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 2,801–2,900 of 5,636
(2024) · doi:10.3390/biomimetics9030162 · Cited by 7
MOSAIC: A Highly Efficient, One-Step Recombineering Approach to Plasmid Editing and Diversification
(2025) · doi:10.1021/acssynbio.4c00657 · Cited by 7
“− 5 Still, in silico designed genetic parts and proteins often do not behave as expected in the complex genetic and molecular contexts of cells or cell-free expression systems.”
Colonna, G. (2024) · Livers · doi:10.3390/livers4020016 · Cited by 7
Greenshields-Watson, A., Abanades, B., & Deane, C. M. (2023) · doi:10.1101/2023.12.08.570786 · Cited by 7
Nuclear receptor interdomain communication is mediated by the hinge with ligand specificity
(2024) · doi:10.1101/2024.02.10.579785 · Cited by 7
PDBminer to Find and Annotate Protein Structures for Computational Analysis
Degn, K., Beltrame, L., Tiberti, M., & Papaleo, E. (2023) · doi:10.1101/2023.05.06.539447 · Cited by 6
Investigating the determinants of performance in machine learning for protein fitness prediction
(2025) · doi:10.1002/pro.70235 · Cited by 6
Mukherjee, S., Douglas, N., & Jimenez, R. (2024) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.3c02765 · Cited by 6
HaloClass: Salt-Tolerant Protein Classification with Protein Language Models
Narang, K., Nath, A., Hemstrom, W., & Chu, S. K. S. (2024) · The Protein Journal · doi:10.1007/s10930-024-10236-7 · Cited by 6
“By avoiding sequence alignment, pLM-based structure predictors have signi�cantly faster runtimes and lower computational demand than alignment-dependent methods, such as AlphaFold (13, 14) or RosettaFold (15).”
MethodConsidering the ethics of large machine learning models in the chemical sciences
Spotte-Smith, E. W. C. (2025) · Machine Learning: Science and Technology · doi:10.1088/2632-2153/adec3c · Cited by 6
Interpreting forces as deep learning gradients improves quality of predicted protein structures
(2023) · doi:10.1016/j.bpj.2023.12.011 · Cited by 6
drMD: Molecular Dynamics for Experimentalists
Shrimpton-Phoenix, E., Notari, E., Kluonis, T., & Wood, C. W. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168918 · Cited by 6
Nearl: extracting dynamic features from molecular dynamics trajectories for machine learning tasks
Zhang, Y., & Vitalis, A. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf321 · Cited by 9
Baid, K., Shrivastava, S., Luc, J., Richard, D. J., Aguiar, J. A., Machado, Y. J., Aicher, S., Siwak, K. C., LeBlanc, E. V., Khatooni, Z., et al. (2025) · Cell Reports · doi:10.1016/j.celrep.2025.115929 · Cited by 8
Meng, S., Li, Z., Zhang, P., Ji, Y., & Schwaneberg, U. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108660 · Cited by 6
Dynamic energy conversion in protein catalysis: From brownian motion to enzymatic function
Niazi, S. K. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.07.050 · Cited by 6
“…expansion toward capturing dynamic properties promises trans-formative insights into energy conversion mechanisms as outlined in Table 34 [25,277,278], heralding a paradigm where machine learning architectures evolve beyond crystallographic snapshots to predict conformational ensembles and…”
InfluentialHu, H., Zhang, C., Xu, Z., Guo, J., Su, A., Li, C., & Duan, H. (2025) · Digital Discovery · doi:10.1039/d5dd00118h · Cited by 9
Santos, R. M., Bastos, V. A., Bagatelli, F. F. M., Valente, R. H., Kurt, L. U., Lima, D. B., Oliveira, C. C., Nogueira, F. C. S., Eleuthério, E. C. A., Carvalho, P. C., et al. (2025) · Journal of Proteomics · doi:10.1016/j.jprot.2025.105535 · Cited by 6
And… cut! – how conformational regulation of CRISPR-Cas effectors directs nuclease activity
Calvert, R. W., & Knott, G. J. (2025) · Biochemical Journal · doi:10.1042/bcj20240481 · Cited by 6
“AI has also enabled the development of computational protein design tools such as RoseTTAFold diffusion [186,187].”
