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 2,101–2,200 of 5,636
In silico screening of herbal phytochemicals to develop a Rasayana for immunity against Nipah virus
Debroy, B., De, A., Bhattacharya, S., & Pal, K. (2023) · Journal of Ayurveda and Integrative Medicine · doi:10.1016/j.jaim.2023.100825 · Cited by 14
“The homology modeling of these two proteins was performed using the Swiss Model (https://swissmodel.expasy.org/) [29] and Robetta (https://robetta.bakerlab.org/) [30,31] webserver, respectively.”
MethodHackley, R. K., Hwang, S., Herb, J. T., Bhanap, P., Lam, K., Vreugdenhil, A., Darnell, C. L., Martínez-Pastor, M., Martin, J. H., Maupin-furlow, J. A., et al. (2024) · Molecular Microbiology · doi:10.1111/mmi.15225 · Cited by 12
“De novo quaternary structural prediction of HVO_2861 was conducted using the RosettaFold server with default parameters (Baek et al., 2021).”
MethodDeep learning-based characterization and redesign of major potato tuber storage protein
Luo, X., Cao, L., Yu, L., Gao, M., Ai, J., Gao, D., Zhang, X., Lucas, W. J., Huang, S., Xu, J., et al. (2024) · Food Chemistry · doi:10.1016/j.foodchem.2024.138556 · Cited by 14
Rohner, V., Lamothe‐Molina, P. J., & Patriarchi, T. (2024) · Journal of Neurochemistry · doi:10.1111/jnc.16045 · Cited by 12
Nicholson, K. R., Cronin, R. M., Prest, R. J., Menon, A. R., Yang, Y., Jennisch, M. K., Champion, M. M., Tobin, D. M., & Champion, P. A. D. (2024) · mBio · doi:10.1128/mbio.03357-23 · Cited by 12
Yeast-based screening platforms to understand and improve human health
Deichmann, M., Hansson, F. G., & Jensen, E. D. (2024) · Trends in biotechnology · doi:10.1016/j.tibtech.2024.04.003 · Cited by 13
Predicting therapeutic and side effects from drug binding affinities to human proteome structures
Sawada, R., Sakajiri, Y., Shibata, T., & Yamanishi, Y. (2024) · iScience · doi:10.1016/j.isci.2024.110032 · Cited by 15
Liao, M., Feng, S., Liu, X., Xu, G., Li, S., Bai, Y., Luo, H., Yao, B., Wang, H., & Tu, T. (2024) · Advanced Science · doi:10.1002/advs.202402441 · Cited by 12
HDBind: encoding of molecular structure with hyperdimensional binary representations
Jones, D., Zhang, X., Bennion, B. J., Pinge, S., Xu, W., Kang, J., Khaleghi, B., Moshiri, N., Allen, J., & Rosing, T. (2024) · Scientific Reports · doi:10.1038/s41598-024-80009-w · Cited by 13
“…drug-like molecules have grown to comprise tens of billions of possibilities 6 , while the number of available protein structures has simultaneously grown with the introduction of AI-enabled 3D structure prediction tools, resulting in over 200 million publicly available predicted structures 7,8 .”
Comparative Mitogenomic Analysis and the Evolution of Rhizoctonia solani Anastomosis Groups
Lin, R., Xia, Y., Liu, Y., Zhang, D., Xiang, X., Niu, X., Jiang, L., Wang, X., & Zheng, A. (2021) · Frontiers in Microbiology · doi:10.3389/fmicb.2021.707281 · Cited by 15
Banaś, A. M., Bocian-Ostrzycka, K. M., Dunin-Horkawicz, S., Ludwiczak, J., Wilk, P., Orlikowska, M., Wyszyńska, A., Dąbrowska, M., Plichta, M., Spodzieja, M., et al. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222413451 · Cited by 13
Machine learning in postgenomic biology and personalized medicine
Ray, A. (2022) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1451 · Cited by 17
“…considering amino acid sequence pattern homology with known structures, residue – residue interactions, and possible three-dimensional structures using neural network in a three-track neural network model (RoseTTAFold), and the codes are available in the public domain (Baek et al., 2021).”
