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 3,701–3,800 of 5,636
The known protein universe is phylogenetically biasedPreprint
Avasthi, P. P., & York, R. A. (2024) · doi:10.57844/arcadia-570f-5cfb · Cited by 3
Evolutionary algorithms accelerate de novo design of potent Nectin-4-specific cancer biologicsPreprint
Tan, E., Frechen, S. C., Broske, B., Messmer, J. M., Kempchen, T. N., McEnroe, B. A., Ferber, D., Waluga, L., Below, E., Hoch, A., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.04.709551 · Cited by 4
Systematic Validation of AlphaFold-Predicted Interactomes with LUCIAPreprint
Zhang, T., Kraft, J., Soh, T. K., Kansy, M., Jonsson, I., & Bosse, J. B. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.02.716051 · Cited by 3
Evolutionary transfer learning enables organism-wide inference of mammalian enhancer landscapesPreprint
Qiu, C., Daza, R. M., Welsh, I. C., Patwardhan, R. P., Martin, B. K., Li, T. W., Yang, S., Mannens, C. C. A., Winter, S. D., Kempynck, N., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.62329/hxkk6249 · Cited by 4
Improving AlphaFold3 by Engineering MSA and Template InputsPreprint
Neupane, P., Liu, J., & Cheng, J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.22.720119 · Cited by 4
AMix-2: Establishing Protein as a Native Modality in Large Language ModelsPreprint
Qiu, K., Wu, Y., Wang, L., Ouyang, Y., Yu, J., Zhou, Z., Lv, C., Xue, D., Song, Y., Zhang, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.30963 · Cited by 4
Shin, W.-H., Kagaya, Y., Jang, W., & Kihara, D. (2026) · Journal of Cheminformatics · doi:10.1186/s13321-026-01224-3 · Cited by 3
Li, G., McWilliams, M., Rodrigues, M., Mearkle, B., Jaafar, N., Golla, V., Yu, H., Yang, H., Ayhan, D. H., Allen, K., et al. (2023) · doi:10.1101/2023.02.14.528535 · Cited by 3
Xia, Y., Pu, Y., Wang, S., Zhuang, J., Liu, D., Hou, M., & Zhang, G. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169128 · Cited by 2
AlphaMut: A Deep Reinforcement Learning Model to Suggest Helix-Disrupting Mutations
Bhargav, P., & Mukherjee, A. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01387 · Cited by 2
ECOD: Classification of domains in AFDB Swiss-Prot structure predictions
Schaeffer, R. D., Zhang, J., Cong, Q., & Grishin, N. V. (2026) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1013431 · Cited by 2
“The outstanding performance of AlphaFold2 at CASP14 [15] and the subsequent development of software such as RoseTTAFold [16], ESMFold [17], and AlphaFold3 [18] has led to the widespread prediction of large protein sets resulting in resources such as the AlphaFold Protein Structure Database (AFDB)…”
Self-citationComputational design of Bax-inhibiting peptides
Vlaar, T., Mayer, B., van der Heide, L., & Ilie, I. M. (2025) · Materials Advances · doi:10.1039/d4ma01142b · Cited by 2
Introduction of multiple disulfide bonds increases the thermostability of transglutaminase
Ono, T., Takahashi, K., Hirao, Y., Mihara, Y., Abe, I., Shirasawa, A., & Sugiki, M. (2025) · Scientific Reports · doi:10.1038/s41598-025-07842-5 · Cited by 2
“Previously, it was essential to utilize experimental structural information; however, the introduction of AlphaFold2 or RoseTTAfold reduced this limitation 20,21 .”
Comparative Analysis of Deep Generative Model for Industrial Enzyme Design
Zhang, B., Meng, Q., Ai, C., Duan, G., Wang, E., & Guo, F. (2024) · Current Bioinformatics · doi:10.2174/0115748936303223240404043202 · Cited by 2
The study of iron‐ and copper‐binding proteome of Fusarium oxysporum and its effector candidates
Kushwah, A. S., Dixit, H., UPADHYAY, V. K., Verma, S. K., & Prasad, R. (2024) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26696 · Cited by 2
Al‐Madhagi, H., Kanawati, A., & Tahan, Z. S. (2024) · Journal of Cellular and Molecular Medicine · doi:10.1111/jcmm.18452 · Cited by 2
“The vaccine protein was modelled using RoseTTafold platform and then validated by Ramachandran plot and other assessment parameters generated from SWISSMODEL in addition to ProsA server.”
