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 2,501–2,600 of 5,636
Nam, K. H. (2025) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2025.109169 · Cited by 8
Trends in substitution models of protein evolution for phylogenetic inference
Ferreiro, D., Pazos, E., & Arenas, M. (2025) · Molecular Phylogenetics and Evolution · doi:10.1016/j.ympev.2025.108473 · Cited by 11
Autoimmunity, epitope analysis, and molecular mimicry
Rojas, M., Acosta‐Ampudia, Y., Monsalve, D. M., Ramírez-Santana, C., Heuer, L. S., Ridgway, W. M., Anaya, J., Lian, Z.-X., & Gershwin, M. E. (2025) · Current Opinion in Immunology · doi:10.1016/j.coi.2025.102681 · Cited by 11
Kumar, N., & Li, Y. (2025) · Food Chemistry · doi:10.1016/j.foodchem.2025.147044 · Cited by 8
EMProt improves structure determination from cryo-EM maps
Li, T., Chen, J., Li, H., Cao, H., & Huang, S. (2025) · Nature Structural & Molecular Biology · doi:10.1038/s41594-025-01723-1 · Cited by 13
“Therefore, to accurately build the all-atom structure, we design a three-track attention network 19,30 to refine Cα positions and predict backbone frames and torsion angles from raw Cα atoms and the density map (Fig.”
Conformation-aware structure prediction of antigen-recognizing immune proteins
Dreyer, F. A., Ludwiczak, J., Martinkus, K., Abanades, B., Alberstein, R. G., Kessel, P., Rao, P., Lee, J. H., Bonneau, R., Watkins, A. M., et al. (2025) · mAbs · doi:10.1080/19420862.2025.2602217 · Cited by 11
“While physics-based approaches like molecular dynamics simulations can characterize these states, 14 their accuracy is often constrained by approximate force fields and the prohibitive computational cost of sampling rare events, even with enhanced sampling techniques.”
Chi, G., Tian, L., Lin, S., Zhang, Y., Hong, X., Li, Q., & He, N. (2025) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.5c04917 · Cited by 8
Foundation models in clinical oncology: Progresses and perspectives
Li, J., Fu, J., Geng, X., & Wang, H. (2025) · Cancer Letters · doi:10.1016/j.canlet.2025.218220 · Cited by 11
Mahtha, S. K., Sureshkumar, V., & Mohanty, D. (2026) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqag002 · Cited by 12
Cho, S., Kaur, B., Lam, K., Gaamouch, F. E., Kuncewicz, K., Doering, N. P., Wolber, G., & Gabr, M. T. (2026) · ChemMedChem · doi:10.1002/cmdc.202500718 · Cited by 9
“An additional full model of the full TREM2 was generated using Robetta ’ s structure prediction tool [39].”
Morehead, A., Liu, J., Neupane, P., & Cheng, J. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103247 · Cited by 11
AI-driven protein engineering: A new paradigm for plant trait design
Fu, R., Jiang, S., Wu, T., Yin, C., Yan, J., & Wang, X. (2026) · Molecular Plant · doi:10.1016/j.molp.2026.03.011 · Cited by 9
Cai, M., & Liu, T. (2026) · Pharmaceuticals · doi:10.3390/ph19050696 · Cited by 10
Sanches, K., Wai, D. C. C., & Norton, R. S. (2021) · Toxicon · doi:10.1016/j.toxicon.2021.08.020 · Cited by 8
Cui, Z., Zhang, S., Zhang, S., Chen, B., Zhu, Y., & Tan, T. (2021) · Chinese Journal of Chemical Engineering · doi:10.1016/j.cjche.2021.08.017 · Cited by 8
Sumner, J., & Qian, S. (2022) · BBA Advances · doi:10.1016/j.bbadva.2022.100063 · Cited by 8
Sundermeyer, L., Bosco, G., Gujar, S., Brocker, M., Baumgart, M., Willbold, D., Weiergräber, O. H., Bellinzoni, M., & Bott, M. H. (2022) · Microbiology Spectrum · doi:10.1128/spectrum.02677-22 · Cited by 8
GraphPLBR: Protein-Ligand Binding Residue Prediction With Deep Graph Convolution Network
Wang, W., Sun, B., Yu, M., Wu, S., Liu, D., Zhang, H., & Zhou, Y. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3239983 · Cited by 9
Bayesian methods in integrative structure modeling
Habeck, M. (2023) · Biological Chemistry · doi:10.1515/hsz-2023-0145 · Cited by 8
“Programs such as AlphaFold2 (Jumper et al. 2021) and RoseT-TAFold (Baek et al. 2021) have invigorated the fi eld of protein structure prediction by achieving unprecedented prediction accuracy matching the quality of experimental structures.”
