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 3,001–3,100 of 5,636
Structures and Molecular Mechanisms of Insect Odorant and Gustatory Receptors
Zhang, X., Ma, D., Wang, J., Su, N., & Guo, J. (2025) · Physiology · doi:10.1152/physiol.00011.2025 · Cited by 5
Self-citationQin, L., Zhang, X., Li, Y., Shi, J., Li, Y., Han, Y., Luo, H., Wang, D., Lin, Y., & Ye, H. (2025) · Biology · doi:10.3390/biology14070840 · Cited by 5
Evolution of macromolecular crystallography beamlines at the Swiss Light Source and SwissFEL
Wang, M. (2025) · Journal of Synchrotron Radiation · doi:10.1107/s1600577525005016 · Cited by 5
A systematic survey of type I secretion systems and their substrate proteins in Salmonella
Yu, M., Chen, Y., Cao, X., Chen, Z., Su, S., Wu, J., Sun, L., Lu, Q., Zhang, C., Deng, Z., et al. (2025) · Virulence · doi:10.1080/21505594.2025.2533414 · Cited by 5
“AlphaFold [35] and RoseTTAFold [36] were used to predict the tertiary structures of the full-length or fragmental SiiE peptides.”
Bioinformatic Analysis of WNT Family Proteins
Midlovets, K. K., Volkova, N. E., & Peka, M. (2025) · Bioinformatics and Biology Insights · doi:10.1177/11779322251353347 · Cited by 5
“To model the full-size tertiary structure of WNT2B (Q93097-1), several tools were used in parallel, including those based on both deep-learning algorithms (AlphaFold3, RoseTTAFold, D-I-TASSER, and DMPfold2) and homology modeling (SWISS-MODEL server).”
InfluentialZhao, Z., Qu, Q., Sun, F., Zang, J., Zheng, B., Zhang, T., Zhao, G., Lv, C., & Wang, Z. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108656 · Cited by 5
Cui, Z., Zhou, T., Wang, Y., Zhang, D., Gu, J., Zhang, Z., Feng, X., Wang, W., & Liu, Y. (2025) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.5c02782 · Cited by 5
Panda, A., Kapoor, J., Hareramadas, B., Naqvi, I., Ganta, S., Chhabra, R., Kumar, S., & Bandyopadhyay, A. (2025) · The Journal of Membrane Biology · doi:10.1007/s00232-025-00360-5 · Cited by 5
“…model. expasy. org/) (accessed on 20 December, 2024) (A. Waterhouse et al. 2018), RoseT-TAFold (https:// robet ta. baker lab. org/) (accessed on 24 December, 2024) (Baek et al. 2021), and TrRosetta (https:// yangl ab. qd. sdu. edu. cn/ trRos etta/) (accessed on 24 December, 2024) (Du et al. 2021).”
Jung, K., Jo, I.-H., Choi, B. Y., & Kim, J. (2025) · BioTech · doi:10.3390/biotech14030073 · Cited by 6
Are amyloid-based materials conducive to tissue engineering?
Patel, K., & Maji, S. K. (2025) · Trends in biotechnology · doi:10.1016/j.tibtech.2025.08.009 · Cited by 5
Kunze, R., Navratil, F., Beichert, J., Geyer, F. K., Floss, D. M., Kolmar, H., Scheller, J., & Pudewell, S. (2025) · mAbs · doi:10.1080/19420862.2025.2563009 · Cited by 5
Strategies to Improve the Efficiency of Enzymatic Carbon Dioxide Conversion In Vitro
Li, J., Zhao, S., Guo, F., Zhang, W., Chen, M., den Haan, R., Xin, F., Jiang, Y., & Jiang, M. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.5c00760 · Cited by 5
Reimagining Polymer Networks from Molecule to Material
Nechmad, N. B., Campos, L. M., Craig, S. L., Deng, C., Diodati, J., Ekim, S. D., Villatoro, E. A. G., Gong, J. P., Herzog‐Arbeitman, A., Huang, X., et al. (2025) · Macromolecules · doi:10.1021/acs.macromol.5c02040 · Cited by 8
Toward the Chemoenzymatic Synthesis of DNA-Encoded Libraries
Schaub, D., Lessing, A., von Haugwitz, G., Meyer, F., Scheuermann, J., & Buller, R. (2026) · ACS Central Science · doi:10.1021/acscentsci.5c01516 · Cited by 6
Kapoor, J., Panda, A., Naqvi, I., Ganta, S., Kumar, S., & Bandyopadhyay, A. (2026) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70118 · Cited by 5
“Although the pLDDT scores were high, we modeled each protein with four additional tools: ESMFold [38], SWISS-MODEL [39], RoseTTAFold [40], and TrRosetta [41] (all tools accessed on October 15, 2024) to enhance confidence in the structural predictions.”
