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 3,901–4,000 of 5,636
Haataja, T., Hansson, H., Moriya, S., Sandgren, M. O. J., & Ståhlberg, J. (2023) · FEBS Journal · doi:10.1111/febs.17029 · Cited by 2
Ravichandran, A., Araque, J. C., & Lawson, J. W. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26641 · Cited by 4
“…advent of next generation protein sequencing techniques, 14 advanced deep learning algorithms for accurate protein tertiary structure prediction, 15,16 and experimental techniques for obtaining conformations at high resolution, 17,18 there is a necessity for developing frameworks that can map…”
MethodCsizi, K., & Reiher, M. (2023) · Journal of Computational Chemistry · doi:10.1002/jcc.27276 · Cited by 2
“3 While efforts have been made to predict structures from sequence information alone, 4–6 most simulations rely on experimentally curated input structures taken from X-ray crystallography or NMR spectroscopy, which are collected in the protein data bank (PDB).”
BackgroundApplication of Artificial Intelligence in Biochemistry Research: A Review
Jada, M. S., Stephen, H., Usman, M. M., & Wurochekke, A. U. (2023) · Journal of Biochemistry Microbiology and Biotechnology · doi:10.54987/jobimb.v11i2.835 · Cited by 3
Yang, Z., Li, X., Sheng, L., Zhu, M., Lan, X., & Gu, F. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae013 · Cited by 2
Signalling of Adrenoceptors: Canonical Pathways and New Paradigms
Mastos, C., Xu, X., Keen, A. C., & Halls, M. L. (2024) · Handbook of experimental pharmacology · doi:10.1007/164_2023_704 · Cited by 5
Exploring Post-Training Quantization of Protein Language Models
Peng, S., Yang, F., Sun, N., Chen, S., Jiang, Y., & Pan, A. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385775 · Cited by 3
“…[12] have been successfully applied for various protein-related tasks, including secondary structure prediction [24], [26], contact prediction [25], [26], 3D structure prediction [1], [16], annotation prediction [4], protein-protein interaction prediction [10], and fitness prediction [9], [14].”
BackgroundAI ‐Based Protein Structure Predictions and Their Implications in Drug Discovery
Kellici, T. F., Hristozov, D., & Morao, I. (2024) · Wiley eBooks · doi:10.1002/9783527840748.ch10 · Cited by 2
Content and structure based attention for graph node classification
Chen, Y., Xie, X., & Weng, W. (2024) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-223304 · Cited by 3
Tang, H., & Robinson, C. V. (2024) · Chem · doi:10.1016/j.chempr.2024.02.022 · Cited by 2
Velocity Estimations in Blood Microflows via Machine Learning Symmetries
Alfonso, G., & Paetz, J. V. C. (2024) · Symmetry · doi:10.3390/sym16040428 · Cited by 2
Scalable computation of anisotropic vibrations for large macromolecular assemblies
Lam, J. H., Nakano, A., & Katritch, V. (2024) · Nature Communications · doi:10.1038/s41467-024-47685-8 · Cited by 2
Li, J., Zou, R., Varrone, A., Nag, S., Halldin, C., & Ågren, H. (2024) · ACS Chemical Neuroscience · doi:10.1021/acschemneuro.4c00029 · Cited by 4
Ambalavanan, A., Mallikarjuna, M. G., Bansal, S., Bashyal, B. M., Subramanian, S., Kumar, A., & Prakash, G. (2024) · Planta · doi:10.1007/s00425-024-04413-2 · Cited by 3
“The amino acid sequences of ten CaNBLRRs used for expression analysis were selected for constructing the 3D models using the Robetta server (https:// robet ta. baker lab. org/) (Baek et al. 2021) with a confidence score of > 0.75.”
InfluentialA Survey of Deep Learning Methods for Estimating the Accuracy of Protein Quaternary Structure Models
Chen, X., Liu, J., Park, N., & Cheng, J. (2024) · Biomolecules · doi:10.3390/biom14050574 · Cited by 2
Engineering G protein‐coupled receptors for stabilization
Velloso, J. P. L., de Sá, A. G. C., Pires, D. E. V., & Ascher, D. B. (2024) · Protein Science · doi:10.1002/pro.5000 · Cited by 2
“…protein mutations, including DUET (Pires et al., 2014), mCSM (Pires et al., 2014), SDM (Pandurangan et al., 2017; Worth et al., 2011), DDGun (Montanucci et al., 2022), MAES-TROweb (Laimer et al., 2016), Dynamut (Rodrigues et al., 2018), Dynamut 2 (Baek et al., 2021), and DDMut (Zhou et al., 2023).”
