Accurate prediction of protein structures and interactions using a 3-track network
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 13 of the 36 sources its claims cite were checked for support.
Abstract
DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research. One-Sentence Summary: Accurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.
Overview
CoChat Summary
TL;DR
RoseTTAFold is a 3-track neural network that integrates 1D sequence, 2D distance-map, and 3D coordinate information to predict protein structures and interactions. It approaches AlphaFold2 accuracy in CASP14, solves challenging crystallography and cryo-EM modeling problems, and generates protein-complex models directly from sequence.
Key findings
- In CASP14, the 3-track RoseTTAFold outperformed the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), the BAKER human group, and the authors’ 2-track models, though its performance was still not as good as AlphaFold2.
- On CAMEO, over 69 medium and hard targets released May 15–June 19, 2021, RoseTTAFold outperformed all other evaluated servers, including Robetta, IntFold6-TS, BestSingleTemplate, and SWISS-MODEL.
- RoseTTAFold models enabled molecular-replacement solutions for four previously unsolved crystallographic datasets; for the cryo-EM p101 Gβγ binding domain, the Cα-RMSD between predicted and refined structure was 3.0 Å over the beta-sheets.
- Among 693 domains from human disease-related proteins, over one-third had predicted lDDT > 0.8, corresponding to an average Cα-RMSD of 2.6 Å on CASP14 targets; many protein-complex models had TM-score > 0.8, with complex generation taking ~30 min on a 24G TITAN RTX GPU.
Methods
- The 3-track network transforms and integrates information at the 1D sequence/MSA level, the 2D distance/orientation-map level, and the 3D backbone-coordinate level, with information flowing between tracks; training used discontinuous sequence crops spanning 260 residues.
- Final 3D structures were generated either by feeding predicted distance/orientation distributions into pyRosetta for all-atom models or by an end-to-end SE(3)-equivariant layer producing backbone coordinates directly.
- Evaluation included CASP14 targets, CAMEO blind server assessment, four X-ray molecular-replacement datasets, a cryo-EM PI3Kγ complex, GPCRs, 693 human disease-related domains, and paired-sequence complexes of known structure, using accuracy comparisons, Cα-RMSD, lDDT, TM-score, and MR/cryo-EM fit.
Limitations
- Stated: hardware memory limitations constrained model size and training; performance remained below AlphaFold2; the end-to-end version was less accurate than the pyRosetta version due to incomplete optimization and neglect of side-chain information; the accuracy predictor did not consistently identify models better than the rapid single-pass method; the network was trained on monomeric proteins, not complexes; and current RoseTTAFold uses only the top 1000 sequences due to memory limits.
- Stated: the Perceiver-based extension for using all available sequences gave promising initial results, but more training is required for rigorous comparison.
- Evident: CASP14 and CAMEO evaluations cover limited target sets and time windows, and the end-to-end model does not produce side chains.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
3 Valid · 8 Not valid · 14 Not checked · 44 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The bi-annual Critical Assessment of Structure (CASP) meetings have demonstrated that deep learning methods such as AlphaFold (1, 2) and trRosetta (3), that extract information from the large database of known protein structures in the PDB, outperform more traditional approaches that explicitly model the folding process.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Abstract
What the sources say
- Not matchedcites [1] Jumper John Evans Richard Pritzel Alexander Green Tim Figurnov Michael Tunyasuvunakool Kathryn Ronneberger Olaf Bates Russ Augustin Žídek Alex Bridgland Clemens Meyer Fourteenth Critical Assessment of Techniques for Protein Structure Prediction
Its entry has no title and year that we can search by.