Synergizing Chemical and AI Communities for Advancing Laboratories of the Future
Oh, S., Fang, X., Lin, I.-H., Dee, P., Dunham, C. S., Copp, S. M., Doyle, A. G., de Alaniz, J. R., & Gu, M. (2026) · ACS Central Science · doi:10.1021/acscentsci.5c01994 · Cited by 7
Bora bridges Aurora-A activation and substrate recognition of PLK1
Miles, J. A., Batchelor, M. R., Walko, M., Gunning, V., Wilson, A. J., Wright, M. H., & Bayliss, R. W. (2026) · EMBO Reports · doi:10.1038/s44319-025-00687-z · Cited by 5
“…advancements in computational modelling that enable accurate predictions of the structures of proteins and their complexes (Bryant et al , 2022; Baek et al , 2021), and specifically AlphaFold3 which has the capability to include phosphorylated side-chains, ligands and ions (Abramson et al ,…”
Barducci, G., Rossi, I., Codicè, F., Rollo, C., Repetto, V., Pancotti, C., Iannibelli, V., Sanavia, T., & Fariselli, P. (2026) · Communications Biology · doi:10.1038/s42003-026-09632-9 · Cited by 10
Computational approaches for RNA structure prediction and design
Kagaya, Y., Liu, B., & Kihara, D. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103097 · Cited by 7
Structural ontogeny of protein-protein interactions
Yang, A., Jiang, H., Jude, K. M., Akpinaroglu, D., Allenspach, S., Li, A. J., Bowden, J., Perez, C. P., Liu, L. D., Huang, P., et al. (2026) · Science · doi:10.1126/science.adx6931 · Cited by 7
Uemura, K., Hiro, S., Attachaipanich, S., Du, R., Yusof, N. I. S. M., Kinoshita, M., Hikosaka, M., & Ohtsuki, G. (2026) · Frontiers in Cellular Neuroscience · doi:10.3389/fncel.2025.1669272 · Cited by 7
Protein dynamics prediction by integrating biophysics and artificial intelligence
Huang, H., Guan, X., Li, W., Zhang, J., & Wang, W. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103223 · Cited by 8
Generative AI for synthetic biology: Designing biological parts, circuits, and genomes
Kim, N., Carluccio, G. D., Zhang, K., & Collins, J. J. (2026) · Cell Systems · doi:10.1016/j.cels.2026.101533 · Cited by 13
“60 These advances were supported by DL-based sequence-to-structure prediction models 51–55 and structure-to-sequence inverse folding frameworks such as ProteinMPNN 61 and LigandMPNN.”
Molecular Modeling and machine learning for predicting high-concentration antibody viscosity
Baizhigitova, D., Wu, I.-E., Kalejaye, L. A., & Lai, P. (2026) · Advanced Drug Delivery Reviews · doi:10.1016/j.addr.2026.115839 · Cited by 5
Jing, Q., Liu, H., & Wu, D. (2026) · Sensors & Diagnostics · doi:10.1039/d5sd00200a · Cited by 5
Reccia, M., Quilli, F., Willems, K., della Rocca, B. M., Raimondo, D., & Chinappi, M. (2026) · Journal of Nanobiotechnology · doi:10.1186/s12951-026-04225-4 · Cited by 5
“The Rosetta suite [225, 226] (that includes a wide range of tools for modelling and analysing macromolecules) and its deep learning-based extension RoseTTAFold [227] have been used for de novo design of transmembrane pores.”
