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 5,301–5,400 of 5,635
Characterizing the biophysical effects of mutations on the XPF-ERCC1 Complex
Pinto, É. S. M. (2024) · Lume (Universidade Federal do Rio Grande do Sul)
SteerAF: Distogram-based Steering of AlphaFold2 toward Alternative ConformationsPreprint
Tang, J., Zhu, Z., Yang, S., & Song, C. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.19.733296 · Cited by 1
Synzymes 2.0: Engineering catalytic function with artificial intelligence and advanced materials
Mohammad, S. F., Ali, F., & Shynara, M. (2026) · Biocatalysis and Biotransformation · doi:10.1080/10242422.2026.2688362
“…from large sequence corpora, these hybrid structure prediction models incorporate physical constraints (distance geometry, stereochemistry) alongside attention mechanisms, enabling accurate modelling of catalytic site geometry with RMSD values below 2.0 Å (Baek et al. 2021; Jumper et al. 2021).”
InfluentialIntegrating experimental and computational approaches for protein–protein interaction discovery
Rapti, A., Janssen, B. J. C., & Bonvin, A. M. J. J. (2026) · Nature Reviews Bioengineering · doi:10.1038/s44222-026-00464-0 · Cited by 4
“RoseTTAFold can reconstruct known protein complexes, including higher-order assemblies, such as the human IL-12 receptor complex 81 .”
Large reasoning models as thinking machines for medicine
Zhou, H.-Y., Rodman, A. M., Liu, P., Rajpurkar, P., Hu, Y., Wong, T. Y., & Topol, E. J. (2026) · Nature Biomedical Engineering · doi:10.1038/s41551-026-01701-y · Cited by 1
“In addition, AI-driven models are now widely applied in protein structure prediction 53,54 and de novo protein design 55,56 , expanding the range of potential drug candidates.”
Srinivas, P., Adebomi, V., Markiewicz, S. M., Wang, K., Chac, D., Lindenauer, K., Huber, N., Tao, Z., Luong, P., Rettie, S., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.22.733822
Biomedical knowledge graphs driving new target identification and novel drug discovery
Dou, P., Yang, X., Jiang, Y., Xie, X., Geng, X., Huang, H., Li, H., & Li, S. (2026) · Targetome · doi:10.48130/targetome-0026-0025 · Cited by 1
Slc44a2 Deficiency Unveils an IFN‐I–Dependent Feedback Control of pDC Egress
Chen, R., Wu, T., Shi, Z., Verma, R. K., Sheng, L., Tao, L., Yang, M., Wang, Y., Zhang, C., Fan, H., et al. (2026) · Advanced Science · doi:10.1002/advs.76325
Genomic scale analysis of assembly-line polyketide synthase diversity and evolution
Lee, S., & Khosla, C. (2026) · Natural Product Reports · doi:10.1039/d6np00052e
Methodology to study proteostasis
Raj, G., Tanti, G. K., & Jain, B. P. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-41553-1.00015-3
Nagi, R., Ozukum, A., Mondal, R., & Deb, C. R. (2026) · Journal of Plant Biochemistry and Biotechnology · doi:10.1007/s13562-026-01082-y
“Therefore, an attempt was made to predict the structure using the two best protein structure predictors (AlphaFold and RoseTTAFold) as per CASP14.”
InfluentialStructure-based pharmacophore modeling approaches using probe-based methods
Sukhorukov, M. V., Shulga, D. A., Morgunov, I. A., Ivanov, N. N., & Palyulin, V. A. (2026) · Russian Chemical Bulletin · doi:10.1007/s11172-026-4954-x
Gao, X., Wang, H., 战乐庆, Yu, J., Jiang, H., Zhangsun, D., Luo, S., & Zhu, X. (2026) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2026.118738
Belyaev, A. V., Bouchnita, A., & Volpert, V. A. (2026) · Biophysics Reviews · doi:10.1063/5.0285157
Artificial Intelligence in Drug Design: Emerging Trends and Applications
Gupta, J., Jain, S. D., Agrawal, A., & Gupta, A. K. (2026) · International Journal of Newgen Research in Pharmacy & Healthcare · doi:10.61554/ijnrph.v4i1.2026.235
“These systems analyse massive healthcare databases and social media information to detect any possible safety signals, which is much faster compared to traditional approaches [20].”
Integrating Mamba State-Space Models into Boltz for Enhanced 3D Protein Structure Prediction
Shaw, K., Ujlambkar, S., Amrutkar, S., Sovani, S., Kumar, S., & Wankhade, R. (2026) · International Conference on Connected Intelligence for Industrial Applications (CI2A) · doi:10.1109/ci2a69097.2026.11576873
“More recently, RoseTTAFold [3] created a 3-track architecture that would allow for exchange of information between three different representations of protein sequences, pairwise relationships of proteins and protein structural representations.”
