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 4,101–4,200 of 5,637
Refinement of Docked Protein-Protein Complexes Using Repulsive Scaling Replica Exchange Simulations
Siebenmorgen, T., Nanji, Y. S., & Zacharias, M. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-3985-6_15 · Cited by 1
Tunbridge, M. J., & Luo, X. (2024) · Transplantation · doi:10.1097/tp.0000000000005128 · Cited by 1
Choi, J., Browning, S., Schmitt‐Keichinger, C., & Fuchs, M. (2024) · Frontiers in Microbiology · doi:10.3389/fmicb.2024.1451285 · Cited by 1
Raoufi, Z., & Abdollahi, S. (2024) · International Immunopharmacology · doi:10.1016/j.intimp.2024.112972 · Cited by 2
Serrano, G. P., Echavarría, C. F., & Mejías, S. H. (2024) · Protein Science · doi:10.1002/pro.5164 · Cited by 3
“This approach allows for the direct modeling of the orientation of the chromo-phore in the binding sites (Baek et al., 2021; Rohl et al., 2004) and protein – chromophore interactions (Baek et al., 2021; Kuhlman, 2019; Wittenberg et al., 2013).”
Shin, J. H., Cuevas, L. M., Roy, R., Bonilla, S. L., Al-Hashimi, H., Greenleaf, W. J., & Herschlag, D. (2024) · RNA · doi:10.1261/rna.080039.124 · Cited by 1
Tavassoli, S., Chung, J. H., Panigrahi, A. R., Shahsavar, A., Lal, A., & Singer, S. T. (2024) · Hemoglobin · doi:10.1080/03630269.2024.2410295 · Cited by 1
“For protein structure prediction, we used Robetta, a protein structure prediction service with a deep learning-based modeling method (http://robetta.bakerlab.org), to build the homology model of Hb Balkh α2-chain [8].”
VIEPred: Predicting Viral Immune Evasion with Multimodal Representation Learning
Liang, B., Wang, N., Huang, H., Hou, Y., & Qiang, X. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2868/1/012029 · Cited by 1
The NGT200 Dataset: Geometric Multi-View Isolated Sign RecognitionPreprint
Ranum, O. A., Wessels, D. R., Otterspeer, G., Bekkers, E. J., Roelofsen, F., & Andersen, J. I. (2024) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.2409.15284 · Cited by 5
Rational drug design targeting g-protein-coupled receptors: a structural biology perspective
Khorn, P. A., Luginina, A. P., Поспелов, В. А., Dashevskii, D. E., Khnykin, A. N., Moiseeva, O. V., Safronova, N. A., Belousov, A. S., Mishin, A., & Borshchevskiy, V. I. (2024) · Biochemistry (Moscow) · doi:10.31857/s0320972524040124 · Cited by 1
Quaternary arrangements of membrane proteins: an aquaporin case
Hrmová, M. (2024) · Biochemical Society Transactions · doi:10.1042/bst20241630 · Cited by 1
Prediction and Analysis of Protein 3D Structures Using Protein Language Model and Streamlit
Srushti, C., Prathibhavani, P. M., Veena, A., & Venugopal, K. R. (2024) · International Conference on Information Management and Technology (ICIMTech) · doi:10.1109/icimtech63123.2024.10780906 · Cited by 2
“Although it significantly outperformed earlier CASPs, it could not produce model structures with remarkable precision whereas AlphaFold2 [4], RosettaFold [5] were shown at CASP14 to predict 3D protein structures with an incredibly high accuracy that is on par with experimental accuracy.”
Inter-chain residue-residue distances prediction method for protein complexes using deep learning
Yilin, P. U., Wang, S., Xia, Y., & ZHANG, G. (2024) · Scientia Sinica Informationis · doi:10.1360/ssi-2024-0296 · Cited by 1
Deciphering bacterial protein functions with innovative computational methods
Cheskis, S., Akerman-Arad, A., & Levy, A. (2024) · Trends in Microbiology · doi:10.1016/j.tim.2024.11.013 · Cited by 2
Scrutinization on Docking against Individually Generated Target Pockets for each Ligand
Zhan, R., Zhang, W., & Huang, J. (2026) · Journal of Pharmaceutical Analysis · doi:10.1016/j.jpha.2026.101759 · Cited by 3
Predicting Protein Folding on Intel’s Data Center GPU Max Series Architecture (PVC)
Ruhela, D., Prasanna, M., & Saxena, A. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00128 · Cited by 1
Advancing Template-Based Flexible Docking of P450-Heme Complexes via JAX MD
Guo, R., Chen, C., Sang, J., Cui, G., Zhang, F., Cui, X., & Li, S. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822743 · Cited by 1
(2025) · doi:10.1371/journal.pone.0299440 · Cited by 1
“Machine-learning prediction of protein 3D structures [35, 36] has also recently been used to predict PPIs [37].”
