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 4,401–4,500 of 5,636
Ricker, B., Franco, E. A. C., Campos, G. D. L., Pelled, G., & Gilad, A. A. (2024) · Open Biology · doi:10.1098/rsob.240092 · Cited by 1
“Amino acid sequences were input to Robetta [40], and structures were predicted using the default settings.”
Effective Entry-Wise Flow for Molecule Generation
Zhang, Q., Yao, J., Yang, Y., Shi, Y., Gao, W., & Wang, X. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00023 · Cited by 2
“…marked by tools like OpenAI’s ChatGPT, exemplifies the potential of language models in mimicking human conversational patterns, while DeepMind’s AlphaFold represents a revolutionary leap in protein folding prediction, offering transformative prospects in bioinformatics and drug discovery [1], [2].”
MethodSARS-CoV-2 spike does not interact with the T cell receptor or directly activate T cells
Gaglione, S. A., Rosales, T. J., Schmidt-Hong, L., Baker, B. M., & Birnbaum, M. E. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2406615121 · Cited by 1
“Computational tools to predict protein structures and interactions are rapidly evolving and easily deployed, particularly with the introduction of AI methods (19, 20).”
Genome Mining and Biological Engineering of Type III Borosins from Bacteria
Xu, K., Guo, S., Zhang, W., Deng, Z., Zhang, Q., & Ding, W. (2024) · International Journal of Molecular Sciences · doi:10.3390/ijms25179350 · Cited by 1
“The structure of KchMA TEV was predicted by Rosetta fold using the Rosetta online server [32].”
MethodMEFold: Memory-Efficient Optimization for Protein Language Models via Chunk and Quantization
Jiang, Y., Sun, N., Lu, Z., Peng, S., Zhang, Y., Yang, F., & Li, T. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10651470 · Cited by 1
“The emergence of deep learning has led to the creation of algorithms such as AlphaFold2 [2] and RoseTTAFold [14], which have shown comparable accuracy to traditional protein structure prediction methods while significantly improving efficiency.”
MethodGenerative Ai: A New Paradigm for Antibody Design and Development
Mondru, A. K., & Sisir, A. T. (2024) · Advances in Computational Sciences and Technology · doi:10.37622/acst/17.1.2024.39-59 · Cited by 2
A lightweight visualization tool for protein unfolding by collision detection and elimination
Qian, H., Chen, Y., & Jiang, Y. (2024) · Frontiers in Computer Science · doi:10.3389/fcomp.2024.1415648 · Cited by 1
Artificial Intelligence and Quantum Computing
Wirtz, B. W. (2024) · Springer texts in business and economics · doi:10.1007/978-3-658-44675-8_13 · Cited by 1
Park, J., Lee, M.-G., Charalampopoulos, D., Park, K., & Chang, P. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.136075 · Cited by 1
Proteome structuring of crown-of-thorns starfish
Zhu, Y., & Lu, Z. (2024) · Frontiers in Marine Science · doi:10.3389/fmars.2024.1487904 · Cited by 1
Rakhi, K., Bhati, R., Jain, M., Singh, A. K., & Muthukumaran, J. (2024) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2024.2415686 · Cited by 1
“…I-Tasser (https://zhanggroup.org/I-TASSER/) (Zhou et al., 2022), Robetta (CM) (https://robetta.bakerlab.org/) (Song et al., 2013), Robetta (RoseTTAFold) (Baek et al., 2021), Robetta (TR) and Robetta (AB)) (Yang et al., 2020) to predict the three-dimensional model of the drug target protein - MurM.”
