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 4,301–4,400 of 5,636
Chattopadhyay, A., Mosa, F. E. S., Light, P. E., & Barakat, K. (2026) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2026.109505 · Cited by 1
Lawrence, T., Mocsonokyova, E., Barde, A. M., Módos, D., Dumas, M., Korcsmáros, T., & Gul, L. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag355 · Cited by 1
AI-Driven Protein Research: From Prediction to Design
Min, G., & Peng, H. (2026) · Methods in molecular biology · doi:10.1007/978-1-0716-5249-7_13 · Cited by 1
Harnessing multispecific antibodies for next-generation cancer treatments
Liu, W.-Q., Xiao-li, Z., & Fan, X. (2026) · Pharmacology & Therapeutics · doi:10.1016/j.pharmthera.2026.109073 · Cited by 1
From First Principles to Function: How AI Is Reshaping Enzyme Design
Lindner, S., Hardy, F. J., & Hilvert, D. (2026) · Biochemistry · doi:10.1021/acs.biochem.6c00356 · Cited by 2
TPS-Flow: Physics-Guided Flow-Based Generative Modeling of Protein Transition Paths
Xu, K., Zhao, L., Tian, Y., Zhou, K., Zang, J., Wang, J., Li, Y., Wang, S., Lin, S., Liu, H., et al. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00807 · Cited by 1
Self-citationJi, R., Jung, J., Cheng, H., Xu, E., Wang, A., Sit, V. M.-S., Pardee, K., & Zhao, Y. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00632 · Cited by 2
Zhang, Y., Cao, X., Yang, L. W., Chen, J., & Hwarari, D. (2026) · Plants · doi:10.3390/plants15142185 · Cited by 1
“For JA and salicylic acid signaling, PLMs have identified COI1-JAZ interaction interfaces and NPR1 oligomerization domains under stress, supporting mechanistic analysis of hormone receptor complexes even in species with incomplete proteome annotations [120].”
Khalil, R., Frasnetti, E., Kurt, H., Hameduh, T., Athar, M., Colombo, G., & Vargiu, A. V. (2026) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.6c01412 · Cited by 2
Lu, S.-Y., Wu, Z. L., Martinez, M., Patel, M., & Skory, C. D. (2026) · Biotechnology Reports · doi:10.1016/j.btre.2026.e00973 · Cited by 1
“The modularity of the enzyme enables the rational design of chimeric endolysins through domain shuffling [19,26,37,39 – 41].”
Analysing open-source protein folding models for nanobody binding prediction
Vogt, Y., Roßberg, R., Habermann, J., Kluge, P., Xu, W., Naouar, M., Hirschberg, S., Miething, C., Bödecker, J., Kalweit, M., et al. (2026) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2026.1858891 · Cited by 1
“We did not include purely language-model-based methods such as OmegaFold (Wu et al., 2022) and ESMFold (Lin et al., 2023), nor the MSA-based models RoseTTAFold (Baek et al., 2021), RoseTTAFoldNA (Baek et al., 2024), Protenix (Protenix Team et al., 2026), or HelixFold 3 (Liu et al., 2024), as these have been shown to b…”
Explainable AI reveals the allosteric blind spot in protein-ligand binding predictions
Parikh, V., Foley, B., Gatlin, W., Ludwick, M., Turano, L., & Verkhivker, G. M. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103448 · Cited by 1
“5 This revolution began with AlphaFold2 near-experimental protein structure prediction, 1,2 extending to multi-chain complexes, 6 sequence-based protein language models (PLMs) ESMFold 7,8 and RoseTTAFold2, 9,10 and generative design frameworks.”
Qian, Z., Zhou, Y., Lin, R., Hong, Y., Xu, Y., Li, S., Gao, J., Zhu, Q., & Zheng, H. (2026) · Journal of Artificial Intelligence Research and Innovation · doi:10.29328/journal.jairi.1001022 · Cited by 1
“machine-learning and deep-learning predictors differ in both representation and model hierarchy [47–50].”