MethodNie, L., Quan, L., Wu, T., He, R., & Lyu, Q. (2022) · Bioinformatics · doi:10.1093/bioinformatics/btac188 · Cited by 12
Interface refinement of low- to medium-resolution Cryo-EM complexes using HADDOCK2.4
Neijenhuis, T., van Keulen, S. C., & Bonvin, A. M. J. J. (2022) · Structure · doi:10.1016/j.str.2022.02.001 · Cited by 12
Weaver, G. C., Arya, R., Schneider, C. L., Hudson, A. W., & Stern, L. J. (2022) · Frontiers in Immunology · doi:10.3389/fimmu.2022.864898 · Cited by 13
“In this article, we evaluate structural models for roseolovirus U20 and U21 proteins produced by next-generation computational machine learning approaches AlphaFold (23) and RoseTTAFold (24).”
MethodInfluentialRodrigues, C. H. M., & Ascher, D. B. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkac381 · Cited by 14
Deep learning approaches for conformational flexibility and switching properties in protein design
Rudden, L. S. P., Hijazi, M., & Barth, P. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.928534 · Cited by 14
“AlphaFold2 and RoseTTAfold present a general solution to the protein folding problem.”
BackgroundMethodInfluentialVarela, D., Karlin, V., & André, I. (2022) · Structure · doi:10.1016/j.str.2022.09.005 · Cited by 13
Cargemel, C., Marsin, S., Noiray, M., Legrand, P., Bounoua, H., de la Sierra-Gallay, I. L., Walbott, H., & Quevillon‐Chéruel, S. (2023) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798323000281 · Cited by 12
Saddhe, A. A., & Potocký, M. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1118670 · Cited by 13
“We assessed them for their folding accuracy based on the Molprobity score, Ramachandran score and Q means plus Z-score criteria (Wang et al., 2016; Waterhouse et al., 2018; Jumper et al., 2021; Baek et al., 2021).”
MethodBest Practices of Using AI-Based Models in Crystallography and Their Impact in Structural Biology
Graille, M., Sacquin‐Mora, S., & Taly, A. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00381 · Cited by 14
Mansoor, S., Baek, M., Madan, U., & Horvitz, E. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.09.01.458592 · Cited by 13
Self-citationEnd-to-End deep structure generative model for protein designPreprint
Lai, B., McPartlon, M., & Xu, J. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.07.09.499440 · Cited by 15
Structural biology at the scale of proteomes
Bouatta, N., & AlQuraishi, M. (2023) · Nature Structural & Molecular Biology · doi:10.1038/s41594-023-00924-w · Cited by 14
Choudhary, P., Anyango, S., Berrisford, J. M., Tolchard, J. L., Váradi, M., & Velankar, S. S. (2023) · Scientific Data · doi:10.1038/s41597-023-02101-6 · Cited by 13
“It also makes it easier to compare PDB structures with the predicted model structures from AlphaFold DB 33,34 , SWISS-MODEL 32 , RoseTTAFold 66 , and many other resources, as these models follow a natural sequence numbering.”
