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 4,001–4,100 of 5,636
Burgin, T., Pfaendtner, J., & Beck, D. A. C. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c04802 · Cited by 2
Gonçalves, R. L., de Souza, G. A. P., Terceti, M. D. S., de Castro, R. F. G., Silva, B. D. M., Novaes, R. D., Malaquias, L. C. C., & Coelho, L. F. L. (2022) · Brazilian Journal of Microbiology · doi:10.1007/s42770-022-00875-2 · Cited by 2
Serre, L., Delaroche, J., Vinit, A., Schoehn, G., Denarier, É., Fourest‐Lieuvin, A., & Arnal, I. (2022) · Journal of Cell Science · doi:10.1242/jcs.260152 · Cited by 2
Lu, J. (2022) · doi:10.1145/3569966.3570102 · Cited by 2
“[9] These approaches have solidly proved the efficiency of the application of artificial intelligence in Protein Folding Problem.”
BackgroundMethodStructural Dynamics Predominantly Determine the Adaptability of Proteins to Amino Acid Deletions
Banerjee, A., & Bahar, İ. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24098450 · Cited by 2
“Finally, we recognize that the introduction of AI-driven structure prediction methods such as AlphaFold2 [60] and RoseTTAFold [61] has been revolutionary.”
MethodIn the Age of Machine Learning Cryo‐EM Research is Still Necessary: A Path toward Precision Medicine
Stephens, D. C., Crabtree, A., Beasley, H. K., Lopez, E. G., Mungai, M., Vang, L., Neikirk, K., Vue, Z., Vue, N., Marshall, A. G., et al. (2023) · Advanced Biology · doi:10.1002/adbi.202300122 · Cited by 2
Watanabe, N., Kuriya, Y., Murata, M., Yamamoto, M., Shimizu, M., & Araki, M. (2023) · Biology · doi:10.3390/biology12060795 · Cited by 2
Sekmen, A., Nasr, K. A., Bilgin, B., Koku, A. B., & Jones, C. (2023) · Biomolecules · doi:10.3390/biom13060923 · Cited by 2
“There is another impactful machine learning approach for tertiary structure prediction called RosettaFold, as described in [18].”
MethodComputational design of industrially relevant enzymes
Osuna, S. (2023) · Advances in catalysis · doi:10.1016/bs.acat.2023.07.001 · Cited by 2
Crystal structures of Streptomyces tsukubaensis sigma factor SigG1 and anti-sigma RsfG
Leite, J. P., Lourenço, F. M., Oliveira, R., Sousa, S. F., Mendes, M. V., & Gales, L. (2023) · Journal of Structural Biology · doi:10.1016/j.jsb.2023.108038 · Cited by 2
Finding information about uncharacterized Drosophila melanogaster genes
Mohr, S. E., Kim, A.-R., Hu, Y., & Perrimon, N. (2023) · Genetics · doi:10.1093/genetics/iyad187 · Cited by 2
Sequence‐Tunable Phase Behavior and Intrinsic Fluorescence in Dynamically Interacting Peptides
Sementa, D., Dave, D. R., Fisher, R. S., Wang, T., Elbaum‐Garfinkle, S., & Ulijn, R. V. (2023) · Angewandte Chemie · doi:10.1002/ange.202311479 · Cited by 2
In silico strategy to model LMP1 of Epstein–Barr virus protein
Salam, D.-S. D. A., Hwang, S. S., Wang, F., Theng, L. B., & Wezen, X. C. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385610 · Cited by 2
“Robetta is one of the most widely used tools with an interactive submission interface that allows custom sequence alignments for various modelling based on deep learning-based methods called RoseTTAFold [17].”
MethodHarnessing Computational Modeling for Efficient Drug Design Strategies
Singh, K., Bhushan, B., Dube, A. K., Jha, A. K., Rani, K., Mishra, A. K., & Porwal, P. (2024) · Letters in Organic Chemistry · doi:10.2174/0115701786267754231114064015 · Cited by 2
ARCIMBOLDO at low resolution: Verification for coiled coils and globular proteins
Caballero, I., Castellví, A., Triviño, J., Jiménez, E., Soler, N., Borges, R. J., & Usón, I. (2024) · Protein Science · doi:10.1002/pro.5136 · Cited by 2
“The use of predicted models (Baek et al., 2021; Jumper et al., 2021) has been extensively incorporated in crystallographic determination methods (Medina et al., 2022; Simpkin et al., 2023).”