The Iconic α-Helix: From Pauling to the Present
Rose, G. D. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-4196-5_1 · Cited by 1
Künstliche Intelligenz in der Proteinforschung: Nobelpreis für Chemie
Welter, K. (2024) · Chemie in unserer Zeit · doi:10.1002/ciuz.202400038 · Cited by 1
Khajouie, P., Sarkar, T., Rauniyar, K., Chen, L., Xu, W., & Raghavan, V. V. (2026) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2026.3654047 · Cited by 1
Haque, N., Wagenknecht, J. B., Ratnasinghe, B. D., & Zimmermann, M. T. (2024) · PLoS ONE · doi:10.1371/journal.pone.0313308 · Cited by 1
Molecular Insight into the Catalytic Mechanism of the Sesquiterpene Cyclase BcABA3
Li, T., Shu, D., Lei, L., Li, Z., Luo, D., Yang, J., Wang, Y., Hou, X., Wang, H., & Tan, H. K. (2024) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.4c07116 · Cited by 1
Hui, W.-H., Chen, Y., & Chang, S. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.139001 · Cited by 1
Castón, J. R., & Luque, D. (2024) · Sub-cellular biochemistry/Subcellular biochemistry · doi:10.1007/978-3-031-65187-8_3 · Cited by 1
Introduction to Atomistic Modeling and Simulation of Biomolecular Systems
Bekker, S., Han, Y., & Vorobyov, I. V. (2024) · Springer eBooks · doi:10.1007/978-3-031-73730-5_1 · Cited by 1
Jia, Y., Liu, Y., Zhang, W., Wang, R., Sun, Y., & Zhang, J. (2025) · Fish & Shellfish Immunology · doi:10.1016/j.fsi.2025.110116 · Cited by 1
Predicting the PARP1 Tertiary Structure by Molecular Modeling Methods
Mustaev, E. A., & Хамитов, Э. М. (2025) · Journal of Structural Chemistry · doi:10.1134/s0022476625050038 · Cited by 1
“The machine-learning based programs AlphaFold2 [10] (and its next version AlphaFold3) and RoseTTAFold [11] are nowadays the most common tools.”
Zakaria, W. N. A., Zahiruddin, H., Zukarnain, Z. A., & Wijaya, A. (2024) · Rwanda medical journal · doi:10.4314/rmj.v81i3.6 · Cited by 1
Three Strategies for Salvaging Explanatory Value in Deep Neural Network Modeling
Verreault-Julien, P. (2025) · Routledge eBooks · doi:10.4324/9781003342816-13 · Cited by 2
Structural engineering of stabilized, expanded epitope nanoparticle vaccines for HPV
Helble, M., Zhu, X., Bhojnagarwala, P. S., Liaw, K., Gao, Y., Kim, A., Bayruns, K., McCanna, M. E., Park, J. H., Konrath, K. M., et al. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1535261 · Cited by 1
Protein Modeling and Structure-Based Drug Design
Klebe, G. (2024) · Springer eBooks · doi:10.1007/978-3-662-68998-1_20 · Cited by 1
Learning Model for Game-Based Long Jump Skills In Children Aged 12-14 Years
Chong, Y., Samsudin, S., & Wasan, A. (2025) · Cuestiones de Fisioterapia · doi:10.48047/8n13wg92 · Cited by 1
Sarkar, S., Yadav, M., & Kumar, A. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-31550-3.00002-0 · Cited by 2
Khan, M. S., Shakya, M., & Verma, C. K. (2025) · Molecular Diversity · doi:10.1007/s11030-025-11148-z · Cited by 1
SEFP: Structure-Based Enzyme Function Prediction
Zhang, Z., Yu, G., Deng, Z., Luo, C., Cai, C., Zhang, W., Hu, F., Choi, K., Wei, Z., Wang, L., et al. (2025) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbbio.2025.3552846 · Cited by 1
Mendes, G. E. M., Maio, A. R., de Oliveira, G. D. S. R., Rosa, L. C., Costa, L. L., de Oliveira, L. C. V., de Freitas, M. S., Silva, R. C. E., Galvão, R. M. D. S., Coutinho, R. C., et al. (2025) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2025.109039 · Cited by 1
Predictive Machine Learning Models for Olfaction
Dutta, P., Jain, D., Gupta, R. K., & Rai, B. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4466-9_4 · Cited by 1
Walker, D. R., Fujimura, G., Vanegas, J. M., & Barbar, E. J. (2025) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2025.1531793 · Cited by 1
Urunanont, P., Mizushima, S., Uchida, T., Ishimori, K., Matiz-Céron, L., & Kuroiwa, A. (2025) · Genes & Genetic Systems · doi:10.1266/ggs.25-00021 · Cited by 1
Application of 3D atom pair map in an attention model for enhanced drug virtual screening
Ryu, G., & Kim, W. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01023-2 · Cited by 1
“Although 3D structures are not always available for certain targets, this limitation can be significantly alleviated by both experimental [5] and in silico modeling [6, 7].”
