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 2,201–2,300 of 5,636
Plant‐specific small peptide AtZSP1 interacts with ROCK1 to regulate organ size in Arabidopsis
Zeng, Y., Tang, Y., Shen, S., Zhang, M., Chen, L., Ye, D., & Zhang, X. (2022) · New Phytologist · doi:10.1111/nph.18093 · Cited by 11
Hao, Z., Zhang, W., Wang, X., Wang, Y., Qin, X., Luo, H., Huang, H., & Su, X. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23084136 · Cited by 11
Meliawati, M., May, T., Eckerlin, J., Heinrich, D., Herold, A., & Schmid, J. (2022) · Applied and Environmental Microbiology · doi:10.1128/aem.00164-22 · Cited by 12
Mechanism of unusual AQP6 activation by mercury binding to a pore-external residue C155
Ma, S., Xie, H., Yu, K., & Yang, J. (2022) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2022.06.025 · Cited by 11
Contributions of Yersinia pestis outer membrane protein Ail to plague pathogenesis
Kolodziejek, A. M., Hovde, C. J., & Minnich, S. A. (2022) · Current Opinion in Infectious Diseases · doi:10.1097/qco.0000000000000830 · Cited by 11
“(b) The predicted Ail structure was generated using the deep learning-based modelling program, RoseTTAFold, and presented with UCSF Chimera [66,67].”
MethodComputational protein design with data‐driven approaches: Recent developments and perspectives
Liu, H., & Chen, Q. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1646 · Cited by 14
“In recent years, data-driven approaches to protein structure prediction and to protein design are gaining momentum, 5 – 7, 14, 15 Besides the task of predicting the structures (and subsequently the functions) of naturally existing proteins, an equally fundamental and challenging computational task…”
BackgroundMethodLearning Correlations between Internal Coordinates to Improve 3D Cartesian Coordinates for Proteins
Li, J., Zhang, O., Lee, S., Namini, A., Liu, Z. H., Teixeira, J. M. C., Forman-Kay, J. D., & Head-Gordon, T. L. (2023) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.2c01270 · Cited by 13
Rodrigues‐da‐Silva, R. N., Conte, F. D. P., da Silva, G., Carneiro-Alencar, A. L., Gomes, P. R., Kuriyama, S. N., Neto, A. A. F., & Lima‐Junior, J. D. C. (2023) · Viruses · doi:10.3390/v15040923 · Cited by 13
“org/, accessed on 10 September 2020) [20,21] based on the full-length amino acid sequence of the protein.”
BackgroundEnhanced sensitivity for pulse dipolar EPR spectroscopy using variable-time RIDME
Wort, J. L., Ackermann, K., Giannoulis, A., & Bode, B. E. (2023) · Journal of Magnetic Resonance · doi:10.1016/j.jmr.2023.107460 · Cited by 11
Singh, S., Machida, S., Tulsian, N. K., Choong, Y. K., Ng, J. D., Shankar, S., Liu, Y., Chandiramani, K. V., Shi, J. R., & Sivaraman, J. (2023) · Advanced Science · doi:10.1002/advs.202207672 · Cited by 15
Growing ecosystem of deep learning methods for modeling protein–protein interactions
Rogers, J. R., Nikolényi, G., & AlQuraishi, M. (2023) · Protein Engineering Design and Selection · doi:10.1093/protein/gzad023 · Cited by 15
Grady, C. J., Franco, E. A. C., Schossau, J., Ashbaugh, R. C., Pelled, G., & Gilad, A. A. (2024) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2024.1355915 · Cited by 11
New Frontiers for Machine Learning in Protein Science
Morgunov, A. S., Saar, K. L., Vendruscolo, M., & Knowles, T. P. J. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.167232 · Cited by 11
Chong, L. C., & Khan, A. M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00226-8 · Cited by 11
Multi-Scale Representation Learning on Proteins
Somnath, V. R., Bunne, C., & Krause, A. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.8102782 · Cited by 11
How to select the best model from AlphaFold2 structures?Preprint
Takei, Y., & Ishida, T. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.05.487218 · Cited by 11
Structural biology in the age of AI
Subramaniam, S. (2023) · Nature Methods · doi:10.1038/s41592-023-02123-3 · Cited by 13
Hetmann, M., Parigger, L., Sirelkhatim, H., Stern, A. C., Krassnigg, A., Gruber, K. F., Steinkellner, G., Ruau, D., & Gruber, C. C. (2024) · Scientific Data · doi:10.1038/s41597-024-03403-z · Cited by 11
“However, we would like to point out that there are additional sophisticated tools available for structural modeling, like RoseTTAFold 18 .”
MethodMSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-TrainingPreprint
Chen, B., Bei, Z., Cheng, X., Li, P., Tang, J., & Song, L. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.10.598380 · Cited by 11
Multi-state Protein Design with DynamicMPNN
Abrudan, A., Ojeda, S. P., Joshi, C. K., Greenig, M., Engelberger, F., Khmelinskaia, A., Meiler, J., Vendruscolo, M., & Knowles, T. P. J. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2507.21938 · Cited by 16
FlyPredictome: A structural atlas of predicted protein-protein interactions in DrosophilaPreprint
Kim, A., Comjean, A., Veal, A., Rodiger, J., Han, M., Hu, Y., & Perrimon, N. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.14.718529 · Cited by 14
(2023) · doi:10.7554/elife.83856 · Cited by 11
Ho, W., Huang, H., & Huang, J. (2023) · Protein Science · doi:10.1002/pro.4739 · Cited by 11
RNA contact prediction by data efficient deep learning
Taubert, O., von der Lehr, F., Bazarova, A., Faber, C., Knechtges, P., Weiel, M., Debus, C., Coquelin, D., Basermann, A., Streit, A., et al. (2023) · Communications Biology · doi:10.1038/s42003-023-05244-9 · Cited by 11
“Since the last CASP competition for protein structure prediction 34 , the most successful methods 8,35 harness the vast amounts of sequence and structure data 36 – 38 to train large end-to-end 5 transformer 39 models, where DeepMind ’ s attention-based AF2 program is the most prominent example.”
MethodUsing deep learning predictions of inter-residue distances for model validation
(2022) · doi:10.1101/2022.08.25.505292 · Cited by 11
Beutler, M., Harnischfeger, J., Weber, M. H. W., Hahnel, S. R., Quack, T., Blohm, A., Ueberall, M. E., Timm, T., Lochnit, G., Rennar, G. A., et al. (2023) · European Journal of Medicinal Chemistry · doi:10.1016/j.ejmech.2023.115179 · Cited by 10
Efficient protein structure generation with sparse denoising models
Jendrusch, M., & Korbel, J. O. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01100-z · Cited by 10
“23,39).”
A fully automated benchmarking suite to compare macromolecular complexes
Studer, G., Robin, X., Bienert, S., Durairaj, J., Škrinjar, P., Tauriello, G., Waterhouse, A. M., & Schwede, T. (2026) · Nature Methods · doi:10.1038/s41592-025-02973-z · Cited by 10
“However, despite the impressive recent progress in prediction accuracy, even the latest developments in the field of structure prediction such as AlphaFold 19,20 and RoseTTAFold 21 have their limitations, highlighting the importance of continuing benchmarking efforts in the future.”
Deep-learning structure elucidation from single-mutant deep mutational scanning
(2025) · doi:10.1038/s41467-025-62261-4 · Cited by 10
Learning from the unknown: exploring the range of bacterial functionality
Mahlich, Y., Zhu, C., Chung, H., Velaga, P. K., De Paolis Kaluza, M. C., Radivojac, P., Friedberg, I., & Bromberg, Y. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad757 · Cited by 10
Liu, J., Neupane, P., & Cheng, J. (2025) · Communications Biology · doi:10.1038/s42003-025-08960-6 · Cited by 10
Österlund, N., Vosselman, T., Leppert, A., Gräslund, A., Jörnvall, H., Ilag, L. L., Marklund, E. G., Elofsson, A., Johansson, J., Sahin, C., et al. (2022) · Molecular & Cellular Proteomics · doi:10.1016/j.mcpro.2022.100413 · Cited by 10
“Recently, the arrival of machine learning – driven protein structure prediction algorithms such as AlphaFold2 (AF2) and RosettaFold has enabled modeling of previously inaccessible protein complexes with an accuracy that rivals experimentally determined structures (23, 24).”
BackgroundKaushik, R. K., & Zhang, K. Y. J. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.11.032 · Cited by 10
“Depending on the approach used and availability of computational resources, the number of decoys may vary from hundreds to thousands [5,9,11,17].”
