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 4,201–4,300 of 5,636
Avery, N. G., Tahti, E. F., Spiegel, P. C., Antos, J. M., McCarty, J., & Amacher, J. F. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.5c05800 · Cited by 1
Yoon, J., Kim, Y., & Lee, H.-J. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3643854 · Cited by 1
Trovão, N. S., Lucaci, A. G., Pradeep, N., Sethi, M., Bono, L. M., Singh, R. S., Clark, K. B., Zaksas, V., Burke, M., Caicedo, A., et al. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-32904-3.00009-1 · Cited by 3
Deep learning–based postprocessing and model building for cryo-electron microscopy maps
Li, T., & Huang, S. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103196 · Cited by 2
Attenuating ETEC virulence using a heat-labile enterotoxin–blocking binding protein
Petersson, M., Pettersen, J. S., Henriksen, H., Duzs, Á., Fernández‐Quintero, M. L., Burlet, N. J., Mojica, N., Krengel, U., Jenkins, T. P., Ward, A. B., et al. (2025) · Gut Microbes · doi:10.1080/19490976.2025.2597567 · Cited by 1
Machine Learning Approaches for Interpretable Antibody Property Prediction Using Structural Data
Michalewicz, K., Barahona, M., & Bravi, B. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5408-8_7 · Cited by 2
Uslupehlivan, M., & Deveci, R. (2025) · Future Virology · doi:10.1080/17460794.2025.2581464 · Cited by 1
Du, S., Wang, H., Geng, F., Zhang, Z., Liu, C., Lu, W., & Wei, G. (2025) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2025.12.026 · Cited by 2
“Utilizing deep learning, AlphaFold2 compares protein sequences with extensive databases of known structures, leveraging evolutionary information and physicochemical principles to achieve near-experimental accuracy in its predictions 35 .”
Gao, H., Camargo, E. A., Ubi, J. N., Duan, X., Tian, X., HaiTeng, D. E. N. G., Zheng, G., & Gao, S. (2025) · Protein Science · doi:10.1002/pro.70410 · Cited by 2
Progress of Deep Learning Prediction of CD8+ T‐Cell Epitopes
Cheng, X., Wu, H., Chen, P., Liu, R., Lei, Y., Mei, H., & Wang, P. (2025) · PROTEOMICS · doi:10.1002/pmic.70101 · Cited by 2
Computational Drug Repurposing
Talevi, A. (2025) · Springer handbooks · doi:10.1007/978-3-031-81728-1_29 · Cited by 2
Molecular Representations for Drug Discovery
Zhang, L., Golts, A., & Garcia, V. L. (2025) · Springer handbooks · doi:10.1007/978-3-031-81728-1_48 · Cited by 2
Optimized Multi-Epitope Norovirus Vaccines Induce Robust Humoral and Cellular Responses in Mice
Xing, Z., Ji, L., Cao, P., Feng, E., Xu, Q., Chen, X., Dai, W., & Jiang, N. (2025) · Vaccines · doi:10.3390/vaccines14010050 · Cited by 1
AutoLoop is an autoregressive deep learning method for protein loop prediction with high accuracy
Wang, T., Zhang, X., Wang, L., Zhang, O., Wang, J., Wang, E., Wu, J., Hu, R., Ge, J., Li, S., et al. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2025.103041 · Cited by 1
Self-citationCordoves‐Delgado, G., García‐Jacas, C. R., Marrero‐Ponce, Y., Águila, S. A., & Uc, G. L. (2026) · Antibiotics · doi:10.3390/antibiotics15010039 · Cited by 1
Neural network–based approach for improving the evaluation of antibody–antigen docking poses
Meta, A., Ruocco, G., & Milanetti, E. (2026) · Frontiers in Physics · doi:10.3389/fphy.2025.1736037 · Cited by 1
“Algorithms such as AlphaFold2 [5, 6] and RoseTTAFold [7] have fundamentally changed the landscape of structural biology by providing near-experimental accuracy in structural predictions, with a significant impact on protein modeling and rational drug design.”
