Accurate prediction of protein structures and interactions using a 3-track network
Open accessThe DOI matches its Crossref record; 85 of the 85 references it cites were found in a registry or an index; 13 of the 36 sources its claims cite were checked for support.
Abstract
DeepMind presented remarkably accurate protein structure predictions at the CASP14 conference. We explored network architectures incorporating related ideas and obtained the best performance with a 3-track network in which information at the 1D sequence level, the 2D distance map level, and the 3D coordinate level is successively transformed and integrated. The 3-track network produces structure predictions with accuracies approaching those of DeepMind in CASP14, enables rapid solution of challenging X-ray crystallography and cryo-EM structure modeling problems, and provides insights into the functions of proteins of currently unknown structure. The network also enables rapid generation of accurate models of protein-protein complexes from sequence information alone, short circuiting traditional approaches which require modeling of individual subunits followed by docking. We make the method available to the scientific community to speed biological research. One-Sentence Summary: Accurate protein structure modeling enables rapid solution of structure determination problems and provides insights into biological function.
Overview
CoChat Summary
TL;DR
RoseTTAFold is a 3-track neural network that integrates 1D sequence, 2D distance-map, and 3D coordinate information to predict protein structures and interactions. It approaches AlphaFold2 accuracy in CASP14, solves challenging crystallography and cryo-EM modeling problems, and generates protein-complex models directly from sequence.
Key findings
- In CASP14, the 3-track RoseTTAFold outperformed the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), the BAKER human group, and the authors’ 2-track models, though its performance was still not as good as AlphaFold2.
- On CAMEO, over 69 medium and hard targets released May 15–June 19, 2021, RoseTTAFold outperformed all other evaluated servers, including Robetta, IntFold6-TS, BestSingleTemplate, and SWISS-MODEL.
- RoseTTAFold models enabled molecular-replacement solutions for four previously unsolved crystallographic datasets; for the cryo-EM p101 Gβγ binding domain, the Cα-RMSD between predicted and refined structure was 3.0 Å over the beta-sheets.
- Among 693 domains from human disease-related proteins, over one-third had predicted lDDT > 0.8, corresponding to an average Cα-RMSD of 2.6 Å on CASP14 targets; many protein-complex models had TM-score > 0.8, with complex generation taking ~30 min on a 24G TITAN RTX GPU.
Methods
- The 3-track network transforms and integrates information at the 1D sequence/MSA level, the 2D distance/orientation-map level, and the 3D backbone-coordinate level, with information flowing between tracks; training used discontinuous sequence crops spanning 260 residues.
- Final 3D structures were generated either by feeding predicted distance/orientation distributions into pyRosetta for all-atom models or by an end-to-end SE(3)-equivariant layer producing backbone coordinates directly.
- Evaluation included CASP14 targets, CAMEO blind server assessment, four X-ray molecular-replacement datasets, a cryo-EM PI3Kγ complex, GPCRs, 693 human disease-related domains, and paired-sequence complexes of known structure, using accuracy comparisons, Cα-RMSD, lDDT, TM-score, and MR/cryo-EM fit.
Limitations
- Stated: hardware memory limitations constrained model size and training; performance remained below AlphaFold2; the end-to-end version was less accurate than the pyRosetta version due to incomplete optimization and neglect of side-chain information; the accuracy predictor did not consistently identify models better than the rapid single-pass method; the network was trained on monomeric proteins, not complexes; and current RoseTTAFold uses only the top 1000 sequences due to memory limits.
- Stated: the Perceiver-based extension for using all available sequences gave promising initial results, but more training is required for rigorous comparison.
- Evident: CASP14 and CAMEO evaluations cover limited target sets and time windows, and the end-to-end model does not produce side chains.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
3 Valid · 8 Not valid · 14 Not checked · 44 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The bi-annual Critical Assessment of Structure (CASP) meetings have demonstrated that deep learning methods such as AlphaFold (1, 2) and trRosetta (3), that extract information from the large database of known protein structures in the PDB, outperform more traditional approaches that explicitly model the folding process.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Abstract
What the sources say
- Not matchedcites [1] Jumper John Evans Richard Pritzel Alexander Green Tim Figurnov Michael Tunyasuvunakool Kathryn Ronneberger Olaf Bates Russ Augustin Žídek Alex Bridgland Clemens Meyer Fourteenth Critical Assessment of Techniques for Protein Structure Prediction
Its entry has no title and year that we can search by.
