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 3,201–3,300 of 5,636
Cao, X., Cao, C., Chen, Z., Li, J., Yao, Z., Zheng, Y., Wu, J., Li, Z., Hu, Y., Hao, G., et al. (2025) · Applied and Environmental Microbiology · doi:10.1128/aem.00557-25 · Cited by 6
“In this study, we also compared the DeepTMHMM prediction results with the experimentally resolved or RoseTTAFold predicted tertiary structures and referred to the publications or databases annotating the proteins, so as to correct the prediction results.”
Ding, X., Chen, Y., Yuan, Z., Zhang, J., Li, X., Xu, H., & Sun, L. (2025) · Aquaculture · doi:10.1016/j.aquaculture.2025.742828 · Cited by 4
McIver, Z., Moraleda-Montoya, A., Chen, Z., Epa, R., Starns, D., Davy, M., García-Alija, M., Baslé, A., Schubert, M., Ndeh, D. A., et al. (2025) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2025.110407 · Cited by 4
“The phase problem of BT0984 GH139 was solved by molecular replacement using the program Phaser (37) or Molrep (38) with a model generated through the RoseTTAfold server (39).”
Expose flexible conformations for intrinsically disordered protein
Yang, J., Ji, W., Cheng, W. X., Wu, G., Sheng, S. T., Zhang, P., Lin, J., Chen, X., & Shi, Q. (2025) · Current Research in Structural Biology · doi:10.1016/j.crstbi.2025.100170 · Cited by 4
“The Robetta predicted structures were obtained in Robetta online server (Baek et al., 2021), which extensively sampled the protein ’ s structural landscape using Rosetta ’ s fragment-based modeling and energy optimization to obtain protein multiple conformation structures.”
An, D., Sharma, S., & Lindau, M. (2025) · Quarterly Reviews of Biophysics · doi:10.1017/s0033583525100048 · Cited by 5
Odnokoz, O., Banerjee, A., Cui, X., Zeng, L., Uddin, A., Li, C., Zhu, Y., Zhang, M., Lü, X., Yarla, N. S., et al. (2025) · Advanced Science · doi:10.1002/advs.202415585 · Cited by 6
Chen, X., Li, X., & Yang, Y. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.146581 · Cited by 6
An iterative deep learning-guided algorithm for directed protein evolution
Li, X., Wang, Q., Li, J., Tang, F., Yang, X., & Lin, Z. (2025) · iScience · doi:10.1016/j.isci.2025.113324 · Cited by 6
Identification and characterization of novel outer membrane proteins of Brachyspira pilosicoli
Panda, A., Kapoor, J., Hareramadas, B., Naqvi, I., Chhabra, R., Kumar, S., & Bandyopadhyay, A. (2025) · Microbes & Immunity · doi:10.36922/mi025230050 · Cited by 4
Aptamers Meet Structural Bioinformatics, Computational Chemistry, and Artificial Intelligence
da Rosa, G., de Castro, M., García-Velásquez, V. M., Pintos, S., Benedetto, J., Grille, L., Valla, S., Álvarez-Salas, L. M., Calzada, V., & Dans, P. D. (2025) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70050 · Cited by 6
Shui, Y., Ge, X., Cao, C., Wang, J., Hu, J., & Liu, Y. (2025) · BMC Biology · doi:10.1186/s12915-025-02407-4 · Cited by 4
“For proteins, coupling with structure prediction models to identify putative binding pockets, followed by voxelization or point cloud construction, would Enable the use of 3D GNN [62–64].”
Self-citationKim, J., Ryu, S., Lee, W. J., Lee, A., Park, H., & Seok, C. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01699 · Cited by 5
Self-citationProtein Design Meets Single-Molecule Detection: Towards Programmable Nanopore Sensors
Liu, X., & Xu, C. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms262110561 · Cited by 4
Advances in semi-rational design of terpene synthases and their modifying enzymes
Liang, X., Fan, B., Wang, J., Qin, Y., Yu, T., Xu, P., Wang, G., An, T., & Chen, S. (2025) · AMB Express · doi:10.1186/s13568-025-01984-5 · Cited by 5
“…it more suitable for the industrial production of Reb D. Structural models were generated through two independent approaches: homologous protein structures from the PDB database and the RoseTTAFold web-based tool ( h t t p s : / / r o b e t t a . b a k e r l a b . o r g /) (Baek et al. 2021).”