- Partly supportedcites [2] Anishchenko I Chidyausiku TM Ovchinnikov S Pellock SJ Baker D De novo protein design by deep network hallucination bioRxiv 2020 2020.07.22.211482 PMC9293396 34853475 sourceExperimental — accuracy not yet measured
The Introduction (page not provided) says deep networks improved protein-structure prediction accuracy, notes an AlphaFold observation at CASP13, and reports that trRosetta outperformed other methods in benchmark tests. The Conclusion says the network learned from native protein structures and contrasts it with physically based approaches. The paper does not establish the claimed CASP comparison in which both AlphaFold and trRosetta outperform approaches that explicitly model folding. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [3] Yang J Anishchenko I Park H Peng Z Ovchinnikov S Baker D Improved protein structure prediction using predicted interresidue orientations Proc Natl Acad Sci U S A 2020 117 1496 1503 31896580 PMC6983395 source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The RoseTTAFold CERS1 model for residues 98 to 304 (Pfam TLC domain) (29) includes six TMH that traverse the membrane in an up and down arrangement (Fig. 3E).”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Providing insights into biological function
What the sources say
- Could not verifycites [29] Cong Q Anishchenko I Ovchinnikov S Baker D Protein interaction networks revealed by proteome coevolution Science 2019 365 185 189 31296772 PMC6948103 sourceExperimental — accuracy not yet measured
The paper’s Abstract (page unavailable) describes coevolution-based protein interaction models in E. coli and M. tuberculosis, not a CERS1 model. Searches for CERS1, the Pfam TLC domain, RoseTTAFold, and six transmembrane helices found no passage in our copy addressing the cited domain identification or the stated membrane arrangement. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in the case of SLP, only a distant model covering part of the N-terminal domain (38% of the sequence) was available in the PDB”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“trRosetta failed to predict the correct fold with the same MSA input (fig. S6)”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 3-track models with attention operating at the 1D, 2D, and 3D levels and information flowing between the three levels were the best models we tested (Fig. 1B), clearly outperforming the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), BAKER human group (ranked second among all groups), and our 2-track attention models on CASP14 targets.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Network architecture development
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
33 more claims
Create a free account to see all 69 claims and to verify the 2 references still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RF has properties well suited for use in a protein design DDPM (Fig. 1a): it generates protein structures with high precision, operates on a rigid-frame representation of residues with rotational equivariance and has an architecture enabling conditioning on design specifications at the individual residue, inter-residue distance and orientation, and 3D coordinate levels.”
From De novo design of protein structure and function with RFdiffusion (2023) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“are the best and most accurate answer to the structure prediction problem to date”
From The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins (2024) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“DeepMind’s AlphaFold2 success in sequence-based protein structure prediction,4 as well as the RoseTTAFold70 open-source counterpart, and the publicly available AlphaFold2 prediction of all human proteins203 are major steps that benefit the scientific community.”
From AlphaFold, Artificial Intelligence (AI), and Allostery (2022) · cites this paper as [70]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The unprecedented accuracy of AlphaFold2,127 RosettaFold,128 and others129,130 offers, at least in principle, the opportunity to virtually screen any protein of interest with the structure-based approach, irrespective of its a priori ligandability (after AlphaFold2, the structural coverage of the human proteome increased from 48% to 76% of the total residues).131”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [128]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The programs were also shown to accurately assess their confidence at the level of individual residues and interdomain contacts (27,28,62).”
From AI-based structure prediction empowers integrative structural analysis of human nuclear pores (2022) · cites this paper as [27]
Experimental — accuracy not yet measured
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability
Katoh, K., & Standley, D. M. (2013) · Molecular Biology and Evolution · doi:10.1093/molbev/mst010 · Cited by 46,209
Features and development of Coot
Emsley, P., Lohkamp, B., Scott, W. G., & Cowtan, K. (2010) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910007493 · Cited by 29,915
Clustal W and Clustal X version 2.0
Larkin, M. A., Blackshields, G., Brown, N. P., Chenna, R., McGettigan, P. A., McWilliam, H., Valentin, F., Wallace, I. M., Wilm, A., Lopez, R., et al. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm404 · Cited by 28,358
Phaser crystallographic software
McCoy, A. J., Grosse-Kunstleve, R. W., Adams, P. D., Winn, M. D., Storoni, L. C., & Read, R. J. (2007) · Journal of Applied Crystallography · doi:10.1107/s0021889807021206 · Cited by 20,612
Self-citationSWISS-MODEL: homology modelling of protein structures and complexes