- Partly supportedcites [2] Anishchenko I Chidyausiku TM Ovchinnikov S Pellock SJ Baker D De novo protein design by deep network hallucination bioRxiv 2020 2020.07.22.211482 PMC9293396 34853475 sourceExperimental — accuracy not yet measured
The Introduction (page not provided) says deep networks improved protein-structure prediction accuracy, notes an AlphaFold observation at CASP13, and reports that trRosetta outperformed other methods in benchmark tests. The Conclusion says the network learned from native protein structures and contrasts it with physically based approaches. The paper does not establish the claimed CASP comparison in which both AlphaFold and trRosetta outperform approaches that explicitly model folding. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [3] Yang J Anishchenko I Park H Peng Z Ovchinnikov S Baker D Improved protein structure prediction using predicted interresidue orientations Proc Natl Acad Sci U S A 2020 117 1496 1503 31896580 PMC6983395 source
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“The RoseTTAFold CERS1 model for residues 98 to 304 (Pfam TLC domain) (29) includes six TMH that traverse the membrane in an up and down arrangement (Fig. 3E).”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Providing insights into biological function
What the sources say
- Could not verifycites [29] Cong Q Anishchenko I Ovchinnikov S Baker D Protein interaction networks revealed by proteome coevolution Science 2019 365 185 189 31296772 PMC6948103 sourceExperimental — accuracy not yet measured
The paper’s Abstract (page unavailable) describes coevolution-based protein interaction models in E. coli and M. tuberculosis, not a CERS1 model. Searches for CERS1, the Pfam TLC domain, RoseTTAFold, and six transmembrane helices found no passage in our copy addressing the cited domain identification or the stated membrane arrangement. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“in the case of SLP, only a distant model covering part of the N-terminal domain (38% of the sequence) was available in the PDB”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“trRosetta failed to predict the correct fold with the same MSA input (fig. S6)”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Enabling experimental protein structure determination
plainSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The 3-track models with attention operating at the 1D, 2D, and 3D levels and information flowing between the three levels were the best models we tested (Fig. 1B), clearly outperforming the top 2 server groups (Zhang-server and BAKER-ROSETTASERVER), BAKER human group (ranked second among all groups), and our 2-track attention models on CASP14 targets.”
§ Accurate prediction of protein structures and interactions using a 3-track neural network > Network architecture development
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
33 more claims
Create a free account to see all 69 claims and to verify the 2 references still open.
- It may state two separate claims as one. 24
- Probably not a substantial claim. 13
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“RF has properties well suited for use in a protein design DDPM (Fig. 1a): it generates protein structures with high precision, operates on a rigid-frame representation of residues with rotational equivariance and has an architecture enabling conditioning on design specifications at the individual residue, inter-residue distance and orientation, and 3D coordinate levels.”
From De novo design of protein structure and function with RFdiffusion (2023) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“are the best and most accurate answer to the structure prediction problem to date”
From The power and pitfalls of AlphaFold2 for structure prediction beyond rigid globular proteins (2024) · cites this paper as [18]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“DeepMind’s AlphaFold2 success in sequence-based protein structure prediction,4 as well as the RoseTTAFold70 open-source counterpart, and the publicly available AlphaFold2 prediction of all human proteins203 are major steps that benefit the scientific community.”
From AlphaFold, Artificial Intelligence (AI), and Allostery (2022) · cites this paper as [70]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The unprecedented accuracy of AlphaFold2,127 RosettaFold,128 and others129,130 offers, at least in principle, the opportunity to virtually screen any protein of interest with the structure-based approach, irrespective of its a priori ligandability (after AlphaFold2, the structural coverage of the human proteome increased from 48% to 76% of the total residues).131”
From Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence (2023) · cites this paper as [128]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The programs were also shown to accurately assess their confidence at the level of individual residues and interdomain contacts (27,28,62).”
From AI-based structure prediction empowers integrative structural analysis of human nuclear pores (2022) · cites this paper as [27]
Experimental — accuracy not yet measured