Dong, H., & Ming, D. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms241512446 · Cited by 11
A Structure-Based Allosteric Modulator Design Paradigm
Li, M., Lan, X., Lu, X., & Zhang, J. (2023) · Health Data Science · doi:10.34133/hds.0094 · Cited by 9
Kumar, S., Banerjee, S., Kaur, A., Sasi, M., Kumari, S., Sachdev, A., & Dahuja, A. (2023) · Food Technology and Biotechnology · doi:10.17113/ftb.61.04.23.8231 · Cited by 8
Pfanzagl, V., Grünwald‐Gruber, C., Leitgeb, U., Furtmüller, P. G., & Obinger, C. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.105402 · Cited by 8
“Comparative modeling (63) and ab-initio prediction using RoseTTAFold (64, 65) of proEPO was done using the service of the Robetta server (https://robetta.bakerlab.org/ ).”
MethodPlatzer, G., Ptaszek, A. L., Böttcher, J., Fuchs, J. E., Geist, L., Braun, D., McConnell, D. B., Konrat, R., Sánchez‐Murcia, P. A., & Mayer, M. (2024) · ChemPhysChem · doi:10.1002/cphc.202300636 · Cited by 8
EnzymeNet: residual neural networks model for Enzyme Commission number prediction
Watanabe, N., Yamamoto, M., Murata, M., Kuriya, Y., & Araki, M. (2023) · Bioinformatics Advances · doi:10.1093/bioadv/vbad173 · Cited by 10
Ko, S., Kim, J., Lim, J., Lee, S., Park, J. Y., Woo, J., Scott-Nevros, Z. K., Kim, J. R., Yoon, H., & Kim, D. (2023) · mSystems · doi:10.1128/msystems.00943-23 · Cited by 8
“For mutant models, the top 1% of AMR gene hits are selected by WGS analysis, and the resulting 768 models are cross-validated for SNP impact by structure prediction using Alphafold2 and RoseTTAFold (53) (Fig.”
BackgroundMethodInfluentialStructural and functional prediction, evaluation, and validation in the post-sequencing era
Li, C., Luo, Y., Xie, Y., Zhang, Z., Liu, Y., Zou, L., & Xiao, F. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.12.031 · Cited by 9
“Notably, breakthroughs in protein structure prediction based on deep learning, such as AlphaFold2[14] and RoseTTAFold[15], have improved AI variant predictors by adding information of protein tertiary structures[16].”
BackgroundMethodSahoo, M., Behera, D. U., Gaur, M., & Subudhi, E. (2024) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2299741 · Cited by 8
“Since the PDB (Protein Data Bank) database did not contain the three-dimensional (3D) structure of the AcrB protein, a computational approach of homology modelling was performed using the RoseTTAFold server (Baek et al., 2021) held by Rosetta Commons (https://robetta.baker-lab.org).”