MethodArchitecture of RabL2‐associated complexes at the ciliary base: A structural modeling perspective
Boegholm, N., Petriman, N.-A., Tanvir, N. M., & Lorentzen, E. (2024) · BioEssays · doi:10.1002/bies.202300222 · Cited by 2
Artificial intelligence-driven health research innovations: Protein sciences
Liu, F., Zhang, G., Liu, Z., Li, C., & Huang, X. (2024) · Medicine Plus · doi:10.1016/j.medp.2024.100043 · Cited by 2
Jácome, R. (2024) · Journal of Molecular Evolution · doi:10.1007/s00239-024-10207-7 · Cited by 3
Recent advances in the integration of protein mechanics and machine learning
Chen, Y., & Chang, S. (2024) · Extreme Mechanics Letters · doi:10.1016/j.eml.2024.102236 · Cited by 3
Aguilera-Durán, G., Hernández-Castro, S., Loera-García, B. V., Rivera-Vargas, A., Alvarez-Baltazar, J. M., Cuevas‐Flores, M. D. R., & Romo‐Mancillas, A. (2024) · Journal of Molecular Modeling · doi:10.1007/s00894-024-06165-y · Cited by 2
“Each server built five models, from which model 1 from each server was selected for quality evaluations and at the end select the best model for further studies [34–36].”
Abulimiti, B., An, H., Yaermaimaiti, G., Kadir, A., Wei, J., Xiang, M., Long, J., Zhang, S., & Zhang, B. (2024) · Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy · doi:10.1016/j.saa.2024.125279 · Cited by 2
Ma, K., Liu, J., Huang, Z., Wu, M., Liu, D., Ren, J., Fan, A., & Lin, W. (2024) · Chemical Science · doi:10.1039/d4sc05590j · Cited by 2
Nematodes exposed to furfural acetone exhibit a species-specific vacuolar H+-ATPase response
Cheng, W., Dai, W., Chen, W., Xue, H., Zhao, Z., Jiang, Z., Li, H., Liu, J., Huang, F., Cai, M., et al. (2024) · Ecotoxicology and Environmental Safety · doi:10.1016/j.ecoenv.2024.117407 · Cited by 2
Gomes, A. A. S., Costa, M. G. S., Louet, M., Floquet, N., Bisch, P. M., & Pérahia, D. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01054 · Cited by 2
Gupta, S., Akhoon, B. A., Sharma, D., Singh, D., Kaul, S., & Dhar, M. K. (2024) · Steroids · doi:10.1016/j.steroids.2024.109557 · Cited by 2
AMPed up immunity: 418 whole genomes reveal intraspecific diversity of koala antimicrobial peptides
Petrohilos, C., Peel, E., Silver, L. W., Belov, K., & Hogg, C. J. (2025) · Immunogenetics · doi:10.1007/s00251-024-01368-2 · Cited by 2
“Three-dimensional structures of the active peptides with non-synonymous SNPs were predicted using RoseTTAFold (Baek et al. 2021) and visualized using Chimera 1.18 (Pettersen et al. 2004) (Supplementary File 7 and Supplementary File 8).”
InfluentialModeling the Possible: Perspectives from Philosophy of Science
Knuuttila, T., Grüne‐Yanoff, T., Koskinen, R., & Wirling, Y. S. (2025) · Routledge eBooks · doi:10.4324/9781003342816 · Cited by 3
Kostelac, A., Hermann, E., Peterbauer, C., Oostenbrink, C., & Haltrich, D. (2025) · FEBS Journal · doi:10.1111/febs.70004 · Cited by 2
“The initial structural predications of the Ka POx and Sc POx monomers were made with ROSETTAFOLD (https://robetta.bakerlab. org/submit.php, accessed in August 2023) [24].”
Pipatthana, M., Phanchana, M., Sangphukieo, A., Charoensutthivarakul, S., Harnvoravongchai, P., Chankhamhaengdecha, S., Prangthip, P., Konpetch, P., Sripong, C., Wongphayak, S., et al. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.02.036 · Cited by 2
“Homology modeling and de novo prediction approaches from SWISS-MODEL [7], i-TASSER [8], trRosetta [9], Robetta [10], ModWeb [11], RoseTTAFold [12], and AlphaFold [13] were used.”