MethodAlphaFold and the future of structural biology
Read, R. J., Baker, E. N., Bond, C. S., Garman, E. F., & van Raaij, M. J. (2023) · IUCrJ · doi:10.1107/s2052252523004943 · Cited by 17
“Since then, other powerful machine-learning algorithms for structure prediction have emerged, including the first (Baek et al. , 2021) and second (Baek et al. , 2023) versions of RoseTTAFold , ESMfold (Lin et al. , 2023) and OpenFold (Ahdritz et al. , 2022), an open-source reimplementation of…”
BackgroundMethodSelf-citationAlphaFold and the future of structural biology
Read, R. J., Baker, E. N., Bond, C. S., Garman, E. F., & van Raaij, M. J. (2023) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798323004928 · Cited by 15
Self-citationDiverse Genomic Embedding Benchmark for functional evaluation across the tree of lifePreprint
West-Roberts, J. A., Kravitz, J., Jha, N., Cornman, A., & Hwang, Y. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.07.10.602933 · Cited by 20
De novo design of triosephosphate isomerases using generative language modelsPreprint
Romero‐Romero, S., Braun, A. E., Kossendey, T., Ferruz, N., Schmidt, S., & Höcker, B. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.10.622869 · Cited by 17
Engineering de novo binder CAR-T cell therapies with generative AIPreprint
Mergen, M., Abele, D., Koleci, N., Fernandez, A. S., Sugden, M., Holzleitner, N., Carr, A., Rieger, L., Leone, V., Reichert, M., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.25.625151 · Cited by 16
Artificial Intelligence (AI) for More Sustainable Chemistry and a Greener Future
Ghasemlou, M., Nguyen, H. C., Talekar, S., Pfeffer, F. M., & Barrow, C. J. (2025) · ACS Sustainable Chemistry & Engineering · doi:10.1021/acssuschemeng.5c00853 · Cited by 12
OPUS-Mut: studying the effect of protein mutation through side-chain modeling
Xu, G., Wang, Q., & Ma, J. (2022) · doi:10.1101/2022.05.10.491420 · Cited by 12
Evaluation of Deep Neural Network ProSPr for Accurate Protein Distance Predictions on CASP14 Targets
Stern, J., Hedelius, B., Fisher, O., Billings, W. M., & Della Corte, D. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222312835 · Cited by 11
“Recent progress in the field of computational structure prediction includes the end-to-end deep learning models Alphafold2 [5] and RoseTTAfold [6] that are able to predict highly accurate protein structures from multiple sequence alignments.”
BackgroundWang, B., Lei, X., Tian, W., Perez-Rathke, A., Tseng, Y.-Y., & Liang, J. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad206 · Cited by 11
The Endothelial Glycocalyx as a Target of Excess Soluble Fms-like Tyrosine Kinase-1
Schulz, A., Drost, C. C., Hesse, B., Beul, K., Boeckel, G. R., Lukasz, A. H., Pavenstädt, H., Brand, M., & Marco, G. S. D. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms24065380 · Cited by 12
(2023) · doi:10.1093/gbe/evad218 · Cited by 11
In silico analysis of crustacean hyperglycemic hormone family G protein-coupled receptor candidates
Kozma, M. T., Pérez‐Moreno, J. L., Gandhi, N. S., Jeppesen, L. H., Durica, D. S., Ventura, T., & Mykles, D. L. (2024) · Frontiers in Endocrinology · doi:10.3389/fendo.2023.1322800 · Cited by 12
Designing Multifunctional Biomaterials via Protein Self‐Assembly
Solomonov, A. V., Kozell, A., & Shimanovich, U. (2024) · Angewandte Chemie · doi:10.1002/ange.202318365 · Cited by 12
Chang, X., Fang, X., Yao, Y., Xu, Z., Wu, C., & Lu, L. (2024) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.3c09308 · Cited by 11
Molecular dynamics simulations of intracellular lipid droplets: a new tool in the toolbox
Sapia, J. L., & Vanni, S. (2024) · FEBS Letters · doi:10.1002/1873-3468.14879 · Cited by 13
Effect of Conformational Variability on the Drug Resistance of Candida auris ERG11p and FKS1
Izumi, H., Nafié, L. A., & Dukor, R. K. (2024) · ACS Omega · doi:10.1021/acsomega.3c08134 · Cited by 11
Computational tools to predict context-specific protein complexes
Csikász‐Nagy, A., Fichó, E., Noto, S., & Reguly, I. Z. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102883 · Cited by 11
From sequence to mechanobiology? Promises and challenges for AlphaFold 3
Zonta, F., & Pantano, S. (2024) · Mechanobiology in Medicine · doi:10.1016/j.mbm.2024.100083 · Cited by 11
“12 This method employs principles similar to AlphaFold but utilizes a more lightweight architecture, making it more accessible to the broader scienti fi c community.”