Extensive antibody search with whole spectrum black-box optimization
Tučs, A., Ito, T., Kurumida, Y., Kawada, S., Nakazawa, H., Saitō, Y., Umetsu, M., & Tsuda, K. (2024) · Scientific Reports · doi:10.1038/s41598-023-51095-z · Cited by 8
Evolution and separation of actinobacterial pyranose and C -glycoside-3-oxidases
Kostelac, A., Taborda, A., Martins, L. O., & Haltrich, D. (2024) · Applied and Environmental Microbiology · doi:10.1128/aem.01676-23 · Cited by 8
Navigating the Frontiers of Machine Learning in Neurodegenerative Disease Therapeutics
Cha, Y., Kagalwala, M. N., & Ross, J. (2024) · Pharmaceuticals · doi:10.3390/ph17020158 · Cited by 11
“Due to the practical challenges associated with crystallography and NMR spectroscopy [62], there has been a growing trend in the accurate de novo prediction of protein structures using bioinformatics and ML (Table 2), including RoseTTAFold [63], I-TASSER [64], AlphaFold [65], and QUARK [66].”
MethodCossío-Bayúgar, R., Martínez-Ibáñez, F., Aguilar-Díaz, H., & Miranda-Miranda, E. (2024) · Parasite · doi:10.1051/parasite/2024003 · Cited by 9
“For proteins without available 3D models, the corresponding Fasta amino acid sequences were submitted to https://robetta. bakerlab.org [1].”
Method(2026) · doi:10.7554/elife.98179.2 · Cited by 8
“The availability of AF2 and related methods ( Jumper et al., 2021 ; Mirdita et al., 2022 ; Evans et al., 2021 ; Baek et al., 2021 ) has enabled structure-based analysis of proteins and protein complexes to an extent that has rapidly transformed many parts of biology and medicine ( Akdel et al.,…”
Biriukov, D., & Vácha, R. (2024) · ACS Physical Chemistry Au · doi:10.1021/acsphyschemau.4c00003 · Cited by 8
Go, E. B., Lee, J. H., Cho, J. H., Kwon, N. H., Choi, J., & Kwon, I. (2024) · Journal of Biological Engineering · doi:10.1186/s13036-024-00418-3 · Cited by 8
“Subsequently, PyRosetta was employed for scoring to ensure that the introduced non-natural amino acid do not adversely impact the overall protein structure [48, 53].”
MethodQiao, S., Cheng, Z., & Li, F. (2024) · Beilstein Journal of Organic Chemistry · doi:10.3762/bjoc.20.66 · Cited by 8
Zilberg, G., Parpounas, A. K., Warren, A. L., Fiorillo, B., Provasi, D., Filizola, M., & Wacker, D. (2024) · Science Advances · doi:10.1126/sciadv.adk4855 · Cited by 8
“The cryo-EM structures of human 5-HT 1e R in complex with G α i1 β 1 γ 2 and bound to mianserin or setiptiline were used as starting points for MD simulations after adding atomic coordinates of the missing ECL2, which was built ab initio with RoseTTAFold ( 65 ).”
MethodShandeep, G., Annaiyan, S., Mannu, J., Somasundaram, P., Kathithachalam, A., Shanmugam, H., & Vijay, S. (2024) · Biocontrol Science and Technology · doi:10.1080/09583157.2024.2358252 · Cited by 8
“Bioinformatics tools such as SWISS-MODEL (SIB-Swiss Institute of Bioinformatics, Switzerland) and ROBETTA (Baker lab, HHMI ’ s Janelia Research Campus, USA) (Baek et al., 2021; Bienert et al., 2017) were employed to model the selected protein targets.”
Li, X., Yu, H., Liu, S., Ma, B.-D., Wu, X., Zheng, X., & Xu, Y. (2024) · Bioresources and Bioprocessing · doi:10.1186/s40643-024-00776-2 · Cited by 8
“The modeling was performed using Robetta (https:// robetta.bakerlab.org/ submit.php) with RoseTTAFold (Baek et al. 2021).”