Hdoufane, I., Oubahmane, M., Habibi, Y., Delaite, C., Alanazi, M. M., & Cherqaoui, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-86961-5 · Cited by 1
“Therefore, the 3D structure was generated by homology modeling approach using four online server tools (Swissmodel 23 , PRotein Interactive MOdeling (PRIMO) 24 , AlphaFold 25 , and RoseTTAFold 26 ).”
InfluentialKoeppe, J. R., Dattelbaum, J. D., Hall, B. L., Mills, S. A., Offerdahl, E. G., Pikaart, M. J., Roberts, R., Sikora, A. K., & Craig, P. (2025) · The Biophysicist · doi:10.35459/tbp.2024.000273 · Cited by 1
Next-generation nephrology: part 1—an aid for genetic and genomic testing in pediatric nephrology
Gupta, A., Jayasinghe, K., Majmundar, A. J., Mann, N., Sinha, R., Sampson, M. G., & Quinlan, C. (2025) · Pediatric Nephrology · doi:10.1007/s00467-025-06697-2 · Cited by 3
“Computed structure models, including alpha-fold, have led to a further explosion of structural biology information in the past several years [71, 72].”
Recent advances in the structure and assembly of non-enveloped spherical viruses
Venkataraman, S., Savithri, H. S., & Murthy, M. R. N. (2025) · Virology · doi:10.1016/j.virol.2025.110454 · Cited by 1
Computational approaches to aid PROTAC drug discovery
Chakraborti, S., & McAulay, K. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-29808-0.00004-2 · Cited by 2
Xiao, D., Yang, C., Yang, J., Hou, M., Jiang, W., Hong, T., & Guo, L. (2025) · Optics Express · doi:10.1364/oe.553410 · Cited by 1
Moraes, A. H., Martins, D. M., & Chagas, M. (2024) · Computer-aided drug discovery and design · doi:10.1007/978-3-031-76718-0_14 · Cited by 2
PocketDTA: A pocket-based multimodal deep learning model for drug–target affinity prediction
Xie, J., Zhong, S., Huang, D., & Shao, W. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108416 · Cited by 1
Fremlén, H., & Burmann, B. M. (2025) · ChemBioChem · doi:10.1002/cbic.202500048 · Cited by 1
In silico λ-dynamics predicts protein binding specificities to modified RNAs
Angelo, M., Zhang, W., Vilseck, J. Z., & Aoki, S. T. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf166 · Cited by 2
“The development of accurate protein folding predictors, such as RoseTTAFold [ 108 ] and AlphaFold [ 109 ], now can provide accessible starting structural models for RNA–protein complexes to use with λ - dynamics.”
Sporophyte-directed gametogenesis in Arabidopsis
Sivakumar, P., Pandey, S., Ramesha, A., Davda, J. N., Singh, A., Kumar, C., Gala, H., Subbiah, V., Adicherla, H., Dhawan, J., et al. (2025) · Nature Plants · doi:10.1038/s41477-025-01932-y · Cited by 1
“Secondary structures were predicted using JPred (RRID:SCR_016504) 70 and RoseTTaFold 71 .”
Wang, X., Zhang, T., Liu, G., Cui, Z., Zeng, Z., Long, C., Zheng, W., & Yang, J. (2025) · Advanced Science · doi:10.1002/advs.202309051 · Cited by 2
Structural Biology for Target Identification and Validation
Dubianok, Y., Kumar, A., & Rak, A. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4418-8_2 · Cited by 1
Exploring neural networks to uncover information-richer features for protein interaction prediction
Grassmann, G., Rienzo, L. D., Ruocco, G., Milanetti, E., & Miotto, M. (2025) · European Biophysics Journal · doi:10.1007/s00249-025-01742-2 · Cited by 3
“The importance of the latter has been growing since the introduction of AlphaFold2 (Jumper et al. 2021) and RoseTTAFold (Baek et al. 2021), which are able to predict 3D protein structures (with a resolution close to experimental data) directly from amino acid sequences.”