Macromolecular crystallography
Afonine, P. V., Albert, A., Diederichs, K., Hermoso, J. A., Krissinel, E., Márquez, J. A., Panjikar, S., Solà, M., Thorn, A., & Usón, I. (2025) · Nature Reviews Methods Primers · doi:10.1038/s43586-025-00433-8 · Cited by 9
Cryo-EM single-particle analysis expanding towards increasingly native samples
Moecking, J., & Zeev‐Ben‐Mordehai, T. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325008332 · Cited by 8
Wang, R., Wang, Z., Zhang, H., Liu, X., Zhu, P., Zhou, F., Ma, J., & Hu, Q. (2025) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2025.118526 · Cited by 7
Reimagining computational macromolecular modeling: AI-driven approaches
Özdemir, E. S., Jang, H., Nussinov, R., Keskin, Ö., & Gürsoy, A. (2025) · Biophysical Journal · doi:10.1016/j.bpj.2025.11.028 · Cited by 8
Exploring functional insights into the human gut microbiome via the structural proteome
Liu, H., Shen, J., Zhang, Z., Wang, J., Zhang, C., Zheng, L., Ni, H., Hong, L., Zhang, J., Xue, D., et al. (2025) · Cell Host & Microbe · doi:10.1016/j.chom.2025.11.001 · Cited by 10
Self-citationDCGAT-DTI: dynamic cross-graph attention network for drug–target interaction prediction
Abir, A. R., Alif, M. N., Zhang, W. C., Ahmed, K. T., & Zhang, W. (2025) · Bioinformatics Advances · doi:10.1093/bioadv/vbaf306 · Cited by 7
Qian, Y., Chang, X., Lv, C., Zang, J., Zhao, G., & Zhang, T. (2025) · Nano Research · doi:10.26599/nr.2025.94907916 · Cited by 6
Deep learning–driven protein binder design for crop improvement
Iqbal, M. S., Bahitwa, R., Azam, A. A., Xu, H., & Wang, H. (2025) · aBIOTECH · doi:10.1016/j.abiote.2025.100018 · Cited by 6
“1A) [12,39].”
Strategic advances for cryo-EM structural studies of small (<100 kDa) GPCRs
Singh, S. K., Agrawal, M., Pattanayak, A., Baidya, M., & Kumari, P. (2026) · Communications Biology · doi:10.1038/s42003-026-09516-y · Cited by 7
“In the current AI era, predictive tools such as AlphaFold2 and RoseTTAFold might provide invaluable preemptive insights into construct design 119,120 .”
LetA defines a structurally distinct transporter family
Santarossa, C., Li, Y., Yousef, S., Hasdemir, H. S., Rodriguez, C. C., Haase, M. A. B., Baek, M., Coudray, N., Pavek, J. G., Focke, K. N., et al. (2026) · Nature · doi:10.1038/s41586-025-09990-0 · Cited by 7
“To accelerate model building for LetAB, RoseTTAFold 59 was used to predict the 3D structure of LetA.”
Self-citationTang, J., Gong, D., Li, H., & Li, S. (2026) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2026.01.039 · Cited by 7
“The paradigm shift was spearheaded by DeepMind’s AlphaFold2 98 and the Baker laboratory’s RoseTTAFold 99 .”
Accessing new dimensions in high-resolution materials exploration by cryo-electron microscopy
Korallı, P., Kyrilis, F. L., Hamdi, F., Chochos, C. L., & Kastritis, P. L. (2026) · Materials Science and Engineering R Reports · doi:10.1016/j.mser.2026.101192 · Cited by 6
Čondić‐Jurkić, K., Alibay, I., Sherman, W., Tollefson, M. R., Walters, W. P., Baker, Z., Chong, L. T., Wei, J. N., Gray, J. J., Weitzner, B. D., et al. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c03137 · Cited by 6
Zhao, J., Tram, K., Yan, H., & Li, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag206 · Cited by 7
Precise DNA base editing using AlphaFold3-based contact modelling
Meng, H., Lei, Z., Yan, Y., Wang, L., Zhang, S., Rao, X., Shao, C., Zhang, X., Chen, K., Yang, L., et al. (2026) · Nature · doi:10.1038/s41586-026-10794-z · Cited by 8
“In fact, in addition to AlphaFold, RoseTTAFold models can also generate CP through different deep learning architectures 54,55 .”
