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 3,801–3,900 of 5,636
Evaluating In‐Context Learning in Large Language Models for Molecular Property Regression
Joe, C. Y., Song, K., & Chang, R. (2026) · Journal of Computational Chemistry · doi:10.1002/jcc.70308 · Cited by 3
Predicting protein interfaces in the age of AlphaFold: Why dynamics and disorder remain a challenge
Omidi, A., Bui, J. M., & Gsponer, J. A. (2026) · Cell Systems · doi:10.1016/j.cels.2025.101508 · Cited by 2
Judge, E., Gramatikoff, K., Milović, L., Minchev, A., & Karabaliev, M. (2026) · The EuroBiotech Journal · doi:10.2478/ebtj-2026-0001 · Cited by 2
“Structure-based simulations and folding predictions enable rapid in silico screening [42].”
Jiang, S., Li, X., Zhao, L., Bai, S., Zhang, D., Meng, H., Cui, Z., Wang, X., Yu, B., & Liu, Y. (2026) · Food Chemistry · doi:10.1016/j.foodchem.2026.148158 · Cited by 2
Advances in Crystallography and Cryo-Electron Microscopy for the Study of Membrane Proteins
Megta, A. K., Punetha, A., Kumari, J., Wei, H., Rosario-Garrido, S., Tranos, J. A., & Petrou, V. I. (2026) · Advances in experimental medicine and biology · doi:10.1007/978-3-032-07523-9_4 · Cited by 2
Yavaş, C., Abuaisha, A. M., Nekay, E., Gezdirici, A., Yilmaz, H. I., Akbulut, E., & Arıcan, P. (2026) · Molecular Biology Reports · doi:10.1007/s11033-026-11496-5 · Cited by 3
“3), protein models were modeled using RosettaFold modeling algo-rithm with ab-initio modeling approach [ 13].”
Deep Learning Meets Synthetic Biology: Applications Across Molecular, Cellular, and Metabolic Scales
Zhao, Y., Yang, C., Xue, B., Liu, H., Wang, S., & Su, H. (2026) · Green Carbon · doi:10.1016/j.greenca.2025.11.003 · Cited by 3
Kamboj, S., & Kumar, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-34059-8.00002-6 · Cited by 3
Introduction to artificial intelligence in multi-omics analysis
Saha, A., Pal, R. K., & Saha, S. (2026) · Progress in molecular biology and translational science · doi:10.1016/bs.pmbts.2026.01.022 · Cited by 2
Beck, J., & Romero‐Romero, S. (2026) · Biochemical Society Transactions · doi:10.1042/bst20253060 · Cited by 3
SARS-CoV-2 Spike Protein XBB.1.5 Mutations Altered Four Conserved Antigenic Determinants
Akbulut, E., Yildirim, M., & Kahraman, H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27041940 · Cited by 3
“In parallel, single-stranded SARS-CoV-2 S protein sequences (wild-type and XBB.1.5) were modeled using the RoseTTAFold option of the Robetta structure prediction server [53].”
InfluentialHarnessing AI to decode protein kinases: Structural, functional, and therapeutic design perspectives
Gomari, M. M., Ntwali, P. V. M., Choupani, E., & Ashayeri, N. (2026) · New Biotechnology · doi:10.1016/j.nbt.2026.02.010 · Cited by 2
De novo engineering of protein interactions: Retrospective and current advances
Khramushin, A., Elizarova, E., & Correia, B. E. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103240 · Cited by 3
The emerging role of high-throughput proteomics in advancing precision medicine
You, J., Deng, Y., Chen, L., Wang, L., Guo, Y., Li, Z.-Y., Feng, J., Yu, Y., & Cheng, W. (2026) · 中国科学通报:英文版 · doi:10.1016/j.scib.2026.02.054 · Cited by 4
Jamasb, A. R., Torné, R. V., Ma, E. J., Du, Y., Harris, C., Huang, K., Hall, D., Liò, P., & Blundell, T. L. (2022) · neural information processing systems · doi:10.52202/068431-1969 · Cited by 4
“Recent developments in protein folding have given rise to an explosion of structural data available to machine learning practitioners [1, 2].”