Interactions between membrane proteins and lipid membrane revealed by cryoEM
He, S., Han, Y., Liu, X., & Guo, Y. R. (2025) · Biophysics Reports · doi:10.52601/bpr.2025.240073 · Cited by 2
PPIFold: a tool for analysis of protein–protein interaction from AlphaPullDown
(2024) · doi:10.1093/bioadv/vbaf090 · Cited by 1
Orientation-Aware Networks for Protein Structure Representation Learning
Li, J., Luo, S., Deng, C., Cheng, C., Guan, J., Guibas, L. J., Peng, J., & Ma, J. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-90252-9_1 · Cited by 1
AI Agents and the Dawn of Post-Authenticity
Hera, O. D. (2025) · Eon · doi:10.56177/eon.6.1.2025.art.1 · Cited by 1
Pražnikar, J. (2025) · Crystals · doi:10.3390/cryst15050455 · Cited by 1
Disembodied Cognition: AI Protein Folding Oracles and Their Discontents
Wallace, R. (2025) · Studies in applied philosophy, epistemology and rational ethics · doi:10.1007/978-3-031-83709-8_16 · Cited by 2
Identifying and quantifying membrane interactions of the protein human cis ‐prenyltransferase
Boren, D. M., Kredi, S., Positselskaya, E., Giladi, M., Haitin, Y., & Vermaas, J. V. (2025) · Protein Science · doi:10.1002/pro.70167 · Cited by 1
“Using the amino acid sequence and RosettaFold (Baek et al. 2021), we have modeled the loop in our simulated structures.”
Machine learning-assisted design of the molecular structure of p -phenylenediamine antioxidants
Wu, Z., Sun, S., Huang, C., Li, Z., Luo, Y., & Wang, X. (2025) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp00483g · Cited by 2
Chevannes, T. D., St‐Jacques, A. D., Loewen, M. E., & Loewen, M. C. (2025) · Biochemistry and Cell Biology · doi:10.1139/bcb-2025-0134 · Cited by 1
Kaur, K., Beghin, J., & Meier‐Stephenson, V. (2025) · Infection Genetics and Evolution · doi:10.1016/j.meegid.2025.105777 · Cited by 1
Spatio-temporal deep networks with feature disentangling for advancing earthquake monitoring
Meng, F., Ren, T., He, X., Dong, Z., Wang, X., & Chen, H. (2025) · Computers & Geosciences · doi:10.1016/j.cageo.2025.105974 · Cited by 1
Evaluating computational tools for protein-coding sequence detection: Are they up to the task?
Champion, D. J., Chen, T., Thomson, S. J., Black, M. A., & Gardner, P. P. (2025) · RNA · doi:10.1261/rna.080416.125 · Cited by 1
Tuveri, G. M., Basile, M., Acosta‐Gutiérrez, S., Kausas, M., Pujals, S., Tian, X., Franzese, G., Ruiz‐Pérez, L., & Battaglia, G. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag357 · Cited by 1
ngx-mol-viewers: Angular components for interactive molecular visualization in bioinformatics
Clementel, D., Conte, A. D., Monzón, A. M., & Tosatto, S. C. E. (2025) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2025.1586744 · Cited by 1
A Survey of Pretrained Protein Language Models
Pokharel, S., Pratyush, P., Chaudhari, M., Heinzinger, M., Caragea, D., Saigo, H., & KC, D. B. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4623-6_1 · Cited by 4
Chemosensory Receptors in Vertebrates: Structure and Computational Modeling Insights
Lamy, A., Rajesh, D., & Pageat, P. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26146605 · Cited by 1
“These include TrRosetta, a distance-based method using a convolution network to predict inter-residue orientations [260,261] and, RoseTTAFold with a three-track neural network for sequence, distance-map, and coordinate levels combining attention mechanisms and end-to-end training [235].”
Kim, J. S., Chen, Z., Garcia, S. A. E., Buhlheller, C., Zhang, B., Richards, S. J., Chen, T., Wu, J., Bruntz, R. C., Gilliam, M., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-61973-x · Cited by 1
“An initial R699 crystal structure was solved by molecular replacement with Phenixusing RoseTTAFold and AlphaFoldmodelsas searchtemplates 51,52 .”