Lin, H., Vogel, H., & Zhang, H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27073142 · Cited by 5
AI-Designed Peptides as Tools for Biochemistry
Hong, L., Vincoff, S., & Chatterjee, P. (2026) · Biochemistry · doi:10.1021/acs.biochem.6c00138 · Cited by 9
Bonin, J. P., Lee, J. S., Liu, Z. H., Kim, P. M., & Kay, L. E. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2537014123 · Cited by 5
“While computational approaches are now widely available for predicting structures of GS conformations (12, 13), they are much less efficient in generating accurate representations of excited states for which little experimental data are available for training (14).”
Jang, Y. E., Kwon, M., Kwon, C. W., Kim, S. G., Hwang, J. S., George, N. P., Paik, S. R., Misra, S., Basith, S., Sheen, S. S., et al. (2026) · Pharmaceutics · doi:10.3390/pharmaceutics18050537 · Cited by 7
Self-citationAbiotic stress sensing in plants: Biochemical and biophysical basis
Lv, Q., Li, J. M., Liu, C., Samraoui, K. R., Hutin, S., Li, X., Dong, F., Xiong, H., Ouyang, Y., Hu, H., et al. (2026) · Molecular Plant · doi:10.1016/j.molp.2026.05.007 · Cited by 8
A Foundation Model of Cancer Genotype Enables Precise Predictions of Therapeutic Response
Kong, J., Lee, I., Boecher, D., Singhal, A., Kelly, M. R., Moon, J., Ahn, C. H., Ock, C., Pratt, D. R., Kumar, T., et al. (2026) · Cancer Discovery · doi:10.1158/2159-8290.cd-25-1735 · Cited by 5
AI for science: Progress, challenges, and perspectives
Xu, Y., Shao, Z., Liu, X., Li, Y., An, Z., Fu, C., Huang, C., Zhang, L., Gao, F., Li, J., et al. (2026) · The Innovation · doi:10.1016/j.xinn.2026.101530 · Cited by 15
Self-citationTryptoline stereoprobe elaboration identifies inhibitors of the GRPEL1–HSPA9 complex
Hayward, R. E., Berkeley, R. F., Gao, Z., Garhammer, M., Morizono, M. A., Njomen, E., Li, H., DeMeester, K. E., Cociorva, V., Herzik, M. A., et al. (2026) · Nature Chemical Biology · doi:10.1038/s41589-026-02348-1 · Cited by 7
Dipolar Order Parameters in Large Systems With Fast Spinning
Franks, W. T., Tatman, B. P., Trenouth, J., & Lewandowski, J. R. (2021) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2021.791026 · Cited by 5
“, 2021) and RoseTTAFold (Baek et al., 2021) there is an almost exponential increase of systems for which a reasonable quality structure or models become available.”
BackgroundMethodIntegration of machine learning with computational structural biology of plants
Chen, J., & Shukla, D. (2022) · Biochemical Journal · doi:10.1042/bcj20200942 · Cited by 5
Li, B., Jin, B., Capra, J. A., & Bush, W. S. (2022) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-122220-112147 · Cited by 5
Comprehensive Linear Epitope Prediction System for Host Specificity in Nodaviridae
Shih, T.-C., Ho, L.-P., Chou, H., Wu, J., & Pai, T. (2022) · Viruses · doi:10.3390/v14071357 · Cited by 5
“We applied both the empirical approaches (Phyre2 [25] and I-TASSER [26]) and state-of-the-art computational (RoseTTAFold) [27] methods.”