Fungal carboxylate transporters: recent manipulations and applications
Wu, T., Li, J., & Tian, C. (2023) · Applied Microbiology and Biotechnology · doi:10.1007/s00253-023-12720-z · Cited by 7
Omori, K. K., Drucker, C. T., Okumura, T. L. S., Carl, N. B., Dinn, B. T., Ly, D., Sacapano, K. N., Tajii, A., & Owens, C. P. (2023) · FEBS Letters · doi:10.1002/1873-3468.14731 · Cited by 6
Nordquist, E. B., Zhang, G., Barethiya, S., Ji, N., White, K. M., Han, L., Jia, Z., Shi, J., Cui, J., & Chen, J. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011460 · Cited by 6
A3DyDB: exploring structural aggregation propensities in the yeast proteome
García‐Pardo, J., Badaczewska-Dawid, A. E., Pintado‐Grima, C., Iglesias, V., Kuriata, A., Kmiecik, S., & Ventura, S. (2023) · Microbial Cell Factories · doi:10.1186/s12934-023-02182-3 · Cited by 7
“Our current understanding of the structural landscape of the yeast proteome has radically changed with the development of deep-learning-based approaches, such as RoseTTA fold [36] or AF2 [21].”
BackgroundMechanism of Nitrone Formation by a Flavin-Dependent Monooxygenase
Johnson, S. B., Li, H., Valentino, H. R., & Sobrado, P. (2024) · Biochemistry · doi:10.1021/acs.biochem.3c00656 · Cited by 6
Li, J., Zhu, Z., & Song, C. (2026) · Quantitative Biology · doi:10.1101/2024.06.09.598121 · Cited by 6
Abdollahi, S., & Raoufi, Z. (2024) · Food Bioscience · doi:10.1016/j.fbio.2024.104812 · Cited by 7
Feng, M., Liu, Y., He, B., Zhong, H., Qu-Bie, A., Li, M., Luo, M., Bao, X., Li, Y., Yan, X., et al. (2024) · Phytochemistry · doi:10.1016/j.phytochem.2024.114228 · Cited by 6
Khan, S. A., Hicks, A., Leite, W. C., Byrnes, J., Gorai, B., Mroginski, M. A., O’Neill, H., & Miller, A. (2024) · Chemical Science · doi:10.1039/d4sc04544k · Cited by 6
Richard, A. C., & Pantazes, R. J. (2024) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26773 · Cited by 5
Yavaş, C., Doğan, M., Özgör, B., Akbulut, E., & Eröz, R. (2024) · Brain and Development · doi:10.1016/j.braindev.2024.104313 · Cited by 6
Antiviral Agents: Structural Basis of Action and Rational Design
Menéndez‐Arias, L., & Gago, F. (2024) · Sub-cellular biochemistry/Subcellular biochemistry · doi:10.1007/978-3-031-65187-8_20 · Cited by 7
Hedger, G., & Yen, H. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.168937 · Cited by 6
Epitope Mapping with Sidewinder: An XL-MS and Structural Modeling Approach
Ströbaek, J., Tang, D., Gueto-Tettay, C. A., Toledo, A. G., Olofsson, B., Hartman, E., Heusel, M., Malmström, J. A., & Malmström, L. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26041488 · Cited by 6
“The recent advancements in protein structure prediction [24–27] have greatly improved the utility of docking algorithms [23,28,29], especially since these AI-based technologies still struggle to predict the binding interfaces of paratopes and epitopes [24,30,31], which lack the coevolutionary…”
Insights in the RSV L polymerase function and structure
Bonneux, B., Ceconi, M., Stobbelaar, K., Herschke, F., & Delputte, P. (2025) · Antiviral Research · doi:10.1016/j.antiviral.2025.106148 · Cited by 6
From Traditional Methods to Deep Learning Approaches: Advances in Protein–Protein Docking
Jiang, L., Zhang, K., Zhu, K., Zhang, H., Shen, C., & Hou, T. (2025) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70016 · Cited by 8
“Baker et al. introduced RoseTTAFold [163], an end- to-end tri-track network based on paired sequence alignments to predict protein complexes.”
De, A., Subramanian, S., Nayak, P., & Pal, K. (2025) · In Silico Pharmacology · doi:10.1007/s40203-025-00355-z · Cited by 7
“To determine a 3D structural model of the MARV 2′-O-MTase domain and cross-validate the predicted model, we performed homology modeling of the 2′-O-MTase domain of MARV using both AF2 and RoseTTAFold (Jumper et al. 2021; Baek et al. 2021 ).”
Heuristic energy-based cyclic peptide design
Zhu, Q., Mulligan, V. K., & Shasha, D. E. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012290 · Cited by 6
Balasco, N., Esposito, L., & Vitagliano, L. (2025) · Biomolecules · doi:10.3390/biom15050674 · Cited by 9
“The revolution was completed in 2021 with the simultaneous release of AlphaFold2 (AF2) [35] and a novel machine learning-based program developed by D. Baker’s group [36].”