17 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability
Katoh, K., & Standley, D. M. (2013) · Molecular Biology and Evolution · doi:10.1093/molbev/mst010 · Cited by 46,209
Features and development of Coot
Emsley, P., Lohkamp, B., Scott, W. G., & Cowtan, K. (2010) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910007493 · Cited by 29,915
Clustal W and Clustal X version 2.0
Larkin, M. A., Blackshields, G., Brown, N. P., Chenna, R., McGettigan, P. A., McWilliam, H., Valentin, F., Wallace, I. M., Wilm, A., Lopez, R., et al. (2007) · Bioinformatics · doi:10.1093/bioinformatics/btm404 · Cited by 28,358
Phaser crystallographic software
McCoy, A. J., Grosse-Kunstleve, R. W., Adams, P. D., Winn, M. D., Storoni, L. C., & Read, R. J. (2007) · Journal of Applied Crystallography · doi:10.1107/s0021889807021206 · Cited by 20,612
Self-citationSWISS-MODEL: homology modelling of protein structures and complexes
Waterhouse, A., Bertoni, M., Bienert, S., Studer, G., Tauriello, G., Gumienny, R., Heer, F. T., de Beer, T. A. P., Rempfer, C., Bordoli, L., et al. (2018) · Nucleic Acids Research · doi:10.1093/nar/gky427 · Cited by 13,067 · cited 2×
“Fortunately,theContinuousAutomated ModelEvaluation(CAMEO)experiment( 7 ) tests structure prediction servers blindly on protein structures as they are submitted to the PDB. RoseTTAFold has been evaluated since 15 May 2021 on CAMEO; over the 69 medium and hard targets released during this time (15 May 2021 to 19 June 20…”
UCSF ChimeraX: Structure visualization for researchers, educators, and developers
Pettersen, E. F., Goddard, T. D., Huang, C. C., Meng, E. C., Couch, G. S., Croll, T. I., Morris, J. H., & Ferrin, T. E. (2021) · Protein Science · doi:10.1002/pro.3943 · Cited by 9,514
Liebschner, D., Afonine, P. V., Baker, M. L., Bunkóczi, G., Chen, V. B., Croll, T. I., Hintze, B., Hung, L.-W., Jain, S., McCoy, A. J., et al. (2019) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798319011471 · Cited by 7,953
Self-citationUniProt: the Universal Protein knowledgebase
Apweiler, R. (2004) · Nucleic Acids Research · doi:10.1093/nar/gkh131 · Cited by 7,498
Towards automated crystallographic structure refinement with phenix.refine
Afonine, P. V., Grosse-Kunstleve, R. W., Echols, N., Headd, J. J., Moriarty, N. W., Mustyakimov, M., Terwilliger, T. C., Urzhumtsev, A., Zwart, P. H., & Adams, P. D. (2012) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444912001308 · Cited by 5,511
Self-citation
Research works printed but not linked: 2
- Bunkóczi G Read RJ phenix. ensembler: a tool for multiple superposition Comput Crystallogr Newsl 2011 2 8 9
- Vagin A Lebedev A ACTA CRYSTALLOGRAPHICA A-FOUNDATION AND ADVANCES INT UNION CRYSTALLOGRAPHY 2 ABBEY SQ, CHESTER, CH1 2HU ENGLAND 2015 71 S19
Cited by
Items 1,901–2,000 of 5,636
Systems biology of Haemonchus contortus – Advancing biotechnology for parasitic nematode control
Zheng, Y., Young, N. D., Wang, T., Chang, B. C. H., Song, J., & Gasser, R. B. (2025) · Biotechnology Advances · doi:10.1016/j.biotechadv.2025.108567 · Cited by 15
Gong, P., Gao, M., Chen, Y., Zhang, M., Huang, Y., Hu, X., Zhao, S., Zhang, H., Pan, M., Cao, B., et al. (2025) · Science China Life Sciences · doi:10.1007/s11427-024-2892-1 · Cited by 14
“With the development of bioinformatics and computational biology, artificial intelligence (AI)-driven protein structure prediction tools including AlphaFold2 (AF2) (Jumper et al., 2021) and RoseTTAFold (Baek et al., 2021) have shown immense potential to identify cross-kingdom interactions.”
Mao, Q., Shang, T., Xu, W., Zhai, S., Zhang, C., Guo, J., Su, A., Li, C., & Duan, H. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c00139 · Cited by 18
Mask-prior-guided denoising diffusion improves inverse protein folding
Bai, P., Miljković, F. N., Liu, X., Maria, L. D., Croasdale-Wood, R., Rackham, O. J. L., & Lu, H. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01042-6 · Cited by 15
“For example, RFdiffusion 17 fine-tunes the protein structure prediction network RoseTTAFold 18 under a denoising diffusion framework to generate 3D protein backbones, and torsional diffusion 19 implements a diffusion process on the space of torsion angles for molecular conformer generation.”
MIC: A deep learning tool for assigning ions and waters in cryo-EM and crystal structures
Shub, L., Liu, W., Skiniotis, G., Keiser, M. J., & Robertson, M. J. (2025) · Nature Communications · doi:10.1038/s41467-025-61315-x · Cited by 15
Luo, Y., & Cai, J. (2025) · Current Proteomics · doi:10.2174/0115701646374018250227075247 · Cited by 15
Jiao, S., Ye, X., Sakurai, T., Zou, Q., Han, W., & Zhan, C. (2025) · BMC Biology · doi:10.1186/s12915-025-02329-1 · Cited by 14
AI sheds new light on genome editing
Qin, Z. S., Deng, Z., Li, C., Wang, D., Ji, X., & Chen, Z. (2025) · Trends in biotechnology · doi:10.1016/j.tibtech.2025.07.011 · Cited by 16
Harnessing CRISPR-Cas systems for point-of-care diagnostic applications
Ghouneimy, A., Aman, R. A., Jiang, W., Ali, Z., & Mahfouz, M. M. (2025) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2025.118417 · Cited by 18
Shugaeva, T. E., Howard, R. J., Haloi, N., & Lindahl, E. R. (2025) · Communications Chemistry · doi:10.1038/s42004-025-01751-4 · Cited by 14