BackgroundRomero-Martínez, D., Gasteazoro, F., Cofas‐Vargas, L. F., Garcia-Hernandez, E., González‐Davis, O., Zavala, G., Rosiles-Becerril, D., Vázquez-Duhalt, R., Trujillo‐Roldán, M. A., & Valdez‐Cruz, N. A. (2026) · Microbial Cell Factories · doi:10.1186/s12934-026-02949-4 · Cited by 2
“Consistent with the Boltz-1 prediction, other algorithms such as AlphaFold [102], RobettaFold [103], and I-TASSER [104] also predict a high helical content in the aggregator peptide fused to the laccase (data not shown).”
Cao, S., Zhang, C., Ning, Z., Li, C., Mao, Q., Cao, Z., Ge, Y., Wu, Y., Guo, J., Cao, Q., et al. (2026) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01807 · Cited by 2
Toward universal binder discovery: Advances in display, computational design and in vivo platforms
Yang, J. K., Pineda, E., & Dickinson, B. C. (2026) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2026.102663 · Cited by 2
Need for speed: advances in the era of high throughput interaction proteomics
Frommelt, F., Uliana, F., Aebersold, R. H., & Fossati, A. (2026) · Molecular Omics · doi:10.1093/molecular-omics/aaiag012 · Cited by 3
The APOL1 variant p.N264K is predicted to block ion flow by occluding a pore at the cell surface
Höffken, V., Console, L., Nelde, N., Pavenstädt, H., Indiveri, C., & Weide, T. (2026) · Life Science Alliance · doi:10.26508/lsa.202503570 · Cited by 2
Plant structural biology: Emerging technologies and future biological insights
Böhm, J. M., & Maurino, V. G. (2026) · The Plant Journal · doi:10.1111/tpj.70786 · Cited by 2
“Computational advances, especially the advent of AI-driven structure prediction tools such as AlphaFold (Abramson et al., 2024; Chen, Zia, et al., 2024; Jumper & Hassabis, 2022) and RoseTTAFold (Baek et al., 2021; Chen, Li, et al., 2024), have further broadened the scope of structural biology, even providing models fo…”
Structural mass spectrometry techniques for characterisation of plant and algal proteins
Durant, R. J., Živković, D., & Bolla, J. R. (2026) · The Plant Journal · doi:10.1111/tpj.70780 · Cited by 2
“At the same time, highly accurate protein structure prediction tools such as AlphaFold and Roset-taFold have reduced the need to solve every structure de novo by XRC or cryo-EM (Baek et al., 2021; Gould et al., 2024).”
AXIS: a Lab-in-the-Loop machine learning approach for automated detection of macromolecular crystals
Personnaz, A., Sung, S., Bourgeas, R., Unni, S., Dupeux, F., Adediran, B., Barbosa, R. L., Humm, A.-S., Osorio, E. C., & Márquez, J. A. (2026) · IUCrJ · doi:10.1107/s2052252526001399 · Cited by 2
MUFLIKHATI, Z., Mangindaan, D., & Enyi, C. U. (2026) · Scientific Reports · doi:10.1038/s41598-026-45190-0 · Cited by 5
“These findings are consistent with reports that AlphaFold2 can achieve near-crystal accuracy in enzyme structure prediction 19,66 .”
