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 1,501–1,600 of 5,636
Complementing machine learning‐based structure predictions with native mass spectrometry
Allison, T. M., Degiacomi, M. T., Marklund, E. G., Jovine, L., Elofsson, A., Benesch, J. L. P., & Landreh, M. (2022) · Protein Science · doi:10.1002/pro.4333 · Cited by 20
“Machine learning (ML)-based algorithms have been hailed as the solution to the protein structure prediction problem and are already being used to predict structures across entire proteomes.(1,2) For example, using protein sequence data as the only user input, AF2(3) can generate models of ordered, monomeric proteins t…”
MethodDocking-based long timescale simulation of cell-size protein systems at atomic resolution
Vakser, I. A., Grudinin, S., Jenkins, N. W., Kundrotas, P. J., & Deeds, E. J. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2210249119 · Cited by 21
Targeting in silico GPCR conformations with ultra-large library screening for hit discovery
Sala, D., Batebi, H., Ledwitch, K., Hildebrand, P. W., & Meiler, J. (2023) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2022.12.006 · Cited by 19
From propensities to patterns to principles in protein folding
Rose, G. D. (2025) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.26540 · Cited by 18
A Deep SE(3)-Equivariant Model for Learning Inverse Protein Folding
McPartlon, M., Lai, B., & Xu, J. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.15.488492 · Cited by 17
Widespread Horizontal Gene Transfer Among Animal VirusesPreprint
Buck, C. B., Welch, N. L., Belford, A. K., Varsani, A., Pastrana, D. V., Tisza, M. J., & Starrett, G. J. (2024) · eLife · doi:10.7554/elife.97647.1 · Cited by 19
Interpreting Potts and Transformer Protein Models Through the Lens of Simplified Attention
Bhattacharya, N., Thomas, N., Rao, R., Dauparas, J., Koo, P. K., Baker, D., Song, Y. S., & Ovchinnikov, S. (2021) · Biocomputing 2022 · doi:10.1142/9789811250477_0004 · Cited by 20
Self-citationSequence-assignment validation in cryo-EM models with checkMySequence
Chojnowski, G. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322005009 · Cited by 20
“Although the release of Artificial Intelligence (AI)-based AlphaFold 2 (AF2) (Jumper et al., 2021) and the similar RoseTTAFold (Baek et al.,2021) represent dramatic progress in the way protein structures are predicted, they did not solve the problem of protein structure determination.”
BackgroundBongiovanni, G., Harder, O. F., Drabbels, M., & Lorenz, U. J. (2022) · doi:10.1101/2022.09.14.507962 · Cited by 20
Robust total X-ray scattering workflow to study correlated motion of proteins in crystals
Meisburger, S. P., Case, D. A., & Ando, N. (2022) · doi:10.1101/2022.08.22.504832 · Cited by 20
A Folding-Docking-Affinity framework for protein-ligand binding affinity prediction
Wu, M.-H., Xie, Z., & Zhi, D. (2025) · Communications Chemistry · doi:10.1038/s42004-025-01506-1 · Cited by 19
“Given AlphaFold (27; 28) and other methods (29; 30; 31; 32; 33; 34; 35) have revolutionized the field of protein folding, accessing three-dimensional protein structures become much easier than before.”
Zhang, Y., Zhang, Z., Kagaya, Y., Terashi, G., Zhao, B., Xiong, Y., & Kihara, D. (2025) · Communications Biology · doi:10.1038/s42003-025-08783-5 · Cited by 19
Tld1 is a regulator of triglyceride lipolysis that demarcates a lipid droplet subpopulation
Speer, N. O., Braun, R. J., Reynolds, E. G., Brudnicka, A., Swanson, J. M. J., & Henne, W. M. (2024) · Journal of Cell Biology · doi:10.1083/jcb.202303026 · Cited by 19
“Although they were very similar, the RoseTTAFold structure was selected for further simulations as it has been demonstrated to better predict membrane structures (Azzaz et al., 2022; Heged ˝ us et al., 2022).”