Linhart, B., Grattan, R. M., David, J. C. L., Jhamba, E. D., Lupinek, C., Focke‐Tejkl, M., Paffett, M. L., Lucero, S. R., Valenta, R., Tapia, L., et al. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27156762 · Cited by 1
Enzyme Engineering: From Classical Strategies to AI-Driven Biocatalyst Design
Ullah, M., Rizwan, M., Andoh, V., Raza, A., Naeem, M., Waheed, M. I., & Chen, Y. (2026) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.6c04272 · Cited by 2
Zang, J., Wang, S., Xu, K., Zhan, X., Tian, Y., Yao, X., & Liu, H. (2026) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70083 · Cited by 1
“Related methods such as RoseTTAFold [43], ESMFold [44] and DeepFold [45] further expand AI-based protein structure prediction, whereas AlphaFold3 [46], Boltz-1 [47] and RoseTTAFold All-Atom (RoseTTAFold AA) [48] extend modeling to multicomponent biomolecular assemblies.”
Du, S., Yang, H., Lu, T., You, X., Zhou, B., & Qian, D. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35251-4_29 · Cited by 1
Computational navigation of constrained multidimensional protein fitness landscapes
Kaushik, R. K., Piroozmand, F., & Re, S. (2026) · FEBS Letters · doi:10.1002/1873-3468.70442 · Cited by 1
Artificial intelligence can support the chemical design of multiepitope vaccine nanocarriers
Garcia-Atutxa, I., & Villanueva‐Flores, F. (2026) · Discover Chemistry. · doi:10.1007/s44371-026-00929-6 · Cited by 1
Multi‐omics–driven precision medicine
Li, H., Zhao, Z., Zhang, Y., Ma, Y., Hu, G., Zeng, M., Yang, Z., Zhao, Z., Zhou, X., Hu, W., et al. (2026) · iMeta · doi:10.1002/imt2.70165 · Cited by 2
He, T., Zhang, S., Chen, J., Zheng, X., Zhao, J., Li, H., Mao, J., Luo, J., Zheng, J., Ma, D., et al. (2026) · iMetaOmics. · doi:10.1002/imo2.70133 · Cited by 1
Design of programmable molecular interfaces for synthetic biology and therapeutic applications
Nickel, L., Pyatova, E., & Correia, B. E. (2026) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2026.102759 · Cited by 1
Angioletti, D., Carli, M., Nobile, M., & Limongelli, V. (2026) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.70082 · Cited by 1
Versini, R., Reys, V., Kravchenko, A., Honorato, R. V., & Bonvin, A. M. J. J. (2026) · Protein Science · doi:10.1002/pro.70793 · Cited by 1
“In fact, artificial intelligence (AI) is now able to predict protein – protein interactions quite accurately (Baek et al., 2021; Evans et al., 2021; Jumper et al., 2021; Lin et al., 2023; ByteDance AML AI4Science Team, 2025), as well as interactions involving nucleic acids, lipids, small molecules…”
Awote, O. K., Onilude, H. A., & Kappo, A. P. (2026) · Current Issues in Molecular Biology · doi:10.3390/cimb48101007 · Cited by 1
“Recent advances in AI-based protein structure prediction have enabled the generation of structural models for experimentally unresolved proteins [110,111].”
How Many Crystal Structures Do You Need to Trust Your Docking Results?
Payne, A. M., Kaminow, B., MacDermott-Opeskin, H., Pulido, I., Scheen, J., Castellanos, M. A., Fearon, D., Chodera, J. D., & Singh, S. (2026) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c03559 · Cited by 2
Narayanasamy, A., Drake, Z. C., Turzo, S. B. A., Rolland, A. D., Prell, J. S., Wysocki, V. H., & Lindert, S. (2026) · Analytical Chemistry · doi:10.1021/acs.analchem.6c01893 · Cited by 1
LoL-align: sensitive and fast probabilistic protein structure alignment
Reifenrath, L., van Kempen, M., Kim, G., Kim, S. H., Radnezhad, M., Gilchrist, C. L. M., Mirdita, M., Steinegger, M., & Söding, J. (2026) · Nature Methods · doi:10.1038/s41592-026-03249-w · Cited by 1
DESIGN: a framework for generative AI-enabled crop molecular design-driven breeding
Xu, F., Fu, R., Cheng, Q., Jiang, S., Yan, J., & Wang, X. (2026) · Science China Life Sciences · doi:10.1007/s11427-025-3406-3 · Cited by 2