Machine learning for evolutionary genetics and molecular evolution
Svetec, N., Lee, U., & Zhao, L. (2026) · Trends in Genetics · doi:10.1016/j.tig.2026.01.013 · Cited by 2
IDPForge: deep learning of proteins with global and local regions of disorder
Castro, S. D., Zhang, O., Liu, Z. H., Forman-Kay, J. D., & Head-Gordon, T. L. (2026) · Nature Communications · doi:10.64898/2026.03.25.714313 · Cited by 5
Descent from a common ancestor restricts exploration of protein sequence space
Isakova, L. H., Streltsova, E., Bochkareva, O., Vlasov, P. K., & Kondrashov, F. A. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2532018123 · Cited by 6
Yensii, N. G., Bella-Omunagbe, M., Dokunmu, T. M., Antonio‐Nkondjio, C., Adebayo, A. H., & Ogunlana, O. O. (2026) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2026.109055 · Cited by 2
ConforFold recovers alternative protein conformations beyond MSA subsampling
Syrlybaeva, R., & Strauch, E. (2026) · Protein Science · doi:10.1002/pro.70564 · Cited by 2
“To further introduce variability, 6% of MSA positions were randomly mutated.”
InfluentialAliFilter: a machine learning approach to alignment filtering
Bianchini, G., Zhu, R., Cicconardi, F., & Moody, E. R. R. (2026) · Molecular Biology and Evolution · doi:10.1093/molbev/msag097 · Cited by 3
AI-driven discovery in protein science for immunology and infectious disease research
Helmy, M., Shafei, F. S. E., Pellegrina, D. V. D. S., Jin, L., Alhossary, A., Wilson, H. L., Mansour, T. A., & Selvarajoo, K. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1760257 · Cited by 2
“Other tools, such as RoseTTAFold and ESMFold (Baek et al., 2021; Lin et al., 2023), have extended these advances, while GenAI-driven models like ProteinMPNN and RFdiffusion now enable de novo protein design with greater efficiency and diversity than conventional pipelines, as reported by their authors (Watson et al.,…”
Molecular Modeling of the Pathogenetic Mechanisms of Neuropsychiatric Disorders
Abdurazakov, A., Abashkin, D. A., Semina, E. V., Chaika, Y. A., & Golimbet, V. E. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27083563 · Cited by 2
Decoding viral evolution through integrative bioinformatics: From genomes to global health
木村, 龍., Hayashi, Y., Fujimoto-Sato, Y., Ishii, H., Suzuki, Y., Katayama, K., Mizukoshi, F., Ryo, A., & Kimura, H. (2026) · Virology · doi:10.1016/j.virol.2026.110920 · Cited by 2
Drug Discovery of Antiviral Inhibitors Targeting Dengue Virus NS4B Protein
Pang, S., Qiu, X., Cai, Z., Zhong, Z., Jiang, H., Zhou, J., & Xu, J. (2026) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.6c00091 · Cited by 2
Repertoire-scale antibody structural prediction informs therapeutic design
Sang, Z., Xiang, Y., Huang, W., Sargunas, P. R., Kim, Y. J., Feng, Z., Taylor, D. J., & Shi, Y. (2026) · Science Advances · doi:10.1126/sciadv.aef7163 · Cited by 4
Yang, J. H., & Bashor, C. J. (2026) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2026.115883 · Cited by 4
Cheng, X., Tang, Z., Li, Z., Hu, S., Qin, K., Zhao, Y., Hao, B., & Hu, Q. (2026) · Chinese Journal of Natural Medicines · doi:10.1016/s1875-5364(26)61178-8 · Cited by 3
AI-driven insights into protein misfolding and innate immunity in neurodegenerative diseases
Deng, H. X., Cao, J. L., Yao, W., Jiang, S. J., Fang, Q. Q., Zhu, B. Y., & Jiang, Y. J. (2026) · Frontiers in Immunology · doi:10.3389/fimmu.2026.1814357 · Cited by 2
“This design allows the model to achieve reliable three-dimensional protein structure predictions relatively quickly and at lower computational cost, striking a favorable balance between prediction accuracy and computational ef fi ciency (163 – 165).”
