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 3,501–3,600 of 5,636
Applications of machine learning in plant biotechnology
Ogra, I. O., Silué, Y., Fawole, O. A., Aremu, A. O., & Opara, U. L. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01166-7 · Cited by 3
Barethiya, S., Huang, J., Stumpf, C., Liu, X., Guan, H., & Chen, J. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013728 · Cited by 4
Driving In Vivo Multienzyme Cascades Forward: Regulatory Strategies for Enhanced Biocatalysis
Yang, Q., Zhu, F.-Y., Zhang, X., Cai, X., (23458368), J.-P. Z., Liu, Z., & Zheng, Y. (2026) · ACS Synthetic Biology · doi:10.1021/acssynbio.5c00951 · Cited by 4
Foundation models and AI agents in oncology drug discovery
Ghanwatkar, Y., Rajdeo, P., & Mahato, R. I. (2026) · Drug Discovery Today · doi:10.1016/j.drudis.2026.104655 · Cited by 4
Dave, P., Gandhi, A., & Dudhat, K. R. (2026) · Journal of Pharmaceutical Innovation · doi:10.1007/s12247-026-10634-7 · Cited by 5
“For instance, AI also plays a critical role in precision diagnostics, where DL models analyze radiological images, pathology slides, and other diagnostic data with a level of accuracy that often [74 ].”
Beyond accuracy: comprehensive alignment for AI-driven molecular design
Zhang, Q. H., Zhuang, X., Zhou, C., Zhu, Y., Xu, T., Li, T., Liu, D., Liu, S., Ding, K., Li, M., et al. (2026) · AI for Science · doi:10.1088/3050-287x/ae5f37 · Cited by 4
Using experimental results of protein design to guide biomolecular energy-function development
Haddox, H. K., Rocklin, G. J., Motta, F. C., Strickland, D., Halabiya, S. F., Cordray, C., Park, H., Klavins, E., Baker, D. A., & DiMaio, F. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014215 · Cited by 6
Self-citationMechanisms of inflammatory bowel diseases: Insights from human genetics and chemical biology
Graham, D. B., & Xavier, R. J. (2026) · Immunity · doi:10.1016/j.immuni.2026.04.002 · Cited by 5
BilboMD: a web-accessible SAXS and AlphaFold-guided modeling pipeline
Classen, S., Mundo, J. T. D., Kulkarni, D. D., Prabhakar, S., Hicks, A., & Hammel, M. (2026) · Nucleic Acids Research · doi:10.1093/nar/gkag377 · Cited by 4
Kaushik, R., & Re, S. (2026) · Journal of Pharmacy & Pharmaceutical Sciences · doi:10.3389/jpps.2026.16146 · Cited by 3
“The availability of high-quality experimental structures, combined with major advances in deep learning–based structure prediction, dramatically expanded the applicability of structure-guided design during the COVID-19 pandemic [4, 7, 11, 19, 21].”
Applications and prospects of cryo-electron tomography in drug discovery and understanding disease
Clemente, C. M., Mobarec, J. C., & Bharat, T. A. M. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103283 · Cited by 3
“Tools such as AlphaFold2 [8] and RoseTTAFold [9] have demonstrated that protein structures could be predicted with near-experimental accuracy from sequence alone.”
Harnessing AlphaFold: Applications in disease understanding, drug discovery, and vaccine design
Kinde, M. Z., Gessese, A. T., Fenta, M. D., Chanie, S. D., & Sisay, T. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.111095 · Cited by 3
Hasdemir, H. S., Li, Y., Kelich, P., Wen, P., & Tajkhorshid, E. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5054-7_1 · Cited by 5
Sharma, S. R. K., Saha, S., Arora, S., Ahlawa, Y. K., Sheoran, S., Mukherjee, S., Sinha, A., Chaudhary, K., & Gosipatala, S. B. (2026) · Disease and Therapeutics · doi:10.1016/j.dist.2026.100012 · Cited by 3
Katerji, M., Rubin, M. R., Lindberg, E., Torres‐Ayuso, P., Siddiqui, A., Funk, A. L., Nyswaner, K. M., Woodroofe, C. C., Wolfe, S., Edwards, Z. C., et al. (2026) · Molecular Cancer Therapeutics · doi:10.1158/1535-7163.mct-25-1042 · Cited by 3
Advancements in characterization of protein dynamics with machine learning
Madani, M., & Tarakanova, A. (2026) · npj Soft Matter · doi:10.1038/s44431-026-00025-w · Cited by 6
“Integrativeapproachesthatblendcryo-EM density interpretationwith sequence-based structure prediction — similar to AlphaFold 46 and RoseTTAFold 47 — are increasingly being employed.”