Abnormal function of EPHA2/p.R957P mutant in congenital cataract
Jing-jin, Z., Zhou, B., Yang, J., Li, Z., Lin, S., Chen, X., Zhang, N., Ye, Q., Ma, X., & Zhu, Y.-H. (2024) · International Journal of Ophthalmology · doi:10.18240/ijo.2024.06.04 · Cited by 2
Dock2D: Synthetic Data for the Molecular Recognition Problem
Bhadra-Lobo, S., Derevyanko, G., & Lamoureux, G. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3407477 · Cited by 3
Zhang, F., Li, Z., Zhao, K., Zhao, P., & Zhang, G. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3411825 · Cited by 2
A deep learning method to predict bacterial ADP-ribosyltransferase toxins
Zheng, D., Zhou, S., Chen, L., Pang, G., & Yang, J. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae378 · Cited by 2
Yin, J., Liu, Y., He, D., Li, P., Qiao, M., Luo, H., Qu, X., Mei, S., Wu, Y., Sun, Y., et al. (2024) · Applied and Environmental Microbiology · doi:10.1128/aem.00741-24 · Cited by 2
“The structural model of NgTrmBL2 was predicted by RoseTTAFold (60).”
BackgroundAcuña-Amador, L., & Barloy-Hubler, F. (2024) · Access Microbiology · doi:10.1099/acmi.0.000771.v3 · Cited by 3
“3D structures of Ffp1 mature proteins were modelled, based on homology modelling, using Robetta [72, 73] and the RoseTTAFold method, as well as Phyre2.”
Kuang, K., Chen, X., Wang, M., Han, W., Qiu, X., Jin, T., Xu, R., Yuan, B., Qian, M., Li, C., et al. (2024) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.4c00654 · Cited by 2
Lai, J., Burley, S. K., & Duarte, J. M. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbae111 · Cited by 2
Soltan, M. A., Abdulsahib, W. K., Eid, R. A., Alshaya, D. S., Sideeg, A. M., Osman, R., Alarabi, T. G. M., Mohamed, G., Al‐Salmi, F. A., Fayad, E., et al. (2024) · Journal of Computational Biophysics and Chemistry · doi:10.1142/s2737416524500376 · Cited by 2
Marcius, D., Ropii, B., Safitri, D. A., Ulum, M. F., Nugrahapraja, H., & Anshori, I. (2024) · Molecular Systems Design & Engineering · doi:10.1039/d4me00073k · Cited by 2
Martínez-Valencia, D., Bañuelos, C., García‐Rivera, G., Talamás‐Lara, D., & Orozco, E. (2024) · PLoS ONE · doi:10.1371/journal.pone.0304842 · Cited by 2
Parallel Convolutional Contrastive Learning Method for Enzyme Function Prediction
Yu, X., Zhou, S., Zang, M., Wang, Q., Liu, C., & Liu, T. (2024) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2024.3447037 · Cited by 2
PB-GPT: An innovative GPT-based model for protein backbone generation
Min, X., Liao, Y., Chen, X., Yang, Q., Ying, J., Zou, J., Yang, C., Zhang, J., Ge, S., & Xia, N. (2024) · Structure · doi:10.1016/j.str.2024.07.016 · Cited by 2
Microscopic marvels: Decoding the role of micropeptides in innate immunity
Naidu, P., & Holford, M. (2024) · Immunology · doi:10.1111/imm.13850 · Cited by 2
Targeting TRP channels: The emerging role of cryogenic electron microscopy in drug discovery
Lopez, K. E., & Horn, W. D. V. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-18653-0.00010-1 · Cited by 3
Lillehoj, E. P., Yu, Y., Verceles, A. C., Imamura, A., Ishida, H., Piepenbrink, K. H., & Goldblum, S. E. (2024) · iScience · doi:10.1016/j.isci.2024.110866 · Cited by 2
AlphaFold2 Predicts Alternative Conformation Populations in Green Fluorescent Protein Variants
Núñez‐Franco, R., Muriel-Olaya, M. M., Jiménez‐Osés, G., & Peccati, F. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01388 · Cited by 3
Austin, K., Torres, J. A., Waters, J. D. V., Balog, E. R. M., Halpern, J. M., & Pantazes, R. J. (2024) · ACS Omega · doi:10.1021/acsomega.4c06481 · Cited by 2
Kim, M., Kim, M., & Ryu, S. (2024) · Journal of Virology · doi:10.1128/jvi.00676-24 · Cited by 3
All‐Atom Protein Sequence Design Based on Geometric Deep Learning
Liu, J., Guo, Z., You, H., Zhang, C., & Lai, L. (2024) · Angewandte Chemie · doi:10.1002/ange.202411461 · Cited by 4
Shin, J., Meinke, G., Bohm, A. A., & Bullock, P. A. (2024) · Journal of Virology · doi:10.1128/jvi.01119-24 · Cited by 2
“For instance, it will be of interest to use cryo-electron microscopy, AlphaFold 3 (100), and RoseTTAFoldNA (101, 102) to determine the co-structure of the OBD and T-ag hexamers bound to ssDNA and fork-like molecules.”