MethodInfluentialLi, J., Chen, B., Fu, Z., Mao, J., Liu, L., Chen, X., Zheng, M., Wang, C.-Y., Wang, C., Guo, Y.-W., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-50209-z · Cited by 19
“Despite the unsuccessful attempts to obtain a crystal structure of MicA and the absence of structural data of homologous proteins, we managed to generate de novo predicted models of MicA using the tFold 55 , RoseTTAFold 56 , and AlphaFold 57 computational methods (Supplementary Fig.”
Montserrat‐Canals, M., Cordara, G., & Krengel, U. (2025) · Quarterly Reviews of Biophysics · doi:10.1017/s0033583524000209 · Cited by 21
“…primary sequence, the recent advances in AI, including large language models (LLMs), have been successfully applied to proteins (e.g., AlphaFold (Jumper et al., 2021; Abramson et al., 2024; Lyu et al., 2024), RoseTTaFold (Baek et al., 2021; Krishna et al., 2024), and ESMFold (Lin et al., 2023)).”
Rational Design Principles for De Novo α-Helical Peptide Barrels with Dynamic Conductive Channels
Niitsu, A., Thomson, A. R., Scott, A. J., Sengel, J. T., Jung, J., Mahendran, K. R., Sodeoka, M., Bayley, H., Sugita, Y., Woolfson, D. N., et al. (2025) · Journal of the American Chemical Society · doi:10.1021/jacs.4c13933 · Cited by 19
Engineering Pichia pastoris for Efficient De Novo Synthesis of 2′-Fucosyllactose
Fang, H., Gao, J., Yu, L., Shi, P., & Zhao, C. (2025) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.5c00598 · Cited by 19
Sharma, S., Yadav, P. D., & Cherian, S. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1535322 · Cited by 27
“RoseTTAfold is a tool that employs neural networks and simultaneously takes into account the arrangement of amino acids, their interactions, and the potential tertiary structures they can form (56).”
Evolving Perspective on the Origin and Diversification of Cellular Life and the Virosphere
Spang, A., Mahendrarajah, T., Offre, P., & Stairs, C. W. (2022) · Genome Biology and Evolution · doi:10.1093/gbe/evac034 · Cited by 22
Methods for the directed evolution of biomolecular interactions
Xie, V. C., Styles, M. J., & Dickinson, B. C. (2022) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2022.01.001 · Cited by 20
Aziz, S., Waqas, M. S., Halim, S. A., Ali, A., Iqbal, A., Iqbal, M., Khan, A., & Al‐Harrasi, A. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.956776 · Cited by 21
“Amongst all TLRs, TLR3 showed the best binding with Neo-4 and Neo-1 with binding energies of -114.47 kcal/mol and -101.08 kcal/mol, respectively, followed by Neo-2 (-91.88 kcal/mol) and Neo-3 (-81.01 kcal/mol).”
BackgroundMethodInfluentialKhatib, I. A., Deng, J., Symes, A., Kerr, M., Zhang, H., Huang, S.-Y. N., Pommier, Y. G., Khan, A., & Shutt, T. E. (2022) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2022.102420 · Cited by 19
“We used RoseTTAFold structure prediction to model TOP1MT binding to mtDNA.”
MethodInfluentialRobin, V., Bodein, A., Scott‐Boyer, M., Leclercq, M., Périn, O., & Droit, A. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.962799 · Cited by 20
“ANNs are exploited as a reference method in several classification tasks (Rohani and Eslahchi, 2019; Baek et al., 2021), but they suffer from some limitations.”
MethodDanazumi, A. U., Gital, S. I., Idris, S., Dibba, L. B. S., Balogun, E. O., & Górna, M. W. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.10.002 · Cited by 19
TDP-43 and NEAT long non-coding RNA: Roles in neurodegenerative disease
Sekar, D., Tusubira, D., & Ross, K. (2022) · Frontiers in Cellular Neuroscience · doi:10.3389/fncel.2022.954912 · Cited by 21
“Conceivably, computational modeling of wild type and mutant TDP-43, for instance using AlphaFold or RosettaFold algorithms (Baek et al., 2021; Jumper et al., 2021) will enable the selection of PS-rich oligonucleotides that can target TDP-43 mutants for functional retention in the nucleus.”