Waterhouse, A., Bertoni, M., Bienert, S., Studer, G., Tauriello, G., Gumienny, R., Heer, F. T., de Beer, T. A. P., Rempfer, C., Bordoli, L., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky427 · Cited by 13,067 · cited 2×
“Fortunately,theContinuousAutomated ModelEvaluation(CAMEO)experiment( 7 ) tests structure prediction servers blindly on protein structures as they are submitted to the PDB. RoseTTAFold has been evaluated since 15 May 2021 on CAMEO; over the 69 medium and hard targets released during this time (15 May 2021 to 19 June 20…”
UCSF ChimeraX: Structure visualization for researchers, educators, and developers
Pettersen, E. F., Goddard, T. D., Huang, C. C., Meng, E. C., Couch, G. S., Croll, T. I., Morris, J. H., & Ferrin, T. E. (2021) · Protein Science · doi:10.1002/pro.3943 · Cited by 9,514
Liebschner, D., Afonine, P. V., Baker, M. L., Bunkóczi, G., Chen, V. B., Croll, T. I., Hintze, B., Hung, L.-W., Jain, S., McCoy, A. J., et al. (2019) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798319011471 · Cited by 7,953
Self-citationUniProt: the Universal Protein knowledgebase
Apweiler, R. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh131 · Cited by 7,498
Towards automated crystallographic structure refinement with phenix.refine
Afonine, P. V., Grosse-Kunstleve, R. W., Echols, N., Headd, J. J., Moriarty, N. W., Mustyakimov, M., Terwilliger, T. C., Urzhumtsev, A., Zwart, P. H., & Adams, P. D. (2012) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444912001308 · Cited by 5,511
Self-citation
Research works printed but not linked: 2
- Bunkóczi G Read RJ phenix. ensembler: a tool for multiple superposition Comput Crystallogr Newsl 2011 2 8 9
- Vagin A Lebedev A ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES INT UNION CRYSTALLOGRAPHY 2 ABBEY SQ, CHESTER, CH1 2HU ENGLAND 2015 71 S19
Cited by
Items 3,401–3,500 of 5,636
Proteins containing 6-crossing knot types and their folding pathwaysPreprint
Sikora, M., Flapan, E., Wong, H., Rubach, P., Garstka, W., Niewieczerzał, S., Rawdon, E. J., & Sulkowska, J. I. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.16.545156 · Cited by 4
Frustrated Microphase Separation Produces Interfacial Environment within Biological CondensatesPreprint
Latham, A. P., Zhu, L., Sharon, D. A., Ye, S., Willard, A. P., Zhang, X., & Zhang, B. (2023) · eLife · doi:10.7554/elife.90750.1 · Cited by 5
Building Representation Learning Models for Antibody Comprehension
Barton, J., Gaspariunas, A., Galson, J. D., & Leem, J. (2023) · Cold Spring Harbor Perspectives in Biology · doi:10.1101/cshperspect.a041462 · Cited by 6
Spotlight on protein structure design
(2024) · Nature Biotechnology · doi:10.1038/s41587-024-02150-1 · Cited by 5
Raisinghani, N., Alshahrani, M., Gupta, G., Tian, H., Xiao, S., Tao, P., & Verkhivker, G. M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.02.15.580591 · Cited by 4
IMPROVING ALPHAFOLD2 PERFORMANCE WITH A GLOBAL METAGENOMIC & BIOLOGICAL DATA SUPPLY CHAINPreprint
Munsamy, G., Bohnuud, T., & Lorenz, P. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.03.06.583325 · Cited by 5
Wang, X., & Shen, K. (2024) · The Innovation Life · doi:10.59717/j.xinn-life.2024.100064 · Cited by 4
Artificial Intelligence Learns Protein Prediction
Heinzinger, M., & Rost, B. (2024) · Cold Spring Harbor Perspectives in Biology · doi:10.1101/cshperspect.a041458 · Cited by 6
cryoSPHERE: Single-particle heterogeneous reconstruction from cryo EMPreprint
Ducrocq, G., Grunewald, L., Westenhoff, S., & Lindsten, F. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.19.599686 · Cited by 4
IgBlend: Unifying 3D Structures and Sequences in Antibody Language ModelsPreprint
Malherbe, C., & Uçar, T. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.01.615796 · Cited by 7
BindingGYM: A Large-Scale Mutational Dataset Toward Deciphering Protein-Protein InteractionsPreprint
Lu, W., Zhang, J., Gu, M., & Zheng, S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.03.626712 · Cited by 8
Harnessing AlphaFold to reveal hERG channel conformational state secretsPreprint
Ngo, K., Yang, P., Yarov-Yarovoy, V. M., Clancy, C. E., & Vorobyov, I. V. (2024) · eLife · doi:10.7554/elife.104901.1 · Cited by 5
SFCalculator: connecting deep generative models and crystallographyPreprint
Li, M., Dalton, K. M., & Hekstra, D. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.12.632630 · Cited by 5
Diffusion generation of peptides crossdocking three finger-loops of snake-venomsPreprint
Coll, J. M. (2025) · ChemRxiv · doi:10.26434/chemrxiv-2025-lmr10 · Cited by 11
Yan, J., Cui, Z., Yan, W., Chen, Y., Pu, M., Li, S., & Ye, S. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.29.651154 · Cited by 5
AlphaFlex: Accuracy modeling of protein multiple conformations via predicted flexible residuesPreprint
Ge, L., Cui, X., Zhao, K., Zhou, X., Zhang, Y., & Zhang, G. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.11.664327 · Cited by 5
Constrained Diffusion for Protein Design with Hard Structural ConstraintsPreprint
Christopher, J. K., Seamann, A., Cui, J., Khare, S. D., & Fioretto, F. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.15.682365 · Cited by 5
Developing Optogenetic Approaches to Study Ca 2+ Signaling ProcessesPreprint
Nonomura, T., Liu, X., Chiu, M., Tan, Z., Lan, T., & Zhou, Y. (2025) · Cold Spring Harbor Perspectives in Biology · doi:10.1101/cshperspect.a041760 · Cited by 4
Wu, Y., Liu, X., Hrovatin, K., Wu, D., Linker, S., Winkel, M., & Tan, F. (2026) · Scientific Data · doi:10.1038/s41597-026-06878-0 · Cited by 4
“…using standard external metrics, including predicted affinity (predicted Kd by AlphaBind 40 and binding affinity rank by Nanobinder 42 ), structural diversity (RMSD and TM-score 43 ), and developability properties (SASA and β -sheet content for stability; and humanness is measured by OASis 44 ).”