Ashim, J., Seo, M. J., Ji, S., Heo, J., & Yu, W. (2025) · Molecular Pharmacology · doi:10.1016/j.molpha.2025.100043 · Cited by 1
Wei, L., Cao, H., Zou, R., Du, ., Zhang, Q., Lu, D., Xu, X., Xu, Y., Wang, W., Chen, X., et al. (2025) · eLife · doi:10.7554/elife.102422.3 · Cited by 2
Alexandrovich, D., Kagan, S., & Mandel‐Gutfreund, Y. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169240 · Cited by 1
Denaturation of firefly luciferase at heat shock temperatures captured in silico
Lashkari, V. D., & Marszałek, P. E. (2025) · Biophysical Journal · doi:10.1016/j.bpj.2025.06.021 · Cited by 1
Han, S., Choi, S., & Kim, J.-Y. (2025) · Proceedings - International Symposium on Computer Architecture/Proceedings · doi:10.1145/3695053.3731006 · Cited by 1
“Recent state-of-the-art PPMs [3, 5, 33, 39] demonstrate exceptional performance through the use of attention mechanisms.”
Porokhin, V., Brown, A. M., & Hassoun, S. (2025) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-025-00613-4 · Cited by 1
“Structural homology models were then constructed using AlphaFold [31, 32] and Robetta [33] (RoseTTAFold [34] model) web servers, two state-of-the-art protein structure prediction methods.”
Géraud, N., Riviere, C., Falcou, C., Cioci, G., Froment, C., Gervais, V., Marcoux, J., Gilleron, M., Nigou, J., Fabre, É., et al. (2025) · Communications Biology · doi:10.1038/s42003-025-08593-9 · Cited by 5
Assessing Computational Strategies for the Evaluation of Antibody Binding Affinities
Autiero, I., Buratto, D., Guo, F., Wang, W., Biswal, M. R., Chan, C., Zhou, R., & Zonta, F. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c01231 · Cited by 1
Qadri, O., Bashir, S., Banday, M., Pal, D., & Fazili, K. M. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.07.09.451832 · Cited by 1
Li, F., Huang, S., Yu, M., Wu, B., Hou, Z., Zhan, P., Cai, S., Liu, Q., Hou, Z., Zhao, J., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.09.14.460210 · Cited by 1
“Prediction of protein structure modeling and molecular docking Homology modeling was performed with Rosettafold with default de novo prediction parameter (Baek et al., 2021).”
MethodSelf-citationTransferability of Geometric Patterns from Protein Self-Interactions to Protein-Ligand InteractionsPreprint
Koehl, A., Jagota, M., Erdmann-Pham, D. D., Fung, A., & Song, Y. S. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.10.01.462692 · Cited by 1
“Deep learning methods have had significant impact in the related problems of protein folding [1, 2] and ligand-based antibiotic discovery [18], where much larger datasets are available.”
BackgroundEditorial: Machine Learning Methodologies to Study Molecular Interactions
Yakimovich, A., Özgür, A., Doğan, T., & Özkırımlı, E. (2021) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2021.806474 · Cited by 1
“With the signi fi cantly elevated performance of deep learning-based single-chain protein structure predictors such as AlphaFold (Jumper et al., 2021) and RosettaFold (Baek et al., 2021), the focus has now been shifting to the accurate prediction of protein complex structures (Evans et al., 2021).”