Ashaolu, T. J. (2026) · Food Bioscience · doi:10.1016/j.fbio.2026.109400
Quiroga, C. (2025) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
A Comprehensive Evaluation of Protein Structure Prediction Models for Short PeptidesPreprint
Ghosh, B., & Mukherjee, A. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.02.736085 · Cited by 2
Chung, D. S., Park, J., Choi, W. J., & Hong, D. (2026) · Scientific Reports · doi:10.1038/s41598-026-60245-y
Expanding all-α-helical protein space through rational computational designPreprint
Albanese, K. I., Chubb, J. J., Gutierrez-Rus, L. I., Leng, X., Kurgan, K. W., Mylemans, B., Ożga, K., Petrenas, R., Romanyuk, A. V., Acevedo‐Jake, A. M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.03.736327
Liao, H., Cui, H.-X., Chen, L.-X., Duan, C.-S., Li, J., Zhao, S., Zhu, Y., & Su, J. (2026) · Nature Communications · doi:10.1038/s41467-026-75234-y · Cited by 1
Advancing the microalgal blue bioeconomy through technological and analytical integration
Kaur, P., Kaur, G., Kaur, J., Kaur, A., & Singh, L. (2026) · Preparative Biochemistry & Biotechnology · doi:10.1080/10826068.2026.2673214
“[189] Several software programs are available to evaluate the biotechnological potential of proteins and to characterize their specific functional features.”
Minhaz, S. P. B., Kheya, T. H., & Sharmin, S. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-31048-4_13
Zhang, Y., Xu, L., Gao, C., Zhang, T., Duan, S., Yin, Y., Yang, X., Sun, Q., Qin, X., Li, G., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.03.736362
Dou, Z., Wu, X., Wan, L., Gong, B., & Wang, L. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c01179
In vivo immune cell engineering from bench to clinical reality
Yu, H., Han, M., Zhao, X., Tang, C., Jia, Y., Jing, W., & Jiang, X. (2026) · Pharmaceutical Science Advances · doi:10.1016/j.pscia.2026.100131
“…lowered the threshold for obtaining target structures, enabling structure-based drug design (SBDD) to cover more targets and pathways related to immune regulation, and providing a designable space for the key molecular components required for in vivo immune cell engineering [162 – 164].”
Efficient Protein Structure Modelling and Analysis Using Graph Neural Networks
Desai, S., MutalikDesai, V., Jaya, A., Patil, A. M., Harlapur, O., Hungund, B. S., & Desai, S. S. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.06.253
Design-CP: Context Parallelism for Design of Protein NanoparticlesPreprint
Tarricone, L., Eisenach, H. E., Muraishi, A., & Deane, C. M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.05439
Quantum Artificial Intelligence for Protein Structure Prediction
Roosan, D., & Khan, R. I. (2026) · Springer eBooks · doi:10.1007/978-3-032-19536-4_5
Trust Without Safeguards: A Red-Teaming Study of ProteinMPNN in Open Protein Design Pipelines
Pope, T., & Patooghy, A. (2026) · International Conference on Dependable Systems and Networks workshops · doi:10.1109/dsn-w70714.2026.00040
“While these metrics do not guarantee biological function, they provide a practical proxy for structural consistency in computational design pipelines [14], [15].”
Evolving strategies for virus discovery
de Andrade, A. A. S., Silverj, A., Josephs, T., & Gregory, A. (2026) · Microbial Genomics · doi:10.1099/mgen.0.001785 · Cited by 1
“…for compiling databases of predicted viral protein structures, other methods showing comparable results are available, such as RoseTTAFold [134], ESMFold [135], Boltz-2 [136], Chai-1 (The Chai discovery team 2024), HelixFold3 [137], Protenix (The ByteDance AML AI4Science Team 2025),…”
Current diabetes drugs: Lessons learned and implications for next-generation therapeutics
Liao, J., Cong, Z., Liu, K., Que, H., & Liu, F. (2026) · The Innovation Drug Discovery · doi:10.59717/j.xinn-drugdisc.2026.100008
Unleashing the potential of S-layer proteins for engineered living materials
Nguyen, C. H. C., Suggs, O., & Ajo-Franklin, C. M. (2026) · Current Opinion in Microbiology · doi:10.1016/j.mib.2026.102789
Zhang, K. (2026) · Research Square · doi:10.21203/rs.3.rs-10307155/v1
Timofeev, A., Bratchikov, A., & Anufriev, A. (2026) · Physchem · doi:10.3390/physchem6030056
De Novo Synthesis in Cancer Immunotherapy: Applications and Prospects
Yang, J., Wu, Y., & Luo, J. (2026) · MedComm · doi:10.1002/mco2.70847
“Therefore, traditional methods remain tethered to the “evolutionary history” of known folds, limiting our ability to create entirely novel architectures tailored for synthetic immune circuits [ 15 ].”