Self-citationMultimodal diffusion for joint design of protein sequence and structure
Zhu, S., Gulati, S., Liu, Y., Kotnis, S., Sun, Q. H., & Shen, Y. (2025) · Protein Science · doi:10.1002/pro.70340 · Cited by 5
“RFdiffusion (Watson et al., 2023) fine-tunes the RoseTTAFold structure prediction model (Baek et al., 2021) for protein structure denoising tasks.”
Chen, Y., Wu, T., Jiang, Y., Nie, L., Li, G., Zhang, Y., Zhou, Z., Xu, J., Quan, L., & Lyu, Q. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01915 · Cited by 5
An industrial automated laboratory for programmable protein evolution
Shen, D., Wang, X., Gao, Y. H., Wang, W., Li, Y., Chen, H., Guo, Y., Cao, S., Huang, Y., Zhang, Y., et al. (2025) · Nature Chemical Engineering · doi:10.1038/s44286-025-00303-w · Cited by 6
DNA Nanostructure‐Templated Multivalency Enables Broad‐Spectrum Virus Inhibition
Umrao, S., Dwivedy, A., Gandavadi, D., Chen, C., Zhou, L., Duan, J., Reddy, M. V., Fāng, Y., & Wang, X. (2025) · Advanced Science · doi:10.1002/advs.202513710 · Cited by 4
Enhancing Enzyme Stability for Biotechnological Applications
Benítez‐Mateos, A. I. (2025) · CHIMIA International Journal for Chemistry · doi:10.2533/chimia.2025.792 · Cited by 4
Design biology and mind–body health
Kumagai, K., Chiba, A., & Yajima, H. (2025) · Journal of Genetic Engineering and Biotechnology · doi:10.1016/j.jgeb.2025.100621 · Cited by 4
“Following AlphaFold, platforms such as Meta ’ s ESMFold and the University of Washington ’ s RoseTTAFold have emerged, providing enhanced prediction accuracy, faster processing speeds, and improved scalability for large datasets 58 .”
Leopard-EM : an extensible 2D template-matching package to accelerate in situ structural biology
Giammar, M., Dickerson, J. L., Hall, L. N., & Lucas, B. A. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325009982 · Cited by 4
RNA regulation mechanisms study using physics-informed machine learning
Liu, H., Zhu, Y., Gao, J., Chen, Z., Zeng, C., & Zhao, Y. (2025) · Communications Physics · doi:10.1038/s42005-025-02452-z · Cited by 4
Xu, X., Zhang, H., Liu, Q., Cheng, Q., Guo, Y., Wei, Y., & Chen, X. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01734 · Cited by 6
Suleman, M., Yaseen, A. R., Naeem, A., Alzahrani, F. M., Alzahrani, K. J., Alsharif, K. F., & Khan, M. (2025) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-025-10862-2 · Cited by 4
UGT708 glycosyltransferases: Nature's architects of C-glycosides
Verma, B., Arora, P., Hussain, S., Devi, R. M., & Gupta, S. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108787 · Cited by 5
Exploring the protein universe with distant similarity detection methods
Sahakyan, H., Mutz, P., Tobiasson, V., & Koonin, E. V. (2025) · Protein Science · doi:10.1002/pro.70397 · Cited by 5
Gupta, A. K., Esih, H., Gradišar, H., & Jerala, R. (2025) · Materials Advances · doi:10.1039/d5ma00792e · Cited by 4