Fan, Z. (2026) · Cancer Letters · doi:10.1016/j.canlet.2026.218578 · Cited by 4
Cao, J., Wang, M., Han, Y., Fu, S., She, Y., Yang, X., Wang, J., & EL-Aty, A. M. A. (2026) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.6c01905 · Cited by 2
Self-citationMembrane Protein Folding and Biogenesis: Insights from Single-Molecule Force Spectroscopy
Kim, S. A., Kim, S., Nam, J., Kim, E., Yoon, T., & Min, D. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c01097 · Cited by 2
Wu, L., Liu, H., Zhao, S., Qin, L., Li, J., Wang, J., Dai, Z., Gu, J., Xu, Y., Li, F., et al. (2026) · Advanced Science · doi:10.1002/advs.75853 · Cited by 2
“Offering a potential solution to this problem, the recent proliferation of AI-based protein structure prediction tools, such as AlphaFold [ 18 ], ESMfold [ 19 ], and RoseTTAFold [ 20 ], has enabled rapid and facile access to massive sets of protein structures.”
Self-citationDeep learning mechanism and its application in biomacromolecules
Li, H., Zhang, G., Yan, B., Ye, Z. P., Zhen, X., & Liu, Y. (2026) · RSC Advances · doi:10.1039/d6ra00550k · Cited by 2
Human antibodies as emerging drugs for antimicrobial resistance
Ridelfi, M., Fonseca, V. Z. G., Sala, C., & Rappuoli, R. (2026) · Trends in Immunology · doi:10.1016/j.it.2026.04.003 · Cited by 2
Colucci, M., Riplinger, C., Altun, A., Neese, F., & Bistoni, G. (2026) · ACS Central Science · doi:10.1021/acscentsci.6c00336 · Cited by 2
Challenges and Vision for Standardization of Biopolymer Data Sets for Machine Learning
Lalonde, J. N., Çırcı, D., Marrone, B. L., Zauscher, S., & Brinson, L. C. (2026) · Biomacromolecules · doi:10.1021/acs.biomac.6c00211 · Cited by 3
Lysozyme revisited: evaluating models of a reference protein in structural biology
Wlodawer, A., Rubach, P., Dauter, Z., Dec, W., Brzeziński, D., Jaskólski, M., & Minor, W. (2026) · Current Research in Structural Biology · doi:10.1016/j.crstbi.2026.100192 · Cited by 2
“…particular macromolecule, but also, with increasing importance, as training sets for computational structure prediction, exemplified by the various versions of AlphaFold (Jumper et al., 2021; Abramson et al., 2024), RoseTTAFold (Baek et al., 2021), or ESMfold (Lin et al., 2023), to name just a few.”
Wang, Z., Liu, Y., Zeng, T., Li, D., Shi, X., Zhang, J., Wang, H., Shi, L., Zhang, J., Bai, Y., et al. (2026) · Soft Matter · doi:10.1039/d6sm00125d · Cited by 2
Prediction of protein–protein interactions and co-complex models with deep learning
Zhang, Z., Liu, Y., & Yu, H. (2026) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2026.102703 · Cited by 3
Translating Alzheimer’s disease proteomics into drug discovery opportunities
Drummond, E., Werry, E. L., Kavanagh, T., Genoud, S., Cho, A., Chen, S., Du, J., Hibbs, D. E., & Kassiou, M. (2026) · Molecular Neurodegeneration Advances · doi:10.1186/s44477-026-00035-y · Cited by 2
“…via nuclear magnetic resonance, X-ray crystallography or cryo-EM, however the development of artificial intelligence (AI) based approaches such as AlphaFold [83] and RoseTTAFold [84] have made this process significantly more accessible, increasing the number of viable target proteins.”