BackgroundAtlas of interactions between SARS-CoV-2 macromolecules and host proteins
Li, G., Tang, Z., Fan, W., Wang, X., Huang, L., Jia, Y., Wang, M., Hú, Z., & Zhou, Y. (2022) · Cell Insight · doi:10.1016/j.cellin.2022.100068 · Cited by 19
Adedeji, E. O., Oduselu, G. O., Ogunlana, O. O., Fatumo, S., Koenig, R., & Adebiyi, E. F. (2022) · Insects · doi:10.3390/insects13111070 · Cited by 20
Moraes, S. N., Becker, J. T., Moghadasi, S. A., Shaban, N. M., Auerbach, A. A., Cheng, A. Z., & Harris, R. S. (2022) · eLife · doi:10.7554/elife.83893 · Cited by 20
“129 We therefore used RoseTTAFold [34] to generate a structural model of KSHV ORF61 for 3130 dimensional comparisons (Figure 1C).”
MethodInfluentialChinnam, N. B., Syed, A., Hura, G. L., Hammel, M., Tainer, J. A., & Tsutakawa, S. E. (2022) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2022.09.023 · Cited by 21
Gao, J., Zheng, H., Wang, X., & Li, Y. (2023) · Enzyme and Microbial Technology · doi:10.1016/j.enzmictec.2023.110197 · Cited by 22
Peptide-based nanomaterials: Building back better & beyond
Conticello, V. P. (2023) · Current Opinion in Solid State and Materials Science · doi:10.1016/j.cossms.2023.101066 · Cited by 21
Xia, Y., Pan, X., & Shen, H. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.168091 · Cited by 20
Trisciuzzi, D., Villoutreix, B. O., Siragusa, L., Baroni, M., Cruciani, G., & Nicolotti, O. (2023) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2023.2218641 · Cited by 22
“But, as more experimental 3D structures of complexes or predicted structures with tools like Alphafold-multimer [75], RoseTTAFold [76] or ColabFold [77] get reported and screened in vitro, this observation may further be revisited and to some extent evolve.”
BackgroundThe splicing isoform Foxp3Δ2 differentially regulates tTreg and pTreg homeostasis
Gu, Q., Zhao, X., Guo, J. F., Jin, Q., Wang, T., Xu, W., Li, L., Zhang, J., Zhang, W., Hong, S., et al. (2023) · Cell Reports · doi:10.1016/j.celrep.2023.112877 · Cited by 21
Cleavage of 14-3-3ε by the enteroviral 3C protease dampens RIG-I-mediated antiviral signaling
Andrews, D. D. T., Mohamud, Y., Vlok, M., Bani, D. A., Hay, B. N., Foster, L. J., Luo, H., Overall, C. M., & Jan, E. (2023) · Journal of Virology · doi:10.1128/jvi.00604-23 · Cited by 19
Allosteric crosstalk in modular proteins: Function fine-tuning and drug design
Abhishek, S., Deeksha, W., Nethravathi, K. R., Davari, M. D., & Rajakumara, E. (2023) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.10.013 · Cited by 21
Scaling up cryo-EM for biology and chemistry: The journey from niche technology to mainstream method
de la Cruz, M. J., & Eng, E. T. (2023) · Structure · doi:10.1016/j.str.2023.09.009 · Cited by 19
The SWISS‐MODEL Repository of 3D Protein Structures and Models
Robin, X., Waterhouse, A. M., Bienert, S., Studer, G., Alexander, L. T., Tauriello, G., Schwede, T. F., & Pereira, J. (2023) · Methods and principles in medicinal chemistry · doi:10.1002/9783527830497.ch6 · Cited by 26
Self-citationInhibition of Trehalose Synthesis in Lepidoptera Reduces Larval Fitness
Tellis, M. B., Mohite, S. D., Nair, V. S., Chaudhari, B. Y., Ahmed, S., Kotkar, H. M., & Joshi, R. S. (2023) · Advanced Biology · doi:10.1002/adbi.202300404 · Cited by 19