Adversarial Attacks against AI-driven Experimental Peptide Design Workflows
Ramanathan, A., & Jha, S. K. (2021) · Annual Workshop on Extreme-scale Experiment-in-the-Loop Computing · doi:10.1109/xloop54565.2021.00010 · Cited by 1
Soni, V., Dawson, T., Li, L., Crandall, K. A., Sherman, J. H., & Keidar, M. (2026) · Materials Today Advances · doi:10.1016/j.mtadv.2026.100931 · Cited by 1
Carbone, A., Laine, É., & Lombardi, G. (2012) · Methods in molecular biology · doi:10.1007/978-1-0716-4828-5_7 · Cited by 1
Amino acid environment affinity model based on graph attention network
Tong, X., Liu, S., Gu, J., Wu, C., Liang, Y., & Shi, X. (2021) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720021500323 · Cited by 1
Matrullo, E. (2012) · PubMed · doi:10.6092/unibo/amsdottorato/4291 · Cited by 1
Wang, Y., Xie, Y., Yu, X., Lin, Y., Luo, X., Xiao, Y., Cai, Q., Xie, H., & Zhang, J. (2021) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/tb-2021-0988 · Cited by 1
Gala, M., Pristaš, P., & Žoldák, G. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23052788 · Cited by 1
Contribution of a Novel Pertussis Toxin-Like Factor in Mediating Persistent Otitis Media
Ma, L., Sedney, C. J., Su, Y., Dewan, K. K., Linz, B., & Harvill, E. T. (2022) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2022.795230 · Cited by 1
Paudel, S., Wachira, J., & McCarthy, P. C. (2021) · Processes · doi:10.3390/pr9122192 · Cited by 1
“The program has incorporated additional neural networks based on thre levels of prot in structure, and it p oduces structures with high accuracies [37].”
BackgroundMethodInfluentialShin, Y., Li, X., Lee, C. S., & Lee, J. (2022) · The Journal of Microbiology · doi:10.1007/s12275-022-1671-5 · Cited by 1
“This algorithm can accurately predict the 3D structures of proteins from their primary amino acid sequences by utilizing previously reported protein structures and sequence databases (Baek et al., 2021; Jumper et al., 2021).”
MethodMolecular represention in AI-assisted synthesis chemistry: from sequence to graph
Wang, H., Jin, L., Feng, J., Dong, Z., Deng, W., & Li, Y. (2022) · Scientia Sinica Chimica · doi:10.1360/ssc-2022-0113 · Cited by 1
Jiang, J. B., Jiménez‐Ortigosa, C., Chen, M., Healey, K. R., Kong, J., Lee, Y.-K., Farrell, D. P., DiMaio, F., Perlin, D. S., & Dai, W. (2022) · Microscopy and Microanalysis · doi:10.1017/s143192762200472x · Cited by 1
Self-citationAntivenom Derived from the Ct1a and Ct17 Recombinant Toxins of the Scorpion Centruroides tecomanus
Meléndez-Zempoalteca, A., Juárez-González, V. R., Rudiño-Piñera, E., Pastor, N., Vargas-Jaimes, L., Valcarcel-Gamiño, J. A., Vázquez-Vuelvas, O. F., Quintero‐Hernández, V., & Valdez-Velázquez, L. L. (2022) · International Journal of Peptide Research and Therapeutics · doi:10.1007/s10989-022-10439-5 · Cited by 1
Yusof, T. Y., Ong, E. B. B., & Teh, A.-H. (2022) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2022.08.144 · Cited by 1
Databases and Tools to Investigate Protein-Metabolite Interactions
de Souza, L. P., & Fernie, A. R. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-2624-5_14 · Cited by 1
Back and forth modeling through biological scales
Pantano, S. (2022) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2022.09.037 · Cited by 1
Disentangling polydisperse biomolecular systems by Chemometrics decomposition of SAS data
Sagar, A., & Bernadó, P. (2022) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2022.08.038 · Cited by 1
Hayashi, S., Koseki, J., & Shimamura, T. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.11.038 · Cited by 1
Mukherjee, I., & Roy, I. (2022) · Indian Journal of Animal Health · doi:10.36062/ijah.2022.14022 · Cited by 1
Suresh, A., Prakash, B., & Kulkarni, K. A. (2022) · Biochemistry and Biophysics Reports · doi:10.1016/j.bbrep.2022.101410 · Cited by 1