InfluentialCollective Variable-Guided Engineering of the Free-Energy Surface of a Small Peptide
Medaparambath, M., Zhilkin, A., & Mendels, D. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00674 · Cited by 3
Expanding the scope of protein language modeling to protein-protein interactions with MSA Pairformer
Akiyama, Y., Zhang, Z., Tang, O., Kim, S., Mirdita, M., Steinegger, M., & Ovchinnikov, S. (2026) · Cell · doi:10.1016/j.cell.2026.06.029 · Cited by 19
Self-citationAI-assisted design of next-generation antibiotics against multidrug-resistant Staphylococcus aureus
Zheng, Y., Jin, F., Chang, Q., Yu, J., Zheng, Y., & Li, Y. (2026) · Pharmacology & Therapeutics · doi:10.1016/j.pharmthera.2026.109092 · Cited by 4
In silico drug discovery pipelines targeting antibiotic resistance: from genomes to leads
Gupta, R., Singh, P., Ravi, K., Abomughaid, M. M., Lakhanpal, S., Sharma, R. V., Kumar, N., & Jha, N. K. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1839606 · Cited by 3
“These tools have shown unprecedented accuracy in predicting protein folds directly from amino acid sequences, often approaching experimental resolution for globular domains (Baek et al., 2021; Qiu et al., 2024; Wang J. et al., 2024).”
On the generalization and usability of cofolding models for GPCR drug discovery
Zhang, L., Friesner, R. A., Miller, E. B., & Rodrigues, J. (2026) · npj Drug Discovery. · doi:10.1038/s44386-026-00066-1 · Cited by 7
Large language medicine: defining a new paradigm in human health
Guni, A., Hu, W., Morley, J., Cohen, I. G., Barnaghi, P. M., & Ashrafian, H. (2026) · Frontiers in Science · doi:10.3389/fsci.2026.1810095 · Cited by 3
“Following the release of roughly 200 million protein structures without experimental input, structural biology is poised to be reshaped by AlphaFold and similar technologies, such as RoseTTAFold (93, 94).”
A curated benchmark for cofolding models on kinase conformational states
Sun, K., & Head-Gordon, T. L. (2026) · npj Drug Discovery. · doi:10.1038/s44386-026-00068-z · Cited by 4
Guven‐Maiorov, E., Sakakibara, N., Ponnamperuma, R. M., Dong, K., Matar, H., King, K. E., & Weinberg, W. C. (2022) · Molecular Carcinogenesis · doi:10.1002/mc.23405 · Cited by 3
“If a protein of interest does not have an available structure, widely used homology modelers such as I ‐ TASSER 77 or state ‐ of ‐ the ‐ art artificial intelligence ‐ based structural modelers such as AlphaFold 78 and Rosetta-Fold 79 can be employed to model the 3D structure of this protein and be used in HMI ‐ PRED a…”
MethodGao, Y., Zhan, J., & Yu, A. C. (2022) · MedComm – Future Medicine · doi:10.1002/mef2.22 · Cited by 3
Structural features of sensory two component systems: a synthetic biology perspective
Nieves, M., Buschiazzo, A., & Trajtenberg, F. (2023) · Biochemical Journal · doi:10.1042/bcj20210798 · Cited by 3
Probst, D. (2023) · CHIMIA International Journal for Chemistry · doi:10.2533/chimia.2023.56 · Cited by 3
Insights into the pathophysiology of DFNA44 hearing loss associated with CCDC50 frameshift variants
Lachgar-Ruiz, M., Morin, M., Martelletti, E., Ingham, N. J., Preite, L., Lewis, M. A., de Castro, L. S. S., Steel, K. P., & Moreno-Pelayo, M. Á. (2023) · Disease Models & Mechanisms · doi:10.1242/dmm.049757 · Cited by 3
Thomson, T. M. (2023) · Frontiers in Pharmacology · doi:10.3389/fphar.2023.1207559 · Cited by 3
“, 2021) or RoseTTA fold (Baek et al., 2021), to accurately predict the structures ofmillions of proteins.”