A 50,688-Reaction Data Set Reveals General Ligands and Mechanistic Diversity in C–N Couplings
Das, J., Zhang, X., Tan, Y., Abdelalim, M., Lu, T., Mauro, C., Regan, C. J., & Cernak, T. (2026) · Journal of the American Chemical Society · doi:10.1021/jacs.6c05959 · Cited by 6
Membrane lipid composition and amino acid sequence determine binding of SARS-CoV-2 fusion peptides
Jiménez-Millán, S., Maestro, A., & Sasselli, I. R. (2026) · Journal of Colloid and Interface Science · doi:10.1016/j.jcis.2026.141021 · Cited by 2
Identification of preeclampsia-associated immune-related risk loci in the Chinese population
Xu, C., Zhou, L., Fang, Q., Niu, Y., Zhao, H., Yang, J., Luo, L., Li, S., Guo, P., Deng, W., et al. (2026) · Taiwanese Journal of Obstetrics and Gynecology · doi:10.1016/j.tjog.2026.03.022 · Cited by 2
Jiang, L., Yang, S., Li, Y., Zhang, Y., Ren, X., Liu, W. T., Fu, H., Bao, C., Qi, Q., Liu, T., et al. (2026) · Frontiers in Microbiology · doi:10.3389/fmicb.2026.1861239 · Cited by 3
“…advances in AlphaFold and RoseTTAFold have substantially improved the accuracy of peptide–protein structural prediction and enabled more reliable interpretation of AFP structure–function relationships, amphiphilic organization, and target-binding interfaces (Baek et al., 2021; Jumper et al., 2021).”
Böhmer, L. M., Chapple, B. P., Amariei, D. A., Hayes, M. A., & Pietruszka, J. (2026) · Natural Product Reports · doi:10.1039/d6np00042h · Cited by 2
Xu, M., Huang, C., Pang, L., Deng, Q., Zhang, H., Qiao, A., Luo, Z., Wang, Z., Hsieh, C., Zhang, Z., et al. (2026) · JACS Au · doi:10.1021/jacsau.6c00732 · Cited by 2
Choi, I., Lee, J., Hwang, K., Kunze, S., Park, J. W., Hwang, S. J., Lim, J., Lee, S., & Song, W. J. (2026) · Journal of the American Chemical Society · doi:10.1021/jacs.6c09177 · Cited by 2
From Chatbots to Chemists: Autonomous Agents for Heterogeneous Catalysis
Jin, M., Liao, C., Xu, Z., Song, Y., He, R., Zhang, Y., Hu, X., & Shen, Z. (2026) · ACS Catalysis · doi:10.1021/acscatal.6c02268 · Cited by 4
Yao, Z., Metts, M., Huber, A. K., Li, J. M., Kinjo, T., Dieckhaus, H., Nallathambi, A., Bowers, A. A., & Kuhlman, B. A. (2026) · Protein Science · doi:10.1002/pro.70696 · Cited by 2
Agbo, C. E., Nwankwo, C. K., Onyehalu, J. C., Agu, M. C., Opah, C., & Nworu, C. S. (2026) · Journal of Pharmacology and Experimental Therapeutics · doi:10.1016/j.jpet.2026.104986 · Cited by 2
Artificial intelligence in vaccine development: applications, implementation, and future directions
Kumar, S. N., Gondane, R., Mahindrakar, S. S., Vyawahare, S., Krishna, R., Subramaniam, S., Nair, B. G., Kumar, G. B., Madhavan, A., Melethadathil, N., et al. (2026) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2026.1870890 · Cited by 2
“Beyond static structural predictions, advanced AI frameworks integrated with molecular dynamics (MD) simulations enable the characterization of protein conformational dynamics over time (Baek et al., 2021; Jumper et al., 2021).”