MethodSong, K., Xu, H., Shi, Y. Y., Zou, X., Da, L., & Hao, J. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.136502 · Cited by 2
Everyone is using biological structures, but how does one find the structure(s) one wants?
Bond, C. S., & Sussman, J. L. (2024) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798324007848 · Cited by 2
Simpson, J., & Kasson, P. M. (2025) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1012812 · Cited by 2
“…protein structure prediction algo-rithm that substantially increased prediction accuracy over prior methods [34] and has been rapidly adopted for different protein design applications [35–37], also spawning a set of related deep-learning approaches for protein structure prediction [38,39].”
A quantitative mapping approach to identify direct interactions within complexomesPreprint
Trepte, P., Secker, C., Choi, S. G., Olivet, J., Ramos, E. S., Cassonnet, P., Golusik, S., Zenkner, M., Beetz, S., Sperling, M., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.08.25.457734 · Cited by 4
Camacho, E., Dong, Y., Angleró-Rodríguez, Y., Smith, D. F. Q., Jacomini, R. D. S., McConnell, S. A., Dimopoulos, G., & Casadevall, A. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.05.07.443077 · Cited by 3
MPDB: a unified multi-domain protein structure database integrating structural analogue detectionPreprint
Peng, C., Zhou, X., Xia, Y., Zhang, Y., & Zhang, G. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.10.27.466092 · Cited by 2
“In the absence of an experimentally solved structure, the user can use models generated by the structure prediction tools, such as AlphaFold2 [2], D-I-TASSER [4], RoseTTAFold [3], CoDiFold [19] or CGLFold [20].”
BackgroundMethodChen, C., Boorla, V. S., Chowdhury, R., Nissly, R. H., Gontu, A., Chothe, S. K., LaBella, L. C., Jakka, P., Ramasamy, S., Vandegrift, K. J., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.03.22.485413 · Cited by 3
Okwei, E., Ganguly, S., Darling, H. L., Harp, J. M., Gulsevin, A., Coin, I., Mchaourab, H. S., Ledwitch, K. V., Kuenze, G., & Meiler, J. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.10.487812 · Cited by 2
Electron counting takes microED to the next level
Corbett, K. D., & Herzik, M. A. (2022) · Nature Methods · doi:10.1038/s41592-022-01518-y · Cited by 2
AlphaFold Prediction of Structural Ensembles of Disordered Proteins
Brotzakis, Z. F., Zhang, S., & Vendruscolo, M. (2023) · doi:10.21203/rs.3.rs-2659892/v1 · Cited by 2
Geller, A. M., Zlotkin, D., Shalom, M., Blum, N., & Levy, A. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.03.26.534264 · Cited by 2
The Multiscale Surface Vision Transformer.Preprint
Dahan, S., Williams, L. Z. J., Rueckert, D., & Robinson, E. C. (2024) · PubMed Central · Cited by 5
A perspective on the sharing of docking data
Aci‐Sèche, S., Bourg, S., Bonnet, P., Rebehmed, J., de Brevern, A. G., & Diharce, J. (2023) · Data in Brief · doi:10.1016/j.dib.2023.109386 · Cited by 2
“Completion can be done with homology modeling (for example, Modeller [17] ), or deep learning approaches which are very numerous now, e.g. AlphaFold [18] , CollabFold [19] , RoseTTAfold [20] .”
Abdelhamid, I., Muscoloni, A., Rotscher, D. M., Lieber, M., Markwardt, U., & Cannistraci, C. V. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.10.552825 · Cited by 5
Molearn: a Python package streamlining the design of generative models of biomolecular dynamics
Musson, S. C., & Degiacomi, M. T. (2023) · The Journal of Open Source Software · doi:10.21105/joss.05523 · Cited by 2
An, X., Bian, J., Zhao, J., Lan, X., Liao, Y., Liu, R., Liang, M., Tang, J., Liu, H., & Qu, J. (2024) · Research Square · doi:10.21203/rs.3.rs-3756664/v1 · Cited by 2
PackDock: a Diffusion Based Side Chain Packing Model for Flexible Protein-Ligand DockingPreprint
Zhang, R., Jiang, X., Cao, D., Yu, J., Chen, M., Fan, Z., Kong, X., Xiong, J., Zhang, Z., Zhang, W., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.01.31.578200 · Cited by 2
Computational Approaches and Drug Discovery: Where Are We Going?