BackgroundGatti, G., Brandolini, M., Mancini, A., Taddei, F., Zannoli, S., Dirani, G., Manera, M., Arfilli, V., Denicolò, A., Marzucco, A., et al. (2023) · Viruses · doi:10.3390/v15081630 · Cited by 3
“The prediction of the 3D structure of the N protein was calculated through RoseTTAFold [26], the algorithm was set with the default parameters and 5 probabilistic models were generated associated with an Angstrom error rate estimation for every single amino acid [27].”
MethodAQcalc : A web server that identifies weak molecular interactions in protein structures
Afshinpour, M., Smith, L. A., & Chakravarty, S. (2023) · Protein Science · doi:10.1002/pro.4762 · Cited by 3
Sarkar, D., Lee, H., Vant, J., Turilli, M., Vermaas, J. V., Jha, S., & Singharoy, A. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00350 · Cited by 3
A Sequence-Based Prediction Model of Vesicular Transport Proteins Using Ensemble Deep Learning
Le, N. Q. K., & Kha, Q. H. (2023) · ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (ACM-BCB) · doi:10.1145/3584371.3612950 · Cited by 4
“As for now, different state-of-the-art results have been achieved for protein structure prediction [27, 28], and they can be integrated into our sequencing information.”
BackgroundComputational modeling of protein–carbohydrate interactions: Current trends and future challenges
Pérez, S. (2023) · Advances in carbohydrate chemistry and biochemistry · doi:10.1016/bs.accb.2023.10.003 · Cited by 4
Homologous acetone carboxylases select Fe(II) or Mn(II) as the catalytic cofactor
Shisler, K. A., Kincannon, W. M., Mattice, J. R., Larson, J. D., Valaydon-Pillay, A., Mus, F., Flusche, T., Nath, A. K., Stoian, S. A., Raugei, S., et al. (2023) · mBio · doi:10.1128/mbio.02987-23 · Cited by 3
“A homology model for A. aromaticum AC was constructed using Robetta comparative modeling (26, 27).”
MethodYan, Z., & Wang, J. (2024) · Communications Chemistry · doi:10.1038/s42004-024-01098-2 · Cited by 6
Self-citationHarnessing AlphaFold to reveal hERG channel conformational state secrets
Ngo, K., Yang, P., Yarov-Yarovoy, V. M., Clancy, C. E., & Vorobyov, I. V. (2025) · eLife · doi:10.1101/2024.01.27.577468 · Cited by 7
Fan, L., Yang, X., Wang, L., & Zhu, X. (2024) · Current Bioinformatics · doi:10.2174/0115748936272939231212102627 · Cited by 4
Mróz, J., Pelc, M., Mitusińska, K., Chorostowska‐Wynimko, J., & Jezela‐Stanek, A. (2024) · Genes · doi:10.3390/genes15030340 · Cited by 3
“In addition, recent breakthroughs in protein structure prediction have been exemplified by AlphaFold, an artificial intelligence (AI)-driven tool developed by DeepMind [99] or RoseTTaFold [104].”