Structural Biology: Current Trends and Future Perspectives
Mishra, A., Khan, K., & Kumar, D. (2025) · Springer eBooks · doi:10.1007/978-981-96-2088-3_11 · Cited by 3
Structural insights on perlecan and Schwartz–Jampel syndrome
Sohail, A. A., Koski, M. K., & Ruddock, L. W. (2025) · Matrix Biology · doi:10.1016/j.matbio.2025.03.002 · Cited by 2
Lebedenko, O. O., Polovinkin, M. S., Kazovskaia, A. A., & Skrynnikov, N. R. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26821 · Cited by 2
Beeby, M., & Daum, B. (2025) · Biomolecules · doi:10.3390/biom15040465 · Cited by 2
De novo rescue of new henipaviruses under BSL-4 conditions – From sequence to pathogen
Haas, G. D., & Lee, B. (2025) · Advances in virus research · doi:10.1016/bs.aivir.2025.03.004 · Cited by 2
Pawlik, A., Drozd, R., & Janusz, G. (2025) · Biomolecules · doi:10.3390/biom15040531 · Cited by 2
“The prediction of the 3D structure of the bacterial laccase was performed via the Robetta server using a fast and accurate deep learning-based method RoseTTAFold [45].”
Crystal Structure Prediction Using a Self-Attention Neural Network and Semantic Segmentation
Zhao, W., Zhou, M., Shao, J., Ren, J., Hu, Y., Han, Y., & Man, Y. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c02345 · Cited by 2
Computer‐Aided Technology for Bioactive Protein Design and Clinical Application
Wang, C., Chen, Y., & Ren, L. (2025) · Macromolecular Bioscience · doi:10.1002/mabi.202500007 · Cited by 4
Bridging Dimensionality Reduction and Stochastic Sampling: The DA2-MC Algorithm for Protein Dynamics
Shen, R., Zhu, Q., Hu, L., Ma, J., Wang, W., & Dong, H. (2025) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5c00921 · Cited by 2
Versatile Imidazole Scaffold with Potent Activity against Multiple Apicomplexan Parasites
Khim, M., Montgomery, J., de Souza, M. L., Delvillar, M., Weible, L. J., Prabakaran, M., Hulverson, M. A., Eck, T., Bheemanabonia, R. Y., Alday, P. H., et al. (2025) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.5c00049 · Cited by 2
Gardnerella fibrinogen-binding protein as a candidate adherence factor
Bulavaitė, A., Dapkūnas, J., Reškevičiūtė, R., Dalgėdienė, I., Valančauskas, L., Baranauskienė, L., & Plečkaitytė, M. (2025) · Frontiers in Cellular and Infection Microbiology · doi:10.3389/fcimb.2025.1556232 · Cited by 2
“…where AlphaFold 2 did not produce con fi dent models, additional structure modeling was performed using a ColabFold-based pipeline incorporating multiple sequence alignments from metagenomic data (Olechnovic ̌ et al, 2023), RoseTTAFold (Baek et al., 2021), and AlphaFold 3 (Abramson et al., 2024).”
Molecular insights into the corin function at the uteroplacental interface
Dong, N., Du, M., & Wu, Q. (2025) · Placenta · doi:10.1016/j.placenta.2025.05.006 · Cited by 2
Progress and challenges for the application of machine learning for neglected tropical diseases
Khew, C., Akbar, R., & Mohd‐Assaad, N. (2025) · F1000Research · doi:10.12688/f1000research.129064.2 · Cited by 2
GOBeacon : An ensemble model for protein function prediction enhanced by contrastive learning
Lin, W., Miller, D., Gu, Z., & Orengo, C. A. (2025) · Protein Science · doi:10.1002/pro.70182 · Cited by 7
“Recent advances in protein structure prediction (Baek et al., 2021; Jumper et al., 2021) have made protein contact maps and 3D structures more accessible.”