MethodWoo, H., Kim, Y., & Seok, C. (2024) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012239 · Cited by 10
Machine learning-assisted substrate binding pocket engineering based on structural information
Wang, X., Xu, K., Zeng, X., Linghu, K., Zhao, B., Yu, S., Wang, K., Yu, S., Zhao, X., Zeng, W., et al. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae381 · Cited by 8
“The conventional steps in enzyme activity engineering include protein structure acquisition [3, 4], substrate binding sites prediction, and evaluating mutagenesis energy [5].”
BackgroundMicrobial production of an aromatic homopolyester
Lee, Y., Kang, M., Jang, W. D., Choi, S. Y., Yang, J. E., & Lee, S. Y. (2024) · Trends in biotechnology · doi:10.1016/j.tibtech.2024.06.001 · Cited by 10
Belyaeva, J., & Elgeti, M. (2024) · eLife · doi:10.7554/elife.99770 · Cited by 8
Predicting protein interactions of the kinase Lck critical to T cell modulation
Gao, M., & Skolnick, J. (2024) · Structure · doi:10.1016/j.str.2024.09.010 · Cited by 8
Generating Protein Structures for Pathway Discovery Using Deep Learning
Georgouli, K., Stephany, R., Tempkin, J. O. B., Santiago, C., Aydin, F., Heimann, M., Pottier, L., Zhang, X., Carpenter, T. S., Hsu, T., et al. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c00816 · Cited by 9
Predicting Crystalline Material Properties with AI: Bridging Molecular to Particle Scales
Chen, W., Li, M., Yao, T., Liu, J., Jia, S., Gao, Z., & Gong, J. (2024) · Industrial & Engineering Chemistry Research · doi:10.1021/acs.iecr.4c03224 · Cited by 10
ProBID-Net: a deep learning model for protein–protein binding interface design
Chen, Z., Ji, M., Qian, J., Zhang, Z., Zhang, X., Gao, H., Wang, H., Wang, R., & Qi, Y. (2024) · Chemical Science · doi:10.1039/d4sc02233e · Cited by 8
Liu, K., Yu, X., Cui, H., Li, W., & Han, W. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.137069 · Cited by 11
DSDPFlex: Flexible-Receptor Docking with GPU Acceleration
Dong, C., Huang, Y., Lin, X., Zhang, H., & Gao, Y. Q. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01715 · Cited by 8
Selenoprotein K at the intersection of cellular pathways
Odunsi, A., Kapitonova, M. A., Woodward, G., Rahmani, E., Ghelichkhani, F., Liu, J., & Rozovsky, S. (2024) · Archives of Biochemistry and Biophysics · doi:10.1016/j.abb.2024.110221 · Cited by 9
Identification, characterization, and design of plant genome sequences using deep learning
Wang, Z., Yuan, H., Yan, J., & Liu, J. (2024) · The Plant Journal · doi:10.1111/tpj.17190 · Cited by 12
Data and AI-driven synthetic binding protein discovery
Li, Y., Duan, Z., Li, Z., & Xue, W. (2025) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2024.12.002 · Cited by 8
Mepperi, J., Mukherjee, S., Goel, K., & Kotamarthi, H. C. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c05439 · Cited by 8
Protein ligand structure prediction: From empirical to deep learning approaches
Zhou, G., & DiMaio, F. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.102998 · Cited by 9
Self-citationHNP-1: From Structure to Application Thanks to Multifaceted Functions
Zhang, J., Liu, Z., Zhou, Z., Huang, Z., Yang, Y., Wu, J., & Liu, Y. (2025) · Microorganisms · doi:10.3390/microorganisms13020458 · Cited by 12
“…to the development of numerous protein design and protein interaction prediction tools including RoseTTA fold, ProteinMPNN as well as RFdiffusion, providing new opportunities to further explore the mechanisms of interaction between HNP-1 and target proteins, receptors, and other entities [158–160].”