Machine learning-assisted investigations toward polymer synthesis
Zhang, Z., Cai, Z., Zhang, W., lu, H., & Chen, M. (2024) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2024-0800 · Cited by 5
Incremental Inverse Design of Desired Soybean Phenotypes
Zavorskas, J., Edwards, H., Marten, M. R., Harris, S. D., & Srivastava, R. (2024) · ACS Omega · doi:10.1021/acsomega.4c01704 · Cited by 2
Sequence‐Sensitivity in Functional Synthetic Polymer Properties
Jin, T., Coley, C. W., & Alexander‐Katz, A. (2024) · Angewandte Chemie · doi:10.1002/ange.202415047 · Cited by 2
AntigenBoost: enhanced mRNA-based antigen expression through rational amino acid substitution
Gao, Y., Zhu, S., Li, H., Hao, X., Chen, W., Pan, D., & Qian, Z. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae468 · Cited by 2
“For antigens without available experimental structures, advanced software such as AlphaFold2 [37] and RosettaFold [56] can be used to predict the protein conformation.”
MethodLi, L., Luo, Q., Yang, S., Wang, H., Mu, Y., Guo, J., & Zhang, F. (2024) · Pest Management Science · doi:10.1002/ps.8496 · Cited by 2
Artificial intelligence in early stages of structure-based drug discovery
Ravichandran, R., Park, S., Skorupan, S., Bessette, K., & Gentile, F. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-23932-8.00001-7 · Cited by 3
Smith, K. P., Chakravarthy, S., Rahi, A., Chakraborty, M., Vosberg, K. M., Tonelli, M., Plach, M. G., Grigorescu, A., Curtis, J. E., & Varma, D. (2024) · Cytoskeleton · doi:10.1002/cm.21954 · Cited by 2
“While machine learning approaches like AlphaFold (Jumper et al. 2021), RoseTTAFold (Baek et al. 2021), and others have broadly advanced the understanding of protein folds, they are not suitable for use in Cdt1 in this context.”
Su, Z., Yin, S., & Wu, Y. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.4c06497 · Cited by 2
AlphaFold Wins Nobel Prize, Gains Functionality, Drops Open Access
Palmer, C. (2024) · Engineering · doi:10.1016/j.eng.2024.12.003 · Cited by 3
Red, gold, and green: comparative genomics of polymorphic leopards from South Africa
Lagcher, E., Lensing, K., Bosse, M., Fischer, K., Camacho, G., McManus, J. S., & Tensen, L. (2024) · Evolution · doi:10.1093/evolut/qpae178 · Cited by 2
The cobalamin processing enzyme of Trichoplax adhaerens
Krams, C., Esser, A. J., Klenzendorf, M., Klotz, K., Spiekerkoetter, U., Jacobsen, D. W., Smith, C. A., Maggiolo, A. O., & Hannibal, L. (2024) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2024.108089 · Cited by 2
Lee, J.-C., Bang, D., & Kim, S. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01255 · Cited by 2
Energy metric prediction for double insertion mutants via the RoseNet deep learning framework
Coffland, S., Christensen, K., Hutchinson, B., & Jagodzinski, F. (2024) · Bioinformatics Advances · doi:10.1093/bioadv/vbae198 · Cited by 2
Zhang, Y., & Vitalis, A. (2025) · Patterns · doi:10.1016/j.patter.2024.101147 · Cited by 3
De novo design protein binders for MBP and GST tags
Zhou, J., Xiao, Y., Tang, Q., Yan, Y., Liu, D., & Zhang, H. (2025) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2025.151322 · Cited by 2
D’Agostino, F., Pinatel, E., Meynhardt, A., Scarlato, V., Vannini, A., & Roncarati, D. (2025) · iScience · doi:10.1016/j.isci.2025.111815 · Cited by 2
Computational modeling of the anti-inflammatory complexes of IL37
Sardag, I., Düvenci, Z. Ş., Belkaya, S., & Timuçin, E. (2025) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2025.108952 · Cited by 2
Pais, R., Nagraj, A. K., Gavade, A., Patel, R., Momin, M., Scheele, J., Seiz, W., & Patil, J. (2025) · Human Antibodies · doi:10.1177/10932607241303614 · Cited by 2
“17,18 The advancement in computational protein structure prediction methods, including AlphaFold 19 and RoseTTAFold, 20 has resulted in rapid growth in the fi eld of protein engineering.”