BackgroundHarish, A. (2021) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/hyknj · Cited by 1
Majd, S. A. M. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.02.09.479702 · Cited by 1
Disentanglement of Entropy and Coevolution using Spectral RegularizationPreprint
Wang, H., Feng, S., Liu, S., & Ovchinnikov, S. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.03.04.483009 · Cited by 1
Self-citationSakrikar, S., Hackley, R. K., Martínez-Pastor, M., Darnell, C. L., Vreugdenhil, A., & Schmid, A. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.03.22.485428 · Cited by 1
Xu, L., Xu, J., Guo, X., Tan, Y., Qiu, T., Tao, J., Tao, S., Liao, Y., Zhang, L., Tian, D., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-1764128/v1 · Cited by 1
Cdc14 Spatiotemporally Regulates Rim4-mRNA Complex Assembly and Stability During MeiosisPreprint
Zhang, R., Feng, W., Qian, S., Li, S., & Wang, F. (2022) · SSRN Electronic Journal · doi:10.1101/2022.12.22.521673 · Cited by 1
Review: Modeling peptide-protein complexes: docking, simulations and machine learning — R0/PR1
Mondal, A., Chang, L., & Pérez, A. (2022) · QRB Discovery · doi:10.1017/qrd.2022.14.pr1 · Cited by 1
Unraveling codon usage of Escherichia coli using machine learningPreprint
Huang, B., Hu, Y., Chen, X., & Lin, S. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.07.527422 · Cited by 2
Polymorphism in maternal HLA-DRB5 is associated with the risk of preeclampsia in Chinese populationPreprint
Xu, C., Zhou, L., Fang, Q., Liu, Y., Yang, J., Luo, L., Li, S., Guo, P., Niu, Y., Deng, W., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-2746165/v1 · Cited by 1
Luisi, B. F., & Stollar, E. J. (2022) · Royal Society of Chemistry eBooks · doi:10.1039/9781837671328-00522 · Cited by 1
Adupa, V., Ustyantseva, E., Kampinga, H. H., & Onck, P. R. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.15.545060 · Cited by 1
Mondal, R., Mandal, M., & Lahiri, T. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.07.10.548240 · Cited by 1
Data-Driven Modeling and Analysis of Fatty Acid Desaturase in PlantsPreprint
McNaughton, A. D., Shanklin, J., Raugei, S., & Kumar, N. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.17.553759 · Cited by 1
Dietrich, J., & Bellstedt, P. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.09.561482 · Cited by 1
Ansell, T. B., Song, W., Coupland, C. E., Carrique, L., Corey, R. A., Duncan, A. L., Cassidy, C. K., Geurts, M. M. G., Rasmussen, T., Ward, A. B., et al. (2023) · Research Square · doi:10.21203/rs.3.pex-2408/v1 · Cited by 1
Deep Learning-based structural and functional annotation of Pandoravirus hypothetical proteinsPreprint
Horder, J. L., Connor, A. J., Duggan, A. L., Hale, J. J., McDermott, F. J., Norris, L. E., Whinney, S. J. D., Mesdaghi, S., Murphy, D., Simpkin, A. J., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.02.569716 · Cited by 1
DNDesign: Enhancing Physical Understanding of Protein Inverse Folding Model via DenoisingPreprint
Lee, Y., & Kim, J. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.05.570298 · Cited by 1
DSDPFlex: An Improved Flexible-Receptor Docking Method with GPU AccelerationPreprint
Dong, C., Huang, Y., Lin, X., Zhang, H., & Gao, Y. Q. (2023) · ChemRxiv · doi:10.26434/chemrxiv-2023-bcw0g-v2 · Cited by 1
Li, Z., Wang, M., Bai, H., Wang, H., Han, J., An, L., Luo, D., Wang, Y., Kuang, W., Nie, X., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.12.571245 · Cited by 1
Xu, B., Li, J., Bao, C., Fu, Z., Mao, J., Liu, L., Chen, X., Zheng, M., Wang, C., Wang, C., et al. (2023) · ChemRxiv · doi:10.26434/chemrxiv-2023-jzr1p · Cited by 1
Author Response: How accurately can one predict drug binding modes using AlphaFold models?
