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] John Jumper , Richard Evans , Alexander Pritzel , Tim Green , Michael Figurnov , Kathryn Tunyasuvunakool , Olaf Ronneberger , Russ Bates , Augustin Žídek , Alex Bridgland , Clemens Meyer , Simon A A Kohl , Anna Potapenko , Andrew J Ballard , Andrew Cowie , Bernardino Romera-Paredes , Stanislav Nikolov , Rishub Jain , Jonas Adler , Trevor Back , Stig Petersen , David Reiman , Martin Steinegger , Michalina Pacholska , David Silver , Oriol Vinyals , Andrew W Senior , Koray Kavukcuoglu , Pushmeet Kohli , Demis Hassabis ., in Fourteenth Critical Assessment of Techniques for Protein Structure Predic
Its entry has no title and year that we can search by.
- Partly supportedcites [2] matched to “De novo protein design by deep network hallucination” (2020) 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] matched to “Improved protein structure prediction using predicted interresidue orientations” (2020) 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] matched to “Protein interaction networks revealed by proteome coevolution” (2019) 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-citationThe Pfam protein families database in 2019
El-Gebali, S., Mistry, J., Bateman, A., Eddy, S. R., Luciani, A., Potter, S. C., Qureshi, M., Richardson, L. J., Salazar, G. A., Smart, A., et al. (2019) · Nucleic Acids Research · doi:10.1093/nar/gky995 · Cited by 4,602
MolProbity: More and better reference data for improved all‐atom structure validation
Williams, C. J., Headd, J. J., Moriarty, N. W., Prisant, M. G., Videau, L. L., Deis, L. N., Verma, V., Keedy, D. A., Hintze, B. J., Chen, V. B., et al. (2018) · Protein Science · doi:10.1002/pro.3330 · Cited by 4,599
Self-citationUniProt: the universal protein knowledgebase
The UniProt Consortium (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1099 · Cited by 4,436
Improved protein structure prediction using potentials from deep learning
Senior, A. W., Evans, R., Jumper, J., Kirkpatrick, J., Sifre, L., Green, T., Qin, C., Žídek, A., Nelson, A. W. R., Bridgland, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1923-7 · Cited by 3,378 · cited 9×
“The biannual Critical Assessment of Structure Prediction (CASP) meetings have demonstrated that deep-learning methods such as AlphaFold ( 1 , 2 ) and trRosetta ( 3 ), which extract information fromthe largedata-baseofknownproteinstructuresintheProteinDataBank(PDB),outperformmoretraditional approachesthatexplicitlymode…”
InfluentialA Completely Reimplemented MPI Bioinformatics Toolkit with a New HHpred Server at its Core
Zimmermann, L., Stephens, A., Nam, S.-Z., Rau, D., Kübler, J., Lozajic, M., Gabler, F., Söding, J., Lupas, A. N., & Alva, V. (2018) · Journal of Molecular Biology · doi:10.1016/j.jmb.2017.12.007 · Cited by 2,522
I-TASSER server: new development for protein structure and function predictions
Yang, J., & Zhang, Y. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv342 · Cited by 2,515
Scoring function for automated assessment of protein structure template quality
Zhang, Y., & Skolnick, J. (2004) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.20264 · Cited by 2,392 · cited 1×
“4B) chains, and in many cases, the resulting models were very close to the actual structures (TM-score (33) > 0.”
Toward the estimation of the absolute quality of individual protein structure models
Benkert, P., Biasini, M., & Schwede, T. (2011) · Bioinformatics · doi:10.1093/bioinformatics/btq662 · Cited by 2,260
The SWISS-MODEL Repository—new features and functionality
Bienert, S., Waterhouse, A., de Beer, T. A. P., Tauriello, G., Studer, G., Bordoli, L., & Schwede, T. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1132 · Cited by 1,745
Maximum-likelihood density modification
Terwilliger, T. C. (2000) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444900005072 · Cited by 1,634
Van Wart, H. E., & Birkedal-Hansen, H. (1990) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.87.14.5578 · Cited by 1,475 · cited 1×
“There is a cysteine in an extension following the predicted prodomain barrel; taken together, these data are consistent with experimental data suggesting that the ADAM prodomain inhibits metalloprotease activity using a cysteine switch (26).”