Tutone, M., & Almerico, A. M. (2024) · Molecules · doi:10.3390/molecules29050969 · Cited by 2
Subcellular thermal profiling enables the deep functional exploration of the mitochondrial proteomePreprint
Rivera-Mejías, P., Sueur, C. L., Kurzawa, N., Becher, I., & Savitski, M. M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.27.582308 · Cited by 2
FoldToken2: Learning compact, invariant and generative protein structure languagePreprint
Gao, Z., Tan, C., & Li, S. Z. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.11.598584 · Cited by 6
Cmai: Predicting Antigen-Antibody Interactions from Massive Sequencing DataPreprint
Song, B., Wang, K., Na, S., Yao, J., Fattah, F. J., von Itzstein, M. S., Yang, D. M., Liu, J., Xue, Y., Liang, C., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.27.601035 · Cited by 3
Self-citationAccurate Prediction of Ligand-Protein Interaction Affinities with Fine-Tuned Small Language ModelsPreprint
Fauber, B. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.00111 · Cited by 2
Benavides, T. L., & Montelione, G. T. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.19.613999 · Cited by 3
Valbuena, R., Nigam, A., Tycko, J., Suzuki, P., Spees, K., Aradhana, Arana, S. M., Du, P. P., Patel, R. A., Bintu, L., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.21.614253 · Cited by 4
Disentangling the CHAOS of intrinsic disorder in human proteinsPreprint
de Vries, I., Bak, J., Salmoral, D. Á., Xie, R., Borza, R., Konijnenberg, M., & Perrakis, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.26.620428 · Cited by 2
Shah, A., & Jayaratnam, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.05966 · Cited by 4
Designing a multi-serotype Dengue virus vaccine: an in silico approach to broad-spectrum immunityPreprint
Singh, A., Glushchenko, O. E., Ustiugova, A. S., Alawi, K. M., Korzinkin, M., Zhavoronkov, A. A., & Castiglione, F. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.02.626364 · Cited by 2
Missense mutations: Backbone structure positional effectsPreprint
Martell, R. I. P., Stege, U., & Jabbari, H. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.23.630208 · Cited by 2
Protein Structure Description with ρ, θ and ϕ : A Case Study with Caenopore-5Preprint
Li, W. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.08.631847 · Cited by 1
Pérez, E. G. (2025) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/214743 · Cited by 2
Free energy calculations for protein designPreprint
Schmidt, L., Wilson, C. J., Behera, S., & de Groot, B. L. (2025) · ChemRxiv · doi:10.26434/chemrxiv-2025-vp1ms · Cited by 4
Harnessing AlphaFold to reveal hERG channel conformational state secretsPreprint
Ngo, K., Yang, P., Yarov-Yarovoy, V. M., Clancy, C. E., & Vorobyov, I. V. (2025) · eLife · doi:10.7554/elife.104901.2 · Cited by 3
Protein structure prediction and design for high-throughput computingPreprint
Mathew, V. S., Kellogg, G. D., & Lai, W. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.18.665594 · Cited by 2
A Paired Database of Predicted and Experimental Protein Peptide Binding Information
Torres, J. A., Kieslich, C. A., & Pantazes, R. J. (2025) · Scientific Data · doi:10.1038/s41597-025-05754-7 · Cited by 3
Protein generation with embedding learning for motif diversificationPreprint
Michalewicz, K., Jin, C., Teare, P., Diethe, T., Barahona, M., Bravi, B., & Mullokandov, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.18790 · Cited by 2
Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel ProjectionPreprint
Chen, S., Guo, M., Wang, C. C., Chen, A. H., Zhang, Y., Chai, J., Yang, Y., Matusik, W., & Chen, P. Y. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.08946 · Cited by 2