Barbosa, D. C. D. S., Holanda, V. N., Lima, E. M. D. A., Cavalcante, M. K. D. A., de Castro, M. C. A. B., Chaves, E. J. F., Rocha, G. B., Silva, C. J. O., de Oliveira, R. N., & de Figueiredo, R. C. B. Q. (2024) · Molecules · doi:10.3390/molecules29194654 · Cited by 11
“In addition, we re-scored the free energies of binding of the simulated complexes in the light of the MM/GBSA method; at last, we also evaluated the enthalpies of binding for these complexes [93,95–98] (see the Supporting Information for more details).”
MethodAI-integrated network for RNA complex structure and dynamic prediction
Liu, H., Chen, Z., Gao, J., Zeng, C., & Zhao, Y. (2024) · Biophysics Reviews · doi:10.1063/5.0237319 · Cited by 15
Protein Modeling with DEER Spectroscopy
Tessmer, M. H., & Stoll, S. (2024) · Annual Review of Biophysics · doi:10.1146/annurev-biophys-030524-013431 · Cited by 14
Wang, T., Huang, W., Xu, K., Sun, Y., Zhang, Q. C., Yan, C., Li, Z., & Yan, N. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2423943122 · Cited by 16
Shao, G., Zhou, T., Yan, T., Guo, Y., Yun, Z., Huang, R., & Fang, L. (2025) · Nanophotonics · doi:10.1515/nanoph-2024-0504 · Cited by 15
“In recent years, AI has been extensively applied in scientific and engineering domains, such as protein structure prediction [54]–[56], weather forecasting [57], [58], etc.”
Zhou, C., Liu, C., Yan, B., Sun, J., Li, S., Li, J., Wang, J., Huang, X., Yan, W., Yang, S., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2417526122 · Cited by 11
“In addition, we observed that the substitution of Thr (polar hydrophilic) with Ile (nonpolar hydrophilic) resulted in an increased spatial distance between the CC1 and CC2 domains, as predicted using RoseTTAFold ( 44 ).”
Self-citationAI protocol for retrieving protein dynamic structures from two-dimensional infrared spectra
Ye, S., Zhu, L., Zhao, Z., Wu, F., Ли, Ж., Wang, B., Zhong, K., Sun, C., Mukamel, S., & Jiang, J. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2424078122 · Cited by 11
“A gradient - based folding algorithm ( 10 , 38 ) is then used to generate the three - dimensional protein backbone structures.”
A new protein isoform encoded by human circular RNA circSLC8a1 contributes to cardiac remodelling
Li, F., Du, W. W., Li, X., Wen, S., Xu, J., Yang, Q., Zhang, C., Ye, T., Wei, J., Wang, S., et al. (2025) · Cardiovascular Research · doi:10.1093/cvr/cvaf058 · Cited by 11
P-type ATPase magnesium transporter MgtA acts as a dimer
Zeinert, R., Zhou, F., Franco, P. H. C., Zöller, J., Madni, Z. K., Lessen, H. J., Aravind, L., Langer, J. D., Sodt, A. J., Storz, G., et al. (2025) · Nature Structural & Molecular Biology · doi:10.1038/s41594-025-01593-7 · Cited by 16
In silico prediction of variant effects: promises and limitations for precision plant breeding
Sendrowski, J., Bataillon, T. M., & Ramstein, G. P. (2025) · Theoretical and Applied Genetics · doi:10.1007/s00122-025-04973-1 · Cited by 14
“…beyond mRNA abundance include gene expression mechanisms like alternative splicing and transcription initiation (Dudnyk et al. 2024; Xu et al. 2024), chromatin state (Zhou and Troyanskaya 2015; Avsec et al. 2021b), and protein structure (Jumper et al. 2021; Baek et al. 2021; Lin et al. 2023).”