Prediction of structural variation
Kalakoti, Y., Sanjeev, A., & Wallner, B. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103003 · Cited by 9
Kim, K., Shim, K., Wang, Y. W., & Yang, D. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.4c00799 · Cited by 8
Transformers in RNA structure prediction: A review
Chaturvedi, M., Rashid, M. A., & Paliwal, K. K. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.03.021 · Cited by 10
“Baek et al. modified RoseTTAFold [157], originally designed to predict the protein structure, to RoseTTAFoldNA [152] for the prediction of RNA tertiary structure.”
Cai, Y., Zhang, Z., Xu, X., Xu, L., Chen, Y., Zhang, G., & Zhou, X. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00004 · Cited by 8
Advances in the biological production of sugar alcohols from biomass-derived xylose
Tang, Y., Ju, X., Chen, X., & Li, L. (2025) · World Journal of Microbiology and Biotechnology · doi:10.1007/s11274-025-04316-8 · Cited by 8
“Alphafold (Jumper et al. 2021) and RoseTTAFold (Baek et al. 2021) are typical examples of significant advances in protein structure prediction accuracy, providing a solid foundation for new enzyme design.”
Ille, A. M., Anas, E., Mathews, M. B., & Burley, S. K. (2025) · Structural Dynamics · doi:10.1063/4.0000765 · Cited by 10
Silva, J. C. F., Schuster, L. A., Sexson, N., Erdem, M., Hulke, R., Kirst, M., Resende, M. F. R., & Dias, R. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1013038 · Cited by 9
Ni, B., & Buehler, M. J. (2026) · Matter · doi:10.1016/j.matt.2026.102706 · Cited by 9
Exploiting Structural Modelling Tools to Explore Host-Translocated Effector Proteins
Amoozadeh, S., Johnston, J. M., & Meisrimler, C. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222312962 · Cited by 8
Méndez-Líter, J. A., Ayuso‐Fernández, I., Csarman, F., de Eugenio, L. I., Míguez, N., Plou, F. J., Prieto, A., Ludwig, R., & Martı́nez, M. J. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222413611 · Cited by 8
“0 or as a separate domain by RoseTTAFold.”
MethodInfluentialPetrov, P. N., Müller, H., & Glaeser, R. M. (2021) · Journal of Structural Biology · doi:10.1016/j.jsb.2021.107827 · Cited by 9
“A uthor M anuscript A uthor M anuscript A uthor M anuscript A uthor M anuscript fold-prediction methods (Baek et al., 2021; Jumper et al., 2021), and thus one is not limited to using templates that are already included in experimental data bases.”
MethodUrdániz, E., Martín, M., Payaslián, F., Defelipe, L. A., Dodes, M., Martínez, M., Alzari, P. M., Cabrera, G., Marti, M. A., & Piuri, M. (2021) · Biochimica et Biophysica Acta (BBA) - Proteins and Proteomics · doi:10.1016/j.bbapap.2021.140745 · Cited by 8
Chen, Y., Li, Y., Yuan, C., Liu, S., Xin, F., Deng, X., & Wang, X. (2022) · Molecular Oral Microbiology · doi:10.1111/omi.12364 · Cited by 8
Dessay, M., Couture, E., Maaroufi, H., Fournier, F., Gagnon, É., Droit, A., Brown, J. P., & Michou, L. (2022) · BMC Medical Genomics · doi:10.1186/s12920-022-01198-9 · Cited by 8
“Tridimensional models of SQSMT1 and DOCK6 These models were generated by AlphaFold 2 (and RoseTTAFold as a comparator to AlphaFold 2) software tools from their amino-acid sequences [30, 31].”