Delivering artificial intelligence–ready genomics with the Maize Genetics and Genomics Database
Haley, O. C., Tibbs‐Cortes, L. E., Harding, S. F., Poretsky, E., Cannon, E. K. S., Portwood, J. L., Gardiner, J. M., Sen, T. Z., Kim, H.-S., Woodhouse, M. R., et al. (2026) · Genetics · doi:10.1093/genetics/iyag005 · Cited by 1
Liu, J., Zeng, D., Hu, B., Wang, W., Hu, S., Cifuentes, A., Ibáñez, E., Zhao, H., & Lu, W. (2026) · Food Science and Human Wellness · doi:10.26599/fshw.2026.9250937 · Cited by 1
Teimoori, P., Khatir, K., & Heidari, M. (2026) · BioMed Research International · doi:10.1155/bmri/9723304 · Cited by 1
“[61].”
Chen, C., Vakirlis, N., Holmer, R., de Ridder, D., & Kupczok, A. (2026) · Genome Biology and Evolution · doi:10.1093/gbe/evag211 · Cited by 1
Brazzolotto, X., Lushchekina, S. V., & Nachon, F. (2026) · Protein Science · doi:10.1002/pro.70467 · Cited by 1
“The AI-based structure prediction tools AlphaFold3, RoseTTAFold, and ESMFold provide very close back-bone conformations of the AB-loop both for pBChE and hBChE-NHML structures.”
InfluentialGidaga, T., Kukułowicz, J., Ogoś, M., & Bajda, M. (2026) · Physical Biology · doi:10.1088/1478-3975/ae3af9 · Cited by 1
Himaja, D., & Bandyopadhyay, D. (2026) · Database · doi:10.1093/database/baag002 · Cited by 1
Zheng, Y. ‐., Liu, T., Tian, G., Yan, S., Zheng, L., Wang, J., & Wang, X. (2026) · Journal of Hazardous Materials · doi:10.1016/j.jhazmat.2026.141287 · Cited by 1
Self-citationRojo-Cortés, F., Roa, C. B., Amado-Hinojosa, P., Fuenzalida‐Uribe, N., González-Ramírez, M. C., Chacón-Álvarez, R., Almonacid-Torres, I., Birman, S., Goodman, L. D., Kanca, O., et al. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2502307123 · Cited by 2
“We generated a three - dimensional model of the protein (28 ) (Fig.”
Zhao, J., Liu, Y., Jiang, Y., Liu, J., & Cai, S. (2025) · International Journal of Food Science & Technology · doi:10.1093/ijfood/vvag019 · Cited by 1
Ahmed, W. S., Fatima, A., Geethakumari, A. M., & Biswas, K. H. (2026) · FEBS Letters · doi:10.1002/1873-3468.70292 · Cited by 1
“The structural model of the full-length PDE5A2 was generated using trRosetta [23,24].”
Design of novel enzymes with the incorporation of noncanonical amino acids
Cheng, L., Yang, L., Song, Z., & Yu, H. (2026) · Critical Reviews in Biotechnology · doi:10.1080/07388551.2025.2612060 · Cited by 1
“Tools including AlphaFold and RoseTTAFold can predict protein structures and interactions with near-experimental accuracy [115,116].”