Flexible protein–ligand docking with diffusion-based side-chain packing
Zhang, R., Jiang, X., Cao, D., Wang, Z., Yu, J., Chen, M., Fan, Z., Kong, X., Xiong, J., Zhang, Z., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2511925122 · Cited by 8
Ge, C., Tae, H., Lu, L., Zhang, Z., Huang, Z., An, B., Wang, Y., Jiang, T., Cai, W., Chang, S., et al. (2026) · Communications Chemistry · doi:10.1038/s42004-025-01885-5 · Cited by 8
CHARMM-GUI Quick Bilayer: Simple and Intuitive One-Stop Membrane Bilayer Builder
Park, S., & Im, W. (2026) · Journal of Molecular Biology · doi:10.1016/j.jmb.2026.169672 · Cited by 4
Gray, J. L., Xiao, Z., Rogga, V. V., Zhang, X., & Tate, E. W. (2026) · Journal of the American Chemical Society · doi:10.1021/jacs.5c12299 · Cited by 6
Mechanistic insights into PCBP1-driven unfolding of selected i-motif DNA at G1/S checkpoint
Sengupta, P., Gillet, N., Obi, I. R., & Sabouri, N. (2026) · Nature Communications · doi:10.1038/s41467-026-68822-5 · Cited by 4
Lipid scrambling: New players, new questions, new opportunities
Rocha‐Roa, C., & Vanni, S. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103227 · Cited by 4
Miles, S., Mourglia‐Ettlin, G., & Chabalgoity, J. A. (2026) · Vaccine · doi:10.1016/j.vaccine.2026.128392 · Cited by 4
Li, Y., Du, G., Chen, J., Lv, X., & Liu, L. (2026) · Biotechnology Advances · doi:10.1016/j.biotechadv.2026.108850 · Cited by 7
Scaramozzino, D., Lee, B. H., & Orellana, L. (2026) · Nature Communications · doi:10.1038/s41467-026-69809-y · Cited by 6
“In recent years, machine learning (ML) approaches such as AlphaFold (AF) 66 and RoseTTA fold 67 have revolutionized the fi eld of protein structure prediction.”
Wang, Z., Wang, S., Guo, J., Mu, Y., Liu, X., Zheng, L., & Li, W. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag088 · Cited by 4
Zhang, J., Wang, S., Gao, L., & Li, Q. (2026) · Journal of Biotechnology · doi:10.1016/j.jbiotec.2026.03.012 · Cited by 4
Xu, S., Yang, S., Jiao, X., Cai, J., Wu, J., & Qiao, J. (2026) · Archives of Microbiology · doi:10.1007/s00203-026-04830-9 · Cited by 5
“Deep learning tools such as AlphaFold and RoseTTAFold have revolutionized protein structure prediction, enabling accurate 3D modeling without extensive experimental data (Baek et al. 2021; Jumper et al. 2021).”
AI-enabled protein design facilitates future plant research and crop breeding
Lou, Y., Wu, T., Xia, F., Zhao, A., & Wang, X. (2026) · PLANT PHYSIOLOGY · doi:10.1093/plphys/kiag147 · Cited by 5
Mishra, R., & Pal, M. K. (2026) · International Journal of Drug Delivery Technology · doi:10.25258/ijddt.16.3s.68 · Cited by 4
Lv, J., Liu, G., Zhou, X., & Chen, Y. (2026) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-026-11013-x · Cited by 4
“Recent advances in protein structure prediction methods (e.g., Rosetta [64] and AlphaFold [65]) have largely alleviated this challenge.”