PYTHIA: Deep Learning Approach for Local Protein Conformation Prediction
Cretin, G., Galochkina, T. V., de Brevern, A. G., & Gelly, J. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22168831 · Cited by 14
Zhao, Y., Miao, Y., Zhi, F., Pan, Y., Zhang, J., Yang, X., Zhang, J. Z. H., & Zhang, L. (2021) · Frontiers in Physics · doi:10.3389/fphy.2021.755253 · Cited by 14
Using machine‐learning‐driven approaches to boost hot‐spot's knowledge
Rosário‐Ferreira, N., Bonvin, A. M. J. J., & Moreira, I. S. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1602 · Cited by 13
“At that time, RoseTTA Fold debut with comparable performance to AlphaFold, the possibility to predict protein–protein complexes, and availability as a public server.(206) DeepMind took one step further and released AlphaFold-Multimer, a model that aims to predict multichains protein complexes contrasting to their orig…”
BackgroundMethodInfluentialZhang, H., Hao, M., Wu, H., Ting, H., Tang, Y., Xi, W., & Wei, Y. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2021.9010064 · Cited by 16
An in-membrane NMR spectroscopic approach probing native ligand-GPCR interaction
Wang, X., Bushra, N., Muschol, M., Madsen, J. J., & Ye, L. (2022) · International Journal of Biological Macromolecules · doi:10.1016/j.ijbiomac.2022.03.099 · Cited by 14
Sánchez-García, R., Macías, J. R., Sorzano, C. Ó. S., Carazo, J. M., & Segura, J. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2022.167556 · Cited by 14
Wang, L., Xu, L., Su, B., Xu, X., & Lin, J. (2022) · Molecular Catalysis · doi:10.1016/j.mcat.2022.112355 · Cited by 15
Rotem‐Bamberger, S., Fahoum, J., Keinan‐Adamsky, K., Tsaban, T., Avraham, O., Shalev, D. E., Chill, J. H., & Schueler‐Furman, O. (2022) · Journal of Biological Chemistry · doi:10.1016/j.jbc.2022.102145 · Cited by 14
“We also generated additional models using a range of different approaches, including RoseTTAFold (http://new. robetta.org (40)), TrRosetta (https://yanglab.nankai.edu.cn/ trRosetta (39)), and ab initio Rosetta folding under constraints derived by GREMLIN (http://gremlin.bakerlab.org) (38).”
MethodProgressive membrane-binding mechanism of SARS-CoV-2 variant spike proteins
Overduin, M., Kervin, T. A., & Tran, A. (2022) · iScience · doi:10.1016/j.isci.2022.104722 · Cited by 14
Glycine Substitution of Residues with Unfavored Dihedral Angles Improves Protein Thermostability
Zhi-li, L., Zhong, Q., Li, J., Zhou, B., Xing, Y.-N., Liu, K., Cao, K., Lan, D., Zhou, T., Wang, Y., et al. (2022) · Catalysts · doi:10.3390/catal12080898 · Cited by 14
Self-citationAssessment of AI-Based Protein Structure Prediction for the NLRP3 Target
Yin, J., Lei, J., Yu, J., Cui, W., Satz, A. L., Zhou, Y., Feng, H., Deng, J., Su, W., & Kuai, L. (2022) · Molecules · doi:10.3390/molecules27185797 · Cited by 14
“AI methods for protein structure predictions, including AlphaFold (AF) [2] and RoseTTAFold (RF) [3], have attracted tremendous interest for their ability to accurately predict protein structures, without relying on structural templates with high sequence similarity.”
BackgroundRalston, C. Y., & Sharp, J. S. (2022) · Antibodies · doi:10.3390/antib11040071 · Cited by 14
Visualizing Intramolecular Dynamics of Membrane Proteins
Ohkubo, T., Shiina, T., Kawaguchi, K., Sasaki, D., Inamasu, R., Yue, Y., Li, Z., Taninaka, K., Sakaguchi, M., Fujimura, S., et al. (2022) · International Journal of Molecular Sciences · doi:10.3390/ijms232314539 · Cited by 14
The structure of the high-affinity nickel-binding site in the Ni,Zn-HypA•UreE2 complex
Zambelli, B., Basak, P., Hu, H. Q., Piccioli, M., Musiani, F., Broll, V., Imbert, L., Boisbouvier, J., Maroney, M. J., & Ciurli, S. (2023) · Metallomics · doi:10.1093/mtomcs/mfad003 · Cited by 14
Loss of CpFTSY Reduces Photosynthetic Performance and Affects Insertion of PsaC of PSI in Diatoms
Nymark, M., Finazzi, G., Volpe, C., Serif, M., Fonseca, D. D. M., Sharma, A., Sánchez, N., Sharma, A. K., Ashcroft, F. J., Kissen, R., et al. (2023) · Plant and Cell Physiology · doi:10.1093/pcp/pcad014 · Cited by 14
Deep, A., Singh, L., Kaur, J., Maheshwaran, V., Bhardwaj, P., Singh, R., & Thakur, K. G. (2023) · Structure · doi:10.1016/j.str.2023.04.008 · Cited by 14
Unanticipated broad phylogeny of BEN DNA-binding domains revealed by structural homology searches
Pan, A., Zeng, Y., Liu, J., Zhou, M., Lai, E. C., & Yu, Y. (2023) · Current Biology · doi:10.1016/j.cub.2023.05.011 · Cited by 14
Residue-level error detection in cryoelectron microscopy models
Reggiano, G., Lugmayr, W., Farrell, D. P., Marlovits, T. C., & DiMaio, F. (2023) · Structure · doi:10.1016/j.str.2023.05.002 · Cited by 14
Self-citationRexha, J., Perta, N., Roscioni, A., Motta, S., Teana, A. L., Maragliano, L., Romagnoli, A., & Marino, D. D. (2023) · Advanced Sensor Research · doi:10.1002/adsr.202300053 · Cited by 16
M Protein from Dengue virus oligomerizes to pentameric channel protein: in silico analysis study
Zeba, A., Sekar, K., & Ganjiwale, A. D. (2023) · Genomics & Informatics · doi:10.5808/gi.23035 · Cited by 14
“RoseTTA fold was used to develop the abinitio model [17].”