Rodríguez‐Sotres, R., & Aguayo‐Ortiz, R. (2025) · Educación Química · doi:10.22201/fq.18708404e.2025.1.89902 · Cited by 2
Generalizable Metamaterials Design Techniques Inspire Efficient Mycelial Materials Inverse Design
Zavorskas, J., Edwards, H., Marten, M. R., Harris, S. D., & Srivastava, R. (2025) · ACS Biomaterials Science & Engineering · doi:10.1021/acsbiomaterials.4c01986 · Cited by 2
Understanding the Role of RING ‐Between‐ RING E3 Ligase of the Human Malaria Parasite
Kumari, V., Vidyarthi, S., Tripathi, A., Chaurasia, N., Rai, N., Shukla, R., Noorie, S. N., Bhati, G., Anjum, S., Anas, M., et al. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26813 · Cited by 2
“RoseTTAFold deep learning-based modeling method available via Robetta server was used to prepare the model of Pf RBR-E3 and its RING1 domain [25].”
Vigneswaran, A., Buschmann, T. A., & Latham, M. P. (2025) · Journal of Magnetic Resonance · doi:10.1016/j.jmr.2025.107865 · Cited by 2
Delineating inter- and intra-antibody repertoire evolution with AntibodyForests
van Ginneken, D., Tromp, V., Stalder, L., Cotet, T., Bakker, S., Samant, A., Reddy, S. T., & Yermanos, A. (2025) · Bioinformatics · doi:10.1101/2025.03.11.642619 · Cited by 2
Technical Basis for Nuclear Magnetic Resonance Approach for Glycoproteins
Kato, K., Yanaka, S., & Yagi, H. (2025) · Springer eBooks · doi:10.1007/978-981-97-6830-1_7 · Cited by 4
Fang, Y., Shi, J., Zuo, Z., Wang, Y., Yin, Z., Wang, Z., Yang, Z., Jia, B., Zhao, Q., & Sun, Y. (2025) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2025.2484447 · Cited by 2
“RoseTTAFold was used to obtain the structure of the IL-1 b protein (Baek et al., 2021).”
André, A., Dias, J., Moutinho, I., Loureiro, J., Leonardo, A., Nogueira, S., Marimon, R., Bule, P., Correia, J., Malhó, R., et al. (2025) · Frontiers in Veterinary Science · doi:10.3389/fvets.2025.1491934 · Cited by 2
“The tridimensional structure of the recombinant C5-PE38 immunotoxin was predicted using the Rosettafold deep learning-based modeling method on the Baker lab’s Robetta server (33).”
Cui, X., Xia, Y., Hou, M., Zhao, X., Wang, S., & Zhang, G. (2025) · BMC Bioinformatics · doi:10.1186/s12859-025-06131-2 · Cited by 3
AlphaLasso—a web server to identify loop and lasso motifs in 3D structure of biopolymers
Rubach, P., Płonka, J., Gren, B. A., da Silva, F. B., Korpacz, M., & Sulkowska, J. I. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf375 · Cited by 4
Modelling Ergonomic Hazard Risks in Manual Handling: Insights from Ponorogo’s Traditional Industry
Arifah, D. A., Rahma, R. A. A., Harmini, T., & Hafidz, D. I. (2025) · The Indonesian Journal of Occupational Safety and Health · doi:10.20473/ijosh.v14i1.2025.98-110 · Cited by 3
Ling, X., Cai, C., Kong, D., Wei, Z., Wu, J., Wang, L., & Deng, Z. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00378 · Cited by 3
Identifying disruptive innovation in the IT sector: a framework for evaluating intercompany impact
Zeidanloo, H. R., & Špaček, M. (2025) · Transactions on Energy Systems and Engineering Applications · doi:10.32397/tesea.vol6.n1.724 · Cited by 3
“Advances in health technologies: Disruptions extend to medical fields through innovations like mRNA vaccines and gene editing [115,116].”