Protein Folding Model Using Quantum Computation
SAITO, R., Okuwaki, K., Mochizuki, Y., Nagai, R., Kato, T., Sugisaki, K., & Minato, Y. (2022) · Journal of Computer Chemistry Japan · doi:10.2477/jccj.2022-0022 · Cited by 2
Kepel, B. J., Kalalo, M. J., & Tallei, T. E. (2022) · Journal of Applied Pharmaceutical Science · doi:10.7324/japs.2023.130304 · Cited by 1
dos Santos, L. M., & de Melo-Minardi, R. C. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-21175-1_7 · Cited by 2
Introduction: Trends, Puzzles, and Hopes for the Future of Healthcare
Ehsani, S., Glauner, P., Plugmann, P., & Thieringer, F. M. (2022) · Future of business and finance · doi:10.1007/978-3-030-99838-7_1 · Cited by 1
Advances in deep learning-based 3D molecular generative models
Yao, S., Song, J., Feng, Z., Jia, L., Zhong, Z., & Song, M. (2022) · Scientia Sinica Chimica · doi:10.1360/ssc-2022-0204 · Cited by 4
A Coyote Optimization Algorithm-trained Dendritic Neuron Model for Prediction Tasks
He, H., Xue, C., Li, Q., & Gao, S. (2022) · Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems (SCIS&ISIS) · doi:10.1109/scisisis55246.2022.10002073 · Cited by 1
“In recent years, more and more artificial neural networks (ANNs) are applied to solve the prediction problem [4], [5].”
Oliva, F., Musiani, F., Giorgetti, A., Rubeis, S. D., Sorokina, O., Armstrong, J. D., Carloni, P., & Ruggerone, P. (2023) · Frontiers in Chemistry · doi:10.3389/fchem.2022.1059593 · Cited by 1
“Finally, note that for isoforms without good quality-templates, users could choose to use predicted structures such as those provided by AF and RosettaFold (Baek et al., 2021) or other modelling packages”
MethodKolodziejek, A. M., Bearden, S. W., Maes, S. E., Montenieri, J. A., Gage, K. L., Hovde, C. J., & Minnich, S. A. (2023) · Applied and Environmental Microbiology · doi:10.1128/aem.01244-22 · Cited by 1
Structural Studies of Pif1 Helicases from Thermophilic Bacteria
Réty, S., Zhang, Y., Fu, W.-T., Wang, S., Chen, W., & Xi, X. (2023) · Microorganisms · doi:10.3390/microorganisms11020479 · Cited by 1
“The full length DdPi1 structure (residues 1-510) was predicted with no ligand by Alphafold and RosettaFold algorithms, both giving very similar results with differences in domains positions (rmsd 5.7 Å).”
MethodInfluentialMolecular docking analysis of juglone with parvulin-type PPiase PrsA from Staphylococcus aureus
Laskar, D. (2023) · Bioinformation · doi:10.6026/97320630019048 · Cited by 1
Searching for Osmosensing Determinants in Poplar Histidine-Aspartate Kinases
Makhokh, H., Lafite, P., Larcher, M. V., Lamblin, F., Chefdor, F., Depierreux, C., Tanigawa, M., Maeda, T., Carpin, S., & Héricourt, F. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24076318 · Cited by 1
“These 3D models were built using a method based on deep learning neural networks [26].”
MethodIn Silico Exploration of Alternative Conformational States of VDAC
Mannella, C. A. (2023) · Molecules · doi:10.3390/molecules28083309 · Cited by 1
“In the last two years, considerable attention has been paid to so-called “artificial intelligence” approaches for predicting protein folding, and the increasing accessibility of algorithms, such as AlphaFold2 [34] and RoseTTAFold [35] for various applications [36].”
BackgroundMethodNIAS‐Server 2.0: A versatile complementary tool for structural biology studies
Feltes, B. C., Pinto, É. S. M., Mangini, A. T., & Dorn, M. (2023) · Journal of Computational Chemistry · doi:10.1002/jcc.27112 · Cited by 1
Milton, M. E., & Visick, K. L. (2023) · Communicative & Integrative Biology · doi:10.1080/19420889.2023.2203626 · Cited by 1
“RoseTTAFold [31] produced a SypA prediction in close agreement to the AlphaFold prediction with a Cα root-mean-square deviation (RMSD) of 0.395 Å.”