MethodMulti epitope vaccine candidate design against Streptococcus pneumonia
Devarakonda, Y., Reddy, M. V. N. J., Neethu, R. S., Chandran, A., & Syal, K. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2167123 · Cited by 13
“The three-track network produces structure predictions with accuracies approaching those of DeepMind at the recent 14th Critical Assessment of Structure Prediction (CASP 14) (Baek et al., 2021).”
Liu, Z., Li, Y., Wei, D., Wang, J., Qiao, C., Li, G., Zhang, G., & Luo, Y. (2023) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.2c00490 · Cited by 10
Self-citationCobb, T., Hwang, I., Soukar, M., Namkoong, S., Cho, U., Safdar, M., Kim, M., Wessells, R. J., & Lee, J. H. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2220556120 · Cited by 12
Ligand Modification-Free Methods for the Profiling of Protein-Environmental Chemical Interactions
Li, Y., Lyu, J., Wang, Y., Ye, M., & Wang, H. (2023) · Chemical Research in Toxicology · doi:10.1021/acs.chemrestox.3c00282 · Cited by 10
Sadeghi, A., Sadeghi, M., Fakhar, M., Zakariaei, Z., & Sadeghi, M. (2024) · Transboundary and Emerging Diseases · doi:10.1155/2024/6621199 · Cited by 12
“Among these, deep learning has shown remarkable success in the recent years, including AlphaFold2 [118] and RoseTTAfold [119].”
Modeling and Predicting Second-Harmonic Generation from Protein Molecular Structure
Asadipour, B., Beaurepaire, E., Zhang, X., Chessel, A., Mahou, P., Supatto, W., Schanne‐Klein, M., & Stringari, C. (2024) · Physical Review X · doi:10.1103/physrevx.14.011038 · Cited by 18
Ferreiro, D., Branco, C., & Arenas, M. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae096 · Cited by 10
Xiang, R., Liu, G., Hou, Y., Xie, L.-X., Wang, Q., & Hu, S. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.133243 · Cited by 10
Meng, H., Cui, Z., Li, Y., Yu, Y., Jiang, S., & Liu, Y. (2024) · Food Science and Human Wellness · doi:10.26599/fshw.2024.9250155 · Cited by 10
Towards the prediction of general biomolecular interactions with AI
Baek, M. (2024) · Nature Methods · doi:10.1038/s41592-024-02350-2 · Cited by 10
Self-citationSequence‐Sensitivity in Functional Synthetic Polymer Properties
Jin, T., Coley, C. W., & Alexander‐Katz, A. (2024) · Angewandte Chemie International Edition · doi:10.1002/anie.202415047 · Cited by 13
Patel, D. T., Stogios, P. J., Jaroszewski, L., Urbanus, M. L., Sedova, M., Semper, C., Le, C., Takkouche, A., Ichii, K., Innabi, J., et al. (2024) · Molecular Systems Biology · doi:10.1038/s44320-024-00076-z · Cited by 12
“Recently, new neural network (NN) and large language model (LLM)-based computational approaches, such as AlphaFold2 (Jumper et al, 2021), RoseTTAFold (Baek et al, 2021), and Evolutionary-scale modeling (ESM) Fold (Lin et al, 2023), have dramatically improved the accuracy of protein 3D structure prediction from primary…”
Membrane transport engineering for efficient yeast biomanufacturing
Li, X., Zhou, M., Zeng, D.-W., Zhu, Y., Zhang, F., Liao, S., Fan, Y.-C., Zhao, X., Zhang, L., & Bai, F. (2024) · Bioresource Technology · doi:10.1016/j.biortech.2024.131890 · Cited by 10
R3Design: deep tertiary structure-based RNA sequence design and beyond
Tan, C., Zhang, Y., Gao, Z., Cao, H., Li, S., Ma, S., Blanchette, M., & Li, S. Z. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae682 · Cited by 10
Application progress of artificial intelligence in tumor diagnosis and treatment
Sun, F., Zhang, L., & Tong, Z. (2025) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1487207 · Cited by 13
Shen, C., Han, X., Cai, H., Chen, T., Kang, Y., Pan, P., Ji, X., Hsieh, C., Deng, Y., & Hou, T. (2025) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.4c02740 · Cited by 10
Arabidopsis GH3 .10 conjugates jasmonates
Ni, B., Klein, M., Hoßbach, B. M., Feussner, K., Hornung, E., Herrfurth, C., Hámberg, M., & Feußner, I. (2025) · Plant Biology · doi:10.1111/plb.70001 · Cited by 10
“10 was obtained from the Robetta structure prediction service (Baek et al .”