The accuracy of electrostatic interactions captured by AI protein structure prediction models
Makhatadze, G. I. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2609610123 · Cited by 3
Artificial intelligence catalyzes antimicrobial peptide design
Liu, Y., Hu, J., Zhang, N., Bai, Y., Yao, Y., & Chen, G. (2026) · Synthetic and Systems Biotechnology · doi:10.1016/j.synbio.2026.05.019 · Cited by 2
She, L., Liang, Z., Zou, Q., & Huo, Y. (2026) · ACS Synthetic Biology · doi:10.1021/acssynbio.6c00386 · Cited by 2
Broske, B., McEnroe, B. A., Binder, S. C., Kempchen, T. N., Fandrey, C. I., Tan, E., Ferber, D., Yong, M. C. R., Kleinert, M., Messmer, J. M., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-76760-5 · Cited by 4
Yong, Q., Chen, C., Zhang, X., Sun, K., He, Y., Pan, R., Meng, Y., Wang, Q., Chai, D., Shao, D., et al. (2026) · International Journal of Pharmaceutics · doi:10.1016/j.ijpharm.2026.127339 · Cited by 2
Toward autonomous science with agentic artificial intelligence
Guo, L. Y., Ting, D. S. J., Su, X., Aliper, A., Zhavoronkov, A. A., & Ting, D. S. W. (2026) · Cell · doi:10.1016/j.cell.2026.08.052 · Cited by 2
Functional evaluation of TCR-pMHC pairs at scale allows in silico TCR reactivity prediction
Messemaker, M., Kwee, B. P. Y., Moravec, Ž., de Paauw, S., Urbanus, J. H. M., Salmoral, D. Á., Geerligs, J., Xie, R., Voogd, R., Morris, B., et al. (2026) · Immunity · doi:10.1016/j.immuni.2026.09.007 · Cited by 4
Network-level control of G protein-coupled receptors: a panacea for chronic diseases?
Boeringer, T., Pardo, M., Craig, C. J., Pozo, A. D., Ladds, G., Hébert, T. E., Dodel, S., Prentice, H., Bejanyan, R., & Maudsley, S. (2026) · Frontiers in Science · doi:10.3389/fsci.2026.1891819 · Cited by 2
“AlphaFold2 and RoseTTAFold have transformed static structure prediction and perform well for many single-state GPCR structures.”
Jas, G. S., Childs, E. W., Middaugh, C. R., & Kuczera, K. (2021) · Biomolecules · doi:10.3390/biom11091351 · Cited by 2
“Significant advances with new experimental approaches and the development of sophisticated theory have provided a much more detailed picture involving the complex pathway of structure formation through folding and the ability to predict three-dimensional structure [37,38].”
BackgroundMoroz, O. V., Blagova, E., Lebedev, A. A., Rodríguez, F. S., Rigden, D. J., Tams, J. W., Wilting, R., Vester, J. K., Longhin, E., Hansen, G. H., et al. (2021) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798321010949 · Cited by 2
Long, M., Toesca, J., & Guillon, C. (2021) · Pathogens · doi:10.3390/pathogens10111502 · Cited by 2
“However, a de novo prediction of the structure of the complete FIV Gag polyprotein using the RoseTTAFold server [65] suggests that FIV SP is prone to fold as an α-helix and might therefore participate as a six-helix bundle (Figure 5).”
MethodInfluentialSpitzer, M. (2022) · Nervenheilkunde · doi:10.1055/a-1650-2220 · Cited by 2
A sequence space search engine for computational protein design to modulate molecular functionality
Malik, A., Banerjee, A., Pal, A., & Mitra, P. (2022) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2022.2042386 · Cited by 2
“Additionally, we go through the structure prediction of the designed sequences corresponding to the representative dataset using the state of art RoseTTAFold software (Baek et al., 2021).”
MethodLi, G., Zhang, Z., Wu, M., Chen, X., Yin, M., Jiang, Y., Huang, X., Jiang, C., & Han, L. (2022) · Bioorganic Chemistry · doi:10.1016/j.bioorg.2022.105819 · Cited by 2
Bi-alignments with affine gaps costs
Stadler, P. F., & Will, S. (2022) · Algorithms for Molecular Biology · doi:10.1186/s13015-022-00219-7 · Cited by 2
“This is of increasing practical interest as recent advances in protein folding [48, 49] provide access to high quality 3D structure predictions.”