MethodEffects of N-glycans on the structure of human IgA2
Ruocco, V., Grünwald‐Gruber, C., Rad, B., Tscheließnig, R., Hammel, M., & Strasser, R. (2024) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2024.1390659 · Cited by 3
Azzam, T., Du, J. J., Flowers, M. W., Ali, A. V., Hunn, J. C., Vijayvargiya, N., Knagaram, R., Bogacz, M., Maravillas, K. E., Sastre, D. E., et al. (2024) · Science Advances · doi:10.1126/sciadv.adk8157 · Cited by 3
“In such computational approaches, neural networks generated by machine learning such as AlphaFold ( 15 , 16 ) and RoseTTAFold ( 17 , 18 ) can be combined with in silico screening methods to efficiently screen and select a large number of variants based on a specific property before experimental…”
Rational Design of Drugs Targeting G-Protein-Coupled Receptors: A Structural Biology Perspective
Khorn, P. A., Luginina, A. P., Pospelov, V. A., Dashevskii, D. E., Khnykin, A. N., Moiseeva, O. V., Safronova, N. A., Belousov, A., Mishin, A., & Borshchevskiy, V. I. (2024) · Biochemistry (Moscow) · doi:10.1134/s0006297924040138 · Cited by 3
Zheng, W. (2024) · PLoS ONE · doi:10.1371/journal.pone.0302504 · Cited by 3
“Thanks to recent revolutions in computational structural biology (accurate protein structure prediction by AlphaFold [1] and RoseTTAFold [2]), it is now feasible to predict native structures for many proteins given their sequences (with some caveats, see [3]), thus practically solving the protein…”
MethodUnlocking the power of AI models: exploring protein folding prediction through comparative analysis
Nevado, P. T., Serrano, E., González-Herrero, A., Bermejo, R., & Rodríguez‐González, A. (2024) · Berichte aus der medizinischen Informatik und Bioinformatik/Journal of integrative bioinformatics · doi:10.1515/jib-2023-0041 · Cited by 4
“The protein structure prediction service Robetta [10] was used to obtain the inference using RoseTTAFold [4].”
MethodImproved prediction of site‐rates from structure with averaging across homologs
Norn, C., Oliveira, F., & André, I. (2024) · Protein Science · doi:10.1002/pro.5086 · Cited by 3
“Structure predictions based on deep learning methods have become very accurate in predicting the structure of proteins (Baek et al., 2021; Jumper et al., 2021; Lin et al., 2023).”
BackgroundLight sensitivity in Beroidae ctenophores: Insights from laboratory studies and genomics
Кривенко, О. В., Kuleshova, O. N., & Баяндина, Ю. С. (2024) · Comparative Biochemistry and Physiology Part A Molecular & Integrative Physiology · doi:10.1016/j.cbpa.2024.111694 · Cited by 3
Buzzatto, M. V., Guerrero, F. C. B., Álvarez, P. A., Zizzias, M. P., Polo, L. M., & Tomes, C. N. (2024) · Bioscience Reports · doi:10.1042/bsr20240117 · Cited by 3
Cao, L., Yu, B., Klauser, P. C., Zhang, P., Li, S., & Wang, L. (2024) · Angewandte Chemie · doi:10.1002/ange.202412843 · Cited by 3
Guo, Z., Zhang, K., Cai, C., Li, X., Zhang, L., Yang, Y., Wang, X., Chen, S., Zhang, L., & Cheng, F. (2024) · The Plant Journal · doi:10.1111/tpj.16979 · Cited by 5
Vince, O., Gowers, G.-O. F., & McGibbon, S. (2024) · GEN Biotechnology · doi:10.1089/genbio.2024.0018 · Cited by 5
“…Uni-Prot, 47 forms the basis of all leading protein structure prediction models (e.g., AlphaFold2, ESMFold, 48 OpenFold, 49 and RoseTTaFold 50 ), protein-ligand models (e.g., NeuralPlexer 51 ), protein function models (e.g., CLEAN, 52 ProteInfer, 53 and ProteinVec 54 ) and protein…”
Xiong, W., Roach, T. G., Ball, N., Corluka, M., Beyer, J., Brown, A. M., & Capelluto, D. G. S. (2024) · Structure · doi:10.1016/j.str.2024.08.003 · Cited by 4
Structural insights into the biosynthetic mechanism of Nα-GlyT and 5-NmdU hypermodifications of DNA
Wen, Y., Guo, W., Meng, C., Yang, J., Xu, S., Chen, H., Gan, J., & Wu, B. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae784 · Cited by 3
Permatasari, G. W., Putranto, R. A., Mardhika, L. D., Aksa, A. A., Setiawati, Y., MINARSIH, H., Riyadi, I., & Ernayunita, E. (2024) · Journal of Tropical Biodiversity and Biotechnology · doi:10.22146/jtbb.90808 · Cited by 3
“In the supplementary information of the RosettaCM publication (Baek et al. 2021), a predicted confidence value that accounts for this is given for comparative modelling domains and was found to correspond with the actual GDT to native.”