Lentini, L., Perriera, R., Corrao, F., Melfi, R., Tutone, M., Carollo, P. S., Fiduccia, I., Pace, A., Ricci, D., Genovese, F., et al. (2025) · Molecular Therapy · doi:10.1016/j.ymthe.2025.03.045 · Cited by 11
Structural biology in variant interpretation: Perspectives and practices from two studies
Varga, M. J., Richardson, M. E., & Chamberlin, A. C. (2025) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2025.03.010 · Cited by 11
Wu, K., Xu, G., Tian, Y., Li, G., Yi, Z., & Tang, X. (2025) · Marine Drugs · doi:10.3390/md23040178 · Cited by 12
“Machine learning, especially deep learning, has been widely used in various fields of computational biology, such as genome research [9,10], biomolecular structure modeling [11,12], drug discovery, drug development [13,14], and medical data analysis [15].”
From reactants to products: computational methods for biosynthetic pathway design
Ding, S., Liu, D., Tian, Y. T., Zhang, D., Xing, H., Chen, J., Liu, Z., & Hu, Q. (2025) · Synthetic and Systems Biotechnology · doi:10.1016/j.synbio.2025.05.005 · Cited by 10
“Several computational tools have been developed to generate protein scaffolds, such as RFDiffusion [96], AlphaFold3 [99], RoseTTAFold [100] and so on.”
af2rave: protein ensemble generation with physics-based sampling
Teng, D., Meraz, V. J., Aranganathan, A., Gu, X., & Tiwary, P. (2025) · Digital Discovery · doi:10.1039/d5dd00201j · Cited by 20
Liu, Y., Shen, R., Zhou, L., Xiao, Q., Yuan, J., & Li, Y. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf312 · Cited by 13
Prediction of aggregation in monoclonal antibodies from molecular surface curvature
Knez, B., Erzin, L., Kos, Ž., Kuzman, D., & Ravnik, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-13527-w · Cited by 9
Luo, J. L., Qi, X., Tian, T., Shang, K., Shi, H., Li, C., Chai, Z., Ding, J., Zhu, Y., & Zhang, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-09509-7 · Cited by 12
Williams, C. J., Chen, V. B., Richardson, D. C., & Richardson, J. S. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325007843 · Cited by 15
Wu, G., Jin, T., Zhou, H., Coley, C. W., Alexander‐Katz, A., & Lu, H. (2025) · ACS Central Science · doi:10.1021/acscentsci.5c01382 · Cited by 10
Wellnitz, J., Ahmad, S., Bagale, N., Cheng, X., Joseph, J., Zeng, H., Bolotokova, A., Dong, A., Reza, S., Ghiabi, P., et al. (2025) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c01972 · Cited by 16
From possibility to precision in macromolecular ensemble prediction
Wankowicz, S. A. M., & Bonomi, M. (2026) · Nature Methods · doi:10.1038/s41592-026-03084-z · Cited by 15
“This overemphasis on static representations is perpetuated in protein structure prediction, limiting these algorithms’ ability to predict protein functions 9–11 .”
Li, C., Zhu, Y., Qi, X., Chai, Z., Luo, J., Shang, K., Tian, T., Shi, H., Li, M., Xu, R., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0334843 · Cited by 13
Dong, R., Wang, J., Tian, J., Xu, G., Liang, Z., Qin, X., Wang, X., Liu, X., Luo, H., Yao, B., et al. (2025) · ACS Catalysis · doi:10.1021/acscatal.5c03170 · Cited by 10
Self-citationArtificial intelligence in protein-based detection and inhibition of AMR pathways
Sadhukhan, S., Bhattacharya, R., Bhattcharya, D., Sahana, S., Pradhan, B., Pandit, S., Gill, H. S., Rajeev, M., Nag, M., & Lahiri, D. (2025) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-025-00710-4 · Cited by 10
“AlphaFold2 and RoseT-TAFold utilizes deep neural network algorithms to accurately predict the monomeric and multimeric structures of transporter proteins [23, 24, 63, 64].”