Mészáros, B., Erdős, G., & Dosztányi, Z. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky384 · Cited by 1,473
Terwilliger, T. C., Grosse-Kunstleve, R. W., Afonine, P. V., Moriarty, N. W., Zwart, P. H., Hung, L.-W., Read, R. J., & Adams, P. D. (2008) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s090744490705024x · Cited by 1,462
Self-citationImproved protein structure prediction using predicted interresidue orientations
Yang, J., Anishchenko, I., Park, H., Peng, Z., Ovchinnikov, S., & Baker, D. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1914677117 · Cited by 1,421 · cited 6×
“described at the CASP14 conference, the AlphaFold2 methodological advances included 1) starting from multiple sequence alignments (MSAs) rather than from more processed features such as inverse covariance matrices derived from MSAs, 2) replacement of 2D convolution with an attention mechanism that better represents in…”
InfluentialSelf-citationHidden Markov model speed heuristic and iterative HMM search procedure
Johnson, L. S., Eddy, S. R., & Portugaly, E. (2010) · BMC Bioinformatics · doi:10.1186/1471-2105-11-431 · Cited by 1,378
HH-suite3 for fast remote homology detection and deep protein annotation
Steinegger, M., Meier, M., Mirdita, M., Vöhringer, H., Haunsberger, S. J., & Söding, J. (2019) · BMC Bioinformatics · doi:10.1186/s12859-019-3019-7 · Cited by 1,145 · cited 1×
“WeusedRoseTTAFoldtopredictthep101G bg binding domain (GBD) structure in a hetero-dimeric PI3K g complex.”
Mariani, V., Biasini, M., Barbato, A., & Schwede, T. (2013) · Bioinformatics · doi:10.1093/bioinformatics/btt473 · Cited by 1,138
The SWISS-MODEL Repository: new features and functionalities
Kopp, J. (2006) · Nucleic Acids Research · doi:10.1093/nar/gkj056 · Cited by 1,006
The lipocalin protein family: structural and sequence overview
Flower, D. R., North, A. C. T., & Sansom, C. E. (2000) · Biochimica et Biophysica Acta (BBA) - Protein Structure and Molecular Enzymology · doi:10.1016/s0167-4838(00)00148-5 · Cited by 868 · cited 1×
“3C) belonging to an extended superfamily that includes metalloprotease inhibitors (MPIs) (25).”
Protein Sequence Analysis Using the MPI Bioinformatics Toolkit
Gabler, F., Nam, S., Till, S., Mirdita, M., Steinegger, M., Söding, J., Lupas, A. N., & Alva, V. (2020) · Current Protocols in Bioinformatics · doi:10.1002/cpbi.108 · Cited by 831
PyRosetta: a script-based interface for implementing molecular modeling algorithms using Rosetta
Chaudhury, S., Lyskov, S., & Gray, J. J. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq007 · Cited by 816 · cited 1×
“In the first, the predicted residue-residue distance and orientation distributions are fed into pyRosetta (5) to generate all-atom models.”
Uniclust databases of clustered and deeply annotated protein sequences and alignments
Mirdita, M., von den Driesch, L., Galiez, C., Martin, M. J., Söding, J., & Steinegger, M. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkw1081 · Cited by 759
Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Shi, Y., Huang, Z., Feng, S., Zhong, H., Wang, W., & Sun, Y. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/214 · Cited by 751
Rethinking Attention with Performers
Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et al. (2020) · arXiv · doi:10.48550/arxiv.2009.14794 · Cited by 695
Levy, M., & Futerman, A. H. (2010) · IUBMB Life · doi:10.1002/iub.319 · Cited by 632 · cited 1×
“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.”
De novo protein design by deep network hallucination
Anishchenko, I., Chidyausiku, T. M., Ovchinnikov, S., Pellock, S. J., & Baker, D. (2020) · doi:10.1101/2020.07.22.211482 · Cited by 629 · cited 1×
“Intrigued by the DeepMind results, and with the goal of increasing protein structure prediction accuracy for structural biology research and advancing protein design (4), we explored network architectures incorporating different combinations of these five properties.”