BackgroundChen, Z., Luo, R., Liu, W., Guo, J.-H., Li, Y., Guo, Y. F., Zhang, K., & Xie, Y. (2022) · IEEE Data Driven Control and Learning Systems Conference (DDCLS) · doi:10.1109/ddcls55054.2022.9858398 · Cited by 2
Huang, Q., Zhang, K., Li, Y., Gan, F., Tang, X., & Tang, B. (2022) · Applied and Environmental Microbiology · doi:10.1128/aem.01503-22 · Cited by 2
Computational Protein–Protein Docking
Zacharias, M. (2022) · Wiley eBooks · doi:10.1002/9783527830503.ch4 · Cited by 4
From an Hsp90 - binding protein to a peptide drug
Ammanath, A. V., Jarneborn, A., Nguyen, M., Wessling, L., Tribelli, P. M., Nega, M., Beck, C., Luqman, A., Selim, K. A., Kalbacher, H., et al. (2022) · microLife · doi:10.1093/femsml/uqac023 · Cited by 2
Engineering the kinetic stability of a β-trefoil protein by tuning its topological complexity
Anderson, D. M., Jayanthi, L. P., Gosavi, S., & Meiering, E. M. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1021733 · Cited by 2
“, 2022), and RoseTTAFold (Baek et al., 2021), now enable the generation of structural models (which may be suitable for Cα-SBM simulations and ACO and LRO calculations) with significant confidence from just the primary sequence.”
BackgroundAndersen, Ø., Rubiolo, J. A., Pirolli, D., Aramburu, Ó., Pampín, M., Righino, B., Robledo, D., Bouza, C., Rosa, M. C. D., & Martı́nez, P. (2023) · Scientific Reports · doi:10.1038/s41598-023-29826-z · Cited by 2
Exploring generality of experimental conformational changes with AlphaFold predictions
Castellví, A., Medina, A., Petrillo, G., Sagmeister, T., Pavkov‐Keller, T., Govantes, F., Diederichs, K., Sammito, M. D., & Usón, I. (2022) · Acta Crystallographica Section A Foundations and Advances · doi:10.1107/s2053273322096462 · Cited by 2
Self-citationLattice Folding Simulation of Peptide by Quantum Computation
SAITO, R., Okuwaki, K., Mochizuki, Y., Nagai, R., Kato, T., Sugisaki, K., & Minato, Y. (2023) · Journal of Computer Chemistry Japan -International Edition · doi:10.2477/jccjie.2022-0036 · Cited by 2
Zhang, M., Li, W., Jin, H., Zhang, L., Mu, Y., & Wang, L. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08505-0 · Cited by 2
A Multimodal Approach towards Genomic Identification of Protein Inhibitors of Uracil-DNA Glycosylase
Muselmani, W., Kashif-Khan, N., Bagnéris, C., Santangelo, R., Williams, M. A., & Savva, R. (2023) · Viruses · doi:10.3390/v15061348 · Cited by 2
“It is therefore suggested that a suitable alternative may be provided via recent developments in structure prediction methods [46,48,72,73].”
BackgroundChen, Z., Shi, Y., Wang, D., Liu, X., Jiao, X., Gao, X., & Jiang, K. (2023) · Pest Management Science · doi:10.1002/ps.7622 · Cited by 2
Baig, D. I., Zafar, Z., Khan, H. A., Younus, A., & Bhatti, M. F. (2023) · PLoS ONE · doi:10.1371/journal.pone.0286428 · Cited by 2
“RoseTTAFold is based on a “3-track neural network” as it considers the patterns in sequences, the interaction of amino acids, and a possible 3D structure of protein [29].”