InfluentialDe novo enzyme design: Controlling structure to design function
Listov, D., & Fleishman, S. J. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103252 · Cited by 16
Atlas of predicted protein complex structures across kingdoms
Qi, X., Ye, C., Liang, J., Wen, S., Li, Y., Ding, K., Hao, Y., Fei, J., Mao, W., Li, L., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-70884-4 · Cited by 12
hdANM: a new comprehensive dynamics model for protein hinges
Khade, P. M., Scaramozzino, D., Kumar, A., Lacidogna, G., Carpinteri, A., & Jernigan, R. L. (2021) · Biophysical Journal · doi:10.1016/j.bpj.2021.10.017 · Cited by 11
Researchers turn to deep learning to decode protein structures
Ornes, S. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2202107119 · Cited by 11
“That same July, a group at the University of Washington in Seattle unveiled RoseTTAFold, a program that uses neural networks to predict protein structures based on scant genomic information (3).”
BackgroundMusila, J. M., & Rokita, S. E. (2022) · Biochemistry · doi:10.1021/acs.biochem.2c00037 · Cited by 10
Cornish, K. A. S., Lange, J., Aevarsson, A., & Pohl, E. (2022) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2022.101919 · Cited by 11
Deng, J. N. (2022) · Wiley eBooks · doi:10.1002/9781119847281.ch18 · Cited by 11
Maize protein structure resources at the maize genetics and genomics database
Woodhouse, M. R., Portwood, J. L., Sen, S., Hayford, R. K., Gardiner, J. M., Cannon, E. K. S., Harper, L. C., & Andorf, C. M. (2023) · Genetics · doi:10.1093/genetics/iyad016 · Cited by 11
Kim, H. H.-S., Uddin, M. R., Xu, M., & Chang, Y. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.168068 · Cited by 12
Circuit Topology Approach for the Comparative Analysis of Intrinsically Disordered Proteins
Scalvini, B., Sheikhhassani, V., van de Brug, N., Heling, L. W. H. J., Schmit, J. D., & Mashaghi, A. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00391 · Cited by 14
Shankar, S. S., Banarjee, R., Jathar, S. M., Rajesh, S., Ramasamy, S., & Kulkarni, M. J. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2220804 · Cited by 11
“The RoseTTAfold (RF) models were prepared using the Robetta web server (Kim et al., 2004; Baek et al., 2021), and the models were validated based on the confidence score.”
MethodAI-based protein models enhance the accuracy of experimentally determined protein crystal structures
Nam, K. H. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1208810 · Cited by 11
Structome: a tool for the rapid assembly of datasets for structural phylogenetics
Malik, A. J., Langer, D., Verma, C. S., Poole, A. M., & Allison, J. R. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad134 · Cited by 12
DeoR regulates lincomycin production in Streptomyces lincolnensis
Zou, J., Mao, Y., Hou, B., Kang, Y., Wang, R., Wu, H., Jiang, Y., & Zhang, H. (2023) · World Journal of Microbiology and Biotechnology · doi:10.1007/s11274-023-03788-w · Cited by 10
Aspergillus oryzae α‐ l ‐rhamnosidase: Crystal structure and insight into the substrate specificity
Makabe, K., Ishida, N., Kanezaki, N., Shiono, Y., & Koseki, T. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26608 · Cited by 10
Abdelkader, E. H., Qianzhu, H., Huber, T., & Otting, G. (2023) · ACS Sensors · doi:10.1021/acssensors.3c01904 · Cited by 10
Evolution of a plant growth-regulatory protein interaction specificity
Ji, Z., Belfield, E. J., Zhang, S., Bouvier, J. W., Li, S., Schnell, J. R., Fu, X., & Harberd, N. P. (2023) · Nature Plants · doi:10.1038/s41477-023-01556-0 · Cited by 12
“Predicted SLY1 structures were obtained from the AlphaFold Protein Structure Database 25,26 (Q9STX3), or predicted by RoseTTAFold 27 or ESMFold 28 .”
Understanding the heterogeneity intrinsic to protein folding.
Bhatia, S., & Udgaonkar, J. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102738 · Cited by 8
“Machine learning algorithms exploiting information so far hidden in the vast database of known protein structures, determined experimentally by scientists, can now predict protein folds with unprecedented accuracy [4,5].”