MethodThe bacterial virulence factor NleA undergoes host‐mediated O‐linked glycosylation
Burns, L., Giannakopoulou, N., Zhu, L., Xu, Y. Z., Khan, R. H., Békal, S., Schurr, E., Schmeing, T. M., & Gruenheid, S. (2022) · Molecular Microbiology · doi:10.1111/mmi.14989 · Cited by 5
Madarász, K., Mótyán, J. A., Bedekovics, J., Miltényi, Z., Újfalusi, A., Méhes, G., & Mokánszki, A. (2022) · Cells · doi:10.3390/cells11213475 · Cited by 5
Bioinformatical Approaches to the Discovery and Classification of Novel Deubiquitinases
Hermanns, T., & Hofmann, K. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-2803-4_9 · Cited by 5
Cryo-EM structure of the diapause chaperone artemin
Parvate, A. D., Powell, S. M., Brookreson, J. T., Moser, T. H., Novikova, I. V., Zhou, M., & Evans, J. E. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.998562 · Cited by 5
“(Figure 3) (Baek et al., 2021; Jumper et al., 2021) show a similar fold for the core region (as expected due to high homology with ferritin), but they fail to capture the C-terminal loop L’ and full helix F positioning.”
BackgroundSolution of the protein structure prediction problem at last: crucial innovations and next frontiers
Agard, D. A., Bowman, G. R., DeGrado, W. F., Dokholyan, N. V., & Zhou, H. (2022) · Faculty Reviews · doi:10.12703/r-01-0000020 · Cited by 5
A novel homozygous synonymous splicing variant in SELENOI gene causes spastic paraplegia 81
Sarma, A. S., Bathula, S., Pragna Lakshmi, T., Ranganath, P., & Dalal, A. B. (2023) · The Journal of Gene Medicine · doi:10.1002/jgm.3501 · Cited by 5
Functional analysis of acyl-CoA dehydrogenases and their application to C22 steroid production
Yuan, C., Li, Y., Han, S., He, B., Zhai, X., Lin, W., Shi, J., Sun, J., & Zhang, B. (2023) · Applied Microbiology and Biotechnology · doi:10.1007/s00253-023-12541-0 · Cited by 5
Structural insights of the toxin-antitoxin system VPA0770-VPA0769 in Vibrio parahaemolyticus
Zhang, Y., Song, X., Chen, C., Liu, L., Xu, Y., Zhang, N., Huang, W., Zheng, J., Yuan, W., Tang, L. M., et al. (2023) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2023.124755 · Cited by 5
Protein model quality assessment using rotation‐equivariant transformations on point clouds
Eismann, S., Suriana, P., Jing, B., Townshend, R. J. L., & Dror, R. O. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26494 · Cited by 5
Molecular dynamics simulations identify the topological weak spots of a protease CN2S8A
Ma, Z., Mu, K., Zhu, J., Xiao, M., Wang, L., & Jiang, X. (2023) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2023.108571 · Cited by 5
Lu, X., Lan, X., Lu, S., & Zhang, J. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102701 · Cited by 5
Investigations of Single-Subunit tRNA Methyltransferases from Yeast
Wang, Z., Xu, X., Li, X., Fang, J., Huang, Z., Zhang, M., Liu, J., & Qiu, X. (2023) · Journal of Fungi · doi:10.3390/jof9101030 · Cited by 5
“…RosettaFold server [42] (robetta.bakerlab.org; To search for the potential substrate tRNA-binding region of yeast single-subunit TRMs, structure predictions of Trm1–5p, Trm12p, Trm13p, and Trm44p were carried out by using the Rose tt aFold server [42] (robe tt a.bakerlab accessed on 1 March 2023).”