Artificial intelligence-enhanced bioavailability studies: Advancing the quality of food
Cheng, H., Liu, L., Zhang, H., Yang, Y., Bai, Y., Wang, S., Yang, M., Lu, W., Cheng, J., & Jin, Y. (2025) · Trends in Food Science & Technology · doi:10.1016/j.tifs.2025.105203 · Cited by 11
Applications of artificial intelligence and nanotechnology in vaccine development
Bahrami, Y., Bolideei, M., Mohammadzadeh, S., Gahrouei, R. B., Mohebbi, E., Haider, K. H., Barzigar, R., & Mehran, M. J. (2025) · International Journal of Pharmaceutics · doi:10.1016/j.ijpharm.2025.126096 · Cited by 13
Challenges and opportunities in technologies and methods for lncRNA structure determination
Degenhardt, M. F. D. S., & Wang, Y. (2025) · Cell & Bioscience · doi:10.1186/s13578-025-01470-2 · Cited by 11
“While 3D predictions for small RNAs ( 100 nucleotides) with reasonable accuracy are currently feasible, they lag far behind protein prediction capabilities [88–90].”
Engineering complexity into protein-based biomaterials for biomedical applications
Gregorio, N. E., Haas, C. M., King, N. P., & DeForest, C. A. (2025) · Nature Reviews Materials · doi:10.1038/s41578-025-00861-8 · Cited by 16
Wang, Y., Ma, Y., Chang, Y.-H., Yan, J., Zhang, J., Cai, M.-Y., & Wei, K. (2025) · Biology · doi:10.3390/biology14121665 · Cited by 13
“Third, the resulting designs undergo computational validation using high-accuracy structure prediction models like AlphaFold2 [155] or RoseTTAFold [156] to verify that the designed sequence folds into the intended structure and maintains the desired binding geometry.”
Nam, J., Lee, Y., Lee, S., Choi, H., Lee, S. Y., & Yang, D. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108782 · Cited by 14
Elsässer, F., Florea, R., Räsch, F., Zedan, M., Şen, N.-E., Pflästerer, T., Kleele, T., Loewith, R., Weis, K., de Souza, N., et al. (2026) · Molecular Systems Biology · doi:10.1038/s44320-025-00182-6 · Cited by 12
“Structural predictions based on Alphafold or RoseTTAFold are now available for over 98% of human proteins (Baek et al, 2021; Tunyasuvunakool et al, 2021), complementing the large body of experimentally solved protein structures.”
Mahmud, M. I., & Banerjee, T. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag229 · Cited by 16
Toyama, Y., & Kay, L. E. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2116325118 · Cited by 12
Early-stage structure-based drug discovery for small GTPases by NMR spectroscopy
Yin, G., Lv, G., Zhang, J., Jiang, H., Lai, T., Yang, Y., Ren, Y., Wang, J., Yi, C., Chen, H., et al. (2022) · Pharmacology & Therapeutics · doi:10.1016/j.pharmthera.2022.108110 · Cited by 11
Self-citationStructures of an active type III-A CRISPR effector complex
Smith, E. M., Ferrell, S. H., Tokars, V. L., & Mondragón, A. (2022) · Structure · doi:10.1016/j.str.2022.05.013 · Cited by 11
Morais, R. D. S., Santo, P. E., Ley, M., Schelcher, C., Abel, Y., Plassart, L., Deslignière, E., Chagot, M.-E., Quinternet, M., Paiva, A. C. F., et al. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2022.167760 · Cited by 12
Dubovski, N., Fierro, F., Margulis, E., Shoshan-Galeczki, Y. B., Peri, L., & Niv, M. Y. (2022) · Progress in molecular biology and translational science · doi:10.1016/bs.pmbts.2022.06.008 · Cited by 11
Prediction of Intrinsic Disorder Using Rosetta ResidueDisorder and AlphaFold2
He, J., Turzo, S. B. A., Seffernick, J. T., Kim, S. S., & Lindert, S. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c05508 · Cited by 11
Yuan, C., Song, S., He, J., Zhang, J., Liu, X., Peña, E. L., Sun, J., Shi, J., Su, Z., & Zhang, B. (2022) · Applied and Environmental Microbiology · doi:10.1128/aem.01303-22 · Cited by 11
Sarkar, D., Majumder, S., Giri, K., & Sabnam, N. (2022) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2022.2139763 · Cited by 12
Integrating model simulation tools and cryo‐electron microscopy
Beton, J. G., Cragnolini, T., Kaleel, M., Mulvaney, T., Sweeney, A., & Topf, M. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1642 · Cited by 11
“133,134 Several recent cryo-EM studies of the NPC also highlighted the utility of recent deep-learning structure prediction methods such as AlphaFold2 135 and RoseTTAfold 136 for model building.”