System Theoretic Methods in Drug Discovery and Vaccine Formulation: Review and Perspectives
Sharma, A., Hsiao, Y.-C., & Dutta, A. (2025) · Drugs and Drug Candidates · doi:10.3390/ddc4030028 · Cited by 2
Leitz, A., Kav, B., Liu, X., Fatafta, H., Jankowski, V., Aggeler, B., Gao, Y., Martin, I. V., Vogt, K., Kramann, R., et al. (2025) · Protein Science · doi:10.1002/pro.70188 · Cited by 2
“Homology modeling using the Robetta web server (Baek et al., 2021) was used to obtain structural models as the starting point for the respective MD simulation, since only the CSD is available in structural databases.”
Cryo-Electron Microscopy-Based Epitope Mapping
Drulyte, I., & Hurdiss, D. L. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4591-8_4 · Cited by 4
Liu, W., Wang, Z., You, R., Xie, C., Wei, H., Xiong, Y., Yang, J., & Zhu, S. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4623-6_14 · Cited by 4
Brubaker, J. K., Booth, K. E. C., Arakawa, A., Furrer, F., Ghosh, J., Sato, T., & Katzgraber, H. G. (2025) · Scientific Reports · doi:10.1038/s41598-025-05565-1 · Cited by 5
“We stepped across peptide sizes N ∈ [4 , 10] and M ∈ [0 , 10], with N = 4 being the minimum length required for a complete cycle (assuming side chains exist) and N = 10 being the full length of the peptide, and M being the number of protein residues included (with M = 0 meaning the protein was…”
Haarmann, M., Scholz, M., Lienkamp, A. C., Burnik, J., Justesen, B. H., Reiners, J., Maier, A., Eggerichs, D., Vocke, K. U., Smits, S. H. J., et al. (2025) · ACS Catalysis · doi:10.1021/acscatal.5c02430 · Cited by 2
Cooper, A., Powers, A., Battaile, K. P., Mohsen, A.-W. A., Johnson, D. K., Lovell, S., & Ghaloul‐Gonzalez, L. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70023 · Cited by 2
“A previous computationally derived structure using RoseTTAFold [10] suggested that TANGO2 adopts an N-terminal nucleophile aminohydrolase (Ntn) tertiary fold, implying a potentially similar hydrolase functional component, that is, hydrolysis of carbon-nitrogen amide bonds [11, 12].”
Cryo-EM led analysis of open and closed conformations of Chagas vaccine candidate TcPOP
Batra, S., Olmo, F., Ragan, T. J., Kaplan, M., Calvaresi, V., Frank, A. M., Lancey, C., Assadipapari, M., Ying, C., Struwe, W. B., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-62068-3 · Cited by 2
“Comparative homology models were obtained with SWISS-MODEL 40 , and when it became available to the scienti fi c community, AlphaFold2 was used to obtain AI-based models 41 .”
Engineering Peptide Modulators for T-Cell Migration by Structural Scaffold Matching
Gattringer, J., Hasinger, S., Weidmann, A., Walczewska-Szewc, K., Jadhav, K. B., Zrzavy, T., Steinmaurer, A., Baeten, P., Perisic, M., Cochrane, W., et al. (2025) · Journal of Medicinal Chemistry · doi:10.1021/acs.jmedchem.5c00677 · Cited by 2
Algebras of actions in an agent's representations of the world
Dean, A., Alonso, E., & Mondragón, E. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2025.104403 · Cited by 2
“The main methods used to integrate symmetries into a representation are to build symmetries into the architecture of learning algorithms [40, 41], use data-augmentation that encourages the model to learn symmetries [42, 43], or to adjust the model’s learning objective to encourage the…”
Rana, T. R. K., & Rajaraman, G. (2025) · Progress in theoretical chemistry and physics · doi:10.1007/978-3-031-85167-4_8 · Cited by 2
Understanding domain swapping in the c-Src SH3 domain through hinge-loop mutagenesis
Salinas-García, M. C., Plaza-Garrido, M., Martínez, J. C., & Cámara-Artigas, A. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325006977 · Cited by 2
Quantum Osteoimmunology: A Paradigm Shift in Understanding and Influencing Bone–Immune Crosstalk
Li, R., Alzaanin, S., Yin, Z., & Smith, P. N. (2025) · ChemMedChem · doi:10.1002/cmdc.202500307 · Cited by 2
Dias, L. M. S., Abranches, D. O., Bastos, A. R. N., Fu, L., Neto, A. N. C., Pereira, R. F. P., Bermudez, V. D. Z., Towe, E., Ferreira, R. A. S., & André, P. S. D. B. (2025) · Journal of Physics Photonics · doi:10.1088/2515-7647/ae0104 · Cited by 4
A Critical Look at the Crystal Structures of cAMP-Dependent Protein Kinases
Wlodawer, A., Rubach, P., Dauter, Z., Dec, W., Minor, W., Brzeziński, D., & Jaskólski, M. (2025) · Kinases and Phosphatases · doi:10.3390/kinasesphosphatases3030019 · Cited by 2
“The whole contents of the PDB have been used for training artificial intelligence-based structure prediction systems such as AlphaFold [4], RoseTTAFold [5], ESMFold [6], and other similar programs.”