BackgroundGuerler, A., Baker, D., van den Beek, M., Gruening, B., Bouvier, D., Coraor, N., Shank, S. D., Zehr, J. D., Schatz, M. C., & Nekrutenko, A. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05389-8 · Cited by 2
Self-citationLEGO-CSM: a tool for functional characterization of proteins
Nguyen, T., de Sá, A. G. C., Rodrigues, C. H. M., Pires, D. E. V., & Ascher, D. B. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad402 · Cited by 2
Biochemist Investigates Protein Folding
Dods, R. F. (2023) · Biomedical Materials & Devices · doi:10.1007/s44174-023-00097-6 · Cited by 2
“Because of computer limitations 260 stretches of amino acids were analyzed at a time, 1D and 2D features combined and averaged and then were fed into the computer program, pyoRosetta 8 to generate coarse grain 9 [14] or all-atom models.”
InfluentialPrediction of protein interactions is essential for studying biomolecular mechanisms
Vakser, I. A. (2023) · PROTEOMICS · doi:10.1002/pmic.202300219 · Cited by 2
“A major development in the field has been the recent emergence of the Deep Learning based approaches [6, 7] that extend the prediction success from the tertiary to the quaternary structure.”
BackgroundLi, L., Zhou, L., Jiang, C., Liu, Z., Meng, D., Luo, F., He, Q., & Yin, H. (2023) · Frontiers in Microbiology · doi:10.3389/fmicb.2023.1243987 · Cited by 4
“We configured the local version of AlphaFold2 (Senior et al., 2020) and RoseTTAFold (Baek et al., 2021) on our laboratory’s computation resource, a Dell PowerEdge R940xa server with four Intel Xeon Platinum 8260 processors (total of 148 cores), 1 TB of RAM, installed with Ubuntu 18.04.6 distribution, python 3.”
BackgroundMethodResultInfluentialAssessment of Grapefruit Expressing Anti-NodT Antibody for Huanglongbing Resistance
Vosburg, C., Sinn, J. P., Orbović, V., Ferrarezi, R. S., Zapien-Macias, J. M., Taylor, E. L., Hilf, M. E., McCollum, G., Gottwald, T. R., Stover, E. W., et al. (2023) · PhytoFrontiers™ · doi:10.1094/phytofr-06-23-0078-r · Cited by 2
Kumar, M., Haque, M. A., & Kaur, P. (2023) · Methods in molecular biology · doi:10.1007/978-1-0716-3491-2_4 · Cited by 2
PreHom-PCLM: protein remote homology detection by combing motifs and protein cubic language model
Shao, J., Zhang, Q., Yan, K., & Liu, B. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad347 · Cited by 2
Surface exposed and charged residues drive thermostability in fungi
Senthilkumar, S., Mahesh, S., Jaisankar, S., & Yennamalli, R. M. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26623 · Cited by 2
“For the proteins that did not have a known 3D structure, we modeled them using RoseTTAFold tool 29 (https:// robetta.bakerlab.org).”
The quest for new robust bacterial monoamine oxidases
Martins, L. O. (2023) · FEBS Journal · doi:10.1111/febs.17002 · Cited by 2
“…analysis (e.g., BLAST [8]) in expanding the portfolio of new enzymes with the recent developments of deep-learning and neural networks tools, such as AlphaFold and RoseTTA-Fold [9,10], has been transformative and instrumental in Structural Biology, Molecular Evolution, and Bio-technology.”
MethodPrediction of interactions between cell surface proteins by machine learning
Su, Z., Griffin, B., Emmons, S. W., & Wu, Y. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26648 · Cited by 2
“30,31 Moreover, they were also been used to predict the interactions between proteins.”
Khairi, M. H. F., Muhammad, N. A. N., Bunawan, H., Daud, K. M., Sulaiman, S., Mohamed‐Hussein, Z., Wong, M., & Ramzi, A. B. (2023) · Physiological and Molecular Plant Pathology · doi:10.1016/j.pmpp.2023.102201 · Cited by 3
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.