BackgroundMethodUsing deep-learning predictions of inter-residue distances for model validation
Sánchez Rodríguez, F., Chojnowski, G., Keegan, R. M., & Rigden, D. J. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322010415 · Cited by 11
Giant Viruses as a Source of Novel Enzymes for Biotechnological Application
de Oliveira, E. G., Carvalho, J. V. R. P., Botelho, B. B., Filho, C. A. D. C., Henriques, L. R., de Azevedo, B. L., & Rodrigues, R. A. L. (2022) · Pathogens · doi:10.3390/pathogens11121453 · Cited by 14
Combining NMR, SAXS and SANS to characterize the structure and dynamics of protein complexes
Delhommel, F., Martínez‐Lumbreras, S., & Sattler, M. (2022) · Methods in enzymology on CD-ROM/Methods in enzymology · doi:10.1016/bs.mie.2022.09.020 · Cited by 13
Kattan, R. E., Ayesh, D., & Wang, W. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad010 · Cited by 11
Sequence and structure alignments in post-AlphaFold era
Rajapaksa, S., Konagurthu, A. S., & Lesk, A. M. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102539 · Cited by 11
Zhang, Z., Gao, S., Lei, Z., Xiong, R., & Cheng, J. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2023.3247025 · Cited by 13
Molecular determinants of acrylamide neurotoxicity through covalent docking
Mueller, N. P. F., Carloni, P., & Alfonso‐Prieto, M. (2023) · Frontiers in Pharmacology · doi:10.3389/fphar.2023.1125871 · Cited by 11
“However, recently developed machine learning-based protein structure prediction algorithms (Baek et al., 2021; Jumper et al., 2021; Ahdritz et al., 2022; Lin et al., 2022) could also be used to generate input protein structures.”
MethodMicrophase separation produces interfacial environment within diblock biomolecular condensates
Latham, A. P., Zhu, L., Sharon, D. A., Ye, S., Willard, A. P., Zhang, X., & Zhang, B. (2025) · eLife · doi:10.7554/elife.90750.4 · Cited by 13
Visualizing everything, everywhere, all at once: Cryo-EM and the new field of structureomics
Lucas, B. A. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102620 · Cited by 14
Álvarez, D., Sapia, J. L., & Vanni, S. (2023) · Current Opinion in Cell Biology · doi:10.1016/j.ceb.2023.102205 · Cited by 12
Piecing together the structural organisation of lipid exchange at membrane contact sites
Khaddaj, R., & Kukulski, W. (2023) · Current Opinion in Cell Biology · doi:10.1016/j.ceb.2023.102212 · Cited by 11
Just Keep Rolling?—An Encompassing Review towards Accelerated Vaccine Product Life Cycles
(2023) · doi:10.3390/vaccines11081287 · Cited by 11
“In addition to AlphaFold, the neural network RoseTTAFold provides another related approach to solve modeling problems and accurately predict protein complexes [80].”
MethodJoiner, J. D., Steinchen, W., Mozer, N., Kronenberger, T., Bange, G., Poso, A., Wagner, S., & Hartmann, M. D. (2023) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2023.105387 · Cited by 11
“The structure of HilE was predicted using the following publicly available prediction structure prediction servers: Alpha-fold2 (52), RoseTTAFold (53) and tFold (https://drug.ai. tencent.com).”