Simulation-guided AI-driven digital twin for plasma etching in semiconductor fabrication
Myung, S., Kim, K., Lee, C., Kim, J., Choi, Y., Kang, G., Kim, N., Jung, B. E., Lee, J., Doh, J., et al. (2026) · Device · doi:10.1016/j.device.2025.101026 · Cited by 1
Mechanism of confinement enhancing enzyme intrinsic activity
Cao, Y., Chen, S., Liang, H., Yang, J., Lou, W., & Ge, J. (2026) · CHINESE JOURNAL OF CATALYSIS (CHINESE VERSION) · doi:10.1016/s1872-2067(25)64827-3 · Cited by 2
Chundru, D., & Ghanem, M. (2026) · Frontiers in Immunology · doi:10.3389/fimmu.2026.1717278 · Cited by 1
Yekeen, A. A., Meyer, C. J., McCoy, M. K., Posner, B. A., & Westover, K. D. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02430 · Cited by 2
Enhanced Sampling and Free Energy Calculations in Protein Simulations
Domene, C., & Furini, S. (2026) · Advances in experimental medicine and biology · doi:10.1007/978-3-032-07511-6_4 · Cited by 2
Role of artificial intelligence in advancing cryo electron microscopy
Borar, P., & Polley, S. (2026) · Progress in molecular biology and translational science · doi:10.1016/bs.pmbts.2026.01.030 · Cited by 1
Rapid and interpretable protein contact map prediction using a pattern-matching strategy
Hacisuleyman, A., & Fasshauer, D. (2026) · Physical Biology · doi:10.1088/1478-3975/ae443c · Cited by 1
Lipinski, C., Tanifuji, R., Connolly, J. A., Breitling, R., Oguri, H., & Takano, E. (2026) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2026.103454 · Cited by 1
Roscovitine derivative optimization via molecular dynamics reveals potent and selective CDK5 binders
Botta, L., Carotenuto, G., Arcieri, M., Nisio, E. D., Perticaroli, V., Castrignanò, T., Saladino, R., & Negri, R. (2026) · Frontiers in Chemical Biology · doi:10.3389/fchbi.2026.1741100 · Cited by 1
Kim, D., & Lee, J. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02734 · Cited by 2
Structural landscape of bacterial urease: implications for catalyst and adaptation
Putri, A. N. H., Islami, R. H., Andrianto, D., Pratama, R., & Pangestu, R. (2026) · Archives of Microbiology · doi:10.1007/s00203-026-04767-z · Cited by 1
“…structural motifs and conformational states that could refine current prediction models, such as AlphaFold (Jumper et al. 2021) and RoseTTAFold (Baek et al. 2021), as well as novel regulatory elements and maturation pathways present in bacteria adapted to environmental niches distinct from…”
Laveglia, V., Ciofalo, C., Morelli, E., Andreini, C., & Rosato, A. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag078 · Cited by 1
Bridging structure and function: artificial intelligence-based modelling of kidney proteins
Wu, S., Wang, W., Zhou, Z. H., Scalzo, F., & Kurtz, I. (2026) · Nature Reviews Nephrology · doi:10.1038/s41581-026-01060-6 · Cited by 1
“…over 1D sequence and multiple sequence alignment (MSA) features, 2D residue–residue (“pair”) relationships (for example, distances or contacts) and 3D coordinates — thereby enabling joint processing of sequence, distance and coordinate data and producing accurate models even without templates 79 .”
InfluentialTawai, J., & Xiong, J. (2026) · Acta Pharmacologica Sinica · doi:10.1038/s41401-026-01756-2 · Cited by 2
“RoseTTAFold complements AlphaFold by rapidly generating high-accuracy protein-protein complex models directly from sequence, enabling fl exible-backbone modeling of regulatory interactions involving SLCs [57].”