Weraduwage, S. M., Whitten, D. A., Kulke, M., Sahu, A., Vermaas, J. V., & Sharkey, T. D. (2023) · Plant Cell & Environment · doi:10.1111/pce.14776 · Cited by 20
Tunnel engineering of gas-converting enzymes for inhibitor retardation and substrate acceleration
Kim, S. M., Kang, S. H., Jeon, B. W., & Kim, Y. H. (2023) · Bioresource Technology · doi:10.1016/j.biortech.2023.130248 · Cited by 21
Wang, T., Wang, L., Zhang, X., Shen, C., Zhang, O., Wang, J., Wu, J., Jin, R., Zhou, D., Chen, S., et al. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad486 · Cited by 21
Self-citationNguyen, N.-Q., Park, S., Gim, M., & Kang, J. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad484 · Cited by 21
“After generating a 3D fold representation from the protein sequence, we could extract information from atomic features at the one-dimensional (1D) sequence level and 3D information encoded at the two-dimensional (2D) distance map level [25].”
MethodGenome-wide screens identify SEL1L as an intracellular rheostat controlling collagen turnover
Podolsky, M. J., Kheyfets, B., Pandey, M., Beigh, A. H., Yang, C. D., Lizama, C. O., Datta, R., Lin, L. L., Wang, Z., Wolters, P. J., et al. (2024) · Nature Communications · doi:10.1038/s41467-024-45817-8 · Cited by 22
Liu, X., Maele, L. V., Matarazzo, L., Soulard, D., da Silva, V. A. D., de Bakker, V., Dénéréaz, J., Bock, F. P., Taschner, M., Ou, J., et al. (2024) · Cell Host & Microbe · doi:10.1016/j.chom.2024.02.002 · Cited by 20
“37 However, while our structure prediction using RoseTTAFold 41 demonstrates the Rossmann-like domain of GT-B glycosyltransferases, 42 transmembrane domains were not detected (Figure 2B).”
Cuadrado, A. F., & Damme, D. V. (2024) · Journal of Experimental Botany · doi:10.1093/jxb/erae088 · Cited by 20
Enhancing cryo-EM structure prediction with DeepTracer and AlphaFold2 integration
Chen, J., Zia, A., Luo, A., Meng, H., Wang, F., Hou, J., Cao, R., & Si, D. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae118 · Cited by 21
The 6-kilodalton peptide 1 in plant viruses of the family Potyviridae is a viroporin
Chai, M., Li, L., Li, Y., Yang, Y., Wang, Y., Jiang, X., Luan, Y., Li, F., Cui, H., Wang, A., et al. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2401748121 · Cited by 19
“AlphaFold2 was used to predict three - dimensional models of 6K1 with default settings (54).”
MethodHermosilla, A. M., Berner, C., Ovchinnikov, S., & Vorobieva, A. A. (2024) · Protein Science · doi:10.1002/pro.5033 · Cited by 17
“Recently, deep learning (DL) models such as Alpha-Fold2 (Jumper et al., 2021), RoseTTaFold (Baek et al., 2021), and language models (LMs) (e.g ESMFold [Lin et al., 2023], OmegaFold [Wu et al., 2022], or RGN2 [Chowdhury et al., 2022]) have out-performed classic ab initio folding simulations.”
MethodSelf-citationReview and Comparative Analysis of Methods and Advancements in Predicting Protein Complex Structure
Zhao, N., Wu, T., Wang, W., Zhang, L., & Gong, X. (2024) · Interdisciplinary Sciences Computational Life Sciences · doi:10.1007/s12539-024-00626-x · Cited by 22
“AlphaFold2 [8] and RoseTTAFold [122] are novel meth-ods for predicting protein structures based on deep learning, which greatly improve the level of protein monomer structure prediction [123].”