MethodCamphecene and ginsamide: dynamics of potential interactions with the influenza virus M2 channel
Borisevich, S. S., & Gureev, M. (2023) · Russian Chemical Bulletin · doi:10.1007/s11172-023-4057-x · Cited by 5
Characterization and Diversification of AraC/XylS Family Regulators Guided by Transposon Sequencing
Pearson, A. N., Incha, M. R., Ho, C. N., Schmidt, M., Roberts, J. B., Nava, A. A., & Keasling, J. D. (2024) · ACS Synthetic Biology · doi:10.1021/acssynbio.3c00441 · Cited by 5
Li, Z., Fan, H.-F., & Ding, W. (2024) · IUCrJ · doi:10.1107/s2052252523010291 · Cited by 5
Carder, J. D., Barile, B., Shisler, K. A., Pisani, F., Frigeri, A., Hipps, K. W., Nicchia, G. P., & Brozik, J. A. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.3c04529 · Cited by 5
Drugging the entire human proteome: Are we there yet?
Smith, M. D., Quarles, L. D., Demerdash, O., & Smith, J. C. (2024) · Drug Discovery Today · doi:10.1016/j.drudis.2024.103891 · Cited by 6
RNA threading with secondary structure and sequence profile
Du, Z., Peng, Z., & Yang, J. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae080 · Cited by 5
Liu, H., Liu, C., Zhang, W., Yuan, Y., Wang, Z., & Huang, J. (2024) · Journal of Proteomics · doi:10.1016/j.jprot.2024.105126 · Cited by 7
Ahmad, F., Tomada, S., Poonsiri, T., & Baric, S. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1291542 · Cited by 6
Kamada, Y., Umeda, C., Mukai, Y., Ohtsuka, H., Otsubo, Y., Yamashita, A., & Kosugi, T. (2024) · Journal of Cell Science · doi:10.1242/jcs.261625 · Cited by 5
Gisdon, F. J., Zunker, M., Wolf, J. N., Prüfer, K., Ackermann, J., Welsch, C., & Koch, I. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae112 · Cited by 6
Fang, T., Szklarczyk, D., Hachilif, R., & von Mering, C. (2024) · Scientific Reports · doi:10.1038/s41598-024-55655-9 · Cited by 6
Simple Scattering: Lipid nanoparticle structural data repository
Kim, L. J., Shin, D. S., Leite, W. C., O’Neill, H., Ruebel, O., Tritt, A., & Hura, G. L. (2024) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2024.1321364 · Cited by 5
Harwardt, J., Geyer, F. K., Schoenfeld, K., Baumstark, D., Molkenthin, V., & Kolmar, H. (2024) · Antibodies · doi:10.3390/antib13020036 · Cited by 6
Embracing artificial intelligence design for better radiopharmaceuticals
Tao, J., Kong, X., Yang, Z., & Zhu, H. (2024) · iRadiology · doi:10.1002/ird3.76 · Cited by 5
Evidence for a compact σ70 conformation in vitro and in vivo
Joron, K., Zamel, J., Kalisman, N., & Lerner, E. (2024) · iScience · doi:10.1016/j.isci.2024.110140 · Cited by 5
Comparative proteomics of a versatile, marine, iron‐oxidizing chemolithoautotroph
Barco, R. A., Merino, N., Lam, B. R., Budnik, B., Kaplan, M., Wu, F., Amend, J. P., Nealson, K. H., & Emerson, D. (2024) · Environmental Microbiology · doi:10.1111/1462-2920.16632 · Cited by 7
Oliayi, M., Emamzadeh, R., & Nazari, M. (2024) · Biochemical Engineering Journal · doi:10.1016/j.bej.2024.109402 · Cited by 5
Molecular Basis of MC1R Activation: Mutation‐Induced Alterations in Structural Dynamics
Cavatão, F. G., Pinto, É. S. M., Krause, M. J., Alho, C. S., & Dorn, M. (2024) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26722 · Cited by 5
Takasawa, T., Matsui, T., Watanabe, G., & Kodera, Y. (2024) · Scientific Reports · doi:10.1038/s41598-024-66763-x · Cited by 5
Multhoff, J., Niemeier, J.-O., Zheng, K., Lim, M. S. S., Barreto, P., Niebisch, J. M., Ischebeck, T., & Schwarzländer, M. (2024) · Journal of Experimental Botany · doi:10.1093/jxb/erae398 · Cited by 5
Hovorková, M., Kaščáková, B., Petrásková, L., Havlíčková, P., Nováček, J., Pinkas, D. M., Gardian, Z., Křen, V., Bojarová, P., & Smatanová, I. K. (2024) · Structure · doi:10.1016/j.str.2024.09.005 · Cited by 5
Ding, S., Cai, Z., Wu, Y., Zhang, H., & Shen, X. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112591 · Cited by 5
Khalil, H. B. (2024) · Genes · doi:10.3390/genes15101306 · Cited by 5
“The Robetta server, a robust protein structure prediction tool, was employed to generate the most accurate models (https://robetta.bakerlab.org/ [42 ]).”