Møiniche, M. V. B., Corneliussen, J. K., Johansen, K. H., Ruiz-Carrasco, A., Paulsen, C., Li, Y., Barra, C., Bangaru, S., Fernández-Quintero, M. L., Bartko, E. A., et al. (2026) · Allergy · doi:10.1111/all.70396 · Cited by 4
Sohn, J., Jeon, M., Lee, H., Lim, J., Ham, S., Park, J., Lee, J., Jung, Y., Lee, G., Min, H., et al. (2026) · Molecular Cell · doi:10.1016/j.molcel.2026.04.030 · Cited by 5
Self-citationProgress in structure prediction and design of adaptive immune receptors
Cohen, T., Hochner, T., & Schneidman‐Duhovny, D. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103326 · Cited by 5
Benchmarking biomedical foundation models
Sáez-Rodríguez, J., Schäfer, P. S. L., Kalavros, N., & Stolovitzky, G. A. (2026) · Nature Methods · doi:10.1038/s41592-026-03182-y · Cited by 7
“FMs are being rapidly developed and hold big promise across biomedical domains, from structural biology 3–5 to ‘virtual cells’ 6,7 , prediction of function from genetic sequence 8–10 , imaging 11 and electronic health records (EHRs) 12 .”
Integrative structure determination of histones H3 and H4 using genetic interactions
Echeverria, I., Braberg, H., Krogan, N. J., & Šali, A. (2022) · FEBS Journal · doi:10.1111/febs.16435 · Cited by 4
Wu, W., Kim, J. S., Richards, S. J., Buhlheller, C., Bailey, A. O., RUSSELL, W., Chen, T., Chen, Z., Chen, Z., Liang, B., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-21197-1 · Cited by 4
Self-citationAI-Based Protein Interaction Screening and Identification (AISID)
Fu, Z., Sha, H. L., & Sha, B. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms231911685 · Cited by 4
A Novel Inovirus Reprograms Metabolism and Motility of Marine Alteromonas
Jia, K., Peng, Y., Chen, X., Jian, H., Jin, M., Yi, Z., Su, M., Dong, X., & Yi, M. (2022) · Microbiology Spectrum · doi:10.1128/spectrum.03388-22 · Cited by 4
Identification and Molecular Modification of Staphylococcus aureus Bacteriophage Lysin LysDZ25
Chang, Y., Li, Q., Zhang, S., Zhang, Q., Liu, Y., Qi, Q., & Lu, X. (2023) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.2c00493 · Cited by 5
Huang, Y., Lei, L., Zhao, Z., Li, Z., Wang, H., Chen, S., Zheng, J., Jiang, G., Guo, X., Li, J., et al. (2023) · Journal of Orthopaedic Research® · doi:10.1002/jor.25653 · Cited by 4
“24 Here, we utilized EQUIBIND, 25 | 179 structure, we evaluated the binding affinity between SOX4 and acetylshikonin and observed that acetylshikonin had the most potential to bind with SOX4 (Figure 5A, binding energy: − 6.54 kcal/ mol, RMSD: 1.376).”
MethodInfluentialSelf-citationIdentification of a conserved α-helical domain at the N terminus of human DNA methyltransferase 1
Hu, Q., Botuyan, M. V., & Mer, G. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.105775 · Cited by 4
“RoseTTAFold (33) also produced a structure comparable to that of DNMT1 N (r.m.s.d. = 2.31 Å for the backbone C α , C, and N atoms of residues Glu22 to Leu90), but with a 33-residue C-terminal helical extension to the fourth α -helix, not present in the experimental structure (Fig.”
BackgroundInfluentialPredicting the Structure of Enzymes with Metal Cofactors: The Example of [FeFe] Hydrogenases
Botticelli, S., Penna, G. L., Minicozzi, V., Stellato, F., Morante, S., Rossi, G. C., & Faraloni, C. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25073663 · Cited by 5
“In the first case ( 1 ), in all the AlphaFold [20,53] (version 2.2.4) predicted structures we looked for a configuration where Cys residues 21, 72, 75, and 78 were able to bind the F-cluster (see sequence alignment in Figure 4).”
BackgroundInfluentialPyCoM: a python library for large-scale analysis of residue–residue coevolution data
Glass, P. E., Alibai, S., Pandini, A., & Dantu, S. C. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae166 · Cited by 4
Billon, C., Piccoli, G. B., Agathe, J. D. S., Stoeva, R., Derive, N., Heidet, L., Berrebi, D. D., Bruneval, P., Jeunemaître, X., & Hureaux, M. (2024) · Molecular Genetics and Genomics · doi:10.1007/s00438-024-02136-3 · Cited by 4
“Wild-type and mutated helix structures of MYH11 were modelled using rosettaFold (Baek et al. 2021).”