Self-citationUsing Dali for Protein Structure Comparison
Holm, L. (2020) · Methods in Molecular Biology · doi:10.1007/978-1-0716-0270-6_3 · Cited by 603
Wolfsberg, T. G., Primakoff, P., Myles, D. G., & White, J. M. (1995) · The Journal of cell biology · doi:10.1083/jcb.131.2.275 · Cited by 502 · cited 1×
“The ADAM (A Disintegrin And Metalloprotease) and ADAMTS families of metalloproteases are encoded by over 40 human genes, mediate cell-cell and cell-matrix interactions (15, 16) and are involved in a range of human diseases, including cancer metastasis, inflammatory disorders, neurological diseases and asthma (16, 17).”
AL2CO: calculation of positional conservation in a protein sequence alignment
Pei, J., & Grishin, N. V. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.8.700 · Cited by 483
Self-citationProtein-level assembly increases protein sequence recovery from metagenomic samples manyfold
Steinegger, M., Mirdita, M., & Söding, J. (2019) · Nature Methods · doi:10.1038/s41592-019-0437-4 · Cited by 445
ECOD: an evolutionary classification of protein domains
Cheng, H., Schaeffer, R. D., Liao, Y., Kinch, L. N., Pei, J., Shi, S., Kim, B.-H., & Grishin, N. V. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003926 · Cited by 426
Self-citationPerceiver: General Perception with Iterative Attention
Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., & Carreira, J. (2021) · arXiv · doi:10.48550/arxiv.2103.03206 · Cited by 414 · cited 1×
“To enable the network to focus on the most relevant sequence information for each region while keeping access to the full multiple sequence alignment in a more memory efficient way, we experimented with the Perceiver architecture (11), updating smaller seed MSAs (up to 100 sequences) with extra sequences (thousands of…”
Relaxation of backbone bond geometry improves protein energy landscape modeling
Conway, P., Tyka, M. D., DiMaio, F., Konerding, D. E., & Baker, D. (2014) · Protein Science · doi:10.1002/pro.2389 · Cited by 407
Self-citationAxial Attention in Multidimensional Transformers
Ho, J., Kalchbrenner, N., Weissenborn, D., & Salimans, T. (2019) · arXiv · doi:10.48550/arxiv.1912.12180 · Cited by 370
GPCRdb in 2021: integrating GPCR sequence, structure and function
Kooistra, A. J., Mordalski, S., Pándy-Szekeres, G., Esguerra, M., Mamyrbekov, A., Munk, C., Keserű, G. M., & Gloriam, D. E. (2021) · Nucleic Acids Research · doi:10.1093/nar/gkaa1080 · Cited by 351 · cited 1×
“S7] and that the DeepAccNet model quality predictor ( 12 ) provides a good measure of actual model accuracy (fig.”
Rao, R., Liu, J., Verkuil, R., Meier, J., Canny, J. F., Abbeel, P., Sercu, T., & Rives, A. (2021) · doi:10.1101/2021.02.12.430858 · Cited by 350
Improved protein structure prediction by deep learning irrespective of co-evolution information
(2021) · doi:10.1038/s42256-021-00348-5 · Cited by 256
OMA orthology in 2021: website overhaul, conserved isoforms, ancestral gene order and more
Altenhoff, A. M., Train, C.-M., Gilbert, K. J., Mediratta, I., Mendes de Farias, T., Moi, D., Nevers, Y., Radoykova, H.-S., Rossier, V., Warwick Vesztrocy, A., et al. (2021) · Nucleic Acids Research · doi:10.1093/nar/gkaa1007 · Cited by 244
Improved protein structure refinement guided by deep learning based accuracy estimation
Hiranuma, N., Park, H., Baek, M., Anishchenko, I., Dauparas, J., & Baker, D. (2021) · Nature Communications · doi:10.1038/s41467-021-21511-x · Cited by 243 · cited 2×
“The increased prediction accuracy was critical for success in all cases; models made with trRosetta did not yield MR solutions.”
Self-citationSE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
Fuchs, F. B., Worrall, D. E., Fischer, V., & Welling, M. (2020) · UvA-DARE (University of Amsterdam) · doi:10.48550/arxiv.2006.10503 · Cited by 243 · cited 1×
“In the second, the averaged 1D and 2D features are fed into a final SE(3)-equivariant layer (6), and following end-to-end training from amino acid sequence to 3D coordinates, backbone coordinates are generated directly by the network Baek et al.”