GTcomplex: Spatial indexing-powered search and alignment of macromolecular complexesPreprint
Margelevičius, M. (2025) · Research Square · doi:10.64898/2025.12.15.694356 · Cited by 2
Towards understanding the mechanisms of the periplasmic pyoverdine maturation
Sugue, M.-F. (2022) · Institutional Repository of Leibniz Universität Hannover (Leibniz Universität Hannover) · doi:10.15488/11907 · Cited by 2
ViSAS for Entering Chemical Space: Virtual Screening of Analog Series and Related AdvancesPreprint
Naveja-Romero, J. J., Saldívar-González, F. I., Prado-Romero, D. L., Ruiz-Moreno, A. J., Velasco-Velázquez, M. A., Miranda-Quintana, R. A., & Medina‐Franco, J. L. (2022) · ChemRxiv · doi:10.26434/chemrxiv-2022-9t2rj · Cited by 3
Navigating the promise and pitfalls of artificial intelligence
(2026) · Nature Microbiology · doi:10.1038/s41564-026-02300-y · Cited by 2
Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic AttentionPreprint
Varner, J. (2026) · arXiv.org · doi:10.48550/arxiv.2603.14717 · Cited by 3
Follonier, O. M., Liu, Y., Campomanes, P., Lafrenaye, L., Racle, J., Alvarez, D., van Gerwen, J., Heinzmann, R., Jänes, J., Kummelstedt, E., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.13.738147 · Cited by 2
Recovering Conformational Heterogeneity from the Protein Data Bank at Scale
Wankowicz, S. A. M. (2026) · The Stacks · doi:10.82153/fjj4-gv26 · Cited by 2
The repetitive local sampling and the local distribution theory
(2021) · doi:10.1002/wcms.1588 · Cited by 2
“In AlphaFold, 20 AlphaFold2 58 and many other RPDD based studies, 21,22,24–29,59, 60 the core information obtained is Conversely, with RPDD, one may in principle construct GJD with su ffi cient sampling and optimization with necessary restraints.”
BackgroundVaradi, M., Nair, S., Sillitoe, I., Tauriello, G., Anyango, S., Bienert, S., Borges, C., Deshpande, M., Green, T., Hassabis, D., et al. (2022) · doi:10.1101/2022.08.01.501973 · Cited by 2
Protein pKa prediction with machine learning
Cai, Z., Luo, F., Wang, Y., Li, E., & Huang, Y. (2021) · doi:10.33774/chemrxiv-2021-7gk5l-v2 · Cited by 2
Identification of a covert evolutionary pathway between two protein folds
Chakravarty, D., Sreenivasan, S., Swint-Kruse, L., & Porter, L. L. (2022) · doi:10.1101/2022.12.08.519646 · Cited by 2
Modeling the Orthosteric Binding Site of the G Protein-Coupled Odorant Receptor OR5K1
Nicoli, A., Haag, F., Marcinek, P., He, R., Kreißl, J., Stein, J., Marchetto, A., Dunkel, A., Hofmann, T., Krautwurst, D., et al. (2022) · doi:10.1101/2022.06.01.494157 · Cited by 2
Evolutionary selection of proteins with two folds
Schafer, J. W., & Porter, L. L. (2023) · doi:10.1101/2023.01.18.524637 · Cited by 2
Schmidt, M., Pearson, A. N., Incha, M. R., Thompson, M. G., Baidoo, E. E. K., Kakumanu, R., Mukhopadhyay, A., Shih, P. M., Deutschbauer, A. M., Blank, L. M., et al. (2021) · doi:10.1101/2021.12.09.472016 · Cited by 2
Xia, Y., Pu, Y., Wang, S., Zhuang, J., Liu, D., Hou, M., & Zhang, G. (2024) · doi:10.1101/2024.11.22.624951 · Cited by 2
ModVAR: A Multimodal Framework for Comprehensive Driver Variant Prediction in Cancer
Wang, Z., Yang, H., Chen, Y., Zhou, T., Wang, Y., Zhou, Q., Xiao, T., Zhang, Q., Zhang, J., & Li, D. (2024) · doi:10.21203/rs.3.rs-4969792/v1 · Cited by 2
HIPPO: HIstogram-based Pseudo-POtential for scoring protein-ssRNA fragment-based docking poses
Kravchenko, A., de Vries, S. J., Smaïl-Tabbone, M., & Chauvot de Beauchene, I. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05733-6 · Cited by 1
“On the other hand, in recent years, various powerful deep learning techniques ([6–8]) brought break-throughs to protein–protein [9] and protein–ligand [10, 11] docking.”