MethodInfluentialSoftware Tools for Optimization of Biocatalysts
Vilím, J., Prokop, Z., & Damborský, J. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-390644-9.00085-8 · Cited by 1
Equilibrium and Nonequilibrium Methods for Free-Energy Calculations With Molecular Dynamics
Chipot, C. J., Gkeka, P., Lelièvre, T., & Stoltz, G. (2023) · Elsevier eBooks · doi:10.1016/b978-0-12-821978-2.00112-4 · Cited by 1
Polymer and Soft Matter Research at Diamond Light Source
Terrill, N. J., Bombardi, A., Carlà, F., Cinque, G., Derry, M. J., Milsom, A., Siligardi, G., Snow, T., Topham, P. D., Zeng, X., et al. (2023) · Synchrotron Radiation News · doi:10.1080/08940886.2023.2207456 · Cited by 1
CovET: A covariation-evolutionary trace method that identifies protein structure–function modules
Konecki, D. M., Hamrick, S., Wang, C., Agosto, M. A., Wensel, T. G., & Lichtarge, O. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.104896 · Cited by 1
“ε additive ab 1⁄4ðMab þWTÞ−ðMa þMbÞ (9)”
BackgroundProtein Interaction Prediction Method Based on Feature Engineering and XGBoost
Zhao, X., & Wang, X. (2023) · BIO Web of Conferences · doi:10.1051/bioconf/20236101021 · Cited by 1
Chattopadhyay, D., Walker, D. R., Rich-New, S. T., Kearney, J. F., & Turnbough, C. L. (2023) · mBio · doi:10.1128/mbio.01172-23 · Cited by 1
Bhati, S. K., Jain, M., Muthukumaran, J., & Singh, A. K. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2240423 · Cited by 1
“The three-dimensional model of the HPPK enzyme was predicted using the Robetta server (https://robetta.bakerlab.org/) (Baek et al., 2021) using the option of RoseTTAFold.”
Learning Causal Biological Networks with Parallel Ant Colony Optimization Algorithm
Zhai, J., Ji, J., & Liu, J. (2023) · Bioengineering · doi:10.3390/bioengineering10080909 · Cited by 2
“[27] proposed to learn causal protein signaling networks using a three-track neural network.”
BackgroundLu, Y., Rejiepu, B., Zhang, D., Cai, D.-C., Yang, K., Tian, T., Zhou, X.-L., & Fan, P. T. (2023) · Kidney & Blood Pressure Research · doi:10.1159/000533144 · Cited by 1
Wang, X., Bensch, S., Huang, X., & Dong, L. (2023) · BMC Ecology and Evolution · doi:10.1186/s12862-023-02155-5 · Cited by 1
“This approach uses a three-track neural network and has shown to be one of the best performing public servers for predicting protein structure [43].”
MethodExploring proten’s conformational space by using encoding layer supervised auto-encoder
Chen, G., & Zhang, Z.-Y. (2023) · Acta Physica Sinica · doi:10.7498/aps.72.20231060 · Cited by 1
Sosnick, T. R. (2023) · Journal of Clinical Investigation · doi:10.1172/jci174915 · Cited by 2
“Although not designed for this task, AlphaFold was adapted to docking (17) by simply creating a hypothetical single-chain protein with a chain break between the two partners, a technique employed by another highly successful AI method that was developed shortly afterward (4).”