Parikh, V., Foley, B., Gatlin, W., Ludwick, M., Turano, L., & Verkhivker, G. M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.02.24.707829 · Cited by 5
Lin, Y., Lee, M., Vermani, A., Jiang, E., Cooman, S. D., Špeťko, M., & AlQuraishi, M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.05.01.722168 · Cited by 6
(2023) · doi:10.1186/s13059-023-03008-6 · Cited by 4
“Recent breakthroughs in protein structure prediction from primary sequence alone [Jumper et al., 2021, Baek et al., 2021] uncovered that integrating comparative and functional genomics into a predictive model can yield groundbreaking insights useful enough to guide mechanistic studies in molecular…”
BackgroundCalia, C. N., & Paesani, F. (2025) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.5c05027 · Cited by 4
Corcoran, W. K., Cosio, A., Edelstein, H. I., & Leonard, J. N. (2025) · GEN Biotechnology · doi:10.1089/genbio.2024.0057 · Cited by 4
“A promising recent advance — and subject of the 2024 Nobel Prize in Chemistry to Baker, Hassabis, and Jumper 21 — is the emergence of protein structural prediction tools such as AlphaFold, 22,23 AlphaFold-Multimer, 24 and Rose TTAFold, 25 which enable structural predictions of proteins for which there is no experiment…”
(2022) · doi:10.1093/gigascience/giac117 · Cited by 4
“Compared to other prediction algorithms such as RoseTTAFold [18], AlphaFold2 has obvious disadvantages in performance [19], as even protein domains can consume long computation times [20].”
Karunanithy, G., Shukla, V. K., & Hansen, D. F. (2023) · doi:10.1101/2023.09.15.557823 · Cited by 4
Influence of Stereochemistry in a Local Approach for Calculating Protein Conformations
da Rocha, W., Liberti, L., Mucherino, A., & Malliavin, T. E. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01232 · Cited by 3
Ab-initio amino acid sequence design from protein text description with ProtDAT
Guo, X.-Y., Li, Y.-F., Liu, Y., Pan, X., & Shen, H.-B. (2025) · Nature Communications · doi:10.1038/s41467-025-65562-w · Cited by 3
Expanding kinetoplastid genome annotation through protein structure comparison
Trinidad-Barnech, J. M., Sotelo-Silveira, J., Do Porto, D. F., & Smircich, P. (2025) · PLOS Pathogens · doi:10.1371/journal.ppat.1013120 · Cited by 3
“Recently, significant advancements have been made in the field of in silico structure prediction, solving this problem for many proteins and opening new possibilities in structural biology and bioinformatics [12–15].”
(2023) · doi:10.1016/j.str.2023.05.012 · Cited by 3
Functionally important residues from graph analysis of coevolved dynamic couplings
Xu, M., Dantu, S. C., Garnett, J. A., Bonomo, R. A., Pandini, A., & Haider, S. (2025) · eLife · doi:10.7554/elife.105005 · Cited by 3
“A most recent approach has combined experimental data from three proteins on stability and function with sequence and structural features to train a ML model to predict functional sites (17).”