Liu, L., Liu, Y., Ye, X., Zhang, S., Li, Y., Zhu, K., Xue, Y., Zhou, J., Zhang, X., & Fang, X. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01264-2 · Cited by 1
“Deep learning has transformed this field, with recent breakthroughs [1–11] exemplified by the AlphaFold [1–3] and RoseTTAFold series [4, 5].”
(2024) · doi:10.1002/1873-3468.14837 · Cited by 1
“For RoseTTAFold [29], mean interface predicted aligned error (pAE) 5 indicated high confidence.”
BackgroundMethodMi, T., Xiao, N., & Gong, H. (2025) · Protein Science · doi:10.1002/pro.70041 · Cited by 1
“AlphaFold2 (Jumper et al. 2021) in CASP14, followed by RoseTTA-Fold (Baek et al. 2021), integrated the inter-residue geometry prediction and geometry-constrained structural modeling in a unified neural network, which markedly suppressed the prediction errors through end-to-end training, enhancing the precision of mono…”
Computational Methods for the Study of Peroxisomes in Health and Disease
van Wijk, N., & Linial, M. (2022) · Physiology · doi:10.5772/intechopen.103178 · Cited by 1
Structure Prediction, Evaluation, and Validation of GPR18 Lipid Receptor Using Free Programs
Michalik, I., Kuder, K., Kieć‐Kononowicz, K., & Handzlik, J. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23147917 · Cited by 1
The rise of the machines in chemistry
Gill, M. L. (2022) · Magnetic Resonance in Chemistry · doi:10.1002/mrc.5304 · Cited by 1
QSAR via multisite λ‐dynamics in the orphaned TSSK1B kinase
Liu, X., Tsang, P. K., Soellner, M. B., & Brooks, C. L. (2023) · Protein Science · doi:10.1002/pro.4623 · Cited by 1
Choi, J. (2023) · iScience · doi:10.1016/j.isci.2023.106911 · Cited by 1
Highly Accurate Protein Structure Classification and Prediction
Saha, A., & Sarkar, I. (2023) · International Conference on Computational Systems and Communication (ICCSC) · doi:10.1109/iccsc56913.2023.10142975 · Cited by 1
Analysis of the Confidence in the Prediction of the Protein Folding by Artificial Intelligence
Nevado, P. T., Serrano, E., González-Herrero, A., Bermejo-Moreno, R., & Rodríguez‐González, A. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-38079-2_9 · Cited by 2
Accelerating AlphaFold2 Inference of Protein Three-Dimensional Structure on the Supercomputer Fugaku
Oyama, Y., Tabuchi, A., & Tokuhisa, A. (2023) · doi:10.1145/3589013.3596674 · Cited by 1
Boland, C., Huang, C., Kaki, S. S., Wang, M., Oliéric, V., & Caffrey, M. (2023) · Crystals · doi:10.3390/cryst13091402 · Cited by 1
Chaudhri, E. N., Abbott, J. M., Islam, N. N., Weber, C. A., Coban, M., Bilgili, A., Squire, J. D., Mantia, S., Wierenga, K. J., & Caulfield, T. R. (2023) · Genes · doi:10.3390/genes14101855 · Cited by 1
Borgese, N., Guillén-Samander, A., Colombo, S. F., Mancassola, G., Berardino, F. D., Zanetti, D., & Carrera, P. (2023) · Biomedicines · doi:10.3390/biomedicines11102657 · Cited by 1
“…substitution of a hydrophobic residue with a polar one might alter the folding of the 30th Calx-β domain, we modeled the structure of the wild-type and mutant domain with Colabfold [19] and RoseTTAFold [21] structural prediction algorithms (Figure 5). conservation number indicated below the bars.”
BackgroundMethodInfluential伏信, 進. (2023) · Bulletin of Applied Glycoscience · doi:10.5458/bag.13.2_136 · Cited by 1
Mohr, S., Aldakul, Y. K., Sun, H., Sawczyc, H., & Lange, A. (2023) · Royal Society of Chemistry eBooks · doi:10.1039/bk9781837670154-00268 · Cited by 1
Promoter DNA recognition by the Enterococcus faecalis global regulator MafR
Moreno‐Blanco, A., Pluta, R., Espinosa, M., Ruiz‐Cruz, S., & Bravo, A. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1294974 · Cited by 1
“AlphaFold Protein Structure Database (Jumper et al., 2021; Varadi et al., 2022) and RoseTTAFold (Baek et al., 2021) were used to obtain three-dimensional models of the OG1RF_10478 protein (Uniprot Q837T7).”