Rational design of monomeric IL37 variants guided by stability and dynamical analyses of IL37 dimers
Sardag, I., Duvenci, Z. S., Belkaya, S., & Timucin, E. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2024.04.037 · Cited by 4
“MSAs were performed with the MMseqs2 software [22,23] without template mode.”
Ito, T., Tojo, Y., Fujii, M., Nishino, K., Kosako, H., & Shinohara, Y. (2024) · ACS Omega · doi:10.1021/acsomega.4c02614 · Cited by 5
Wang, T., Zhang, X., Zhang, O., Chen, G., Pan, P., Wang, E., Wang, J., Wu, J., Zhou, D., Wang, L., et al. (2024) · Research · doi:10.34133/research.0408 · Cited by 6
Self-citationPotapova, T. M., Слєсарчук, В. Ю., & Логвиненко, Н. В. (2024) · Медична освіта · doi:10.11603/m.2414-5998.2024.1.14582 · Cited by 4
Weaver, G. C., Schneider, C. L., Becerra‐Artiles, A., Clayton, K., Hudson, A. W., & Stern, L. J. (2024) · Frontiers in Immunology · doi:10.3389/fimmu.2024.1363156 · Cited by 4
Structural Analysis of the Drosophila melanogaster GSTome
Petiot, N., Schwartz, M., Delarue, P., Senet, P., Neiers, F., & Nicolaï, A. (2024) · Biomolecules · doi:10.3390/biom14070759 · Cited by 6
Krishnan, S. R., Sharma, D., Nazeer, Y., Bose, M., Rajkumar, T., Jayaraman, G., Madaboosi, N., & Gromiha, M. M. (2024) · Antibody Therapeutics · doi:10.1093/abt/tbae018 · Cited by 6
Chen, G., & Zhang, Z. (2024) · ACS Omega · doi:10.1021/acsomega.4c04161 · Cited by 4
In Silico Prediction of CNS Bioavailability
Talevi, A. (2024) · AAPS introductions in the pharmaceutical sciences · doi:10.1007/978-3-031-62604-3_4 · Cited by 6
Protein ligand binding site prediction using graph transformer neural network
Ishitani, R., Takemoto, M., & Tomii, K. (2024) · PLoS ONE · doi:10.1371/journal.pone.0308425 · Cited by 4
Vepřek, L. H. (2024) · Science studies · doi:10.14361/9783839472286 · Cited by 4
One‐Pot Synthesis of (S)‐Flavanones by a Double‐Face Promiscuous Chemo‐Enzymatic Cascade of Lipases
Ubertini, V., Capecchi, E., Tomaino, E., Piccinino, D., Marchi, E. D., Bizzarri, B. M., Carotenuto, G., Castrignanò, T., & Saladino, R. (2024) · ChemCatChem · doi:10.1002/cctc.202400974 · Cited by 5
Wang, A. L., Mishkit, O., Mao, H., Arivazhagan, L., Dong, T., Lee, F., Bhattacharya, A., Renfrew, P. D., Schmidt, A. M., Wadghiri, Y. Z., et al. (2024) · Acta Biomaterialia · doi:10.1016/j.actbio.2024.08.052 · Cited by 5
Teaching protein structure and function through molecular visualization
Baland, E., Jiménez, L. P., & Mateus, A. (2024) · Biochemistry and Molecular Biology Education · doi:10.1002/bmb.21860 · Cited by 4
An open source in silico workflow to assist in the design of fusion proteins
Lalaurie, C. J., Zhang, C., Liu, S., Bunting, K. A., & Dalby, P. A. (2024) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2024.108209 · Cited by 4
Bonefont, L. E., Davenport, H., Chaton, C. T., Korotkov, K. V., & Rohde, K. H. (2024) · Molecular Microbiology · doi:10.1111/mmi.15314 · Cited by 5
“All three neural network prediction pipelines produced high-confidence models with the predicted local distance difference test (pLDDT) scores of 85.5, 77.8, and 73.0 for best models from AlphaFold2, RoseTTAFold2, and AlphaFold3, respectively.”