Unexpected Applications of AlphaFold in Molecular Sciences
Jiang, J., Wang, G., Li, D., Hayes, N., Jones, B., Shi, Y., Qiu, H., Zhang, B. S. S., Zhou, T., & Wei, G.-W. (2026) · Annual Review of Biochemistry · doi:10.1146/annurev-biochem-051424-071952 · Cited by 3
All-atom MD simulations of amyloid–membrane interactions: Setup, execution, and analysis
Bundschuh, B. F., Kley, F., Fatafta, H., & Strodel, B. (2026) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2026.01.031 · Cited by 1
Liu, J., Lian, S., Zhu, C., & Zhu, G. (2026) · Biotechnology Advances · doi:10.1016/j.biotechadv.2026.108865 · Cited by 1
Bouhraoua, Y. H., Osmanli, Z., Tosatto, S. C. E., & Monzón, A. M. (2026) · Journal of Molecular Biology · doi:10.1016/j.jmb.2026.169755 · Cited by 1
Rose, B., Olivas, E. M., Prasad, P. R., Li, Z., Wang, F., Sroge, C., Talosig, A. R., Carpenter, B. P., Martin, R. W., Fowler, W. C., et al. (2026) · Chemistry of Materials · doi:10.1021/acs.chemmater.5c02998 · Cited by 1
Thermodynamic prediction of RNA cellular activity from sequence via conformational ensembles
Geng, A., Roy, R., Ken, M. L., Li, L., Chime, A., Assi, H. A., Liu, B., Bou‐Nader, C., Lee, Y., Zhang, J., et al. (2026) · Cell · doi:10.1016/j.cell.2026.02.021 · Cited by 4
Context-informed subgraph foundation models enable interpretable protein-function prediction
Zhou, Z., Rao, J., Zhang, Z., Ma, R., Yang, J., & Zheng, S. (2026) · Cell Systems · doi:10.1016/j.cels.2026.101535 · Cited by 1
Martínez, R., Vásquez, C., Vásquez, V., Novoa-González, J., Poblete, J., Onoda, A., Sadr, A. S., Davari, M. D., & Bernal, C. (2026) · Catalysts · doi:10.3390/catal16030280 · Cited by 1
Neonatal Fc receptor (FcRn)-targeted design of protein nanocages for sustained circulation
Lee, Y., Kang, D., Ahn, W., Kwon, S., Hu, Y., Kim, N. R., Go, Y., Shin, K.-H., & Lee, E. J. (2026) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2026.151611 · Cited by 1
Best Practices in Mixed-Solvent Molecular Dynamics and Solvent-Site-Biased Docking
Prieto, J. M., Estrada, J. A. D. C., Clemente, C. M., & Marti, M. A. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00082 · Cited by 1
ProtCross: Bridging the PDB-AlphaFold Gap for Binding Site Prediction with Protein Point Clouds
Zhong, S., & Jiang, Y. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c03224 · Cited by 2
Persistent Local Laplacian Prediction of Protein–Ligand Binding Affinities
Liu, J., & Feng, H. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c02460 · Cited by 1
Anticalins: A viable alternative to nanobodies? –from discovery to AI-driven development: A review
Luo, Y., Zhang, J., Dong, Z., & Ding, Y. (2026) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2026.151623 · Cited by 2
Polymerized Short Sequences as a Template for Protein Folding and Evolution
Jin, T., Sass, J., Gao, W., Hurst, A. A., Coley, C. W., & Alexander‐Katz, A. (2026) · Nano Letters · doi:10.1021/acs.nanolett.6c00527 · Cited by 2
Accurate protein-protein interactions modeling through physics-informed geometric invariant learning
(2026) · doi:10.1038/s42003-026-09809-2 · Cited by 1
“Furthermore, the accuracy of contact restraints can be utilized as a custom scoring function to refine the final pre-64 dictions of methods like AlphaFold [11] and RosettaFold [9].”
Generative Artificial Intelligence-Empowered Virtual Evolution of Enzyme with the VERnet Model
Li, C., Xu, W., Yang, H., Li, Y., Zhang, L., Chen, Z., Wang, S., Xie, Y., Li, H., Liu, Y., et al. (2026) · ACS Catalysis · doi:10.1021/acscatal.6c00759 · Cited by 1
β‐Triketone‐Based Ionizable Cationic Lipids Synthesized via Click Chemistry for siRNA Delivery
Li, H., Tang, H., Mu, Y., Chen, S., Floreancig, P. E., Wang, J., Huang, Y., & Li, S. (2026) · Advanced Science · doi:10.1002/advs.202515482 · Cited by 1
“A siRNA duplex was modeled with AlphaFold 3 [ 56 ] and embedded in explicit TIP3P water together with six cationic lipid molecules, giving a negative: positive charge ratio of ≈ 3:1 in accordance with the formulation protocol.”