Global Optimization of Large Molecular Systems Using Rigid-Body Chain Stochastic Surface Walking
Guan, T., Xie, X.-T., Zhang, X., Shang, C., & Liu, Z. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c00350 · Cited by 6
“To date, with the help of AI tools such as AlphaFold 55 and RoseTTAFold, 56 researchers can predict protein native states and even reversely design new proteins for a specific function by exploiting the AI technique and the known protein structure data.”
Amino acids hydrophobic properties in proteins are derived from their atomic polarities
Cedano, J. A., Querol, E., & Mozo-Villarias, Á. (2025) · European Biophysics Journal · doi:10.1007/s00249-025-01764-w · Cited by 7
“Why is it useful to get insight into the hydrophobic character of amino acids—and their scales—in times of Alpha-Fold2 (Akdel et al. 2022) or Rosetta 3D (Baek et al. 2021) structure prediction algorithms?”
Hou, M., Li, M., Li, Y., Wu, X., Long, D., Sun, D., & Zeng, J. (2025) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2025.118297 · Cited by 8
Lush, M. E., Tsai, Y.-Y., Chen, S., Münch, D., Peloggia, J., Sandler, J. E., & Piotrowski, T. (2025) · Nature Communications · doi:10.1038/s41467-025-60251-0 · Cited by 7
Targeted Discovery and Characterization of Type‐II PKS‐NRPS Hybrid DNA‐Alkylating Antibiotics
Nie, Q., Fang, S., Wu, L., Gao, R., Hu, Y., Ding, D., Pan, H., Pei, Z., He, J., Zhou, Q., et al. (2025) · Angewandte Chemie International Edition · doi:10.1002/anie.202512820 · Cited by 6
Geometric deep learning assists protein engineering. Opportunities and Challenges.
García-Vinuesa, J., Rojas, J., Soto-García, N., Mart'inez, N., Alvarez-Saravia, D., Uribe-Paredes, R., Davari, M. D., Conca, C., Asenjo, J., & Medina-Ortiz, D. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108790 · Cited by 7
“These methods offer precision and flexibility, though they often require detailed structural templates and face challenges in handling variable-length sequences (Baek et al., 2021).”
Hong, Z., Liu, J., & Chen, Y. (2021) · Biophysical Chemistry · doi:10.1016/j.bpc.2021.106666 · Cited by 6
Breakthrough Discovery in Protein Structure Prediction and the Promise of New Treatments
Komaroff, A. L. (2021) · JAMA · doi:10.1001/jama.2021.15728 · Cited by 6
Precision materials: Computational design methods of accurate protein materials
Wang, S., & Ben‐Sasson, A. J. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102367 · Cited by 6
Martins, M., da Silva, M. F., Dinamarco, T. M., & Goldbeck, R. (2022) · Process Biochemistry · doi:10.1016/j.procbio.2022.09.018 · Cited by 6
Identifying well-folded de novo proteins in the new era of accurate structure prediction
Peñas-Utrilla, D., & Marcos, E. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.991380 · Cited by 8
“The three-dimensional structure of the designed proteins was predicted from their amino acid sequence using local installations of AlphaFold2 (Jumper et al., 2021) and the PyRosetta version of RoseTTAFold (Baek et al., 2021).”
BackgroundMethodAhmed, S., Chattopadhyay, G., Manjunath, K., Bhasin, M., Singh, N., Rasool, M., Das, S., Rana, V., Khan, N., Mitra, D., et al. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.997653 · Cited by 7
“RoseTTA fold uses a three-track neural network with multiple connections between the tracks to inspect the relationship within and between the patterns in protein sequences, distances and coordinates simultaneously (Baek et al., 2021).”
BackgroundMethodEmbedding AI in the Protein Crystallography Workflow
Gildea, R. J., Orr, C. M., Paterson, N. G., & Hall, D. R. (2022) · Synchrotron Radiation News · doi:10.1080/08940886.2022.2114723 · Cited by 6
A multilayer dynamic perturbation analysis method for predicting ligand–protein interactions
Gu, L., Ли, Б., & Ming, D. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-04995-2 · Cited by 6
“…experimentally increased rapidly, but advanced protein structure prediction programs are giving an ever-increasing number of new structures with reliable accuracy at an unprecedented rate [17, 18], which poses a great new challenge for the computational characterization of protein LBSs.”