MethodStructural Studies of Ion Channels: Achievements, Problems, and Perspectives
Zhorov, B. S., & Tikhonov, D. B. (2024) · Biochemistry (Moscow) Supplement Series A Membrane and Cell Biology · doi:10.1134/s199074782470017x · Cited by 3
“Another significant resource is the RoseTTAFold server [118] which also relies on artificial intelligence techniques.”
Balogun, E. O., Joseph, G. I., Olabode, S. C., Dayaso, N. A., Danazumi, A. U., Bashford-Rogers, R. J. M., McKerrow, J. H., Jeelani, G., & Caffrey, C. R. (2024) · Pathogens · doi:10.3390/pathogens13100850 · Cited by 3
“The 3D structures of the designed putative antigens were predicted using Ro-seTTAFold from the Robe tt a webserver [53].”
MethodVincenzi, M., Mercurio, F. A., Manna, S. L., Palumbo, R., Pirone, L., Marasco, D., Pedone, E. M., & Leone, M. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms251910616 · Cited by 3
“Nevertheless, artificial intelligence software mainly relying on deep learning approaches, like AlphaFold [17,18] and RosettaFold [19], has lately attracted a lot of attention.”
Notbohm, J., & Perica, T. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102952 · Cited by 4
Accurate and Fast Prediction of Intrinsic Disorder Using flDPnn
Wang, K., Hu, G., Wu, Z., & Kurgan, L. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-4196-5_12 · Cited by 3
Srivastava, G. N., Liu, M., Ni, X., Pu, L., & Bryliński, M. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-4196-5_5 · Cited by 4
Understanding the Directed Evolution of a Natural-like Efficient Artificial Metalloenzyme
Mukherjee, A., & Roy, S. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c06994 · Cited by 3
Soté, W. O., & Comar, M. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01927 · Cited by 3
High‐Throughput Evaluation of Natural Diversity of F‐Type ATP Synthase Rotor Ring Stoichiometries
Osipov, S. D., Zinovev, E. V., Anuchina, A. A., Kuzmin, A., Minaeva, A. V., Ryzhykau, Y. L., Vlasov, A. V., & Gushchin, I. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26790 · Cited by 3
“Several other approaches with similar performance have been released soon thereafter [30–32].”
Cruz, D. G. D. L., Castillo, D. A., Trujillo, C., Medina, C. A., Hurtado, V., Gil, J., Padmanabhan, M. S., Restrepo, S., Dinesh‐Kumar, S. P., Germain, H., et al. (2025) · Molecular Plant-Microbe Interactions · doi:10.1094/mpmi-08-24-0086-r · Cited by 4
Altered Octopamine synthesis impairs tyrosine metabolism affecting Helicoverpa armigera vitality
Patil, Y. P., Wagh, D. S., Barvkar, V. T., Gawari, S. K., Pisalwar, P., Ahmed, S., & Joshi, R. S. (2025) · Pesticide Biochemistry and Physiology · doi:10.1016/j.pestbp.2025.106323 · Cited by 3
Efforts to Downsize Base Editors for Clinical Applications
Song, B. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26052357 · Cited by 3
Structural assembly of the PAS domain drives the catalytic activation of metazoan PASK
Dhungel, S., Xiao, M. J., Rajesh, R. P., & Kikani, C. K. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2409685122 · Cited by 3
“C domains were modeled using RosettaFold and ESMFold (43, 44).”
Nonequilibrium dynamics of the helix–coil transition in polyalanine
Conradi, M., Christiansen, H., Majumder, S., Müller, F., & Wolfhard Janke, E. (2025) · The Journal of Chemical Physics · doi:10.1063/5.0245056 · Cited by 3
NMR Structural Characterization of SARS-CoV-2 ORF6 Reveals an N-Terminal Membrane Anchor
Ninot‐Pedrosa, M., Pálfy, G., Razmazma, H., Crowley, J., Fogeron, M., Bersch, B., Barnes, A. B., Brutscher, B., Monticelli, L., Böckmann, A., et al. (2025) · Journal of the American Chemical Society · doi:10.1021/jacs.4c17030 · Cited by 5
AI-Assisted Native Proteomics: Delineating Ribosomal Protein Conformations Pre- and Post-Assembly
Zhang, W., Sun, C., Xu, Z., & Xu, W. (2025) · Analytical Chemistry · doi:10.1021/acs.analchem.5c01431 · Cited by 3
Editing metacaspase (StMC7) gene enhances late blight resistance in Russet Burbank potato
Poudel, B., Sathe, A., Bede, J. C., & Kushalappa, A. C. (2025) · PLoS ONE · doi:10.1371/journal.pone.0325702 · Cited by 3
“The protein structure of StMC7 was predicted using RoseTTAFold [23].”