Self-citationAndris, E., Kormaník, J. M., Kalvoda, T., Řezáč, J., & Rulı́šek, L. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02330 · Cited by 1
Peña-Ortiz, L. J., Hernández‐Pérez, J. M., León‐Chávez, B. A., Eguibar, J. R., Solano-Altamirano, J. M., & Vargas-Castro, V. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27073297 · Cited by 1
Clement, H. C., Corrales-García, L., Carpanta, V., Jaimes, G., Montero-Dominguez, P. A., Diego‐García, E., & Corzo, G. A. (2026) · Amino Acids · doi:10.1007/s00726-026-03521-5 · Cited by 1
“The three-dimensional models for Bs2 were created by using the algorithms I-Tasser (Zhou et al. 2022), Alpha-Fold (Abramson et al. 2024), Modeller (Sali 1995), and Rosetta-Fold (Baek et al. 2021 ).”
Use of hydrogen deuterium exchange mass spectrometry in tandem with modern structural biology
Nyvall, H. G., Shaw, A. L., Walsh, E. E., Bhatti, H., & Burke, J. E. (2026) · Biochemical Journal · doi:10.1042/bcj20250131 · Cited by 2
Self-citationSelvaraj, A., Jayawant, M., Kayalvizhi, N., Krishnan, M., Puvaneshvari, N., Kumar, A. W. S., & Rameshkumar, N. (2026) · Methods · doi:10.1016/j.ymeth.2026.04.006 · Cited by 1
Shen, R., Zhao, M., Wang, W., & Dong, H. (2026) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.6c00485 · Cited by 1
How and Why Does Knowledge‐Based Biased Docking Improve Molecular Docking Performance?
Prieto, J. M., Lannot, J. O., Clemente, C. M., Modenutti, C. P., Turjanski, A. G., & Marti, M. A. (2026) · ChemMedChem · doi:10.1002/cmdc.202501058 · Cited by 1
“More recently, AI-based methods such as AlphaFold-Multimer [41] and RoseTTAFold [42] have shown a remarkable ability to predict protein – protein complex structures directly from sequences, without requiring preexisting structural information.”
Deepasree, K., & Ramaiah, S. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1822250 · Cited by 1
“Due to this unavailability of a template protein, the query sequence was submitted to AlphaFold Colab (a Google DeepMind software) and RoseTTAFold (an ab initio modelling tool) to predict the three-dimensional structure (Jumper et al., 2021; Mirdita et al., 2022; Baek et al., 2021).”
Advances and opportunities for computational interrogation of plant proteins
Bohling, S. M., Musharoff, S. A., & Gunn, L. H. (2026) · The Plant Journal · doi:10.1111/tpj.70899 · Cited by 2
Iqbal, S., Chen, J., Pal, D., & Shen, B. (2026) · Drug Discovery Today · doi:10.1016/j.drudis.2026.104687 · Cited by 1
Marine microalgal biofuels: toward a systems-based circular biofactory
Feng, S., Ngo, H. H., Cai, Z., Guo, W., & Zhang, H. (2026) · Trends in biotechnology · doi:10.1016/j.tibtech.2026.04.006 · Cited by 1
Using generative AI to transform peptide hits into small molecule leads
Mills, J., & Lau, Y. H. (2026) · Beilstein Journal of Organic Chemistry · doi:10.3762/bjoc.22.51 · Cited by 1
Estimating the EGFR Ligand‐Binding Affinity and Pose via Molecular Docking Simulations
Nguyen, H. A., Vu, V. V., Quang, D. T., & Ngô, S. T. (2026) · ChemistrySelect · doi:10.1002/slct.202502695 · Cited by 1
Downstream processes: Fundamental and novel insights
Ebrahimi, M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-12-819533-8.00007-5 · Cited by 1
Roy, R. S., Oh, J., Abeer, A. N. M. N., Giraldo, M. I., Ikegami, T., Weaver, S. C., Vasilakis, N., Yoon, B.-J., & Qian, X. (2026) · NAR Molecular Medicine · doi:10.1093/narmme/ugag024 · Cited by 1
Howard, J. B., Narayanasamy, A., & Lindert, S. (2026) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.6c00265 · Cited by 1
Aggad, W. S., Mishra, S. K., Alqahtani, T., Guendouzi, A., TÓTH, Z., & Zaki, M. E. A. (2026) · Virus Research · doi:10.1016/j.virusres.2026.199746 · Cited by 1
“Furthermore, the 3D structure of the constructed vaccine was modelled via Robetta (Baek et al., 2021).”