Structure prediction and engineering of de novo proteins
Qi, L., & Isalan, M. (2025) · Biochimica et Biophysica Acta (BBA) - Proteins and Proteomics · doi:10.1016/j.bbapap.2025.141100 · Cited by 2
LeBlanc, C. J., Agarwal, P., Demaray, J., Hu, G. F., Zintel, M. A., Lam, A., Hernandez, J. E. C., & Staller, M. V. (2026) · Cell Systems · doi:10.1016/j.cels.2026.101701 · Cited by 3
Targeting the unexplored 'dark proteome': Novel approaches in drug discovery
Singh, D. (2025) · Current Proteomics · doi:10.1016/j.curpro.2025.100020 · Cited by 2
Diverse conformational ensembles define the shared folding-allosteric landscapes of protein kinases
Chaurasiya, D. K., & Naganathan, A. N. (2025) · Biophysical Journal · doi:10.1016/j.bpj.2025.09.035 · Cited by 4
AlphaFold3-guided optimization of a photoactivatable endonuclease for top-down genome engineering
Yone, H., Kono, H., Sato, M., & Ohta, K. (2025) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2025.110762 · Cited by 2
“…prediction tools has been introduced: RoseTTAFold employs a three-track neural network to integrate sequence, distance, and coordinate information (3); ESMFold leverages protein language models to generate high-quality structures directly from single sequences without requiring multiple sequence…”
Yang, Y., Kang, D., Mihalache, B., Vexler, S., Jain, S., Peng, H., Annabi, N., Yang, S., & Chen, I. A. (2025) · Nucleic Acids Research · doi:10.1093/nar/gkaf984 · Cited by 3
Reaction Engineering of In Vitro Natural Product Biosynthesis: Challenges and Strategies
Sánchez‐García, E., Lütz, S., & Nett, M. (2025) · ChemBioChem · doi:10.1002/cbic.202500571 · Cited by 2
Thermophilic Chassis-Enabled High-Throughput Selection of a Thermostable Fluorogenic Reporter
Shin, S., Triola, E.-K. H., Granja‐Travez, R. S., López, C. A., Wood, N. M., Riley, L. A., Guss, A. M., Dale, T., & Jha, R. K. (2025) · ACS Synthetic Biology · doi:10.1021/acssynbio.5c00573 · Cited by 2
Generative Artificial Intelligence for Function-Driven De Novo Enzyme Design
Xuan, Q., De-hang, W., Shi, Z., Xiaoping, L., & Ma, H. (2025) · Synthetic biology and engineering · doi:10.70322/sbe.2025.10015 · Cited by 4
Probe-based identification of metal-binding sites using deep learning representations
Xu, S., & Onoda, A. (2026) · Nature Communications · doi:10.1038/s41467-026-74657-x · Cited by 2
Habib, A., Xu, X., Xie, J., & Zhu, N. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26199828 · Cited by 2
“The technology provides a comprehensive understanding of a protein’s structure by allowing information to move between one, two-, and 3D levels [69].”
A survey of ADP-ribosyltransferase families in the pathogenic Legionella
Krysińska, M., Gradowski, M., Baranowski, B., Pawłowski, K., & Dudkiewicz, M. (2025) · BMC Genomics · doi:10.1186/s12864-025-11994-z · Cited by 2
“The structures of representative proteins from new ART-like families were modelled with the use of two different tools: AlphaFold (Jumper et al., 2021) and RoseTTAFold (Baek et al., 2023).”