BackgroundSarkar, D., Kulke, M., & Vermaas, J. V. (2023) · Biomolecules · doi:10.3390/biom13010107 · Cited by 6
Smart de novo Macromolecular Structure Modeling from Cryo-EM Maps
Si, D., Chen, J., Nakamura, A., Chang, L., & Guan, H. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.167967 · Cited by 6
Chien, Y.-C. C., Madarász, K., Csoma, S. L., Mótyán, J. A., Huang, H., Méhes, G., & Mokánszki, A. (2023) · Cancers · doi:10.3390/cancers15030898 · Cited by 6
Izumi, H., Aoki, H., Nafié, L. A., & Dukor, R. K. (2023) · ACS Omega · doi:10.1021/acsomega.2c08075 · Cited by 6
Ivanov, I., Smoukov, S. K., Nourafkan, E., Landfester, K., & Schwille, P. (2023) · Wiley eBooks · doi:10.1002/9781119555568.ch12 · Cited by 7
Sun, Y., Liu, K., Yun, T., Ni, Z., Zhu, Y., Chen, L., Bao, H., Ye, W., Hua, J., Huo, S.-X., et al. (2023) · Virus Research · doi:10.1016/j.virusres.2023.199111 · Cited by 6
“The RosettaFOLD tool was used to model the transmembrane region of the E2 protein (Baek et al., 2021), and cell Y.-y. Sun et al. Virus Research 331 (2023) 199111 membranes were labeled using Discovery Studio software.”
MethodSchneider, A., Bergsch, J., & Lipps, G. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad261 · Cited by 6
“The ensemble of AlphaFold2 was more diverse whereas the RoseTTAFold ensemble had an overall RMSD of only 1.4 Å.”
MethodInfluentialFoundation Models for Speech, Images, Videos, and Control
Paaß, G., & Giesselbach, S. (2023) · Artificial intelligence: foundations, theory, and algorithms/Artificial intelligence: Foundations, theory, and algorithms · doi:10.1007/978-3-031-23190-2_7 · Cited by 7
HINT, a code for understanding the interaction between biomolecules: a tribute to Donald J. Abraham
Kellogg, G. E., Marabotti, A., Spyrakis, F., & Mozzarelli, A. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1194962 · Cited by 7
“In the last few years, AlphaFold2 and RoseTTAFold (Baek et al., 2021; Jumper et al., 2021) achieved an astonishing power of prediction of protein three-dimensional structures thanks to the application of deep learning methods that revolutionized the approach applied until then (Goulet and Cambillau, 2022) This new cap…”
BackgroundHameduh, T., Mokry, M., Miller, A. D., Heger, Z., & Haddad, Y. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00134 · Cited by 6
Sooriyabandara, M. G. C., Bandaranayake, A., Jayasundara, S., Hathurusinghe, B. M., Marasinghe, M. S. L. R. P., Prasad, G. A. T., Abeywardana, V. P. M. K., Pinidiya, M. A., Nilanthi, R. M. R., & Bandaranayake, P. C. G. (2023) · PLoS ONE · doi:10.1371/journal.pone.0269967 · Cited by 6
Abdollahi, S., & Raoufi, Z. (2023) · Microbial Pathogenesis · doi:10.1016/j.micpath.2023.106317 · Cited by 6
Deciphering Enzyme Mechanisms with Engineered Ancestors and Substrate Analogues
Gao, T., Damborský, J., Janin, Y. L., & Marek, M. (2023) · ChemCatChem · doi:10.1002/cctc.202300745 · Cited by 7
Efraimidis, E., Krokidis, M. G., Exarchos, T. P., Lázár, T., & Vlamos, P. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms241713543 · Cited by 7
Zhang, P., Maruoka, M., Suzuki, R., Katani, H., Dou, Y., Packwood, D. M., Kosako, H., Tanaka, M., & Suzuki, J. (2023) · Nature Communications · doi:10.1038/s41467-023-40934-2 · Cited by 6
“Whileconsidering the 3D structure of Xkr8 and Xkr9 14,15 and a predicted structure of mouse Xkr4 by the RoseTTAFold server 25 , validated by the software verify 3D and PROCHECK, potential calcium-binding sites were iden-ti fi ed: D123 and D127 on TM1 and E310 on TM3 of Xkr4 coordinate a pocket…”
Wong, A. R., Yang, A. W. H., Gill, H. S., Lenon, G. B., & Hung, A. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107495 · Cited by 6
E2EDA: Protein Domain Assembly Based on End-to-End Deep Learning
(2023) · doi:10.1021/acs.jcim.3c01387 · Cited by 6
Oh, C., Buckley, P. M., Choi, J., Hierro, A., & DiMaio, D. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2307721120 · Cited by 7
Jia, K., Kilinc, M., & Jernigan, R. L. (2023) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2023.1227193 · Cited by 7
Wu, A., Wang, Y., Ali, A., Xu, Z., Zhang, D., Toksanbaevich, Z. K., Sheng, J., & Yi, J. (2023) · Frontiers in Veterinary Science · doi:10.3389/fvets.2023.1238634 · Cited by 6
Developing similarity matrices for antibody-protein binding interactions
Islam, S., & Pantazes, R. J. (2023) · PLoS ONE · doi:10.1371/journal.pone.0293606 · Cited by 7
Human tauopathy strains defined by phosphorylation in R1-R2 repeat domains of tau
Smith, E. D., Vo, Q., Giasson, B. I., Borchelt, D., Prokop, S., & Chakrabarty, P. (2023) · Acta Neuropathologica Communications · doi:10.1186/s40478-023-01664-0 · Cited by 7
“Using RoseTTAFold [41], we noticed that both Phospho-Plus Variant 4 and Variant 5 display a more open conformation compared to its parent P301L tau.”