Self-citationFunctional Design and Biophysical Characterization of Analyte-Responsive Polymers
Curley, C. E., Dold, K. J., Torres, J. A., Richard, A. C., Sanders, E., Halpern, J. M., Pantazes, R. J., & Balog, E. R. M. (2025) · Biomacromolecules · doi:10.1021/acs.biomac.5c00066 · Cited by 1
Oliw, E. H. (2025) · Archives of Biochemistry and Biophysics · doi:10.1016/j.abb.2025.110574 · Cited by 1
Denger, A., & Helms, V. (2025) · Molecules · doi:10.3390/molecules30153226 · Cited by 1
Brunello, F. G., Erra, L., Nicola, J., & Martí, M. A. (2025) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1012829 · Cited by 1
“More importantly, recent advances in machine learning approaches for protein structure prediction, such as AlphaFold, RoseT-TAFold or ESMFold, have completely changed the protein structure landscape [22,23].”
Zhang, C., Condon, A., & Duc, K. D. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbaf179 · Cited by 1
Progress and challenges for the application of machine learning for neglected tropical diseases
Khew, C., Akbar, R., & Mohd‐Assaad, N. (2025) · F1000Research · doi:10.12688/f1000research.129064.3 · Cited by 5
Neta, G. C. D. O., da Silva, J. W. B., Rocha, R. M. L., Duarte, A. K. D. S. F., Gomes, E. S. B., Zanchi, F. B., Marques, C. D. S., & Fraga, C. A. D. C. (2025) · Cell Biochemistry and Biophysics · doi:10.1007/s12013-025-01830-2 · Cited by 1
“The tertiary structure of the multi-epitope vaccine was modeled using the ROBETTA server (RoseTTAFold method) (https://robetta.bakerlab.org/) (accessed September 14, 2023) [42].”
The Future of Drug Discovery: An AI-Driven Perspective
Asim, M. N., Böhm, M., & Dengel, A. R. (2025) · Springer eBooks · doi:10.1007/978-3-031-93623-4_11 · Cited by 1
Structure and function of a fungal AB toxin-like chimerolectin involved in anti-nematode defense
Schmieder, S. S., Cordara, G., Kersten, F., Steiner, K., Samin, C. H., Plaza, D. F., Ali-Ahmad, A., Bøggild, A., Karlsen, J. L., Sokołowska, B., et al. (2026) · The EMBO Journal · doi:10.1038/s44318-026-00812-1 · Cited by 1
“…structure prediction for CCTX2 was initially carried out using the Robetta server (Kim et al, 2004) (https://robetta.bakerlab.org), based on the Rosetta simulation framework (Baek et al, 2021), applying the ‘ comparative modeling ’ protocol and automatic template selection (Song et al, 2013b).”
Varas, N., Jarosinski, M. A., Chen, Y., Ni, C., Grabowski, R., Tai, N., Herzog, R. I., Ismail‐Beigi, F., Yang, Y., Cherrington, A. D., et al. (2025) · ACS Pharmacology & Translational Science · doi:10.1021/acsptsci.5c00362 · Cited by 3
Aksoy, M., Krupitskaya, M., & Singh, S. (2025) · Plants · doi:10.3390/plants14172607 · Cited by 1
“Tertiary structure models of the extracted PH domain sequences were generated using homology-and ab initio-based modeling platforms, including SwissModel [58], Phyre2 [59], IntFold [60], I-Tasser [61], Robetta [62], Modeller [63], and QUARK [64].”
Tahzima, R., Charon, J., Díaz, A., Jonghe, K. D., Massart, S., Michon, T., & Vranken, W. (2025) · Frontiers in Virology · doi:10.3389/fviro.2025.1501616 · Cited by 1
Yang, L., Gao, Y. Q., Huang, Y., & Yang, J. (2025) · Scientia Sinica Chimica · doi:10.1360/ssc-2025-0169 · Cited by 2
Artificial intelligence in GPCR drug discovery: A paradigm shift in computational pharmacology
Vinter, A., & Grgičević, I. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-29808-0.00047-9 · Cited by 1
Zhang, Y., Zhong, S., Xu, S., Wang, Z., Xin, C., Ni, F., Yan, F., Lu, X., Sun, S., Wang, H., et al. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.147637 · Cited by 1
Structure of Bovine Glycine N-Acyltransferase Clarifies Its Catalytic Mechanism
Ebrecht, A. C., Badenhorst, C. P. S., Bornscheuer, U. T., Read, R. J., Opperman, D. J., & van Dijk, A. A. (2025) · Biochemistry · doi:10.1021/acs.biochem.5c00315 · Cited by 1
Self-citationZhang, D., Li, Y., Liu, Y., Li, G., & Chu, H. (2025) · Chemical Research in Chinese Universities · doi:10.1007/s40242-025-5157-y · Cited by 1
Aksenova, A. Y., Zhuk, A. S., Stepchenkova, E. I., Semenikhin, V. A., & Langovoy, M. (2025) · Ecological genetics · doi:10.17816/ecogen637074 · Cited by 1
Docking With Rosetta and Deep Learning Approaches in CAPRI Rounds 47–55
Harmalkar, A., Chu, L., Canner, S. W., Samanta, R., Frick, R., Dávila-Hernández, F. A., Sarma, S., Hitawala, F. N., & Gray, J. J. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70016 · Cited by 1
Inferring dynamic information from protein structures by Gaussian integrals and deep learning
Vilicich, F., Bottino, N., Su, Z., Yin, S., & Wu, Y. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag446 · Cited by 1
Luzik, D. A., & Skrynnikov, N. R. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70050 · Cited by 1
“For example, the popular generative model RFdiffusion is based on the previously developed neural network RoseTTAFold [28]; this model has shown excellent performance in protein structure predictions, as well as protein binder design, enzyme active site scaffolding, and so forth [24].”