The Shape of Things to Come: α-Helical Membrane Protein Folding on the Ribosome
Lambden, E., Lewis, B. R., Baker, Z. L. R., Dilworth, M. V., Johnston, E. C., Palacios‐Ortega, J., Patel, K., Pilkington, C. P., Findlay, H. E., Booth, P. J., et al. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.6c00236 · Cited by 1
EpiMII: Structure-Aware Graph Neural Networks for MHC-II Epitope Generation
Yuan, J., Xu, X., Sun, Z., Zhu, S., Wei, C., Liang, T., Ge, J., Xie, X., Chen, Y., Feng, Z., et al. (2026) · Research · doi:10.34133/research.1311 · Cited by 2
Quantum-inspired Bayesian probability algorithm for nuclear mass predictions
Tan, K., Liu, J., & Wang, C. (2026) · Physical Review C · doi:10.1103/ysj2-1g7q · Cited by 1
The evolution of display technologies for antibody drug discovery
Rojo-Gallegos, J., Tang, J. Q., Yarmarkovich, M., & DeKosky, B. J. (2026) · Trends in biotechnology · doi:10.1016/j.tibtech.2026.04.021 · Cited by 1
Carbohydrate-decorated NHC–metal complexes: from bioorganometallic design to biomedical function
Franklin, M., & Das, R. (2026) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2026.218102 · Cited by 1
Salehi, S., Mottaghi-Dastjerdi, N., Shahbazi, B., Ahmadi, N., Ghorbani, A., Soltany‐Rezaee‐Rad, M., Yazdani, F., Khoshdel, F., & Niazi, M.-J. (2026) · Discover Oncology · doi:10.1007/s12672-026-04783-x · Cited by 1
Protein language models for structural biology
Xiang, C., Cheng, B., Peng, Z., & Yang, J. (2026) · Nature Computational Science · doi:10.1038/s43588-026-00993-z · Cited by 2
Duncan, M., Sylvester, T. P., Walden, E., Lozano, J. R., Turner, E., Duncan, S., Mitchell, R. F., McKenna, D. D., & Adams, R. (2026) · Insects · doi:10.3390/insects17060587 · Cited by 2
“We predicted structures for all 122 TETRA ORs using two deep learning models: AlphaFold version 2.3.2 [11] and RoseTTAFold version All-Atom (RFAA) [9].”
InfluentialStructural and functional mapping of protective human monoclonal antibodies against enterovirus A71
Zhou, D., Kotecha, A., Kelly, J. T., Huang, P.-N., Chen, Y., Walter, T. S., Duyvesteyn, H. M. E., Owens, R. J., Ho, S., Lin, T., et al. (2026) · Science Advances · doi:10.1126/sciadv.aee8217 · Cited by 1
“Although there has been considerable progress in the use of AI methods for predicting protein structure ( 38 , 39 ), antibodies remain especially challenging, and the substantial set of structural data presented here may contribute to improving the algorithms.”