MethodAccurate positioning of functional residues with robotics-inspired computational protein design
Krivacic, C. T., Kundert, K., Pan, X., Pache, R. A., Liu, L., Conchúir, S. Ó., Jeliazkov, J. R., Gray, J. J., Thompson, M. C., Fraser, J. S., et al. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2115480119 · Cited by 8
Lu, H., Li, J., Yang, P., Jiang, F., Liu, H., & Cui, F. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.883436 · Cited by 8
Grossman, A. S., Escobar, C. A., Mans, E. J., Mucci, N. C., Mauer, T. J., Jones, K. A., Moore, C. C., Abraham, P. E., Hettich, R. L., Schneider, L. G., et al. (2022) · Frontiers in Microbiology · doi:10.3389/fmicb.2022.800366 · Cited by 9
Developing PROteolysis TArgeting Chimeras (PROTACs) for hematologic malignancies
Wu, Y., Zhang, J., Zhu, X., & Zhang, Y. (2022) · Cancer Letters · doi:10.1016/j.canlet.2022.215808 · Cited by 9
Mitra, N., & Dey, S. (2022) · Plant Science · doi:10.1016/j.plantsci.2022.111398 · Cited by 8
Kalyvianaki, K., Panagiotopoulos, A. A., Patentalaki, M., Castanas, E., & Kampa, M. (2022) · Frontiers in Endocrinology · doi:10.3389/fendo.2022.954629 · Cited by 8
Eddie, B. J., Bird, L. J., Pelikan, C., Mußmann, M., Martínez‐Pérez, C., Pinamang, P., Malanoski, A. P., & Glaven, S. M. (2022) · mSphere · doi:10.1128/msphere.00223-22 · Cited by 8
Martel, A., & Gabel, F. (2022) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2022.08.010 · Cited by 8
Essential Role of Loop Dynamics in Type II NRPS Biomolecular Recognition
Corpuz, J. C., Patel, A., Davis, T. D., Podust, L. M., McCammon, J. A., & Burkart, M. D. (2022) · ACS Chemical Biology · doi:10.1021/acschembio.2c00523 · Cited by 8
Schmidt, H., Mauer, K., Glaser, M., Dezfuli, B. S., Hellmann, S. L., Gomes, A. L. S., Butter, F., Wade, R. C., Hankeln, T., & Herlyn, H. (2022) · BMC Genomics · doi:10.1186/s12864-022-08882-1 · Cited by 8
“For estimating the precision of the structure predictions, we employed an additional protein structure prediction program, RoseTTAFold [73] (Supplementary Table S5).”
MethodInfluentialFanelli, A., & Sullivan, M. L. (2022) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2022.10.004 · Cited by 10
Fontana, F., & Gelain, F. (2022) · Nanotechnology Reviews · doi:10.1515/ntrev-2022-0455 · Cited by 8
Prophage-Derived Regions in Curtobacterium Genomes: Good Things, Small Packages
Evseev, P. V., Lukianova, A. A., Tarakanov, R. I., Tokmakova, A. D., Popova, A. V., Kulikov, E. E., Shneider, M. M., Ignatov, A. N., & Анатольевич, М. К. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24021586 · Cited by 8
Molecular Simulation Study on the Interaction between Porcine CR1-like and C3b
Hou, Z., Yin, W., Hao, Z., Fan, K., Sun, N., Sun, P., & Li, H. (2023) · Molecules · doi:10.3390/molecules28052183 · Cited by 8
The identification and phylogenetic analysis of SARS‐CoV ‐2 delta variants in Taiwan
Liu, L., Tsai, J., Chu, J. J. H., Chen, C., Chen, L., Lin, P., Tsai, C., Hsu, M., Chuang, W., Hwang, S., et al. (2023) · The Kaohsiung Journal of Medical Sciences · doi:10.1002/kjm2.12665 · Cited by 8
Burroughs, A. M., & Aravind, L. (2023) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqad029 · Cited by 10
Pepe, A., Lasenby, J., & Chacón, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30923-6_7 · Cited by 9
A unique resistance mechanism is associated with RBgh2 barley powdery mildew adult plant resistance
Moolhuijzen, P., Ge, C., Palmiero, E., & Ellwood, S. R. (2023) · Theoretical and Applied Genetics · doi:10.1007/s00122-023-04392-0 · Cited by 8
Spiers, A. J., Dorfmueller, H. C., Jerdan, R., McGregor, J., Nicoll, A., Steel, K., & Cameron, S. (2023) · PLoS ONE · doi:10.1371/journal.pone.0286540 · Cited by 8
AlphaCutter: Efficient removal of non‐globular regions from predicted protein structures
Tam, C., & Iwasaki, W. (2023) · PROTEOMICS · doi:10.1002/pmic.202300176 · Cited by 9
Lin, I., Rupert, P. B., Pilat, K., Ruff, R. O., Friend, D. J., Chan, M. K., Clarke, M., Hoffstrom, B. G., Carter, J. V., Meshinchi, S., et al. (2023) · Frontiers in Drug Discovery · doi:10.3389/fddsv.2023.1216516 · Cited by 8
“To complete model building, the RoseTTAFold MSLN model was used as a guide template iteratively across the three models.”