MethodZhao, X., Zhang, K., Zhang, H., Bi, M., He, Y., Cui, Y., Tan, C., Ma, J., & Qi, M. (2023) · Frontiers in Plant Science · doi:10.3389/fpls.2023.1283489 · Cited by 15
“RosetaTTAFold (Baek et al., 2021) was used for modeling, and con fi dence scores were 0.81 and 0.78, respectively.”
MethodInfluentialKespohl, B., Hegele, A., Düsterhöft, S., Bakker, H., Buettner, F. F. R., Hartig, R., Lokau, J., & Garbers, C. (2023) · FEBS Journal · doi:10.1111/febs.17015 · Cited by 16
Debroy, B., Chowdhury, S., & Pal, K. (2023) · Journal of Genetic Engineering and Biotechnology · doi:10.1186/s43141-023-00575-w · Cited by 21
Exploring structure-based drug discovery of GPCRs beyond the orthosteric binding site
Chen, Z., Ren, X., Zhou, Y., & Huang, N. (2024) · hLife · doi:10.1016/j.hlife.2024.01.002 · Cited by 15
“However, advancements in structural biology technologies have led to the release of 1102 experimental structures for 180 unique GPCRs (as of June 2023), along with a wealth of easily accessible arti fi - cial intelligence (AI)-predicted structures [2 – 4].”
Machine learning as a tool in theoretical science
Douglas, M. R. (2022) · Nature Reviews Physics · doi:10.1038/s42254-022-00431-9 · Cited by 14
Expanding the Database of Signal-Anchor-Release Domain Endolysins Through Metagenomics
Gontijo, M. T. P., Teles, M. P., Vidigal, P. M. P., & Brocchi, M. (2022) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-022-09948-y · Cited by 14
Moving towards reproducible machine learning
(2021) · Nature Computational Science · doi:10.1038/s43588-021-00152-6 · Cited by 18
De novo design of RNA and nucleoprotein complexesPreprint
Favor, A., Quijano, R. N., Chernova, E., Kubaney, A., Weidle, C., Esler, M. A., McHugh, R., Carr, A., Hsia, Y., Juergens, D., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.01.679929 · Cited by 17
Self-citationMatsuura, H., Sakai, N., Toma-Fukai, S., Muraki, N., Hayama, K., Kamikubo, H., Aono, S., Kawano, Y., Yamamoto, M., & Hirata, K. (2023) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798323007039 · Cited by 14
Two mosquito odorant receptors with reciprocal specificity mediated by a single amino acid residue
Franco, F. P., Xu, P., Harris, B. J., Yarov-Yarovoy, V., & Leal, W. S. (2022) · doi:10.1101/2022.03.22.485336 · Cited by 14
Rao, A., Lyu, B., Jahan, I., Lubertozzi, A., Zhou, G., Tedeschi, F., Jankowsky, E., Kang, J., Carstens, B., Poss, K. D., et al. (2023) · Development · doi:10.1242/dev.201376 · Cited by 13
AlphaFold2 modeling and molecular dynamics simulations of an intrinsically disordered protein
Guo, H.-B., Huntington, B., Perminov, A., Smith, K., Hastings, N., Dennis, P., Kelley-Loughnane, N., & Berry, R. (2024) · PLOS ONE · doi:10.1371/journal.pone.0301866 · Cited by 13
Sedaghat, N., & Etemadifar, M. (2022) · Multiple Sclerosis and Related Disorders · doi:10.1016/j.msard.2021.103341 · Cited by 13
Recent advances in the inference of deep viral evolutionary history
Mifsud, J. C. O., Suchard, M. A., Holmes, E. C., & Lemey, P. (2025) · Journal of Virology · doi:10.1128/jvi.00292-25 · Cited by 16
TCRdesign: an antigen-specific generative language model for de novo design of T-cell receptors
Li, X., Yang, Q., Xu, L., Dong, W., Wang, K., Dong, S., Wang, W., Luo, G., Zhang, X., Yang, T., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf691 · Cited by 19
Reproducibility, validation, and failure modes across classical and AI-driven molecular docking
Kittelson, K. S., Martins, A. C. F., Santos, R. P., Celante, G., & Gomes, R. D. S. (2026) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-026-00849-8 · Cited by 17
Arif, S. M., Floto, R. A., & Blundell, T. L. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.857000 · Cited by 13
Recent progress in strategies for steroid production in yeasts
Jiang, Y., & Lin, J. (2022) · World Journal of Microbiology and Biotechnology · doi:10.1007/s11274-022-03276-7 · Cited by 13
BindWeb : A web server for ligand binding residue and pocket prediction from protein structures
Xia, Y., Xia, C., Pan, X., & Shen, H. (2022) · Protein Science · doi:10.1002/pro.4462 · Cited by 13
A cold‐active esterase enhances mesophilic properties through Mn 2+ binding