Molecular basis for the dopamine reuptake and inhibition mechanism of human dopamine transporter
Yin, J., Liu, C., Zhang, S., Xie, M., Yuan, X., Wang, Y., Chen, M., Zhou, N., Yang, Z., Chen, M., et al. (2026) · Structure · doi:10.1016/j.str.2026.05.005 · Cited by 1
Exploring ligand flexibility in nucleic acid scaffolds using graph neural networks
Zeng, C., Gao, J., Liu, H., Zhuo, C., & Zhao, Y. (2026) · Biophysical Journal · doi:10.1016/j.bpj.2026.06.010 · Cited by 1
Richter, V. P., Osman, A. M., Guella, F. L., Werhli, A. V., & Machado, K. (2026) · ACM Symposium on Applied Computing · doi:10.1145/3748522.3779838 · Cited by 1
Kapoor, J., Panda, A., Rajagopal, R., Kumar, S., & Bandyopadhyay, A. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00870 · Cited by 3
Emerging technologies for the discovery of biosynthetic genes in plants
Jaczkowski, A., Bültemeier, A., Seligmann, B., Pucker, B., & Franke, J. (2026) · Natural Product Reports · doi:10.1039/d6np00011h · Cited by 1
Greife, A., Liu, R., Köhler, P. S., Heinze, K. G., Hemmen, K., & Peulen, T.-O. (2026) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2026.1814859 · Cited by 1
“However, we demonstrated how limited information can be useful to falsify competing structural models by combining structural prediction tools such as AlphaFold (Abramson, et al., 2024) or RoseTTAFold (Baek et al., 2021) with integrative coarse-grained approaches for multi-scale simulations in the Integrative Modeling…”
Singh, S., Singh, R., & Sharma, S. (2026) · BioData Mining · doi:10.1186/s13040-026-00577-7 · Cited by 2
Reverse engineering of BNIP3 identifies a mitochondrial protective peptide
Hendgen-Cotta, U. B., Roth, A., Beuck, C., Messiha, D., Settelmeier, S., Shah, S. B., Korste, S., Bravo‐Rodriguez, K., Blueggel, M., Cansiz, F., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-73993-2 · Cited by 1
The role of protein embeddings for protein–protein interaction prediction with graph neural networks
Balbi, L., Sousa, R. T., Cotovio, P. G., & Pesquita, C. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag313 · Cited by 1
Ahmad, M., Iqbal, M. W., Mirza, M. U., Raza, M. A., Alghamdi, H. A., Haider, S. Z., Nawaz, M. Z., & Yu, K. (2026) · Enzyme and Microbial Technology · doi:10.1016/j.enzmictec.2026.110927 · Cited by 1
Bullough, P. A., Wilson, J. S., Berry, H. L., & Fagan, R. P. (2026) · IUCrJ · doi:10.1107/s2052252526005105 · Cited by 1
Mechanistic insights into DCPIB inhibition of VRAC: Electrostatic control and binding plasticity
Gaitán‐Peñas, H., Llabrés, S., Pedrola, M., González‐Subías, M., Juárez‐Jiménez, J., Pusch, M., Lavilla, R., & Estévez, R. (2026) · The Journal of General Physiology · doi:10.1085/jgp.202513953 · Cited by 1
Esler, M. A., Werther, R. A., Doyle, L., Ubilla‐Rodriguez, N. C., Schwensen, J. S., Hallinan, J. P., Lambert, A. R., Young, J. C., Silverstein, M., & Stoddard, B. L. (2026) · Nucleic Acids Research · doi:10.1093/nar/gkag608 · Cited by 1
Huang, Y., Ge, R., Wu, L., Sun, Y., Wang, Z., & Cao, M. (2026) · ACS Synthetic Biology · doi:10.1021/acssynbio.6c00199 · Cited by 1
Seo, Y. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27135774 · Cited by 1
“Membrane proteins remain underrepresented in many training sets, binding sites may be state-dependent, and lipids or accessory subunits can create determinants that static structures do not capture [66,67].”
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.