InfluentialPetris, P. C., & Sweere, A. J. M. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c04105 · Cited by 4
Frohn, S., Haas, F. B., Chavez, B. G., Dreyer, B. H., Reiss, E., Ziplys, A., Weichert, H., Hiltemann, S., Ugalde, J. M., Meyer, A. J., et al. (2024) · Plant Cell & Environment · doi:10.1111/pce.15198 · Cited by 4
Modelling of SARS-CoV-2 spike protein structures at varying pH values
Niu, Z., Kementzidis, G., Zhang, P., Zhang, Z., Essuman, B., Hasegawa, K., Rafailovich, M. H., Simon, M., Aktas, B. H., Papadopoulos, E., et al. (2024) · Molecular Simulation · doi:10.1080/08927022.2024.2415524 · Cited by 4
“The initial structure of the S-protein is from the protein data bank (6VXX.pdb) [15], and the missing loops in 6VXX structure are added by Robetta [49].”
SCUBA-D: a freshly trained diffusion model generates high-quality protein structures
(2024) · Nature Methods · doi:10.1038/s41592-024-02465-6 · Cited by 4
Deciphering the mechanism underlying poor aqueous solubility of extracted quinoa proteins
Xie, Y., Han, M., Wu, Y., Xu, X., & Guo, Q. Q. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.137270 · Cited by 4
Liu, T., Yan, S., Sun, W., You, X., Zheng, L., & Wang, X. (2024) · Environment International · doi:10.1016/j.envint.2024.109159 · Cited by 4
Mahmoudi, I., Quignot, C., Martins, C., & Andreani, J. (2024) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1012650 · Cited by 4
Zheng, L., Shen, J., Zhang, Y., Chen, F., Chen, G., Mei, X., Zhou, J., Chang, Y., & Xue, C. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.139068 · Cited by 4
Zeng, Q., Chen, J., Dai, B., Jiang, F., & Wu, Y. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01386 · Cited by 6
Dynamics and kinetics in structural biology: the example of DNA photolyase
Moffat, K. (2025) · Quarterly Reviews of Biophysics · doi:10.1017/s0033583524000222 · Cited by 4
GFLearn: Generalized Feature Learning for Drug-Target Binding Affinity Prediction
Huang, Z., Weng, X., & Ou-Yang, L. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3538497 · Cited by 4
Performance of Hybrid Strategies Combining MDockPP and AlphaFold2 in CAPRI Rounds 47–55
Duan, R., Xu, X., Qiu, L., Zhang, S., & Zou, X. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26805 · Cited by 4
High performance-oriented computer aided drug design approaches in the exascale era
Rizzi, A., & Mandelli, D. (2025) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2025.2468289 · Cited by 4
“It is interesting to note that with the advent of accurate deep learning models for protein structure prediction [23,24], nowadays fully in-silico SBDD campaigns can be envisioned.”
Genome editing for disease resistance in crops
Han, X., Li, S., Xie, K., & Li, G. (2025) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2024-1218 · Cited by 6
Predicting the structure-altering mechanisms of disease variants
Arnaudi, M., Utichi, M., Tiberti, M., & Papaleo, E. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.102994 · Cited by 5
Maurino, V. G. (2025) · Journal of Plant Physiology · doi:10.1016/j.jplph.2025.154522 · Cited by 5
Protein Structure Prediction Tools and Computational Approaches
Garavano, N., Sadosky, F., & Bulgheroni, F. (2023) · Fusion of Multidisciplinary Research An International Journal · doi:10.63995/mwcu4408 · Cited by 5
Gomari, M. M., Alidadi, M., Rostami, N., & Bencherif, S. A. (2025) · Advanced NanoBiomed Research · doi:10.1002/anbr.202500017 · Cited by 5
NMR in the Age of Modern Biomedical Research and Drug Discovery
Lu, X., Myint, W., Muli, C. S., Larion, M., Matsuo, H., & Walters, K. J. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169302 · Cited by 5
Combining simulations and experiments – a perspective on maximum entropy methods
Stöckelmaier, J., & Oostenbrink, C. (2025) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp01263e · Cited by 6
“16,17 Many established computational methods like comparative modeling 18 and AI-based structure predictors like Rosettafold 19 Fig.”