Protein research in millets: current status and way forward
Ceasar, S. A., Prabhu, S., & Ebeed, H. T. (2024) · Planta · doi:10.1007/s00425-024-04478-z · Cited by 19
“An artificial intelligence (AI)-based protein structure prediction tool, Alpha-Fold, was introduced for quick and accurate prediction of protein structures (Jumper et al. 2021; Baek et al. 2021).”
Haribabu, J., Madhavan, G., Swaminathan, S., Panneerselvam, M., Moraga, D., Gayathri, D., Echeverría, C., Arulraj, A., Mangalaraja, R. V., Kokkarachedu, V., et al. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.134870 · Cited by 19
Improved deep learning prediction of antigen–antibody interactions
Gao, M., & Skolnick, J. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2410529121 · Cited by 22
“In pursuit of this goal, the remarkable success of AlphaFold 2 (AF2) ( 1 ), originally created to predict the atomic structure of individual proteins, has spurred new developments to predict protein–protein complexes using deep learning ( 2 – 4 ).”
BackgroundBharadwaj, S., Deepika, K., Kumar, A., Jaiswal, S., Miglani, S., Singh, D., Fartyal, P., Kumar, R., Singh, S., Singh, M. P., et al. (2024) · Chemical Biology & Drug Design · doi:10.1111/cbdd.14639 · Cited by 21
“(Baek et al. 2021).”
Li, J., Li, J., Cao, L., Chen, Q., Ding, D., & Kang, L. (2024) · Microbiome · doi:10.1186/s40168-024-01928-4 · Cited by 19
“4A), the three-dimensional structure of which was generated using RoseTTAFold [40] (Fig.”
MethodSystematic discovery of antibacterial and antifungal bacterial toxins
Nachmias, N., Dotan, N., Rocha, M. C., Fraenkel, R., Detert, K., Kluzek, M., Shalom, M., Cheskis, S., Peedikayil‐Kurien, S., Meitav, G., et al. (2024) · Nature Microbiology · doi:10.1038/s41564-024-01820-9 · Cited by 20
Yadav, M. K., Dahiya, V., Tripathi, M. K., Chaturvedi, N., Rashmi, M., Ghosh, A., & Raj, V. S. (2024) · European Journal of Pharmacology · doi:10.1016/j.ejphar.2024.177103 · Cited by 19
GRACE: Generative Redesign in Artificial Computational Enzymology
Hu, R.-E., Yu, C., & Ng, I. (2024) · ACS Synthetic Biology · doi:10.1021/acssynbio.4c00624 · Cited by 19
Targeting adhesion G protein-coupled receptors. Current status and future perspectives
Ließmann, F., von Bredow, L., Meiler, J., & Liebscher, I. (2024) · Structure · doi:10.1016/j.str.2024.10.022 · Cited by 21
Predicting adaptive immune receptor specificities by machine learning is a data generation problem
Mason, D. M., & Reddy, S. T. (2024) · Cell Systems · doi:10.1016/j.cels.2024.11.008 · Cited by 24
Ma, S., Zhu, F., Zhang, P., Xu, Y., Zhou, Z., Yang, H., Tan, C., Chen, J., & Pan, P. (2025) · Scientific Reports · doi:10.1038/s41598-024-84823-0 · Cited by 20
“Three key indicators—GDT-HA, RMSD, and MolProbity—were employed to assess the quality of the tertiary model 56 .”