Karelina, M., Noh, J. J., & Dror, R. O. (2023) · eLife · doi:10.7554/elife.89386.2.sa3 · Cited by 1
De novo -designed minibinders expand the synthetic biology sensing repertoirePreprint
Weinberg, Z. Y., Soliman, S. S., Kim, M. S., Shah, D. H., Chen, I. P., Ott, M., Lim, W. A., & El‐Samad, H. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.01.12.575267 · Cited by 2
The Impacts of AI at Scale: Evidence from Research ScientistsPreprint
Yu, Z. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4711334 · Cited by 4
Li, Z., Wang, M., Bai, H., Wang, H., Han, J., An, L., Luo, D., Wang, Y., Kuang, W., Nie, X., et al. (2024) · eLife · doi:10.7554/elife.94853 · Cited by 1
Li, Z., Wang, M., Bai, H., Wang, H., Han, J., An, L., Luo, D., Wang, Y., Kuang, W., Nie, X., et al. (2024) · eLife · doi:10.7554/elife.94853.1 · Cited by 1
NeuroFold: A Multimodal Approach to Generating Novel Protein Variants in silicoPreprint
Amani, K., Fish, M., Smith, M. D., & Castroverde, C. D. M. (2024) · bioRxiv · doi:10.1101/2024.03.12.584504 · Cited by 4
Murphy, D., Mesdaghi, S., Rodríguez, F. S., Simpkin, A. J., Elliott, L. G., & Rigden, D. J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.13.589297 · Cited by 1
De novo-designed minibinders expand the synthetic biology sensing repertoirePreprint
Weinberg, Z. Y., Soliman, S. S., Kim, M. S., Shah, D. H., Chen, I. P., Ott, M., Lim, W. A., & El‐Samad, H. (2024) · eLife · doi:10.7554/elife.96154 · Cited by 1
De novo-designed minibinders expand the synthetic biology sensing repertoirePreprint
Weinberg, Z. Y., Soliman, S. S., Kim, M. S., Chen, I. P., Ott, M., & El‐Samad, H. (2024) · eLife · doi:10.7554/elife.96154.1 · Cited by 2
Doffini, V., von Lilienfeld, O. A., & Nash, M. A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.05167 · Cited by 1
Building up complexity in structural biology studies
Nogales, E. (2024) · Nature Structural & Molecular Biology · doi:10.1038/s41594-024-01324-4 · Cited by 2
H3-OPT: Accurate prediction of CDR-H3 loop structures of antibodies with deep learningPreprint
Chen, H., Fan, X., Zhu, S., Pei, Y., Zhang, X., Zhang, X., Liu, L., Qian, F., & Tian, B. (2024) · eLife · doi:10.7554/elife.91512.3 · Cited by 2
Computational Tools for Structural Analysis of Proteins
Brezovský, J., Sethi, A., & Surpeta, B. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00089-0 · Cited by 1
Protein Language Models in Directed EvolutionPreprint
Maguire, R., Bloznelyte, K., Adepoju, F., Armean-Jones, M., Dewan, S., Fozzard, S., Goddard, S., Gupta, A., Ibrahimi, E., Jones, F. P., et al. (2026) · bioRxiv · doi:10.1101/2024.08.20.608752 · Cited by 3
Protein secondary structure and remote homology detectionPreprint
Al-Fatlawi, A. H., Hossen, M. B., El-Hendi, F., & Schroeder, M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.09.03.611022 · Cited by 1
Li, J., Wei, J., Li, Y., Zhang, S., Jiang, S., Chen, Y., Li, Y., Feng, Y., Kang, X., Liu, W., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4989707/v1 · Cited by 1
Elias, J., Rosin, J. J., Keplinger, A. J., & Ruthenburg, A. J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.10.04.616721 · Cited by 1
Wei, L., Cao, H., Zou, R., Du, ., Zhang, Q., Lu, D., Xu, X., Xu, Y., Wang, W., Chen, X., et al. (2024) · eLife · doi:10.7554/elife.102422 · Cited by 2
“To investigate the reason why this enzyme is capable to act on alginate, its structure was predicted using Robetta, and aligned with GAGase II and GAGase VII.”