Diocaretz, B. C., Tűzesi, Á., & Herdean, A. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7030060 · Cited by 3
Kapitan, V. Y., & Choi, M. C. H. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06185-2 · Cited by 4
“Released alongside AlphaFold2, it achieves high accuracy while requiring fewer computational resources, democratizing access to structural modeling [37].”
Human FASTK preferentially binds single‐stranded and G‐rich RNA
(2025) · doi:10.1111/febs.70155 · Cited by 3
“To validate our low-resolution experimental densities, we fitted FASTK atomic models created with RoseTTAFold [34] or AlphaFold2 [35].”
Barhoon, M., & Mahdiuni, H. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01029 · Cited by 3
Biocatalytic potential of microbial CYP450s in the degradation of selected environmental pollutants
Petriti, V., Mondal, A., & Ding, Y. (2025) · Medicinal Chemistry Research · doi:10.1007/s00044-025-03457-7 · Cited by 3
“Protein structural models generated by AI tools such as AlphaFold3 [77] and RoseTTAFold [78] further enhance ML/AI-driven predictions by offering structural insights, signi fi cantly improving the accuracy and throughput of enzyme discovery.”
Bridging prion biology and Alzheimer’s disease: from pathogenic seeds to precision therapeutics
Wang, W., Feng, Z., Shu, L., Hu, Y., Chen, Y., Zhang, B., & Huang, H. (2025) · Frontiers in Molecular Neuroscience · doi:10.3389/fnmol.2025.1660151 · Cited by 3
Wang, C., & Zhang, B. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01329 · Cited by 5
Brezinova, M., Brotzakis, Z. F., Horne, R. I., Chowdhury, V. R., Gregory, R. C., Bian, Y., Díaz, A. G., Gentile, F., & Vendruscolo, M. (2025) · Molecular Systems Biology · doi:10.1038/s44320-025-00159-5 · Cited by 8
“With the advent of deep learning methods in structural biology (Jumper et al, 2021; Baek et al, 2021), there have been several successful attempts to accelerate and improve the docking process with the use of machine learning (Corso et al, 2022; Stärk et al, 2022; Wong et al, 2022; Méndez-Lucio et…”
Cao, Z., Shang, T., Cao, S., Wang, Z., Wang, Z., Mao, Q., Guo, J., & Duan, H. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01111-3 · Cited by 4
“Models such as AlphaFold [24, 25], RosettaFold [26], and ESMFold [27] have greatly improved the accuracy and efficiency of protein and peptide structure prediction.”
Senet, P., Guzzo, A., Delarue, P., Laforge, C., Maisuradze, G. G., Heydel, J.-M., Neiers, F., & Nicolaï, A. (2026) · Chemical Science · doi:10.1039/d5sc06411b · Cited by 3
Multiplex mapping of protein–protein interaction interfaces
He, J., Zou, L.-N., Pareek, V., & Benkovic, S. J. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2425774122 · Cited by 5
“Advances in machine learning (ML)–based structural prediction ( 7 – 10 ) raises the possi bility that where experimental structures are absent, computation models can fill in the gap.”
Jawarkar, R. D., Deshmukh, P. K., Mandwale, B., & Long Chaiu, M. I. N. G. (2026) · Artificial Intelligence Chemistry · doi:10.1016/j.aichem.2026.100108 · Cited by 3
PHA synthase variant design using a conditional variational autoencoder
Tenkanen, T., Ylinen, A., Jouhten, P., Penttilä, M. E., & Castillo, S. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014087 · Cited by 3
“However, the accuracy and quality of the protein representation, and thus also model’s performance, could be enhanced in future by the new advances in protein structure prediction such as AlphaFold [19] or RoseTTAFold [42].”