ProxyBind: A compendium of binding sites for proximity-induced pharmacology
Rovers, E., Liu, L., & Schapira, M. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.11.010 · Cited by 3
“We also limited our approach to proteins (and homologs) with structural information in the protein data-bank, but recent breakthroughs in protein structure predictions [68–70] may enable a future expansion of the analysis to the entire human proteome.”
Muñoz‐Clares, R. A., Fernández‐Silva, A., Mújica‐Jiménez, C., & Martínez‐Flores, S. (2023) · Journal of the Mexican Chemical Society · doi:10.29356/jmcs.v67i3.2022 · Cited by 3
AlphaFold for a medicinal chemist: tool or toy?
Ivanenkov, Y. A., Evteev, S. A., Малышев, А. В., Terentiev, V. A., Bezrukov, D. S., Ereshchenko, A., Korzhenevskaya, A. A., Zagribelnyy, B. A., Шегай, П. В., & Каприн, А. Д. (2024) · Russian Chemical Reviews · doi:10.59761/rcr5107 · Cited by 3
Emergence of two distinct spatial folds in a pair of plant virus proteins encoded by nested genes
Legarda, E. G., Elena, S. F., & Mushegian, A. R. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.107218 · Cited by 3
Refinement of Protein Structures with a Memetic Algorithm. Examples with SARS-CoV-2 Proteins
Filgueiras, J. L., & Santos, J. C. A. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-61137-7_13 · Cited by 3
Crosstalk of multiomics approaches with medicinal plants of therapeutic importance
Jabeen, F., Khursheed, N., Ahmad, R., Rasool, S., Ali, A., & Ganie, S. A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-23971-7.00002-x · Cited by 6
Pang, A., Luo, Y.-S., Zhou, J.-P., Cai, X., Huang, L.-G., Zhang, B., Liu, Z.-Q., & Zheng, Y.-G. (2024) · Biotechnology Journal · doi:10.1002/biot.202400203 · Cited by 2
“48–50] However, within the realm of protein engineering, the ability to accurately predict the quantitative properties of protein mutants, particularly those with high sequence similarity, remains inadequate.”
Computational Approaches for Structure-Assisted Drug Discovery and Repurposing
Pandey, A. K., & Verma, S. (2024) · Springer eBooks · doi:10.1007/978-981-97-7123-3_9 · Cited by 3
How pairs of insertion mutations impact protein structure: an exhaustive computational study
Li, C., Zheng, Y., & Jagodzinski, F. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbae138 · Cited by 3
Norton, T., & Bhattacharya, D. (2024) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168818 · Cited by 5
Song, J. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms252312817 · Cited by 3
Integrative Approaches to Study Virus Structures
Stuart, D. I., Oksanen, H. M., & Abrescia, N. G. A. (2024) · Sub-cellular biochemistry/Subcellular biochemistry · doi:10.1007/978-3-031-65187-8_7 · Cited by 3
Old Moats for New Models: Openness, Control, and Competition in Generative Artificial Intelligence
Azoulay, P., Krieger, J., & Nagaraj, A. (2025) · Entrepreneurship and Innovation Policy and the Economy · doi:10.1086/732852 · Cited by 12
Ju, H., Shi, P., Lei, Z., Wang, X., Yang, L., Cao, X., Gao, Y., Hou, Z., Xu, X., Guo, L., et al. (2025) · Scientia Sinica Chimica · doi:10.1360/ssc-2024-0267 · Cited by 3
Simulations of pH and thermal effects on SARS-CoV-2 spike glycoprotein
Niu, Z., Kementzidis, G., Rafailovich, M. H., Simon, M., Papadopoulos, E., Aktas, B. H., & Deng, Y. (2025) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2025.1545041 · Cited by 3
Ji, S., Yin, P., Li, T., Du, X., Chen, W., Zhang, R., Yang, X., & Zhang, X. (2025) · BMC Genomics · doi:10.1186/s12864-025-11342-1 · Cited by 4
Khatooni, Z., Broderick, G., Anand, S. K., & Wilson, H. L. (2025) · PLoS ONE · doi:10.1371/journal.pone.0314254 · Cited by 3
Integrative Protein Assembly With LZerD and Deep Learning in CAPRI 47–55
Christoffer, C. W., Kagaya, Y., Verburgt, J. C., Terashi, G., Shin, W., Jain, A., Sarkar, D., Aderinwale, T. W., Subramaniya, S. R. M. V., Wang, X., et al. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26818 · Cited by 3