Marchetti, A., Orlando, M., Mangiagalli, M., & Lotti, M. (2022) · FEBS Journal · doi:10.1111/febs.16661 · Cited by 13
Sowa, S. T., Bosetti, C., Galera‐Prat, A., Johnson, M. S., & Lehtiö, L. (2022) · Biomolecules · doi:10.3390/biom12111688 · Cited by 13
Molecular Dynamics Simulation of Protein Cages
Lu, C., Xue, P., & Lu, D. (2023) · Methods in molecular biology · doi:10.1007/978-1-0716-3222-2_16 · Cited by 13
Simpkin, A. J., Caballero, I., McNicholas, S. J., Stevenson, K., Jiménez, E., Rodríguez, F. S., Fando, M. S., Uski, V., Ballard, C. C., Chojnowski, G., et al. (2023) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798323006289 · Cited by 14
Jia, W., Peng, J., Zhang, Y., Zhu, J., Qiang, X., Zhang, R., & Shi, L. S. (2023) · Food Research International · doi:10.1016/j.foodres.2023.113640 · Cited by 13
Krokidis, M. G., Dimitrakopoulos, G. Ν., Vrahatis, A. G., Exarchos, T. P., & Vlamos, P. (2024) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2023.1323182 · Cited by 15
Protein thermal sensing regulates physiological amyloid aggregation
Marijan, D., Momchilova, E. A., Burns, D., Chandhok, S., Zapf, R., Wille, H., Potoyan, D. A., & Audas, T. E. (2024) · Nature Communications · doi:10.1038/s41467-024-45536-0 · Cited by 14
“However, despite remarkable advances in prediction tools 51,52 and theoretical models 53 the question remainslargelyunresolved 54,55 .”
Lin, P., Li, H., & Huang, S. (2024) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2024.102789 · Cited by 14
Key Proteomics Tools for Fundamental and Applied Microalgal Research
Plouviez, M., & Dubreucq, É. (2024) · Proteomes · doi:10.3390/proteomes12020013 · Cited by 13
“0 generate protein structure fast and accurately [137], preventing the need for the laborious, time-consuming and expensive experimental techniques for protein structure determination such as X-ray crystallography [136].”
MethodZhang, B., Hou, Z., Yang, Y., Wong, K., Zhu, H., & Li, X. (2024) · Communications Biology · doi:10.1038/s42003-024-06332-0 · Cited by 13
Machine learning in biological physics: From biomolecular prediction to design
Martin, J., Mateos, M., Onuchic, J. N., Coluzza, I., & Morcos, F. (2024) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2311807121 · Cited by 18
Gastrointestinal jumbo phages possess independent synthesis and utilization systems of NAD+
Li, C., Liu, K., Gu, C., Li, M., Zhou, P., Chen, L., Sun, S., Li, X., Wang, L., Ni, W., et al. (2024) · Microbiome · doi:10.1186/s40168-024-01984-w · Cited by 18
“For RoseTTAFold predictions, run_e2e_ver.sh script was used to predict the three-dimensional structure of NAMPT and NadD proteins [41].”
Protein design accelerates the development and application of optogenetic tools
Zhu, L., Wang, Y., Wu, X., Wu, G., Zhang, G., Liu, C., & Zhang, S. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.02.014 · Cited by 13
“The groundbreaking work of AlphaFold has also catalyzed the development of other AI models for protein structure prediction by setting a new benchmark for accuracy and efficiency, such as RoseTTAFold [171] and OpenFold [172].”
Pang, Y. T., Yang, L., Kuo, K. M., & Gumbart, J. C. (2026) · Chemical Science · doi:10.1039/d5sc08253f · Cited by 13
Ali, N. F., Khan, S., & Zahid, S. (2025) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2025.108430 · Cited by 13
Xu, S., & Onoda, A. (2025) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.4c01288 · Cited by 13
Artificial intelligence in de novo protein design
Yao, J., & Wang, X. (2025) · Medicine in Novel Technology and Devices · doi:10.1016/j.medntd.2025.100366 · Cited by 16
Therapeutic peptides and their delivery using lipid-based nanoparticles
Yen, J.-H., Chang, C., Wu, T., Yang, C.-H., Hsu, H., & Liou, J.-W. (2025) · Tzu Chi Medical Journal · doi:10.4103/tcmj.tcmj_321_24 · Cited by 13
Predicting the structures of cyclic peptides containing unnatural amino acids by HighFold2
Zhu, C., Cao, S., Shang, T., Guo, J., Su, A., Li, C., & Duan, H. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf202 · Cited by 13
“Tools such as AlphaFold2 [9], AlphaFold-Multimer [10], RoseTTAFold [11], and ESMFold [12] have achieved remarkable accuracy in predicting the structures of protein monomers and protein–protein complexes.”