Haltom, J., Trovão, N. S., Guarnieri, J. W., Pan, V., Singh, U., Tsoy, S., O’Leary, C. A., Bram, Y., Widjaja, G. A., Cen, Z., et al. (2025) · Molecular Biology and Evolution · doi:10.1093/molbev/msaf211 · Cited by 2
“…network-2 (RGN2) (Chowdhury et al. 2022), a language and deep learning model that surpasses AlphaFold2 (Jumper et al. 2021) and RoseTTAFold (Baek et al. 2021) in predicting orphan gene protein structures (Chowdhury et al. 2022), to infer 3D structures for the WT ORF10 protein and for the…”
AbTune: layer-wise selective fine-tuning of protein language models for antibodies
Xu, X., & Bonvin, A. M. J. J. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag374 · Cited by 2
Kaneko, N., Himeno, M., Kobayashi, Y., Tanifuji, R., Kubota, H., Mizoguchi, H., Muroi, M., Suzuki, T., Sugiyama, M., Dohmae, N., et al. (2025) · RSC Chemical Biology · doi:10.1039/d5cb00268k · Cited by 2
Burgin, T. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01813 · Cited by 2
The proteome-scale study of iron-binding proteins of bread wheat
Bharti, A. K., & Verma, S. K. (2025) · Metallomics · doi:10.1093/mtomcs/mfaf036 · Cited by 3
Olfactory GPCRs through the lens of structural bioinformatics
Nicoli, A., Bößl, F., Moschen, A. D. C., Ferri, F., Rienaecker, C., & Pizio, A. D. (2025) · Chemical Senses · doi:10.1093/chemse/bjaf038 · Cited by 2
Unraveling the molecular mechanism of in situ surface-initiated thrombogenesis
Hansen, A., Kementzidis, G., Essuman, B., Niu, Z., Sheriff, J., Chernyshenko, V. O., Deng, Y., Rafailovich, M. H., & Galanakis, D. K. (2025) · Journal of Thrombosis and Haemostasis · doi:10.1016/j.jtha.2025.09.042 · Cited by 2
Pacheco, J. E., Saha, S., Lee, J. Y., Culhane, K. J., Bahar, İ., & Vilardaga, J. (2025) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2025.110913 · Cited by 2
“We mutated LAPTH to PTH, and the missing residues of PTH 1 R (L56–R104, G247–A275, and A394–D398) were constructed using Robetta (34) and ModLoop (35).”
Effect of stereochemical constraints on the structural properties of folded proteins
Logan, J. A., Sumner, J., Grigas, A. T., Shattuck, M. D., & O’Hern, C. S. (2025) · Physical review. E · doi:10.1103/9wf9-ywhw · Cited by 2
Completion of partial structures using Patterson maps with the CrysFormer machine-learning model
Pan, T., Dramko, E., Miller, M. D., Kyrillidis, A., & Phillips, G. N., Jr. (2025) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798325009659 · Cited by 2
Targeting SOX9: designing a novel vaccine against triple-negative breast cancer
Hatamian, G., Ebrahimpour, A., Nejabat, M., & Hadizadeh, F. (2025) · Scientific Reports · doi:10.1038/s41598-025-25499-y · Cited by 2
A multimodal framework for comprehensive driver variant prediction in cancer
Yang, H., Chen, Y., Zhou, T., Wang, Y., Zhou, Q., Xiao, T., Zhang, Q., Zhang, J., Li, D., & Wang, Z. (2025) · Communications Medicine · doi:10.1038/s43856-025-01209-7 · Cited by 2
Peptide screening, design, and application for detecting small-molecule contaminants in food
Shao, Y., Wang, M., She, Y., Cao, Z., Jin, F., Jin, M., Wang, J., & El‐Aty, A. M. A. (2025) · Trends in Environmental Analytical Chemistry · doi:10.1016/j.teac.2025.e00290 · Cited by 2
Self-citationNovel computational pipeline to identify target sites for broad spectrum antiviral drugs
(2025) · doi:10.1016/j.antiviral.2025.106322 · Cited by 2
Two-Component Systems in Pasteurellaceae and Their Roles in Virulence
Martin, E. M., Guerrero-Barrera, A. L., & Avelar-González, F. J. (2025) · Veterinary Sciences · doi:10.3390/vetsci12121140 · Cited by 2
Chattopadhyay, A., Fatehi, M., Mosa, F. E. S., Gruber, B., Light, P. E., & Barakat, K. (2025) · Scientific Reports · doi:10.1038/s41598-025-30298-6 · Cited by 2
“To generate a comprehensive full-length model, we utilized the Swiss-Model server 11,12 and Robetta 13 , integrating deep learning tools AlphaFold 14 and RoseTTAFold 13 .”