Ilyas, A., & Batool, K. (2025) · Premier journal of science. · doi:10.70389/pjs.100106 · Cited by 1
Computational Protocols to Study Phytochromes
Nag, P., Wei, C., Mackintosh, M. J., & Schapiro, I. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4791-2_8 · Cited by 1
From Large to Small Cytokine Receptor Antagonists
Leźnicki, P., Deacon, K., Waszkowycz, B., & Unitt, J. F. (2025) · SLAS DISCOVERY · doi:10.1016/j.slasd.2025.100280 · Cited by 1
Computational Biology in Plants: Technological Innovations in the Post-Genomic Era
Kitony, J., Padgitt‐Cobb, L. K., Hartwick, N. T., & Michael, T. P. (2025) · Springer eBooks · doi:10.1007/978-981-95-0583-8_23 · Cited by 1
Singh, A., Iyyappan, Y., Rakesh, V., Gupta, M., & Kaur, S. (2025) · Indian Journal of Entomology · doi:10.55446/ije.2025.3053 · Cited by 1
“Consequently, protein structures were modelled using the accurate deep learning-based RoseTTAFold method (Baek et al., 2021).”
Schumacher, M. A., Singh, R. R., & Salinas, R. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169486 · Cited by 1
Liao, X., Li, Y., Wu, Y., Wen, L., Jing, M., Chen, B., Li, X., & Shang, X. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.5c00631 · Cited by 1
Yang, M. J., Liu, S., Chen, G., Liu, X., Sun, D., Zhang, J., Wang, Y., Chen, S., Tian, R., & Hu, Z. (2025) · Cell Genomics · doi:10.1016/j.xgen.2025.101039 · Cited by 3
“34,35 For example, the distinctive structural features of FrCas9, especially its protein-DNA interaction mechanisms, can serve as training templates for AI algorithms to identify better and novel Cas systems.”
Biondini, M. C., Sessa, M., Vassallo, A., Chiappori, F., Zannotti, M., Mancini, A., Giovannetti, R., & Pucciarelli, S. (2025) · Marine Drugs · doi:10.3390/md23100410 · Cited by 1
“A model for each domain was obtained using RoseTTaFold, the deep learning tool of Rosetta [50].”
Computational cyclic peptide design machine learning & Rosetta based methods
Sarmeili, F., Siegler, H., Powers, A. C., & Hosseinzadeh, P. (2025) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2025.09.016 · Cited by 1
Roche, R., Tarafder, S., Suseendran, P., Wang, X., & Bhattacharya, D. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4828-5_14 · Cited by 1
From Infinite Helices to β Sheets: Structural Insights from Electronic Structure Calculations
Adasme‐Carreño, F., Muñoz‐Gutierrez, C., Bedoya, M., & Ireta, J. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01087 · Cited by 1
Protein Structural Model Selection Informed by Comparison of Predicted Ligand Binding Poses
Karelina, M., & Dror, R. O. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01925 · Cited by 1
Wat, J. H., West, T., Pizzala, N. J., Alvarez, S., Wang, Y., Chen, M., & Reppert, M. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.5c06200 · Cited by 1
Paratope plasticity determines anti-HER2 (4B5) antibody specificity
Warren, P. D., Landowski, T. H., Dodson, M. S., Gulzar, A., Palting, J. D., Walker, E., Towne, P., & Smith, M. H. (2025) · mAbs · doi:10.1080/19420862.2025.2583770 · Cited by 1
“22 The C-terminal peptide residues 1239–1255 were extracted for further investigation.”