Artificial Intelligence and Breast Cancer Management: From Data to the Clinic
Feng, K., Yi, Z., & Xu, B. (2025) · Cancer Innovation · doi:10.1002/cai2.159 · Cited by 22
Paries, M., Hobecker, K., Luelmo, S. H., Binci, F., Guercio, A. M., Usländer, A., Cardoso, C., Si, Y., Wankner, L., Bashyal, S., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2427021122 · Cited by 19
De Novo Multi‐Mechanism Antimicrobial Peptide Design via Multimodal Deep Learning
Li, X., Gong, H., Wang, Y., Zhao, Y., Li, L., Bao, P., Kong, Q., Fu, J., Wan, B., Zhang, Y., et al. (2026) · Advanced Science · doi:10.1002/advs.202515835 · Cited by 5
GPU-I-TASSER: a GPU accelerated I-TASSER protein structure prediction tool
MacCarthy, E., Zhang, C., Zhang, Y., & KC, D. B. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btab871 · Cited by 20
Nassar, R., Brini, E., Parui, S., Liu, C., Dignon, G. L., & Dill, K. A. (2022) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.1c00916 · Cited by 20
VHH Structural Modelling Approaches: A Critical Review
Vishwakarma, P., Vattekatte, A. M., Shinada, N. K., Diharce, J., Martins, C., Cadet, F., Gardebien, F., Etchebest, C., Nadaradjane, A. A., & de Brevern, A. G. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms23073721 · Cited by 24
“…were carried out with six different software and online tools: Modeller with single-template and multi-template [84], ModWeb [258,259], SwissModel with the best sequence identity template and a second time with the best GMQE score [134], AlphaFold 2 [91], RoseTTAfold [251] and NanoNet [253].”
BackgroundMethodUnraveling coevolutionary dynamics using ecological genomics
Cornille, A., Ebert, D., Stukenbrock, E. H., de la Vega, R. C. R., Tiffin, P., Croll, D., & Tellier, A. (2022) · Trends in Genetics · doi:10.1016/j.tig.2022.05.008 · Cited by 19
Brodowski, M., Pierpaoli, M., Janik, M., Kowalski, M. K., Ficek, M., Ślepski, P., Trzaskowski, B., Swain, G. M., Ryl, J., & Bogdanowicz, R. (2022) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2022.132427 · Cited by 21
Probing ligand binding of endothiapepsin by `temperature-resolved' macromolecular crystallography
Huang, C., Aumonier, S., Engilberge, S., Eriş, D., Smith, K. M. L., Leonarski, F., Wojdyla, J. A., Beale, J. H., Buntschu, D., Pauluhn, A., et al. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s205979832200612x · Cited by 19
A New Structural Model of Apolipoprotein B100 Based on Computational Modeling and Cross Linking
Jeiran, K., Gordon, S. M., Sviridov, D. O., Aponte, A. M., Haymond, A. N., Piszczek, G., Lucero, D., Neufeld, E. B., Vaisman, I. I., Liotta, L. A., et al. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms231911480 · Cited by 20
“In addition, the computational model of subunit II domain 1 simple β-sheet did not match with the DSSO cross-link data (Supplementary Figure S4).”
Asgard ESCRT-III and VPS4 reveal conserved chromatin binding properties of the ESCRT machinery
Nachmias, D., Melnikov, N., Zorea, A., Sharon, M., Yemini, R., De-picchoto, Y., Tsirkas, I., Aharoni, A., Frohn, B. P., Schwille, P., et al. (2022) · The ISME Journal · doi:10.1038/s41396-022-01328-2 · Cited by 19
Duran, P., Loya‐López, S., Ran, D., Tang, C., Calderon‐Rivera, A., Gomez, K., Stratton, H. J., Huang, S., Xu, Y., Wijeratne, E. M. K., et al. (2023) · British Journal of Pharmacology · doi:10.1111/bph.15974 · Cited by 19
Distinguishing features of fold‐switching proteins
Chakravarty, D., Schafer, J. W., & Porter, L. L. (2023) · Protein Science · doi:10.1002/pro.4596 · Cited by 20
Fluid protein fold space and its implications
Porter, L. L. (2023) · BioEssays · doi:10.1002/bies.202300057 · Cited by 20
“protein structure prediction algorithms, such as AlphaFold2 (AF2),[9] RoseTTAfold,[10] RGN2,[11] and ESM-fold,[12] which generally predict a single fold for a given amino acid sequence.”