MethodChakraborty, A., Hussain, A., & Sabnam, N. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2292795 · Cited by 2
“…proteins with more than 30% sequence similarity in the PDB databank were not available, the tertiary structures of the six representative proteins were predicted using a fold-recognition method, RoseTTAFold, accessible on the web server Robetta (https://robetta.bakerlab.org/) (Baek et al., 2021).”
Production of a Bacteriocin Like Protein PEG 446 from Clostridium tyrobutyricum NRRL B-67062
Liu, S., Lu, S.-Y., Patel, M., Qureshi, N., Dunlap, C. A., Hoecker, E. C., & Skory, C. D. (2024) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-023-10211-1 · Cited by 1
“3B, and this structure model was validated independently by the Baker Lab with RoseT-TAFold using the UniProt multiple sequence alignment from Pfam [31].”
MethodLuo, H., Qu, X., Deng, X., He, L., Wu, Y., Liu, Y., He, D., Yin, J., Wang, B., Gan, F., et al. (2024) · Applied and Environmental Microbiology · doi:10.1128/aem.02048-23 · Cited by 1
“The structural models of the signal peptide-lacking forms of NgHtrA (A-ΔS), NgHtrB (B-ΔS), and NgHtrC (C-ΔS) were predicted by RoseTTAFold (74).”
MethodZheng, Z., Zhang, B., Zhong, B., Yu, J., Liu, K., Li, Z., Zhu, J., Wei, T., & Chen, H.-F. (2026) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1014290 · Cited by 1
“GPDL [49] combined ESMFold [16] with constrained hallucination and inpainting strategies to generate highly designable and diverse scaffolds around given motifs.”
Consistent Protein Structure Determination Using Sparse NMR Data
Shen, Y. (2024) · Royal Society of Chemistry eBooks · doi:10.1039/bk9781839167898-00181 · Cited by 1
Rehneke, L., & Schäfer, P. (2024) · BioEssays · doi:10.1002/bies.202300172 · Cited by 1
Exploring the selectivity of cytochrome P450 for enhanced novel anticancer agent synthesis
Čivić, J., McFarlane, N. R., Masschelein, J., & Harvey, J. N. (2024) · Faraday Discussions · doi:10.1039/d4fd00004h · Cited by 1
Unveiling success determinants for AMB-assisted phase expansion of fusion proteins in ARP/wARP
Cardona-Echavarría, M. C., Santillán, C., Miranda‐Blancas, R., Stojanoff, V., & Rudiño-Piñera, E. (2024) · Journal of Structural Biology · doi:10.1016/j.jsb.2024.108089 · Cited by 1
The Predicted Structure of a Thermophilic Malate Synthase
Nielsen, S., Orton, J., & Howard, B. (2024) · American Journal of Undergraduate Research · doi:10.33697/ajur.2024.103 · Cited by 1
High-Resolution Tomography, Molecular Model Building and Visualization
Bartesaghi, A. (2024) · Focus on structural biology · doi:10.1007/978-3-031-51171-4_9 · Cited by 1
Kaushik, R. K., Kumar, N., & Launey, T. (2024) · Livestock diseases and management · doi:10.1007/978-981-99-9195-2_13 · Cited by 2
Molecular determinants of Ras-mTORC2 signaling
Smith, S. F., Islam, A. F. M. T., Alimukhamedov, S., Weiss, E. T., & Charest, P. G. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.107423 · Cited by 1
“A predicted structure of RasC is shown as a rainbow ribbon, generated using the Robetta server and UCSF ChimeraX (61, 62).”
Patil, V., Desai, S. A., Patel, V. P., & Somase, V. (2024) · Current Pharmaceutical Biotechnology · doi:10.2174/0113892010295441240515074348 · Cited by 2
Burgardt, N. I., Melian, N. A., & Flecha, F. L. G. (2024) · Environmental Microbiology Reports · doi:10.1111/1758-2229.13278 · Cited by 1
“BaCopA1 homology models were generated using Phyre2 (Kelley et al., 2015), MODELLER (Webb & Sali, 2016), tr-Rosetta (Baek et al., 2021; Du et al., 2021), AlphaFold 2 (Jumper et al., 2021) and RosettaFold (Baek et al., 2021; Mirdita et al., 2022).”
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
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.