IMPLEMENTING ARTIFICIAL INTELLIGENCE IN DRUG RESEARCH DEVELOPMENT
Obbalareddy, S., Shahi, S., & Dubey, A. (2025) · BULLETIN OF STOMATOLOGY AND MAXILLOFACIAL SURGERY · doi:10.58240/1829006x-2025.21.6-361 · Cited by 5
FoldExplorer: Fast and Accurate Protein Structure Search with Sequence-Enhanced Graph Embedding
Liu, Y., Zhang, Y., Zhou, Z. P., & Shen, H. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169412 · Cited by 6
Xia, Y., Lin, X., Ma, Z., Hu, J., Li, Y., Xie, Z., Li, H., Li, Y., Zhao, Z., Yang, L., et al. (2025) · APL Computational Physics · doi:10.1063/5.0283692 · Cited by 4
Kim, M., Bae, H., Jo, G., Kim, K.-W., Lee, S. J., Yoo, J., & Joo, K. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf579 · Cited by 4
An interaction-derived graph learning framework for scoring protein–peptide complexes
Tao, H., Wang, X., & Huang, S. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01136-1 · Cited by 7
“Although coordinate-based equivariant graph networks 37–39 and transformers 40–42 have recently revolutionized protein structure prediction, traditional GNNs provide a more robust framework in the representation of interactions 27,30 .”
Mammalian antiviral proteins ZAP and KHNYN can independently restrict CpG-enriched avian viruses
Becker, J. T., Mickelson, C. K., Pross, L. M., Sanders, A. E., Vogt, E. R., Shepherd, F. K., Wick, C., Barkhymer, A. J., Aron, S. L., Fay, E. J., et al. (2025) · PLoS Biology · doi:10.1371/journal.pbio.3003471 · Cited by 5
“Using two structural prediction algorithms, we generated models of the four zinc fingers of chicken ZAP (ggaZAP, residues 1–220) by both comparative modeling based on human ZAP (RobettaCM [44], PDB: 6UEJ [42]) and ab initio folding by RoseTTAFold [45] (S3A and S3B Fig).”
Current landscape with an analytical outlook: Chikungunya virus vaccine development
Zhao, X., Yang, L., Mi, Y., Lu, Y., Sun, B., Zhang, Y., Yang, Y.-X., Sun, Y., Zhang, L., Lin, L., et al. (2025) · The Innovation Medicine · doi:10.59717/j.xinn-med.2025.100173 · Cited by 4
Lightweight MSA design advances protein folding from evolutionary embeddings
Cao, H., Zhou, X., Gao, Z., Wang, C., Gao, X., Zhang, Z., Hsieh, C., de la Fuente‐Núñez, C., Gu, C., Liu, G., et al. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103574 · Cited by 4
Metadata
- Authors
- Baek, M., DiMaio, F., Anishchenko, I., Dauparas, J., Ovchinnikov, S., Lee, G. R., Wang, J., Cong, Q., Kinch, L. N., Schaeffer, R. D., Millán, C., Park, H., Adams, C., Glassman, C. R., DeGiovanni, A., Pereira, J. H., Rodrigues, A. V., van Dijk, A. A., Ebrecht, A. C., Opperman, D. J., Sagmeister, T., Buhlheller, C., Pavkov-Keller, T., Rathinaswamy, M. K., Dalwadi, U., Yip, C. K., Burke, J. E., Garcia, K. C., Grishin, N. V., Adams, P. D., Read, R. J., & Baker, D.