Yang, X., Li, J., Liu, G., Bian, L., Feng, M., Liu, Y., Li, K., Shang, J., Fang, Y., Xu, T., et al. (2025) · Horticultural Plant Journal · doi:10.1016/j.hpj.2025.02.002 · Cited by 3
Ghamsari, F. A., Ghadaksaz, A., Ebrahimi, M. T., Varzaneh, M. B., Iranbakhsh, A., & Sepahi, A. A. (2025) · Process Biochemistry · doi:10.1016/j.procbio.2025.04.005 · Cited by 3
Sandkuhler, S. E., & Mackenzie, S. (2025) · The Journal of Cell Biology · doi:10.1083/jcb.202503010 · Cited by 3
Suryaningsih, S., & Belhassen, Y. (2025) · Scientechno Journal of Science and Technology · doi:10.70177/scientechno.v3i3.1743 · Cited by 3
NMR Pure Shift Spectroscopy and Its Potential Applications in the Pharmaceutical Industry
Qiu, M., Zhu, W., Zheng, X., Chen, Z., & Lin, Y. (2025) · ChemBioChem · doi:10.1002/cbic.202401012 · Cited by 4
Predicting Protein Function in the AI and Big Data Era
Percudani, R., & Rito, C. D. (2025) · Biochemistry · doi:10.1021/acs.biochem.5c00186 · Cited by 3
“32,33 Large-scale deep learning-based prediction of the structure of protein complexes was introduced with RoseTTAFold 34 and further enhanced with AlphaFold multimer 35 and AlphaFold 3 (AF3).”
AcrDB update: Predicted 3D structures of anti‐ CRISPRs in human gut viromes
Khatri, M., Shanmugam, N. R. S., Zhang, X., Patel, R. S. K. R., & Yin, Y. (2025) · Protein Science · doi:10.1002/pro.70177 · Cited by 4
Zhang, X., Sun, H., Hu, Y., Li, Z., Geng, Z. Z., Gao, Z., Hao, Q., Qi, F., & Ding, W. (2025) · Journal of Applied Crystallography · doi:10.1107/s1600576725003218 · Cited by 3
Non-aromatic fluorescence from single α-helical peptides
González-González, C., Lopez-Blanco, R., Gonzalez‐Vera, J. A., D’Ingiullo, S., Bouzada, D., Melle‐Franco, M., Orte, Á., & Vázquez, M. E. (2025) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2025.102631 · Cited by 3
Pre-trained language models for protein and molecular design
Zhang, E., Pan, Z., Yao, Z., Dong, T., Chen, G., Deng, T., Chen, S., & Chen, C. Y. (2025) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp00785b · Cited by 3
Zeidanloo, H. R., & Špaček, M. (2025) · Journal of Innovation and Entrepreneurship · doi:10.1186/s13731-025-00541-5 · Cited by 3
Predicting RNA Structure Utilizing Attention from Pretrained Language Models
Papazoglou, I., Chatzigoulas, A., Tsekenis, G., & Cournia, Z. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02094 · Cited by 4
Dawson, J. E., Smith, I. N., Tushar, A. M., & Eng, C. (2025) · Structure · doi:10.1016/j.str.2025.06.002 · Cited by 3
Avashthi, H., Angadi, U. B., Majumdar, S. G., Bhati, J., Singh, D. B., Chandra, M., Singh, J. K., Sinha, A., Shah, S., & Mishra, D. C. (2025) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-025-00558-6 · Cited by 3
PHACE: Phylogeny-Aware Detection of Molecular Coevolution
Kuru, N., & Adebalı, O. (2025) · Molecular Biology and Evolution · doi:10.1093/molbev/msaf150 · Cited by 4
Zhang, C., Condon, A., & Duc, K. D. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf322 · Cited by 6
Heuristic multi-site optimization for protein sequence design using Masked Protein Language Models
Wang, L., Wang, Y., Chen, Q., Xiao, L., Liu, X., & Chen, J. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014365 · Cited by 4
Singh, G., Shreya, S., Yadav, S., & Akhter, Y. (2025) · World Journal of Microbiology and Biotechnology · doi:10.1007/s11274-025-04510-8 · Cited by 3
“Since the AlphaFold data - base entry for Rv1258c was only available in the outward-open state, we generated an inward-facing model using RosettaFold via the Robetta server, which provides reli - able conformational predictions for membrane transporters (Baek et al. 2021).”
Efficiently quantifying dependence in massive scientific datasets using InterDependence Scores
Radhakrishnan, A., Jain, Y., Uhler, C., & Lander, E. S. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2509860122 · Cited by 4
Tran, N., Frenette, A. P., & Holyoak, T. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2503549122 · Cited by 3
“S3 ) ( 48 ).”