InfluentialModeling orientational features via geometric algebra for 3D protein coordinates prediction
(2023) · doi:10.1002/mma.9608 · Cited by 8
“…starting from its amino acid sequence (or primary structure) and include interresidue distances (e.g. distance between amino acid pairs), the secondary structures of the proteins (e.g. the local folding patterns such as helices or sheets), the potential energy and others 2,10,11,18,19,20,21 .”
InfluentialAntonio, L. M., Martins, G. H., Aragão, A. Z. B., Quel, N. G., Zazeri, G., Houry, W. A., & Ramos, C. H. I. (2023) · Plants · doi:10.3390/plants12162925 · Cited by 9
Li, L., Liu, Z., Meng, D., Liu, Y., Liu, T., Jiang, C., & Yin, H. (2023) · mSystems · doi:10.1128/msystems.00720-23 · Cited by 8
Homozygous MFN2 variants causing severe antenatal encephalopathy with clumped mitochondria
Chevrollier, A., Bonnard, A. A., Ruaud, L., Guéguen, N., Perrin, L., Desquiret‐Dumas, V., Guimiot, F., Becker, P., Lévy, J., Reynier, P., et al. (2023) · Brain · doi:10.1093/brain/awad347 · Cited by 9
METTL4-mediated N-methyladenine DNA modification regulates thermotolerance in Arabidopsis thaliana
Cai, L., Ma, A., Lei, J., & He, C. (2023) · Plant Science · doi:10.1016/j.plantsci.2023.111916 · Cited by 9
Hou, W., Wu, H., Wang, W., Wang, R., Wang, H., Wang, S., Wang, B., & Wang, H. (2023) · Frontiers in Microbiology · doi:10.3389/fmicb.2023.1295678 · Cited by 9
“The initial tertiary structure was predicted by Robetta server 9 (Baek et al., 2021).”
BackgroundDeepRank2: Mining 3D Protein Structures with Geometric Deep Learning
Crocioni, G., Bodor, D. L., Baakman, C. A. B., Parizi, F. M., Rademaker, D. T., Ramakrishnan, G., van der Burg, S., Marzella, D. F., Teixeira, J. M. C., & Xue, L. C. (2024) · The Journal of Open Source Software · doi:10.21105/joss.05983 · Cited by 8
Multi-level bioinformatics resources support drug target discovery of protein–protein interactions
Liu, J., Zhang, X., Huang, Y., Hao, G., & Yang, G. (2024) · Drug Discovery Today · doi:10.1016/j.drudis.2024.103979 · Cited by 8
Citores, L., Ragucci, S., Gay, C., Russo, R., Chambery, A., Maro, A. D., Iglesias, R., & Ferreras, J. M. (2024) · Toxins · doi:10.3390/toxins16040185 · Cited by 8
“Edodin structure was predicted using the structure prediction tools AlphaFold2 [26] and RoseTTAFold [27].”
MethodApprehensions and emerging solutions in ML-based protein structure prediction
Dahlström, K. M., & Salminen, T. A. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102819 · 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.