Protein interaction networks revealed by proteome coevolution
Cong, Q., Anishchenko, I., Ovchinnikov, S., & Baker, D. (2019) · Science · doi:10.1126/science.aaw6718 · Cited by 241 · cited 1×
“We tested the endto-end 3-track network on paired sequence alignments for complexes of known structures (32) (see Methods and table S4 for details) containing two (Fig.”
Self-citationKim, M., Suh, J., Romano, D., Truong, M. H., Mullin, K., Hooli, B., Norton, D., Tesco, G., Elliott, K., Wagner, S. L., et al. (2009) · Human Molecular Genetics · doi:10.1093/hmg/ddp323 · Cited by 234
Improvement of molecular-replacement models with Sculptor
Bunkóczi, G., & Read, R. J. (2011) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910051218 · Cited by 209
Self-citationCrystal structures of VAP1 reveal ADAMs' MDC domain architecture and its unique C‐shaped scaffold
Takeda, S., Igarashi, T., Mori, H., & Araki, S. (2006) · The EMBO Journal · doi:10.1038/sj.emboj.7601131 · Cited by 202 · cited 1×
“The ADAMs contain prodomain and metalloprotease domains; the fold of the metalloprotease isknown( 23 , 24 ),butthefoldoftheprodomain, which has no homologs of known structure, is not.”
Toward optimal fragment generations for ab initio protein structure assembly
Xu, D., & Zhang, Y. (2013) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.24179 · Cited by 201
TRAM, LAG1 and CLN8: members of a novel family of lipid-sensing domains?
Winter, E., & Ponting, C. P. (2002) · Trends in Biochemical Sciences · doi:10.1016/s0968-0004(02)02154-0 · Cited by 181 · cited 1×
“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.”
Glassman, C. R., Mathiharan, Y. K., Jude, K. M., Su, L., Panova, O., Lupardus, P. J., Spangler, J. B., Ely, L. K., Thomas, C., Skiniotis, G., et al. (2021) · Cell · doi:10.1016/j.cell.2021.01.018 · Cited by 181 · cited 1×
“Such an understanding is important for dissecting the specific actions of IL-12 and IL-23 and generating inhibitors that block IL-12 without affecting IL-23 signaling.”
Self-citationKlein, T., & Bischoff, R. (2011) · Journal of Proteome Research · doi:10.1021/pr100556z · Cited by 179 · cited 2×
“…thrombospondin motifs) families of metalloproteases are encoded by more than 40 human genes, mediate cell-cell and cell-matrix interactions ( 20 , 21 ), and are involved in a range of human diseases, including cancer metastasis, inflammatory disorders, neurological diseases, and asthma ( 21 , 22 ).”
Haas, J., Barbato, A., Behringer, D., Studer, G., Roth, S., Bertoni, M., Mostaguir, K., Gumienny, R., & Schwede, T. (2018) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25431 · Cited by 168 · cited 1×
“Fortunately, the Continuous Automated Model Evaluation (CAMEO) experiment (7) tests structure prediction servers blindly on protein structures as they are submitted to the PDB.”
MoRDa, an automatic molecular replacement pipeline
Vagin, A., & Lebedev, A. (2015) · Acta Crystallographica Section A Foundations and Advances · doi:10.1107/s2053273315099672 · Cited by 165
SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning
Hanson, J., Paliwal, K. K., Litfin, T., & Zhou, Y. (2019) · Genomics, Proteomics & Bioinformatics · doi:10.1016/j.gpb.2019.01.004 · Cited by 165
Lalani, S. R., Liu, P., Rosenfeld, J. A., Watkin, L. B., Chiang, T., Leduc, M. S., Zhu, W., Ding, Y., Pan, S., Vetrini, F., et al. (2016) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2015.12.008 · Cited by 143 · cited 1×
“By comparison, a homology model based on very distant ( 15% sequence identity) homologs had multiple alignment shifts that misplace key conserved residues (fig.”