BackgroundMethodCryo-Electron Microscopy and Cryo-Electron Tomography of Viruses
Luque, D., & Castón, J. R. (2023) · Springer series in biophysics · doi:10.1007/978-3-031-36815-8_12 · Cited by 2
Standke, H. G., Kim, L., & Owens, C. P. (2023) · The Protein Journal · doi:10.1007/s10930-023-10158-w · Cited by 1
DrugBank Online: A How‐to Guide
Klinger, C. M., Cox, J., So, D., Stauth, T., Wilson, M., Wilson, A., & Knox, C. (2023) · Methods and principles in medicinal chemistry · doi:10.1002/9783527830497.ch3 · Cited by 2
Sketching Proteins with Bare Hands in VR
Ma, D., Lee, J. H., Jin, T., Lee, S.-H., Kim, H. M., & Bae, S.-H. (2023) · ACM Symposium on User Interface Software and Technology (UIST) · doi:10.1145/3586182.3616675 · Cited by 1
Understanding the contagiousness of Covid-19 strains: A geometric approach
Vottero, P., Olivetti, E. C., D'Agostino, L. C., Grazia, L. D., Vezzetti, E., Aminpour, M., Tuszyński, J. A., & Marcolin, F. (2023) · Journal of Molecular Graphics and Modelling · doi:10.1016/j.jmgm.2023.108670 · Cited by 1
Thermococcus kodakarensis TK0353 is a novel AP lyase with a new fold
Caffrey, P. J., Eckenroth, B. E., Burkhart, B. W., Zatopek, K. M., McClung, C. M., Santangelo, T. J., Doublié, S., & Gardner, A. F. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.105503 · Cited by 1
Mironov, P. A., & Shenkarev, Z. O. (2023) · Vestnik Moskovskogo universiteta Seria 16 Biologia · doi:10.55959/10.55959/msu0137-0952-16-78-3s-3 · Cited by 1
Exploring the free energy landscape of proteins using magnetic tweezers
Sun, H., Le, S., Guo, Z., & Chen, H. (2024) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2023.12.008 · Cited by 1
Experimentation on Greeting Before Entering the Classroom
Fadilah, A., Handayani, S. R., Hidayat, S. P., Tabroni, I., Osca, S., & Cale, W. (2023) · Journal Emerging Technologies in Education · doi:10.55849/jete.v1i3.370 · Cited by 1
Deep Learning for the Structure‐Based Binding Free Energy Prediction of Small Molecule Ligands
Mysore, V. P., Patel, N., & Ojewole, A. A. (2024) · Wiley eBooks · doi:10.1002/9783527840748.ch11 · Cited by 1
Okmane, L., Fitkin, L., Sandgren, M. O. J., & Ståhlberg, J. (2024) · FEBS Open Bio · doi:10.1002/2211-5463.13774 · Cited by 1
Host-pathogen interactions: databases and approaches for data generation
Bano, Y., & Shrivastava, A. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95890-5.00006-5 · Cited by 2
Lai, H.-S., & Chen, C. (2024) · International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC) · doi:10.5220/0012431600003657 · Cited by 1
Computational approaches to phytochemical drug discovery
Sarı, S., & Şöhretoğlu, D. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-16102-5.00009-2 · Cited by 1
Mejia, S., Santos, J. L. B., & Noutsos, C. (2024) · Plants · doi:10.3390/plants13070987 · Cited by 1
“The amino acid sequences were submitted to the RobeTTAFold website to generate 3D protein images [55] with default parameters.”
MethodTraditional and machine learning approaches in structure-based drug virtual screening
Zhang, H., & Gao, Y. Q. (2024) · Chinese Journal of Chemical Physics · doi:10.1063/1674-0068/cjcp2312128 · Cited by 2
Li, G. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95917-9.00020-1 · Cited by 1
On the renormalisation group, protein folding, and naturalness
Patrascu, A. T. (2024) · Physica Scripta · doi:10.1088/1402-4896/ad4189 · Cited by 1
“However, recently [16], an AI has been trained on predicting such structures, and it did it quite aston-ishingly at an accuracy of over 95 percent, being way above any alternatives tried.”
BackgroundChen, Q. (2024) · Springer eBooks · doi:10.1007/978-981-99-8251-6_7 · Cited by 1
Li, C., Wei, T.-Y., Cheung, M. S., & Tsai, M.-Y. (2024) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.3c07938 · Cited by 1
Geometric Algebra Models of Proteins for Three-Dimensional Structure Prediction: A Detailed Analysis
Pepe, A., Lasenby, J., & Chacón, P. (2024) · Springer proceedings in mathematics & statistics · doi:10.1007/978-3-031-55985-3_6 · Cited by 1
Artificial Intelligence and Quantum Computing
Wirtz, B. W. (2024) · Springer texts in business and economics · doi:10.1007/978-3-031-50289-7_8 · Cited by 1
Ngo, V. A. (2024) · Biophysical Journal · doi:10.1016/j.bpj.2024.06.028 · Cited by 1
McCarthy, S., & Gonen, S. (2024) · Advanced Science · doi:10.1002/advs.202404786 · Cited by 2
Developing Lead Compounds of eEF2K Inhibitors Using Ligand–Receptor Complex Structures
Xu, J., Yu, W., Luo, Y., Liu, T., & Su, A. (2024) · Processes · doi:10.3390/pr12071540 · 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.