BackgroundMethodAI for Manufacturing and Healthcare: a chemistry and engineering perspectivePreprint
Chen, J., Yuan, Y., Ziabari, A., Xu, X., Zhang, H., Christakopoulos, P., Bonnesen, P. V., Ivanov, I. N., Ganesh, P., Chen, W., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.01520 · Cited by 25
Accurate de novo design of high-affinity protein binding macrocycles using deep learning
Rettie, S. A., Juergens, D., Adebomi, V., Bueso, Y. F., Zhao, Q., Leveille, A. N., Liu, A., Bera, A. K., Wilms, J. A., Üffing, A., et al. (2024) · doi:10.1101/2024.11.18.622547 · Cited by 19
Self-citationAssessing protein model quality based on deep graph coupled networks using protein language model
(2023) · doi:10.1093/bib/bbad420 · Cited by 18
(2023) · doi:10.1093/bioinformatics/btad739 · Cited by 18
Cryo-EM structures of apo-APC/C and APC/CCDH1:EMI1 complexes provide insights into APC/C regulation
Höfler, A., Yu, J., Yang, J., Zhang, Z., Chang, L., McLaughlin, S. H., Grime, G. W., Garman, E. F., Boland, A., & Barford, D. (2024) · Nature Communications · doi:10.1038/s41467-024-54398-5 · Cited by 18
“Last, the huge advances in the accuracy and reliability of protein structure prediction achieved through AlphaFold 28,29 and RoseTTAFold 47 , allow the interpretation of dif fi cult-to-build regions of cryo-EM maps.”
Pauken, K. E., Alhalabi, O., Goswami, S., & Sharma, P. (2025) · Cancer Cell · doi:10.1016/j.ccell.2025.03.005 · Cited by 22
Self-iterative multiple-instance learning enables the prediction of CD4+ T cell immunogenic epitopes
Shen, L.-C., Zhang, Y., Wang, Z., Littler, D. R., Liu, Y., Tang, J., Rossjohn, J., Yu, D., & Song, J. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01073-z · Cited by 21
“Second, advances in structural prediction algorithms like AlphaFold3, coupled with emerging high-resolution structural biology techniques, promise to dramatically expand the database of TCR-pMHC-II complexes 58,59 , facilitating the atomic-level modelling of immune recognition.”
Computational function prediction of bacteria and phage proteins
Grigson, S. R., Bouras, G. S., Dutilh, B. E., Olson, R., & Edwards, R. A. (2025) · Microbiology and Molecular Biology Reviews · doi:10.1128/mmbr.00022-25 · Cited by 25
“Models like AlphaFold (73) and RoseTTAFold (141) leverage deep neural networks to analyze multiple sequence alignments, capturing evolutionary and geometric relation ships to "fold" proteins.”
Non-model bacteria as platforms for endogenous gene expression in synthetic biology
Poppeliers, J., Boon, M., Mey, M. D., Masschelein, J., & Lavigne, R. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00354-x · Cited by 18
“…structure of a protein is intrinsically related to its function, the development of open-source software to computationally predict protein structures (for example, ColabFold and RoseTTAFold) has greatly increased the number of available protein structures and their functions in databases 82,83 .”
Chemical probes for enzyme imaging: challenges in design, synthesis and biomedical applications
Nguyen, J., Zabijak, M., & Poręba, M. (2025) · Chemical Science · doi:10.1039/d5sc05683g · Cited by 23
Computational Landscape in Drug Discovery: From AI/ML Models to Translational Application
Sharma, D., Anabala, M., Jain, V. V., Shyam, M., Prince, S. E., & Muniyan, R. (2025) · Scientifica · doi:10.1155/sci5/1688637 · Cited by 22
“RoseTTAFold program utilizes a three-track neural network to predict diverse structures with limited available data, generating monomeric, multimeric, and protein–protein complex structures [81].”