IntFOLD: an integrated web resource for high performance protein structure and function prediction
McGuffin, L. J., Adiyaman, R., Maghrabi, A. H. A., Shuid, A. N., Brackenridge, D. A., Nealon, J. O., & Philomina, L. S. (2019) · Nucleic Acids Research · doi:10.1093/nar/gkz322 · Cited by 131 · 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…”
Necessary Role for the Lag1p Motif in (Dihydro)ceramide Synthase Activity
Spassieva, S., Seo, J.-G., Jiang, J. C., Bielawski, J., Alvarez-Vasquez, F., Jazwinski, S. M., Hannun, Y. A., & Obeid, L. M. (2006) · Journal of Biological Chemistry · doi:10.1074/jbc.m608092200 · Cited by 121 · cited 1×
“A central crevice extends into the membrane and is lined with residues required for activity (His182 and Asp213) (30) or conserved (W298), as well as a pathogenic mutation (H183Q) found in progressive myoclonus epilepsy and dementia that decreases ceramide levels (31).”
Zhong, S., & Khalil, R. A. (2019) · Biochemical Pharmacology · doi:10.1016/j.bcp.2019.03.033 · Cited by 119 · cited 1×
“The ADAMs contain prodomain and metalloprotease domains; the fold of the metalloprotease isknown( 23 , 24 ),butthefoldoftheprodomain, which has no homologs of known structure, is not.”
Kremer, L. S., Distelmaier, F., Alhaddad, B., Hempel, M., Iuso, A., Küpper, C., Mühlhausen, C., Kovács-Nagy, R., Satanovskij, R. M., Graf, E., et al. (2016) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2015.12.009 · Cited by 115 · cited 1×
“3A) with well-aligned active-site residues that are conserved in TANGO2 orthologs (Fig.”
Read, R. J., & McCoy, A. J. (2011) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910051371 · Cited by 111
Self-citationMasked Label Prediction: Unified Message Passing Model for Semi-Supervised ClassificationPreprint
Shi, Y., Huang, Z., Feng, S., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.03509 · Cited by 100
Impairment of ceramide synthesis causes a novel progressive myoclonus epilepsy
Vanni, N., Fruscione, F., Ferlazzo, E., Striano, P., Robbiano, A., Traverso, M., Sander, T., Falace, A., Gazzerro, E., Bramanti, P., et al. (2014) · Annals of Neurology · doi:10.1002/ana.24170 · Cited by 94 · cited 1×
“This active-site composition (His 182 , Asp 213 , and potentially a neighboring Ser 212 ) suggests testable reaction mechanisms for the enzyme (Fig.”
Terwilliger, T. C., Grosse-Kunstleve, R. W., Afonine, P. V., Moriarty, N. W., Zwart, P. H., Hung, L. W., Read, R. J., & Adams, P. D. (2008) · PubMed · doi:10.17863/cam.52329 · Cited by 91
Self-citationCrystal Structure of the Catalytic Domain of Human ADAM33
Orth, P., Reichert, P., Wang, W., Prosise, W. W., Yarosh-Tomaine, T., Hammond, G., Ingram, R. N., Xiao, L., Mirza, U. A., Zou, J., et al. (2004) · Journal of Molecular Biology · doi:10.1016/j.jmb.2003.10.037 · Cited by 90 · cited 1×
“The ADAMs contain prodomain and metalloprotease domains; the fold of the metalloprotease isknown( 23 , 24 ),butthefoldoftheprodomain, which has no homologs of known structure, is not.”
Ju, F., Zhu, J., Shao, B., Kong, L., Liu, T.-Y., Zheng, W.-M., & Bu, D. (2021) · Nature Communications · doi:10.1038/s41467-021-22869-8 · Cited by 84
Assessment of protein assembly prediction in CASP12
Lafita, A., Bliven, S., Kryshtafovych, A., Bertoni, M., Monastyrskyy, B., Duarte, J. M., Schwede, T., & Capitani, G. (2018) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25408 · Cited by 67
Ab initio solution of macromolecular crystal structures without direct methods
McCoy, A. J., Oeffner, R. D., Wrobel, A. G., Ojala, J. R. M., Tryggvason, K., Lohkamp, B., & Read, R. J. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1701640114 · Cited by 60
Self-citationKono, M., Sugiura, K., Suganuma, M., Hayashi, M., Takama, H., Suzuki, T., Matsunaga, K., Tomita, Y., & Akiyama, M. (2013) · Human Molecular Genetics · doi:10.1093/hmg/ddt207 · Cited by 54
Milev, M. P., Saint‐Dic, D., Zardoui, K., Klopstock, T., Law, C., Distelmaier, F., & Sacher, M. (2021) · Journal of Inherited Metabolic Disease · doi:10.1002/jimd.12312 · Cited by 53 · cited 1×
“Ntn superfamily members with structures similar to the RoseTTAFold model suggest that TANGO2 functions as an enzyme that might hydrolyze a carbon-nitrogen bond in a membrane component (18).”