Bead model hydrodynamics: an in-depth comparison between GRPY and ZENO
Brookes, E., Żuk, P. J., & Rocco, M. (2025) · European Biophysics Journal · doi:10.1007/s00249-025-01758-8 · Cited by 2
Kanaris, M., Lee, J., Chang, B. S. W., & Christendat, D. (2025) · Molecular Biology and Evolution · doi:10.1093/molbev/msaf129 · Cited by 2
Deep Learning Approaches for Protein Secondary Structure Prediction
Afroz, U. I., Das, S., & Siddique, N. H. (2024) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit64611.2024.11021832 · Cited by 2
“As a result, hybrid models that combine CNNs with LSTM [4] networks have been developed.”
Oliw, E. H. (2025) · Archives of Biochemistry and Biophysics · doi:10.1016/j.abb.2025.110490 · Cited by 2
Mind the gap: An embedding guide to safely travel in sequence space
Wu, A., Trolliet, Q., Rajendran, A., Lála, J., & Angioletti‐Uberti, S. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014433 · Cited by 3
“This latter idea has been exploited to build protein folding algorithms, including the most recent and accurate ones, such as AlphaFold [18], RosettaFold [19] or ESMFold [7].”
Arun, A., Annaiyan, S., Raveendran, M., Nagachandrabose, S., Pushpam, R., Shandeep, G., & Jena, N. K. (2025) · Rhizosphere · doi:10.1016/j.rhisph.2025.101130 · Cited by 2
Karpova, Y. D., Piatz, S., Bordet, G., & Tulin, A. V. (2025) · Cells · doi:10.3390/cells14141049 · Cited by 2
“Models of deletional mutants in the PARG catalytic domain were generated with RosettaFold, AlphaFold, or Chai-1 [23,24].”
Liu, Y., Chen, L.-H., Chen, Q., & Liu, H. (2025) · National Science Review · doi:10.1093/nsr/nwaf290 · Cited by 4
Design principles of protein–protein interfaces
Kim, C. H., Kim, T. H., & Choi, J. (2025) · Bulletin of the Korean Chemical Society · doi:10.1002/bkcs.70051 · Cited by 2
Structural Variability of Pfam Domains Based on Alphafold2 Predictions
Poretsky, E., Andorf, C. M., & Sen, T. Z. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70021 · Cited by 2
DEGRONOPEDIA: A practical guide to identifying and targeting protein degrons
Szulc, N. A., & Pokrzywa, W. (2025) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2025.06.014 · Cited by 4
Accelerating structural dynamics through integrated research informatics
Eisenbraun, B., Ho, A. D., Meyer, P. A., & Sliz, P. (2025) · Structural Dynamics · doi:10.1063/4.0000759 · Cited by 2
Harit, A., Sun, Z., & Moubayed, N. A. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.07.142 · Cited by 4
Goldberg, N., Bril, D., Eisenstein, M., Olender, T., Savidor, A., Bialik, S., Pietrokovski, S., & Kimchi, A. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf1334 · Cited by 5
Novel adomaviruses associated with blotchy bass syndrome in black basses (Micropterus spp.)
Iwanowicz, L. R., Raines, C. D., Young, K. T., Blazer, V. S., Walsh, H. L., Smith, G., Holt, C., Odenkirk, J. S., Jones, T., Hessenauer, J., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0326402 · Cited by 3
“Sequences without clear hits in HHpred searches were queried via Dali using predicted protein structure from AlphaFold2 or RoseTTAfold predictions [28–30].”
Umeda, K., Yamanaka, S., Imamura, M., Nagae, F., Fukuda, S., Watanabe, H., Uchihashi, T., Takada, S., & Ando, T. (2026) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5c03517 · Cited by 2
Large-scale multi-omic biosequence transformers for modeling protein–nucleic acid interactionsPreprint
Chen, S. F., Steele, R., Hocky, G. M., Lemeneh, B., Lad, S., & Oermann, E. (2026) · PLoS ONE · doi:10.1371/journal.pone.0341501 · Cited by 2
Crosstalk between RNA secondary and three-dimensional structure prediction: a comprehensive study
Wang, D., Jiang, Y., He, L., Zhang, L., Zhou, R., & Zhang, D. (2026) · RNA Biology · doi:10.1080/15476286.2026.2655096 · Cited by 2
“…remarkable progress in deep learning-based structural modelling of biological macromolecules, even the state-of-the-art methods, including the recent AlphaFold3 [31], still cannot achieve a level of accuracy in RNA 3D structure modelling comparable to that of protein structure prediction [28,30].”