MethodPrédiction de structures biomoléculaires complexes par AlphaFold 3
Taly, A., & Verger, A. (2024) · médecine/sciences · doi:10.1051/medsci/2024124 · Cited by 5
Artificial intelligence in drug discovery: Current applications and future directions
Alanazi, A. A. A., Fahad, . I. A. A., Almorshed, A. S. A., Alrbian, A. A. M., Alnughaymishi, A. A. S., Al-Mutairi, N. H. B., Alajmi, A. A., & Otaibi, S. G. A. (2022) · International Journal of Health Sciences · doi:10.53730/ijhs.v6ns10.15290 · Cited by 5
“One useful exercise in structure-based medication design is the comparative examination of protein-binding pockets at the structural genomics scale [96].”
BackgroundRyan‐Phillips, F., Henehan, L., Ramdas, S., Palace, J. A., Beeson, D., & Dong, Y. Y. (2024) · Biomedicines · doi:10.3390/biomedicines12112549 · Cited by 6
“Furthermore, RosettaFold [14] and more recently AlphaFold3 have demonstrated significant advacements in the accurate prediction of protein-ligand interactions [15].”
Computational engineering of water-soluble human potassium ion channels through QTY transformation
Smorodina, E., Tao, F., Qing, R., Yang, S., & Zhang, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-76603-7 · Cited by 5
Jointly Embedding Protein Structures and Sequences through Residue Level Alignment
Birnbaum, F., Jain, S., Mądry, A., & Keating, A. E. (2024) · PRX Life · doi:10.1103/prxlife.2.043013 · Cited by 7
Lee, J., Kim, D., Jun, D. W., & Kim, Y. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01397 · Cited by 5
Jagadeesh, J., & Vembar, S. S. (2024) · Scientific Reports · doi:10.1038/s41598-024-79937-4 · Cited by 7
Gao, Y., Wang, H., Zhou, J., & Yang, Y. (2025) · Current Research in Structural Biology · doi:10.1016/j.crstbi.2024.100163 · Cited by 6
Deep learning methods for proteome-scale interaction prediction
Yoon, M. S., Bae, B., Kim, K. H., Park, H., & Baek, M. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102981 · Cited by 7
Self-citationda Silva, F. L. B., Paco, K., Laaksonen, A., & Ray, A. (2025) · Biophysical Reviews · doi:10.1007/s12551-025-01276-z · Cited by 7
Tang, X., Deng, J., He, C., Xu, Y., Bai, S., Guo, Z., Du, G., Ouyang, D., & Sun, X. (2025) · Journal of Controlled Release · doi:10.1016/j.jconrel.2025.113629 · Cited by 7
SELFprot: Effective and Efficient Multitask Finetuning Methods for Protein Parameter Prediction
Wilson, M. O., Coudrat, T., & Warden, A. C. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02230 · Cited by 6
Barkan, E., Siddiqui, I., Cheng, K. J., Golts, A., Shoshan, Y., Weber, J. K., Mota, Y. C., Ozery-Flato, M., & Sautto, G. A. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.03.038 · Cited by 6
“Breakthroughs in deep learning for protein structural modeling, particularly AlphaFold [21 – 23] and RoseTTAFold [53], have transformed efforts toward protein structure prediction.”