MethodComputational analysis of protein–protein interactions of cancer drivers in renal cell carcinoma
Pei, J., Zhang, J., & Cong, Q. (2023) · FEBS Open Bio · doi:10.1002/2211-5463.13732 · Cited by 11
Self-citationEmbracing Heterogeneity: Challenging the Paradigm of Replisomes as Deterministic Machines
Lewis, J. S., van Oijen, A. M., & Spenkelink, L. M. (2023) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00436 · Cited by 13
Physically based machine learning for hierarchical materials
Fazio, V., Pugno, N. M., Giustolisi, O., & Puglisi, G. (2024) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2024.101790 · Cited by 14
Yao, H., Wang, X., Chi, J., Chen, H., Liu, Y., Jiayi, Y., Yu, J., Ruan, Y., Xiang, X., Pi, J., et al. (2024) · Molecules · doi:10.3390/molecules29050964 · Cited by 12
Fermentation Practices Select for Thermostable Endolysins in Phages
Oechslin, F., Zhu, X., Morency, C., Somerville, V., Shi, R., & Moineau, S. (2024) · Molecular Biology and Evolution · doi:10.1093/molbev/msae055 · Cited by 13
Cao, S., Bai, J., Jin, Y., Zheng, Y., Li, N., & Xue, C. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3377197 · Cited by 11
Adupa, V., Ustyantseva, E., Kampinga, H. H., & Onck, P. R. (2024) · Nature Communications · doi:10.1038/s41467-024-46587-z · Cited by 11
“The initial configuration of DNAJB6b for the all-atom molecular dynamics simulations is obtained using homology modeling based on four different structure predictors: Robetta, TR-Rosetta, RaptorX, and Al-91 phafold [33–38].”
MethodBan, Y., Yang, H., Jiang, J., Wang, C., Lv, B., & Feng, Y. (2024) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2024.132090 · Cited by 11
Programmable in vitro and in vivo folding of single-stranded nucleic-acid wireframe origami
Zhang, T., Qian, X., Cui, H., Li, Q., Du, X., Fu, X., Gu, H., Zeng, W., & Wei, B. (2024) · Chem · doi:10.1016/j.chempr.2024.04.023 · Cited by 11
Protein Retrieval via Integrative Molecular Ensembles (PRIME) through Extended Similarity Indices
Chen, L., Mondal, A., Pérez, A., & Miranda‐Quintana, R. A. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c00362 · Cited by 11
Cracking the chaperone code through the computational microscope
Guarra, F., Sciva, C., Bonollo, G., Pasala, C., Chiosis, G., Moroni, E., & Colombo, G. (2024) · Cell Stress and Chaperones · doi:10.1016/j.cstres.2024.08.001 · Cited by 11
“The continuously increasing computing power, combined with the advent of artificial intelligence structural prediction methods, 89-91 promises to expand the role of computational/theoretical approaches even more in the next few years.”
BackgroundStabilization of the hexasome intermediate during histone exchange by yeast SWR1 complex
Jalal, A. S. B., Girvan, P., Chua, E. Y. D., Liu, L., Wang, S., McCormack, E. A., Skehan, M. T., Knight, C. L., Rueda, D., & Wigley, D. B. (2024) · Molecular Cell · doi:10.1016/j.molcel.2024.08.015 · Cited by 11
“AlphaFold (Jumper et al., 2021) and RoseTTAFold (Baek et al., 2021) model was used to generate the additional residues of the Swr1 ATPase observed in the 3.8 Å SWR1-hexasome-dimer volume.”
InfluentialReaching New Heights in Genetic Code Manipulation with High Throughput Screening
Lino, B. R., Williams, S. J., Castor, M. E., & Deventer, J. A. V. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00329 · Cited by 11
NEFFy: a versatile tool for computing the number of effective sequences
Haghani, M., Bhattacharya, D., & Murali, T. M. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf222 · Cited by 14
Photopharmacology of Ion Channels through the Light of the Computational Microscope
Nin‐Hill, A., Mueller, N. P. F., Molteni, C., Rovira, C., & Alfonso‐Prieto, M. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms222112072 · Cited by 12
Ford, B. A., Sullivan, G. J., Moore, L. R., Varkey, D., Zhu, H. X., Ostrowski, M. D., Mabbutt, B. C., Paulsen, I. T., & Shah, B. S. (2021) · Biochemical Society Transactions · doi:10.1042/bst20200244 · Cited by 13
Faruk, N. F., Peng, X., Freed, K. F., Roux, B., & Sosnick, T. R. (2022) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.1c01255 · Cited by 12
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.