Wei, L., Cao, H., Zou, R., Du, M., Zhang, Q., Lu, D., Xu, X., Xu, Y., Wang, W., Chen, X., et al. (2024) · eLife · doi:10.7554/elife.102422.1 · Cited by 4
AlphaFold-Metainference: Prediction of Structural Ensembles of Disordered ProteinsPreprint
Brotzakis, Z. F., Zhang, S., Murtada, M. H., & Vendruscolo, M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.09.622758 · Cited by 1
RNA-Protein Interaction Classification via Sequence EmbeddingsPreprint
Matus, D., Runge, F., Franke, J. K. H., Gerne, L., Uhl, M., Hutter, F., & Backofen, R. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.08.622607 · Cited by 3
JRSeek: Artificial Intelligence Meets Jelly Roll Fold Classification in VirusesPreprint
Sanchez, J. E., Guo, W., Li, C., Li, L., & Xiao, C. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.27.635132 · Cited by 1
Kolossváry, I., & Coffey, R. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.12.638002 · Cited by 1
BaCNet: Deep Learning Accelerates Novel Antibiotic Discovery Against Resistant PathogensPreprint
Otani, Y., Koga, D., Wakizaka, Y., & Shimizu, H. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.26.640477 · Cited by 1
Non-Canonical Crosslinks Confound Evolutionary Protein Structure ModelsPreprint
Lacombe, R. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.03.17.643596 · Cited by 1
Wei, L., Cao, H., Zou, R., Du, ., Zhang, Q., Lu, D., Xu, X., Xu, Y., Wang, W., Chen, X., et al. (2025) · eLife · doi:10.7554/elife.102422.2 · Cited by 1
OpenComplex I: Predicting Three-Dimensional Atomic-Level Structures of Biomolecular ComplexesPreprint
Yu, J., Chen, Z., Li, Z., Zeng, M., Lin, W., Huang, H., & Ye, Q. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.03.25.643589 · Cited by 1
Structural insights into FOXP2 multimerization and interactions from AlphaFold3 modelingPreprint
Adnan, R., & Al-Fatlawi, A. H. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.04.25.650520 · Cited by 1
An improved model for prediction of de novo designed proteins with diverse geometriesPreprint
Orr, B., Crilly, S. E., Akpinaroglu, D., Zhu, E., Keiser, M. J., & Kortemme, T. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.06.02.657515 · Cited by 2
Ning, Z., Ming, Y., Zhang, C., Cao, S., Li, C., Guo, J., & Duan, H. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.06.09.658607 · Cited by 6
Human brain mapping at the Singularity
Rokem, A. (2025) · Aperture Neuro · doi:10.52294/001c.138847 · Cited by 1
EZpred: Improving Deep Learning‐Based Enzyme Function Prediction Using Unlabeled Sequence Homologs
Zhang, C., Liu, Q., & Freddolino, L. (2026) · Advanced Science · doi:10.1101/2025.07.09.663945 · Cited by 1
Fold first, ask later: structure-informed function annotation of Pseudomonas phage proteinsPreprint
Longin, H., Bouras, G. S., Grigson, S. R., Edwards, R. A., Hendrix, H., Lavigne, R., & van Noort, V. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.17.665397 · Cited by 3
Ali, H., Thynne, E., Ellis, T., Booth, C., Bates, R. E., Hope, M. S., Wallington, E. J., Crean, E. E., Pachinger, L., Saur, I. M. L., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.22.671746 · 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.