Liu, Y., Moretti, R., Wang, Y., Dong, H., Yan, B., Bodenheimer, B., Derr, T., & Meiler, J. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00822 · Cited by 13
From data to discovery: leveraging big data in plant natural products biosynthesis research
McConnachie, M. M., Nguyen, T. M., Kim, T., Nguyen, T., & Dang, T. T. (2025) · The Plant Journal · doi:10.1111/tpj.70288 · Cited by 14
“AI-based protein structure predictors, such as Alpha-Fold (Jumper et al., 2021), ESMFold (Lin et al., 2023), and RoseTTAFold (Baek et al., 2021), hold significant promise for advancing plant biosynthetic pathway elucidation, particularly in predicting enzyme functions.”
Zhang, C., Wang, W., Zhu, N., Cao, Z., Wu, Y., Mao, Q., Zhu, C., Zhang, C., Guo, J., & Duan, H. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01393 · Cited by 18
The Roles of EDA2R in Ageing and Disease
Farrington, G., Tonge, L., Branagan, T., Sudirman, S., Fang, C., Luk, L. Y. P., Kır, S., Bolis, M., Ahmetov, I. I., & Ross, K. (2025) · Aging Cell · doi:10.1111/acel.70282 · Cited by 17
“RoseTTAFold (Baek et al. 2021), from the University of Washington, follows a similar principle but uses a lighter, modular architecture that processes sequence, pair, and 3D data simultaneously.”
A survey on memory-efficient transformer-based model training in AI for science
Tian, K., Qiao, L., Liu, B., Jiang, G., Li, S., & Li, D. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-025-50302-6 · Cited by 16
“Although AlphaFold2 and RoseTTAFold [40] achieved break-throughs in atomic resolution structure prediction, they rely on MSA and similar protein structure templates to achieve better performance.”
Swarms of large language model agents for protein sequence design with experimental validation
Wang, F. Y., Lee, D. S., Kaplan, D. L., & Buehler, M. J. (2026) · Digital Discovery · doi:10.1039/d6dd00282j · Cited by 17
Tran, N. H., Xu, J., & Li, M. (2021) · Briefings in Bioinformatics · doi:10.1093/bib/bbab493 · Cited by 14
Kang, B., Seok, C., & Lee, J. (2022) · Bulletin of the Korean Chemical Society · doi:10.1002/bkcs.12468 · Cited by 13
Li, Z., Sun, C., Lou, L., & Li, Z. (2022) · Biotechnology and Bioengineering · doi:10.1002/bit.28061 · Cited by 13
P-Loop Channels: Experimental Structures, and Physics-Based and Neural Networks-Based Models
Tikhonov, D. B., & Zhorov, B. S. (2022) · Membranes · doi:10.3390/membranes12020229 · Cited by 13
Mosaic Evolution of Beta-Barrel-Porin-Encoding Genes in Escherichia coli
Chen, X., Cai, X., Chen, Z., Wu, J., Hao, G., Luo, Q., Liu, S., Zhang, J., Hu, Y., Zhu, G., et al. (2022) · Applied and Environmental Microbiology · doi:10.1128/aem.00060-22 · Cited by 13
Encoding protein dynamic information in graph representation for functional residue identification
Chiang, Y., Hui, W.-H., & Chang, S. (2022) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2022.100975 · Cited by 13
Modulating albumin-mediated transport of peptide-drug conjugates for antigen-specific Treg induction
Lau, C. Y. J., Benne, N., Lou, B., Zharkova, O., Ting, H. J., ter Braake, D., van Kronenburg, N. C. H., Fens, M. H. A. M., Broere, F., Hennink, W. E., et al. (2022) · Journal of Controlled Release · doi:10.1016/j.jconrel.2022.06.025 · Cited by 15
Self-citationDade, C. M., Douzi, B., Cambillau, C., Ball, G., Voulhoux, R., & Forest, K. T. (2022) · Acta Crystallographica Section D Structural Biology · doi:10.1107/s2059798322007033 · Cited by 14
Anti-trypanosomatid structure-based drug design – lessons learned from targeting the folate pathway
Panecka-Hofman, J., Poehner, I., & Wade, R. C. (2022) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2022.2113776 · Cited by 22
“the significant advances in predictive power of new protein structure prediction methods, such as AlphaFold [115] and RoseTTAfold [116].”