From Molecules to Medicine: Molecular Dynamics and Docking in Breast Cancer Therapeutics
Bozorgpour, R. (2025) · Clinical Breast Cancer · doi:10.1016/j.clbc.2025.09.008 · Cited by 3
Murguiondo, C., de Lacoba, M. G., García-Miró, A., Routsi, R., Prieto, A., & Barriuso, J. (2025) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2025.147822 · Cited by 3
MechFind: a computational framework for de novo prediction of enzyme mechanisms
Hartley, A. D., Upadhyay, V., Boorla, V. S., & Maranas, C. D. (2026) · Nature Communications · doi:10.1038/s41467-026-71957-0 · Cited by 4
Wuyun, Q., Liu, Q., Ni, W., Peng, C., Zhang, Z., Zhou, X., Hu, G., Freddolino, L., & Zheng, W. H. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70059 · Cited by 5
“…the final monomer MSAs from DeepMSA2 are used as input for AlphaFold2 [2] (8-embedding), OpenFold [22], UniFold [23], ColabFold [24], RosettaFold [25], ESMFold [26], OmegaFold [27], DeepPotential [28], and AttentionPotential (an extension of DeepPotential utilizing an MSA transformer…”
Le, T., Jia, B., Sun, C., Zhou, Y.-F., Qi, Y., Liu, H., Bian, H., Tian, C., Wang, J., Xue, F., et al. (2025) · Vaccine · doi:10.1016/j.vaccine.2025.127841 · Cited by 4
Self-citationChen, S., Zheng, A., Yu, W., & Zhan, C. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06272-4 · Cited by 5
“Another method through modeling protein complex structures, AlphaFold-Multimer, introduced by Baek et al [21].”
Rath, J. A., Rudden, L. S. P., Nouraee, N., Que, T. X. Y., Gunten, C. V., Pérez, C., Birch, F., Bhugowon, Y., Füglistaler, A., Souleiman, A. C., et al. (2025) · Nature Biomedical Engineering · doi:10.1038/s41551-025-01532-3 · Cited by 3
Алексеева, М. Г., Borisevich, S. S., Yusupova, A. R., Reznikova, D. A., Мавлетова, Д. А., Nesterov, A. A., Ilyina, M. G., Акимова, Н. И., Shtil, A. A., & Даниленко, В. Н. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms262110560 · Cited by 4
“3 were predicted on the basis of Al-phaFold2 [33], RoseTTAFold [34], I-TASSER [35–37], IntFold5 [38], and scoring functions [39].”
InfluentialLarge language model agents as experimental orchestrators in data-driven enzyme engineering
Gao, Y., Fu, L., & Si, T. (2025) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2025.103376 · Cited by 5
Wang, J., Wang, P., Tian, F., Liu, Q., Hai, M., Guo, Z., Wang, Y., Li, Y., & Wang, Y. (2025) · Veterinary Sciences · doi:10.3390/vetsci12111074 · Cited by 4
“The tertiary structure of MEBPV was predicted using the Robetta server (https://robetta.bakerlab.org/ , accessed on 13 May 2024) [49].”
Self-citationHarnessing deep learning in bioinformatics- opportunities, challenges, and ethical considerations
Rani, N., Chaudhary, P., Bhoomika, B., Kumar, U., Nikhil, Khatana, K., Kumar, N., Mavi, A. K., Mathur, M., & Singh, S. (2025) · Vita Scientia · doi:10.65116/vitascientia.v1i1.rev.01 · Cited by 3
Zalewska, A., Jurczak-Kurek, A., Kwiatek, M., Myung, H., & Górniak, M. (2025) · BMC Biology · doi:10.1186/s12915-025-02445-y · Cited by 3
“Next, spatial models of all TFP domains were calculated using the Robetta [42] online server.”
Sun, X., xiao, Q., Zhang, N., Li, W., Luo, H., Gao, Y., Zhang, L., Fan, Y., Jiang, P., Huang, Y., et al. (2026) · Angewandte Chemie International Edition · doi:10.1002/anie.6395554 · Cited by 5
RAPID-Net: Accurate Pocket Identification for Binding-Site-Agnostic Docking
Balytskyi, Y., Hubenko, I., Balytska, A., & Kelly, C. V. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01744 · Cited by 7
Ye, S., Wang, B., Ли, Ж., Zhu, L., Sun, C. Y., Mukamel, S., & Jiang, J. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2522772122 · Cited by 4
Addressing infectious diseases in Africa by accelerating drug discovery through data science
Turón, G., Hlozek, J., Duran‐Frigola, M., Chibale, K., & Woodland, J. G. (2025) · Communications Medicine · doi:10.1038/s43856-025-01211-z · Cited by 3
“Advances in AI-driven tools for predicting protein structure, such asAlphaFold 67 andESMFold 68,69 ,arebringingthe fi eldclosertoperforming molecular docking experiments on proteins for which crystallographic data are lacking.”