Haas, J., Gumienny, R., Barbato, A., Ackermann, F., Tauriello, G., Bertoni, M., Studer, G., Smolinski, A., & Schwede, T. (2019) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25815 · Cited by 45 · 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…”
Improving homology modeling from low-sequence identity templates in Rosetta: A case study in GPCRs
Bender, B. J., Marlow, B., & Meiler, J. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1007597 · Cited by 44
RUPEE: A fast and accurate purely geometric protein structure search
Ayoub, R., & Lee, Y. (2019) · PLOS ONE · doi:10.1371/journal.pone.0213712 · Cited by 42
Wang, Y., Virtanen, J., Xue, Z., & Zhang, Y. (2017) · Nucleic Acids Research · doi:10.1093/nar/gkx349 · Cited by 39
Ceramide synthases: Reflections on the impact of Dr. Lina M. Obeid
Kim, J. L., Mestre, B., Shin, S.-H., & Futerman, A. H. (2021) · Cellular Signalling · doi:10.1016/j.cellsig.2021.109958 · Cited by 25
The DBSAV Database: Predicting Deleteriousness of Single Amino Acid Variations in the Human Proteome
Pei, J., & Grishin, N. V. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.166915 · Cited by 21
Self-citationBunkóczi, G., Wallner, B., & Read, R. J. (2015) · Structure · doi:10.1016/j.str.2014.11.020 · Cited by 18
Self-citationTANGOing along the protein secretion pathway.
Rabouille, C., & Kondylis, V. (2006) · Genome biology · doi:10.1186/gb-2006-7-4-213 · Cited by 9 · cited 1×
“The RoseTTAFold model of TANGO2 adopts an N-terminal nucleophile aminohydrolase (Ntn) fold (Fig.”
RoseTTAFold: The first release of RoseTTAFold
Baek, M., DiMaio, F., Anishchenko, I. V., Dauparas, J., Ovchinnikov, S., Wang, J., & Baker, D. A. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.5068264 · Cited by 7
Self-citation
Research works printed but not linked: 2
- 2011, phenix. ensembler: a tool for multiple superposition, Comput Crystallogr Newsl, 2, 8
- 2015, in ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES (INT UNION CRYSTALLOGRAPHY 2 ABBEY SQ, CHESTER, CH1 2HU, ENGLAND, 71, S19
Cited by
Accurate structure prediction of biomolecular interactions with AlphaFold 3
Abramson, J., Adler, J., Dunger, J., Evans, R., Green, T., Pritzel, A., Ronneberger, O., Willmore, L., Ballard, A. J., Bambrick, J., et al. (2024) · Nature · doi:10.1038/s41586-024-07487-w · Cited by 15,861
ColabFold - Making protein folding accessible to all
Mirdita, M., Schütze, K., Moriwaki, Y., Heo, L., Ovchinnikov, S., & Steinegger, M. (2021) · doi:10.1101/2021.08.15.456425 · Cited by 9,391
Self-citationVaradi, M., Anyango, S., Deshpande, M., Nair, S., Natassia, C., Yordanova, G., Yuan, D., Stroe, O., Wood, G., Laydon, A., et al. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkab1061 · Cited by 7,850
Evolutionary-scale prediction of atomic level protein structure with a language model
Lin, Z., Akin, H., Rao, R., Hie, B., Zhu, Z., Lu, W., Smetanin, N., Verkuil, R., Kabeli, O., Shmueli, Y., et al. (2022) · doi:10.1101/2022.07.20.500902 · Cited by 5,990
Protein complex prediction with AlphaFold-Multimer
Evans, R., O’Neill, M., Pritzel, A., Antropova, N., Senior, A., Green, T., Žídek, A., Bates, R., Blackwell, S., Yim, J., et al. (2021) · doi:10.1101/2021.10.04.463034 · Cited by 3,808
“In practice we use a weighted combination of pTM and ipTM as our model confidence metric, in order to account for some intra-chain confidence in our model ranking:”
Method
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.