Mamun, Y., Aguado, A., Preza, A. M., Kadel, A., Mogallur, A., Gonzalez, B., Rosa, J. D. L., Diaz, D., Evdokimova, P., Karki, U., et al. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.03.041 · Cited by 5
“State-of-the-art structure prediction tools such as AlphaFold [2] and RoseTTaFold [3] have recently allowed researchers to predict structures of proteins and biomolecular complexes with unprecedented success.”
Recent developments in cystic fibrosis drug discovery: where are we today?
Lopes‐Pacheco, M., Winters, A. G., Jackson, J. J., Olson, J. A., Kim, M., Ledwitch, K. V., Tedman, A., Jhangiani, A. R., Schlebach, J. P., Meiler, J., et al. (2025) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2025.2490250 · Cited by 6
“Further, AI/ML-based tools like AlphaFold [113] and RoseTTAFold [114] have revolutionized protein structure prediction, achieving atomic-level accuracy with significantly faster computation times compared to conventional physics-based methods.”
Bioinformatic discovery of type 11 secretion system (T11SS) cargo across the Proteobacteria
Grossman, A. S., Mucci, N. C., Kauffman, S., Rafi, J., & Goodrich‐Blair, H. (2025) · Microbial Genomics · doi:10.1099/mgen.0.001406 · Cited by 8
AI-Empowered Genome Decoding: Applications of Large Language Models in Genomics
Li, S., Fan, W., & Zhou, Y. (2025) · Frontiers of digital education. · doi:10.1007/s44366-025-0051-1 · Cited by 4
Ferreira, T., Pereira, F. B., Gonçalves, F. A. M. M., da Costa, A., Cavaco-Paulo, A. M., & Castro, T. G. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.144813 · Cited by 5
Sequence-free landscape inference for directed evolution
Towers, S., James, J., Steel, H., & Kempf, I. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014713 · Cited by 6
Lopez-Mateos, D., Narang, K., & Yarov-Yarovoy, V. (2026) · Journal of General Physiology · doi:10.1085/jgp.202413705 · Cited by 5
Annotating the pangenome reveals the diversity in the genetic basis for metabolic enzymes
Ardalani, O., Phaneuf, P. V., Krishnan, J., Li, G., Burrows, J., Nielsen, L. K., & Palsson, B. Ø. (2026) · Science Advances · doi:10.1126/sciadv.aeb3363 · Cited by 5
Amunts, A. (2021) · Nature Plants · doi:10.1038/s41477-021-01050-5 · Cited by 5
Geerds, C., Bleymüller, W. M., Meyer, T., Widmann, C., & Niemann, H. H. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322000432 · Cited by 5
Mallery, E. L., Yanagisawa, M., Zhang, C., Lee, Y., Robles, L. M., Alonso, J. M., & Szymanski, D. B. (2022) · Journal of Cell Science · doi:10.1242/jcs.259825 · Cited by 7
Liu, H., Peck, X. Y., Choong, Y. K., Ng, W. S., Engl, W., Raghuvamsi, P. V., Zhao, Z., Anand, G. S., Zhou, Y., Sivaraman, J., et al. (2022) · Virology · doi:10.1016/j.virol.2022.03.010 · Cited by 5
Berger, T. M. I., Michaelis, C., Probst, I., Sagmeister, T., Petrowitsch, L., Puchner, S., Pavkov‐Keller, T., Gesslbauer, B., Grohmann, E., & Keller, W. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.867136 · Cited by 5
Self-citationSilué, N., & Campbell‐Valois, F. (2022) · mSphere · doi:10.1128/msphere.00115-22 · Cited by 6
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.