- Affiliations
- University of Washington (US)
- Harvard University (US)
- The University of Texas Southwestern Medical Center (US)
- Howard Hughes Medical Institute (US)
- University of Cambridge (GB)
- Stanford Medicine (US)
- Lawrence Berkeley National Laboratory (US)
- North-West University (ZA)
- University of the Free State (ZA)
- University of Graz (AT)
- University of Victoria (CA)
- University of British Columbia (CA)
- Corresponding author
- Baker, David
- ORCID
- Baek, Minkyung
- DiMaio, Frank
- Anishchenko, Ivan
- Dauparas, Justas
- Ovchinnikov, Sergey
- Lee, Gyu Rie
- Wang, Jue
- Cong, Qian
- Kinch, Lisa N.
- Schaeffer, R. Dustin
- Millán, Claudia
- Park, Hahnbeom
- Adams, Carson
- Glassman, Caleb R.
- Pereira, Jose H.
- Rodrigues, Andria V.
- van Dijk, Alberdina A.
- Ebrecht, Ana C.
- Opperman, Diederik J.
- Sagmeister, Theo
- Buhlheller, Christoph
- Rathinaswamy, Manoj K
- Dalwadi, Udit
- Yip, Calvin K
- Burke, John E
- Grishin, Nick V.
- Adams, Paul D.
- Read, Randy J.
- Baker, David
- Venue
- Science
- Publisher
- openRxiv
- Published
- 2021-06-15
- Volume
- 373
- Issue
- 6557
- Pages
- 871-876
- ISSN
- 0036-8075 (ISSN-L)
- PMC
- PMC7612213
- OpenAlex
- W3186179742
- Semantic Scholar
- 51362860fb8ad08255660303550ed4bc345535fc
- Cited by
- 5,549
- References
- 85
- Citations by year
- 2026: 912 · 2025: 1108 · 2024: 1165 · 2023: 1144 · 2022: 982 · 2021: 227
- FWCI
- 247.22
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Science (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (submittedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion, cc-by)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion, cc-by)
- DESY Publication Database (PUBDB) (Deutsches Elektronen-Synchrotron) (submittedVersion)
- Apollo (University of Cambridge) (submittedVersion, cc-by)
- Apollo (cc-by)
- Funders
- National Science Foundation (GM127390, 1937533)
- Welch Foundation (I‐1505)
- Washington Research Foundation
- Microsoft
- TU Graz, Internationale Beziehungen und Mobilitätsprogramme
- Wellcome Trust (Z/17/Z, 209407/Z/17/Z, 209407)
- G. Harold and Leila Y. Mathers Foundation
- Diamond Light Source
- Open Philanthropy Project
- Global Challenges Research Fund (ST/R002754/1)
- Schmidt Family Foundation
- European Synchrotron Radiation Facility
- Austrian Science Fund (P 29432, DOC 50)
- National Institutes of Health (DP5OD026389, RO1-AI51321)
- Canadian Institutes of Health Research (168998, 168907)
- Science and Technology Facilities Council (ST/R002754/1)
- Deutsches Elektronen-Synchrotron
- National Institute of General Medical Sciences (P01GM063210, R35GM127390, R01GM123089)
- National Institute of Allergy and Infectious Diseases (R01AI051321)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Structural Biology › Enzyme Structure and Function
- Keywords
- protein structure prediction, protein-protein complex prediction, distance maps, sequence-based structure prediction, CASP14, protein function prediction
- MeSH terms
- Deep Learning, Amino Acid Sequence, Computer Simulation, Membrane Proteins, Models, Molecular, Protein Conformation, Proteins, Neural Networks, Computer, Protein Folding, Crystallography, X-Ray, Cryoelectron Microscopy, Protein Subunits, Databases, Protein, Receptors, G-Protein-Coupled, Multiprotein Complexes, Sphingosine N-Acyltransferase, ADAM Proteins
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.