Decoding protein binding plasticity via integrated deep ribosome display and deep learning
Tang, M., Li, J., Li, Z., Cui, J., & Qi, H. (2025) · Communications Biology · doi:10.1038/s42003-025-09160-y · Cited by 2
Repetitive proteins that undergo large conformational changes evade structural prediction algorithms
Chang, M. P., Jin, T., Gudinas, A. P., Fernández, D., Alexander‐Katz, A., Matsui, T., & Mai, D. J. (2025) · The Journal of Chemical Physics · doi:10.1063/5.0304777 · Cited by 2
Mulvaney, T., Kryshtafovych, A., & Topf, M. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.70099 · Cited by 2
“Although adopted as standard since CASP15, other estimates of model accuracy also exist, such as the RosettaFold estimate of positional error (the smaller the better) [18].”
On the Variation of Structural Divergence Among Residues in Enzyme Evolution
Echave, J., & Carpentier, M. (2026) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.70103 · Cited by 2
“However, machine learning methods have substantially improved both the speed and accuracy of protein structure prediction, making structural data more accessible [18–22].”
Expanding the Molecular and Pathologic Spectrum of HSPB8 Myopathy and Distal Motor Neuropathy
Putko, B. N., Sorenson, E. J., Cui, G., Liewluck, T., Niu, Z., Litchy, W. J., Mer, G., & Milone, M. (2025) · Neurology Genetics · doi:10.1212/nxg.0000000000200332 · Cited by 2
IHMValidation: Assessment of Integrative Structure Models Deposited to the Protein Data Bank
Zalevsky, A. O., Vallat, B. K., Webb, B., Tangmunarunkit, H., Sekharan, M. R., Shafaeibejestan, A., Ganesan, S. J., Sagendorf, J. M., Jeffries, C. M., Trewhella, J., et al. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169598 · Cited by 3
Computational Peptide Design for Diverse Structures and Functions
Rettie, S., Juergens, D., & Bhardwaj, G. (2025) · Wiley eBooks · doi:10.1002/9781119824701.ch05 · Cited by 3
From Knowledge Tree to Knowledge Forest: Harnessing Chemical Understanding with Machine Learning
Zhao, D., Zhao, Y., Rong, C., Zhang, H., Liu, C., & Liu, S. (2025) · Acta Physico-Chimica Sinica · doi:10.1016/j.actphy.2025.100233 · Cited by 2
Wu, J., Sun, J., Liang, T., Zhang, Y., Zhang, H., Zhang, T., Feng, X., Gao, P., Xu, P., & Li, J. (2025) · Chemical Science · doi:10.1039/d5sc08898d · Cited by 2
Han, B.-G., Tran, T. T. P., & Kim, B. C. (2025) · Journal of the Korean Physical Society · doi:10.1007/s40042-025-01553-w · Cited by 2
A Brief Introduction to the Convergence of Artificial Intelligence and Biotechnology
Marcellin, M. C., Pescaroli, G., Schmidt, M., Trump, B. D., Tubbs, T. B., Villegas-Torres, M. F., Lambert, J. H., Haggenmiller, C., Blume, Y. B., Kamrud, A. J., et al. (2026) · NATO science for peace and security series. A, Chemistry and biology · doi:10.1007/978-3-032-05246-9_2 · Cited by 3
Struct2GO-Enhanced: Multimodal Graph Attention Improves Protein Function Prediction
Shi, Z., Vo, T. H., Le, N. Q. K., & Chua, M. C. H. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c02419 · Cited by 3
Kolossváry, I. (2026) · PNAS Nexus · doi:10.1093/pnasnexus/pgaf408 · Cited by 3
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.