MethodLooking for SARS-CoV-2 Therapeutics Through Computational Approaches
Vincenzi, M., Mercurio, F. A., & Leone, M. (2022) · Current Medicinal Chemistry · doi:10.2174/0929867329666221004104430 · Cited by 13
Synthetic Biology Meets Machine Learning
Sieow, B. F., Sotto, R. D., Seet, Z. R. D., Hwang, I. Y., & Chang, M. W. (2022) · Methods in molecular biology · doi:10.1007/978-1-0716-2617-7_2 · Cited by 16
Srinivasan, S., Ghosh, C., Das, S., Thakare, A., Singh, S., Ganesh, A., Mahawar, H., Jaisimha, A., Krishna, M., Chattopadhyay, A., et al. (2022) · Scientific Reports · doi:10.1038/s41598-022-23780-y · Cited by 13
Mann, L., Ganapathy, U. S., Abdelaziz, R., Lang, M. A., Zimmerman, M., Dartois, V. A., Dick, T., & Richter, A. (2022) · Microbiology Spectrum · doi:10.1128/spectrum.02760-22 · Cited by 13
Zhu, F., Ma, S., Wen, H., Rao, M., Zhang, P., Peng, W., Cui, Y., Yang, H., Tan, C., Chen, J., et al. (2022) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2022.2154846 · Cited by 16
“To obtain the three-dimensional structure of a protein, the Robetta server (https://robetta.baker-lab.org/) was used to construct the protein model (Baek et al., 2021), and the PROCHECK server (https://www.ebi.ac.uk/thorn-ton-srv/software/PROCHECK/), the ERRAT server (https://saves. mbi.ucla.edu/),…”
MethodWeraduwage, S. M., Sahu, A., Kulke, M., Vermaas, J. V., & Sharkey, T. D. (2023) · Plant Direct · doi:10.1002/pld3.483 · Cited by 13
“The initial protein structure was homology modeled with the RoseTTAfold web server (Baek et al., 2021) and solvated in explicit water.”
Functional Protein Dynamics Directly from Sequences
Jia, K., Kilinc, M., & Jernigan, R. L. (2023) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c05766 · Cited by 13
Modulation of Allosteric Control and Evolution of Hemoglobin
Brunori, M., & Miele, A. E. (2023) · Biomolecules · doi:10.3390/biom13030572 · Cited by 13
“The “future” proved that Perutz’s vision was correct, and due to the open data accumulated in public databases, artificial intelligence algorithms such as ECOD (Evolutionary Classification Of protein Domains [49]), AlphaFold [50] and RoseTTA Fold [51,52] can now predict with accuracy structural features based on the a…”
BackgroundMészáros, B., Park, E., Malinverni, D., Sejdiu, B. I., Immadisetty, K., Sandhu, M., Lang, B., & Babu, M. M. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102608 · Cited by 13
Chiliveri, S. C., Shen, Y., Baber, J. L., Ying, J., Sagar, V., Wistow, G. J., Anfinrud, P., & Bax, A. (2023) · Journal of the American Chemical Society · doi:10.1021/jacs.3c05710 · Cited by 14
Small Molecules against Metastatic Tumors: Concrete Perspectives and Shattered Dreams
Serra, M., Rubes, D., Schinelli, S., & Paolillo, M. (2023) · Cancers · doi:10.3390/cancers15164173 · Cited by 13
The energetics and evolution of oxidoreductases in deep time
McGuinness, K. N., Fehon, N., Feehan, R., Miller, M., Mutter, A. C., Rybak, L. A., Nam, J., AbuSalim, J. E., Atkinson, J. T., Heidari, H., et al. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26563 · Cited by 13
Recent Advances in Structural Studies of Single-Stranded RNA Bacteriophages
Thongchol, J., Lill, Z., Hoover, Z., & Zhang, J. (2023) · Viruses · doi:10.3390/v15101985 · Cited by 17
Role of environmental specificity in CASP results
Roterman, I., Stąpor, K., & Konieczny, L. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05559-8 · Cited by 13
“The three-track neural network linking a one-dimensional sequence level with the distance map, and the coordinate level expressing the integration of these three approaches was applied in CASP14 with good results [26].”
Ricker, B., Mitra, S., Castellanos, E., Grady, C. J., Woldring, D., Pelled, G., & Gilad, A. A. (2023) · Open Biology · doi:10.1098/rsob.230019 · Cited by 13
“The structure of EPG was predicted using RoseTTAFold [28] protein structure prediction software and visualized with the PyMol molecular visualization system.”
MethodBiophysical and structural characterization of a multifunctional viral genome packaging motor
Prokhorov, N. S., Davis, C. R., Maruthi, K., Yang, Q., Sherman, M. B., Woodson, M., White, M. A., Miller, L. M., Jarrold, M. F., Catalano, C. E., et al. (2023) · Nucleic Acids Research · doi:10.1093/nar/gkad1135 · Cited by 13
“We used AI, machine learning-based structure prediction tools, including different implementations of Alphafold2 and Rosettafold, to predict the quaternary structure of the termi-nase protomer ( 60 , 69 , 70 ).”
MethodHormazábal-Abarza, F., Bustos, D., Rodríguez-Arriaza, F., Sáez, D., Urra, G., Parra-Palma, C., Méndez-Yáñez, Á., Ramos, P., & Morales‐Quintana, L. (2024) · Plant Physiology and Biochemistry · doi:10.1016/j.plaphy.2024.108417 · Cited by 13
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.