Exploring quantum annealing for coarse-grained protein folding
Scheiber, T., Heller, M., & Giebel, A. (2026) · Scientific Reports · doi:10.1038/s41598-026-46916-w · Cited by 2
“Recent advances in artificial intelligence (AI) models have enabled the successful prediction of structures for a diverse array of proteins [3, 4, 5].”
Araya, E. R., & Serra, E. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1914731 · Cited by 2
“Built on similar principles, other powerful models have emerged, including RoseTTAFold (RF), RoseTTAFold2 (RF2), and RoseTTAFoldNA (RFNA) (Baek et al., 2023; 10.3389/fbinf.2026.1914731 Baek et al., 2021; Baek, 2022).”
InfluentialThe structure of CatSper is revealed: happy days for sperm biology
Barratt, C. L. R. (2021) · Human Reproduction · doi:10.1093/humrep/deab204 · Cited by 2
Cryo-EM analysis of Ebola virus nucleocapsid-like assembly
Wang, Y., Binning, J. M., Pintilie, G. D., Chiu, W., Amarasinghe, G. K., Leung, D. W., & Su, Z. (2021) · STAR Protocols · doi:10.1016/j.xpro.2021.101030 · Cited by 2
“Alternatively, the rapidly emerging predictive methods of protein structures assisted by deep learning algorithms may aid the generation of preliminary models for further refinement (Jumper et al., 2021; Baek et al., 2021).”
Novel Pathogenic De Novo INS p.T97P Variant Presenting With Severe Neonatal DKA
Lal, R., Moeller, H. P., Thomson, E. A., Horton, T. M., Lee, S., Freeman, R., Prahalad, P., Poon, A. S. Y., & Annes, J. P. (2021) · Endocrinology · doi:10.1210/endocr/bqab246 · Cited by 2
Kenny, S. E., Antaw, F., Locke, W. J., Howard, C. B., Korbie, D. J., & Trau, M. (2022) · Life · doi:10.3390/life12030363 · Cited by 3
Whole-proteome structures shed new light on posttranslational modifications
Joosten, R. P., & Agirre, J. (2022) · PLoS Biology · doi:10.1371/journal.pbio.3001673 · Cited by 2
“The recent artificial intelligence revolution in protein structure prediction, spearheaded by DeepMind’s AlphaFold [1] and swiftly seized upon by RoseTTAFold [2], is allowing scientists to arrive at an accurate structural model of a protein, or at least parts of it, in a matter of hours.”
BackgroundRecent Trends and Future Prospects of Materials and Process Informatics
Muroga, S. (2022) · Seikei-Kakou · doi:10.4325/seikeikakou.34.250 · Cited by 2
In silico and in vitro analysis of THCA synthase gene in Moroccan Cannabis Sativa, L
Badrana, F., Fahime, E. E., Mokhtari, A., Soulaymani, A., Safini, N., Chaouni, B., Malka, G., & Amri, H. E. (2022) · F1000Research · doi:10.12688/f1000research.123384.2 · Cited by 2
New era in structural biology with the AlphaFold program
Miyazono, K., & Tanokura, M. (2022) · Translational and Regulatory Sciences · doi:10.33611/trs.2022-005 · Cited by 4
Wheadon, M. J., & Townsend, C. A. (2022) · ACS Chemical Biology · doi:10.1021/acschembio.2c00474 · Cited by 2
Roles of Conformations on Predictions of Peptide Properties
Sindhikara, D., & Johnston, J. M. (2022) · ACS symposium series · doi:10.1021/bk-2022-1417.ch004 · Cited by 2
Computation empowers CRISPR discovery and technology
Shang, S., Cai, X. S., & Qi, L. S. (2022) · Nature Computational Science · doi:10.1038/s43588-022-00321-1 · Cited by 3
Artificial intelligence revolution in structure prediction for entire proteomes
Zou, J. (2022) · MedComm – Future Medicine · doi:10.1002/mef2.19 · Cited by 2
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.