang, C., Qu, Y., Peng, Z., Wang, Y., Zhu, H., Chen, D., & Cao, L. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.10.579791 · Cited by 28
P( all-atom ) Is Unlocking New Path For Protein DesignPreprint
Qu, W., Guan, J., Ma, R., Zhai, K., Wu, W., & Wang, H. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.16.608235 · Cited by 21
Deep Local Analysis evaluates protein docking conformations with locally oriented cubes
Mohseni Behbahani, Y., Crouzet, S., Laine, E., & Carbone, A. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac551 · Cited by 16
How accurately can one predict drug binding modes using AlphaFold models?
Karelina, M., Noh, J. J., & Dror, R. O. (2023) · doi:10.7554/elife.89386.1 · Cited by 16
Nordquist, E. B., Zhao, M., Kumar, A., & MacKerell, A. D. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01189 · Cited by 15
Probing the modulation of enzyme kinetics by multi-temperature, time-resolved serial crystallography
Schulz, E. C., Prester, A., von Stetten, D., Gore, G., Hatton, C. E., Bartels, K., Leimkohl, J.-P., Schikora, H., Ginn, H. M., Tellkamp, F., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-61631-2 · Cited by 15
AlphaFold Protein Structure Database for Sequence-Independent Molecular Replacement
Chai, L., Zhu, P., Chai, J., Pang, C., Andi, B., McSweeney, S., Shanklin, J., & Liu, Q. (2021) · Crystals · doi:10.3390/cryst11101227 · Cited by 15
Hallucination of closed repeat proteins containing central pockets
An, L., Hicks, D. R., Zorine, D., Dauparas, J., Wicky, B. I. M., Milles, L. F., Courbet, A., Bera, A. K., Nguyen, H., Kang, A., et al. (2023) · Nature Structural & Molecular Biology · doi:10.1038/s41594-023-01112-6 · Cited by 15
Self-citationMalbranke, C., Rostain, W., Depardieu, F., Cocco, S., Monasson, R., & Bikard, D. (2023) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1011621 · Cited by 15
“Structural biology has been a field of major breakthroughs these last years with the increasing success of Deep Learning models for secondary structure prediction [47, 48], ligand or protein binding site prediction [49, 50] and of course tertiary structure prediction with frameworks such as AlphaFold2 [20], RoseTTAFol…”
BackgroundHartley, S. M., Tiernan, K. A., Ahmetaj, G., Cretu, A., Zhuang, Y., & Zimmer, M. (2022) · PLOS ONE · doi:10.1371/journal.pone.0267560 · Cited by 15
“AlphaFold2[1, 2] and RoseTTAfold[3] are two freely available programs that can predict threedimensional protein structures from their amino acid sequence with atomic accuracy.”
BackgroundKulikova, A. V., Diaz, D. J., Chen, T., Cole, T. J., Ellington, A. D., & Wilke, C. O. (2023) · Scientific Reports · doi:10.1038/s41598-023-40247-w · Cited by 15
The coming wave of confluent biosynthetic, bioinformational and bioengineering technologies
Pretorius, I. S., Dixon, T. A., Boers, M., Paulsen, I. T., & Johnson, D. L. (2025) · Nature Communications · doi:10.1038/s41467-025-58030-y · Cited by 21
“Recent years have seen exciting breakthroughs in the application of machine learning to protein structure prediction 43,44 and to protein design 45,46 culminating in the award of the 2024 Nobel Prize for Chemistry.”
Wang, W., Peng, Z., & Yang, J. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01223-x · Cited by 20
Haas, C. M., Jasti, N., Dosey, A. M., Allen, J. D., Gillespie, R. A., McGowan, J., Leaf, E. M., Crispin, M., DeForest, C. A., Kanekiyo, M., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2409566122 · Cited by 15
A survey on large language models in biology and chemistry
Ashyrmamatov, I., Gwak, S. J., Jin, S.-Y., Jun, I., Ucak, U. V., Lee, J. Y., & Lee, J. (2026) · Experimental & Molecular Medicine · doi:10.1038/s12276-025-01583-1 · Cited by 17
“The application of transformer architectures to biological problems has led to substantial breakthroughs, with AlphaFold2 (AF2) 10 and RoseTTA-Fold 11 emerging as landmark models in protein structure prediction.”
Ultra-large virtual screening unveils potent agonists of the neuromodulatory orphan receptor GPR139
de Vaca, I. C., Trapkov, B., Shen, L., Vo, D. D., Zhang, X., Yang, Y., Pezeshki, M., Zhang, X., Bällgren, F., Saleh, A., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-66845-y · Cited by 22
Narra, M., Ray, A., Polley, B., Yang, H., & Bhowmik, P. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1718810 · Cited by 21
“However, advances in machine learning, particularly structure prediction tools like AlphaFold (Senior et al., 2020), AlphaFold2 (Jumper et al., 2021), and RoseTTAFold (Baek et al., 2021), have signi fi cantly improved the prediction of protein structures and functions.”
Alshorman, J., Mehran, M. J., Bahrami, Y., Mohammadzadeh, S., Barzigar, R., Morshedi, M., Haider, K. H., Tembo, K. M., Rong, S.-J., Jadgal, N., et al. (2026) · Clinical and Experimental Medicine · doi:10.1007/s10238-026-02107-5 · Cited by 22
“However, antibody structure prediction remains challenging because antibodies exhibit high conformational variabil - ity, particularly in the CDR H3 loop, and general protein structure predictors can underperform in these regions( 66, 141).”
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.