InfluentialUnderlying Polymorphism: Superhelical Crystallization Induces Architectural and Functional Diversity
Zhang, Y., Pan, T., Guerin, S., Zhang, J., Tang, Y., Qiu, Z., Li, Q., Zhang, J., Wei, F., Wang, J., et al. (2025) · Small · doi:10.1002/smll.202510542 · Cited by 1
Self-citationSima, I., Cristea, D.-M., Iantovics, L. B., & Niculescu, V. (2025) · Biomimetics · doi:10.3390/biomimetics10110763 · Cited by 1
“RoseTTAFold [33], developed by the Baker lab, is another deep learning-based method for protein structure prediction [34].”
Durmuş, H., Clemen, C. S., Uçar, E. Ö., Hofmann, A., Schlötzer-Schrehardt, U. M., Mertoğlu, E., Ceylaner, S., Dursun, M., Sewry, C. A., Schröder, R., et al. (2025) · Journal of Neuromuscular Diseases · doi:10.1177/22143602251387026 · Cited by 1
“In the absence of an experimentally determined 3D structure of human kyphoscoliosis peptidase (UniProt Q8NBH2), the AlphaFold database of 3D structures predicted by the DeepMind/AlphaFold project 16 was used to visualize the protein structure (Figure 2J) and assess the impact of the p.(Cys243Arg) mutation.”
Selectivity Approaches in Therapeutic Antibody Design
Fouad, M. A. (2025) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c01830 · Cited by 1
Enzyme-Mediated Carbon Dioxide Fixation: Catalytic Mechanisms and Computational Insights
Kai, W., Jingxuan, Z., & Li, Q. (2025) · Synthetic biology and engineering · doi:10.70322/sbe.2025.10017 · Cited by 1
Sequence-based calculation of local energetic frustration in proteins
Kuhn, A. M., Contessoto, V. G., Onuchic, J. N., & Phillips, G. N., Jr. (2025) · Structural Dynamics · doi:10.1063/4.0000781 · Cited by 1
Deep learning analysis of ions accelerated at shocks
Swierc, P., Caprioli, D., Orusa, L., & Černetič, M. (2026) · Journal of Cosmology and Astroparticle Physics · doi:10.1088/1475-7516/2026/06/071 · Cited by 1
“In the life sciences, for example, some revolutionary applications include protein structure prediction [42, 43] or antibacterial discovery [44].”
Parnandi, V. A., Trivedi, P. M., Panchal, H., Suryawanshi, G., & Patkar, R. (2025) · Current Biology · doi:10.1016/j.cub.2025.10.082 · Cited by 2
Lammi, C., Pugliese, R., d’Adduzio, L., Musazzi, U. M., Aiello, G., Fanzaga, M., Musco, M. S., & Bollati, C. (2025) · Cosmetics · doi:10.3390/cosmetics12060267 · Cited by 1
Dynamic interplay at the gates: All-Atom simulations reveal isoform-specific aquaporin 7 inhibition
Hegde, A. K., Dsouza, L. A., Singh, M. K., Pati, S., & Dehury, B. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.111336 · Cited by 1
Kassegne, K., Shen, H., Chen, S., Xu, S., Li, J., Xu, B., Deitsch, K., Wang, Y., Zhou, X.-N., & Chen, J. (2025) · EBioMedicine · doi:10.1016/j.ebiom.2025.106041 · Cited by 1
“The variable domain (residues 169–321) of RIFIN PF3D7_0900200— was modelled via ColabFold 33 (integrating MMseqs2 homology search 34 with AlphaFold2/RoseTTAFold), 35,36 whereas the LILRB1 structure was extracted from its cocrystal with PF3D7_1254800 (PDB: 6ZDX).”
Chen, J., Li, T., He, J., & Huang, S. (2025) · Structure · doi:10.1016/j.str.2025.11.004 · Cited by 2
Zhan, J., Ho, M., Esser, L., Maslanka, C., Pastan, I., & Xia, D. (2025) · Antibody Therapeutics · doi:10.1093/abt/tbaf028 · Cited by 1
Prompt-based multimodal representation learning for drug repurposing
Liu, J., Kaicheng, U., Rana, D., Zhang, S. M., Yu, J., Yang, S., Jin, B., Wang, X., Yang, Z., Tang, H., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf636 · Cited by 2
Realistic transition paths for large biomolecular systems: A Langevin bridge approach
Koehl, P., Delarue, M. H., & Orland, H. (2026) · The Journal of Chemical Physics · doi:10.1063/5.0314611 · Cited by 1
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.