BackgroundBonds and bytes: The odyssey of structural biology
Hoff, S., Zinke, M. C., Izadi‐Pruneyre, N., & Bonomi, M. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102746 · Cited by 11
“Tools such as AF2, RoseTTAFold [11], OmegaFold [12], and OpenFold [13], which enable quick and accurate protein”
MethodDeep learning applications in protein crystallography
Matinyan, S., Filipčík, P., & Abrahams, J. P. (2024) · Acta Crystallographica Section A Foundations and Advances · doi:10.1107/s2053273323009300 · Cited by 10
AI-driven GPCR analysis, engineering, and targeting
Velloso, J. P. L., Kovacs, A. S., Pires, D. E. V., & Ascher, D. B. (2024) · Current Opinion in Pharmacology · doi:10.1016/j.coph.2023.102427 · Cited by 10
Foldy: An open-source web application for interactive protein structure analysis
Roberts, J. B., Nava, A. A., Pearson, A. N., Incha, M. R., Valencia, L. E., Ma, M., Rao, A., & Keasling, J. D. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011171 · Cited by 12
Harnessing iron‑sulfur enzymes for synthetic biology
Shomar, H., & Bokinsky, G. (2024) · Biochimica et Biophysica Acta (BBA) - Molecular Cell Research · doi:10.1016/j.bbamcr.2024.119718 · Cited by 11
Rooney, J., Rivera‐de‐Torre, E., Li, R., McLean, K., Price, D. R. G., Nisbet, A. J., Laustsen, A. H., Jenkins, T. P., Hofmann, A., Bakshi, S., et al. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.04.019 · Cited by 15
“Briefly, following removal of signal peptides, tertiary peptide models were generated using RoseT-TAFold [32].”
Xu, Z., Chen, P., Yan, R., Chen, G., Qian, J., Zhu, G., Chen, M., & Guo, Y. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25084362 · Cited by 13
“At least 50 replicates were performed per treatment, and each beetle was only used once.”
MethodCrawshaw, S., Murphy, A. M., Rowling, P. J. E., Nietlispach, D., Itzhaki, L. S., & Carr, J. P. (2024) · Viruses · doi:10.3390/v16050676 · Cited by 12
Plant protein–lipid interfaces studied by molecular dynamics simulations
Neubergerová, M., & Pleskot, R. (2024) · Journal of Experimental Botany · doi:10.1093/jxb/erae228 · Cited by 10
Li, M., Chen, B., Xu, M., Li, F., Geng, Y., Chen, D., Ouyang, P., Huang, X., & Deng, Y. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1392178 · Cited by 12
Autophagy and machine learning: Unanswered questions
Yang, Y., Pan, Z., Sun, J., Welch, J. D., & Klionsky, D. J. (2024) · Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease · doi:10.1016/j.bbadis.2024.167263 · Cited by 15
Wolters, R. M., Ferguson, J. A., Nuñez, I. A., Chen, E. E., Sornberger, T. A., Myers, L., Oeverdieck, S., Raghavan, S. S. R., Kona, C. R., Handal, L. S., et al. (2024) · Immunity · doi:10.1016/j.immuni.2024.05.002 · Cited by 10
Insights into AlphaFold’s breakthrough in neurodegenerative diseases
Mubeen, H., Masood, A., Zafar, A., Khan, Z. Q., Khan, M. Q., & Nisa, A. U. (2024) · Irish Journal of Medical Science (1971 -) · doi:10.1007/s11845-024-03721-6 · Cited by 11
“Being a three-part NN, RoseTTAFold was created with the influence of AF [90].”
Protein–Protein Interaction Prediction via Structure‐Based Deep Learning
Liu, Y., Liu, Y., & Li, Z. (2024) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26721 · Cited by 10
Bacteriophage-Based Bioanalysis
Parker, D. R., & Nugen, S. R. (2024) · Annual Review of Analytical Chemistry · doi:10.1146/annurev-anchem-071323-084224 · Cited by 10
Tulika, T., Ruso‐Julve, F., Ahmadi, S., Ljungars, A., Rivera‐de‐Torre, E., Wade, J., Fernández‐Quintero, M. L., Jenkins, T. P., Belfakir, S. B., Ross, G. M. S., et al. (2024) · Structure · doi:10.1016/j.str.2024.07.014 · Cited by 12
All‐Atom Protein Sequence Design Based on Geometric Deep Learning
Liu, J., Guo, Z., You, H., Zhang, C., & Lai, L. (2024) · Angewandte Chemie International Edition · doi:10.1002/anie.202411461 · Cited by 10
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.