Generative-AI-assisted knowledge-based augmented exploration in nanophotonics
Iwanaga, M., & Watanabe, K. (2025) · Science and Technology of Advanced Materials Methods · doi:10.1080/27660400.2025.2596940 · Cited by 3
“After the breakthrough of mastering the games, a scientific application of genAI has been used to predict protein structures [7–11].”
Li, W., & Wang, W. (2025) · Quantitative Biology · doi:10.1002/qub2.70024 · Cited by 3
Jiao, S., Sun, W., & Hu, Y. (2025) · Angewandte Chemie International Edition · doi:10.1002/anie.202521539 · Cited by 3
Combined computational, rational, and empirical design of boiling-resistant keratinase
Yang, Y., Luo, Y., Ding, Y., Yao, Y., Liu, J., Xu, Z., Li, Y., Li, H., Gan, F., Tang, X., et al. (2025) · Applied and Environmental Microbiology · doi:10.1128/aem.01860-25 · Cited by 3
“The recent successes of machine-learning prediction algorithms such as RoseTTAFold (32) and AlphaFold (33) allow the generation of highly accurate protein models, which not only facilitate structure-based rational protein engineering but also greatly promote the development of automated computational design tools to i…”
Wei, C., Yu, L., Pu, Z., Wang, X., Zhai, Q., Jin, Y., & Tian, F. (2025) · Food Bioscience · doi:10.1016/j.fbio.2025.107605 · Cited by 3
Leal, L. R. S., de Sena, M. G. A. M., Invenção, M. D. C. V., de Moura, I. A., de Jesus, A. L. S., de Sousa, G. F., Barros, B. R. D. S., de Melo, C. M. L., Pena, L., Paolini, F., et al. (2025) · Vaccines · doi:10.3390/vaccines14010031 · Cited by 3
“The three-dimensional structure of the EnvNS1 construct was modeled using RoseTTaFold via the Robetta server [76].”
Iqbal, S., Eng, E. T., Kamal, M. A., & Shen, B. (2026) · BMC Artificial Intelligence · doi:10.1186/s44398-025-00017-2 · Cited by 3
“Recent advances in AI-based protein structure prediction tools have shown promise in overcoming these obstacles [115, 168, 169].”
Velásquez-Mejía, L., Vidal-Limon, A., Flores-Vargas, G., Ruíz-May, E., Scavone, P., de la Fuente‐Núñez, C., & Zamora‐Briseño, J. A. (2026) · Journal of Applied Microbiology · doi:10.1093/jambio/lxag036 · Cited by 4
Opportunities and Challenges of Machine Learning in Atomic Layer Deposition
Westermayr, J., Bent, S. F., & Tonner, R. (2026) · Chemistry of Materials · doi:10.1021/acs.chemmater.5c03271 · Cited by 3
Opportunities and challenges in protein structure prediction
Wang, W., Su, B., Xiang, C., & Yang, J. (2026) · Quantitative Biology · doi:10.1002/qub2.70035 · Cited by 3
Chen, X., Deng, Y. C., Yang, X., Zhang, Y., Huang, Y., Li, S., Yang, H., Shi, Q., Wu, S., Chen, S., et al. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01192-1 · Cited by 3
Novack, D., & Filizola, M. (2026) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2026.103248 · Cited by 4
AI-Driven Design of Miniproteins as Potential Allosteric Modulators
Liu, X., Sun, Y., Xia, Y., Li, H., & Yan, Z. (2026) · Pharmaceuticals · doi:10.3390/ph19030480 · Cited by 3
Bailey, J., Spina, S. C., Hu, A., Phan, N., Getman, R. B., & Kimmel, B. R. (2026) · ACS Engineering Au · doi:10.1021/acsengineeringau.5c00099 · Cited by 3
Nema, P., Purohit, A., Soni, V., & Kashaw, S. K. (2026) · Mini-Reviews in Medicinal Chemistry · doi:10.2174/0113895575388386251212074901 · Cited by 3
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.