BackgroundThe SKMT Algorithm: A method for assessing and comparing underlying protein entanglement
Bale, A., Rambo, R. P., & Prior, C. B. (2023) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1011248 · Cited by 8
Mei, X., Zhang, Y., Jiang, X., Liu, G., Shen, J., Xue, C., Xiao, H., & Chang, Y. (2023) · Journal of the Science of Food and Agriculture · doi:10.1002/jsfa.13164 · Cited by 6
Insights into virulence: structure classification of the Vibrio parahaemolyticus RIMD mobilome
Kinch, L. N., Schaeffer, R. D., Zhang, J., Cong, Q., Orth, K., & Grishin, N. V. (2023) · mSystems · doi:10.1128/msystems.00796-23 · Cited by 7
Self-citationJamal, G. A., Jahangirian, E., Hamblin, M. R., Shirali, M., Mirzaei, H., & Tarrahimofrad, H. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2291179 · Cited by 6
“RoseTTAFold architecture enables the network to collectively reason about the relationship between a protein’s chemical components and its folded structure (Baek et al., 2021).”
Roy, B. G., Choi, J., & Fuchs, M. (2024) · Biomolecules · doi:10.3390/biom14010062 · Cited by 10
Hamey, J. J., Nguyen, A., Haddad, M., Vázquez-Campos, X., Pfeiffer, P. G., & Wilkins, M. R. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.105639 · Cited by 7
Sun, R., Zheng, P., Chen, P., Wu, D., Zheng, J., Liu, X., & Hu, Y. (2024) · Chemistry - A European Journal · doi:10.1002/chem.202304164 · Cited by 10
Irreversible light-activated SpyLigation mediates split-protein assembly in 4D
Munoz‐Robles, B. G., & DeForest, C. A. (2024) · Nature Protocols · doi:10.1038/s41596-023-00938-0 · Cited by 6
“If split sites have not been identified for a protein, computational tools such as AlphaFold 52 and RoseTTAFold 53 may aid in identifying split sites based on the protein structure.”
Structured Tandem Repeats in Protein Interactions
Donagh, J. M., Marchesini, A., Spiga, A., Fallico, M. J., Arrías, P. N., Monzón, A. M., Vagiona, A.-C., Gonçalves-Kulik, M., Mier, P., & Andrade-Navarro, M. A. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25052994 · Cited by 7
“As a result, functions in the regulation of expression We also obtained predictions using the Robetta structure prediction server (using RoseTTAFold [42]). of apoptosis) and TPR (phosphorylation). evolutionary These predictions contain less disorder. variation in the number of TR units we…”
MethodGuillon, C., Robert, X., & Gouet, P. (2024) · Pathogens · doi:10.3390/pathogens13030241 · Cited by 8
“Finally, we used D-I-Tasser which is an evolution of I-Tasser (see above Because they are based on different AI-driven processes, we have used four of them to predict the structure of Tax: AlphaFold 2 [40], RoseTTAFold [41], ESMFold [42] and D-I-Tasser [43] (Figure 3).”
InfluentialPredicting small molecules solubility on endpoint devices using deep ensemble neural networks
Ramos, M. C., & White, A. D. (2024) · Digital Discovery · doi:10.1039/d3dd00217a · Cited by 12
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.