De novo design of epitope-specific antibodies via a structure-driven computational workflow
Wu, F., Zhao, Y. S., Wu, J., Jiang, B., He, B., Huang, L.-K., Qin, C., Xiao, Y., Yang, F., Wang, R., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-67361-9 · Cited by 27
“While recent de novo protein binder design methods, such as RFDiffusion 24 , BindCraft 25 , and AlphaProteo 26 , have demonstrated high success rates, they are supported by robust protein structure prediction techniques like RoseTTAFold 27 , AlphaFold-Multimer 28 , and AlphaFold-3 29 .”
Yu, S., Hu, Y., Cao, T., Zhu, Y., Li, H., You, T., & Xu, F. (2025) · Progress in Polymer Science · doi:10.1016/j.progpolymsci.2025.102070 · Cited by 25
Artificial intelligence driven protein design and sustainable nanomedicine for advanced theranostics
Esmaeilpour, D., Hamblin, M. R., Cheng, J., Khosravi, A., Liu, J., Zarepour, A., Zarrabi, A., Sillanpaa, M., Zare, E. N., Shen, J., et al. (2026) · Bioactive Materials · doi:10.1016/j.bioactmat.2026.01.036 · Cited by 41
Strategies for enhancing protein solubility: methods, applications, and prospects
Cao, R., Wang, W., Zhang, Z., Wang, C., Huang, Q., Yan, L., Zhang, J., & Cheng, J. (2026) · npj Science of Food · doi:10.1038/s41538-026-00743-5 · Cited by 26
“Toolssuchas AlphaFold 112 and RoseTTAFold 113 now allow researchers to predict high-fi delity 3D structures from amino acid sequences, providing a topological basis to visualize surface-exposed hydrophobic patches.”
Experiment-guided AlphaFold3 resolves measurement-consistent protein ensembles
Maddipatla, A., Sellam, N. B., Bojan, M., Masalitin, V., Vedula, S., Schanda, P., Marx, A., & Bronstein, A. M. (2026) · Nature Biotechnology · doi:10.1038/s41587-026-03166-5 · Cited by 28
Structural Insights into the Human Mitochondrial Pyruvate Carrier Complexes
Xu, L., Phelix, C. F., & Chen, L. Y. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c00879 · Cited by 20
Biological Parts for Plant Biodesign to Enhance Land-Based Carbon Dioxide Removal
Yang, X., Liu, D., Lu, H., Weston, D. J., Chen, J., Muchero, W., Martin, S., Liu, Y., Hassan, M. M., Yuan, G., et al. (2021) · BioDesign Research · doi:10.34133/2021/9798714 · Cited by 18
“Recently, two AI-based computational tools, AlphaFold and RoseTTAFold, became available for high-accuracy prediction of protein structure from sequence information alone [145, 146].”
MethodWang, L., Zhang, J., Wang, D., & Song, C. (2022) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1009972 · Cited by 18
Fessner, N. D., Badenhorst, C. P. S., & Bornscheuer, U. T. (2022) · ChemCatChem · doi:10.1002/cctc.202200156 · Cited by 20
Errors in structural biology are not the exception
Gao, Y., Thorn, V., & Thorn, A. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322011901 · Cited by 19
Jindra, M. A., Choe, K., Chowdhury, R., Kong, R., Ghaffari, S., Sweedler, J. V., & Pfleger, B. F. (2023) · Metabolic Engineering · doi:10.1016/j.ymben.2023.02.012 · Cited by 18
AsiteDesign: a Semirational Algorithm for an Automated Enzyme Design
Rodà, S., Terholsen, H., Meyer, J. R. H., Cañellas-Solé, A., Guallar, V., Bornscheuer, U. T., & Kazemi, M. (2023) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c07091 · Cited by 18
Surface ID: a geometry-aware system for protein molecular surface comparison
Riahi, S., Lee, J. H., Sorenson, T., Wei, S., Jäger, S., Olfati‐Saber, R., Zhou, Y., Park, A., Wendt, M., Minoux, H., et al. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad196 · Cited by 24
Exploiting conformational dynamics to modulate the function of designed proteins
Rennella, E., Sahtoe, D. D., Baker, D. A., & Kay, L. E. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2303149120 · Cited by 18
Self-citation
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.