Metal-dependent and metal-free mechanisms of peptide condensate catalysts
Massarano, T., Yang, Y., Leshem, A. B., Eran, O., Wang, X., Dong, H., & Lampel, A. (2026) · Nature Communications · doi:10.1038/s41467-026-71117-4 · Cited by 3
AID and TET2 cooperate to demethylate Irf4 for plasma cell fate in germinal center B cells
He, M., D’Aulerio, R., Pinho, L. G., Doukoumopoulos, E., Yong, T., Vieira, R. C., Oliveira, M. M. S., Eiben, L., Termote, M., Galvani, R. G. A., et al. (2026) · The Journal of Experimental Medicine · doi:10.1084/jem.20260096 · Cited by 3
Tan, Z., Chan, C. H., Maleska, M., Jara, B. B., Lohman, B. K., Ricks, N. J., Bond, D. R., & Hammond, M. C. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23031183 · Cited by 3
Takei, Y., & Ishida, T. (2022) · Bioengineering · doi:10.3390/bioengineering9030118 · Cited by 3
“Various prediction methods have been developed to date [1,2], two major types of which are homology modeling and de novo modeling.”
MethodZhu, L., & Li, W. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23084426 · Cited by 4
“Such structural information can be obtained via experimental approaches or the state-of-art computational methods such as AlphaFold [78] or RossetaFold [79].”
MethodLi, Z., Liu, R., Liu, Y., Zhao, M., Luan, J., Wang, Y., Shang, W., Song, X., Sun, Y., & Han, F. (2022) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2022.04.104 · Cited by 4
Active Learning Module for Protein Structure Analysis Using Novel Enzymes
Kelz, J. I., Takahashi, G. R., Safizadeh, F., Farahmand, V., Crosby, M. G., Uribe, J. L., Kim, S. H., Sprague‐Piercy, M. A., Diessner, E. M., Norton‐Baker, B., et al. (2022) · The Biophysicist · doi:10.35459/tbp.2021.000209 · Cited by 3
Dumont, M. E., & Konopka, J. B. (2022) · Biomolecules · doi:10.3390/biom12060761 · Cited by 3
Closing the loop on crowdsourced science
Robson, J. M., & Green, A. A. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2205897119 · Cited by 4
“Predicting the three-dimensional structure that a protein will adopt has been an important research problem for 50 y, but major advances have recently been achieved through artificial intelligence (AI) networks (17, 18).”
BackgroundAlignMe: an update of the web server for alignment of membrane protein sequences
Staritzbichler, R., Yaklich, E. L., Sarti, E., Ristic, N., Hildebrand, P. W., & Forrest, L. R. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac391 · Cited by 3
Wang, B., Lin, J. H., Hoag, M. R., Wright, M., Ma, M., Cai, W., Kankanamalage, S. G., & Liu, Y. (2022) · Antibody Therapeutics · doi:10.1093/abt/tbac019 · Cited by 3
Golosov, A. A., Flyer, A. N., & Monovich, L. G. (2022) · ACS symposium series · doi:10.1021/bk-2022-1417.ch008 · Cited by 4
Nuñez-Ortiz, N., Díaz‐Rosales, P., Cabrera, J. A. G., Serra, C. R., Enes, P., Tafalla, C., & Gómez-Casado, E. (2022) · Fish & Shellfish Immunology · doi:10.1016/j.fsi.2022.08.018 · Cited by 3
Estimation of model accuracy by a unique set of features and tree-based regressor
Bitton, M., & Keasar, C. (2022) · Scientific Reports · doi:10.1038/s41598-022-17097-z · Cited by 3
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 · doi:10.1002/ange.202203591 · Cited by 3
Quade, B. N., Marshall, A., & Parker, M. D. (2022) · American Journal of Physiology-Cell Physiology · doi:10.1152/ajpcell.00221.2022 · Cited by 3
Zhu, J., Zou, J., Li, F., Gao, Y., Wang, L., Sun, Y. E., Zhu, J., Zhang, X., Xue, K., Li, G., et al. (2022) · MedComm – Future Medicine · doi:10.1002/mef2.15 · Cited by 4
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.