STAGE: Semantic-to-Task Graph Enhancement for Heterogeneous Graph Contrastive Learning
Wan, E., Mo, X., & Tang, R. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3498-1_34
Wang, Z., Wang, Y., Shao, J., & Li, Z. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3498-1_33
Deep Learning Models Capture Umbrella Sampling-Derived Energetic Trends: A Troponin C Case Study
Narayanasamy, A., Moretti, R., Meiler, J., & Lindert, S. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c01925
Motif-Aware Graph Attention Networks for Hemolytic Peptide Prediction
Meng, Q., Tan, B., Ma, Y., & Guo, F. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3716-6_27
Multilevel in silico structural analysis of WNT proteins
Midlovets, K. K., Volkova, N., & Peka, M. (2026) · Current Research in Structural Biology · doi:10.1016/j.crstbi.2026.100196
Anderson, J., Rossi, M., & Clark, W. (2025) · International Journal of Pharmaceutical and Phytopharmacological Research · doi:10.51847/6jtpi8neii
Protein Design and Synthetic Biology
Wipat, A., & Hallinan, J. S. (2026) · Springer eBooks · doi:10.1007/978-3-032-11023-7_5
McBride, J. M., & Fitch, W. T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.12673
(2026) · Nature Computational Science · doi:10.1038/s43588-026-01031-8
Evaluation of AlphaFold3 for Predicting Human Heme-Binding Protein Structures
Nam, K. H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27146278
“Artificial intelligence (AI)–based prediction of protein structure, such as AlphaFold2 (AF2) [28], ESMFold [29], and RoseTTAfold [30], has opened new avenues for protein structure modeling with high accuracy.”
Ogawa, Y., & Shirai, T. (2026) · Current Opinion in Biotechnology · doi:10.1016/j.copbio.2026.103553
Xiao, J., Wang, W. B., Ma, Y. B., Dong, Z. Y., Li, J., Su, J. G., & Li, J. (2026) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.6c00754
Farrag, M. A. (2026) · Vector-Borne and Zoonotic Diseases · doi:10.1177/15303667261469037
“RoseTTAFold introduced a three-track network integrating 1D sequence, 2D distance/orientation, and 3D coordinate representations, allowing rapid and accurate predictions of monomer structures and protein – protein complexes (Table 2; Baek et al., 2021).”
Next-Generation Food Enzymology: From Metagenomic Discovery to AI-Driven Biocatalyst Design
Schwartz, M., Ladeira, R., Neiers, F., Nicolaı̈, A., Hocquet, D., & Loupiac, C. (2026) · Journal of Agricultural and Food Chemistry · doi:10.1021/acs.jafc.6c04349
Översti, S., Lytras, S., Kawakubo, S., Ito, J., & Ghafari, M. (2026) · Journal of Virology · doi:10.1128/jvi.01687-25 · Cited by 1
Schmidt, B. C., Pilgram, L., Babben, S., Trenner, J., Gago‐Zachert, S., Pezzini, F., Tueting, C., Behrens, S., Tahir, M., Grau, J., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.16.738854
Lowe, V. M., Smith, A. K., Parakra, R. D., Toci, E. M., Meyers, C. L. F., & Deredge, D. J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.14.738285
Pandey, B., & Tyagi, C. (2026) · Molecular Biotechnology · doi:10.1007/s12033-026-01594-x
Zhao, W., Pan, X., Yang, W., LIU, Z., Wei, X., Lin, A., Tang, B., Zhang, L., Xiao, M., Zeng, Q., et al. (2026) · Probiotics and Antimicrobial Proteins · doi:10.1007/s12602-026-11131-6
De Novo Design of Protein Nanopores: From Minimal Peptides to AI-Driven Design
Vorobieva, A. A., Samanta, R., & Thillo, T. V. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00990
Wang, T. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7008958
Intelligent antigen design combined with yeast display enhances targeted immune responses
Ma, Y.-F., Yin, G.-H., Pan, Y. L., & Liu, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag393
“The RMSD cutoff of 3 Å was selected based on commonly used criteria for assessing structural similarity and consistency in protein structure comparison studies [ 2, 20, 36, 37].”
Ensembles of in silico structures enable T cell peptide-MHC binding predictionPreprint
Lyudovyk, O., Levine, J., Pathil, M., Martis, S., Streltsov, A., Sethna, Z. M., Elhanati, Y., Balachandran, V., Morris, Q., & Greenbaum, B. D. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.14.738340 · Cited by 2
MOLECULAR DOCKING AS A TOOL FOR STRUCTURAL ELUCIDATION OF BIOACTIVE COMPOUNDS: A REVIEW
Ajibola, A., Lawal, R., Ojumah, E., & Ofili, C. (2026) · Zeugma Biological Science · doi:10.55549/zbs.1949886
Shan, Y., & Wang, Y. (2026) · IEEE International Conference on Pattern Recognition, Machine Vision and Artificial Intelligence (PRMVAI) · doi:10.1109/prmvai70103.2026.11605881
“Representative protein language models such as SeqVec [3], ESM [4] and ProtBert [5] have demonstrated strong performance in downstream biological tasks, including structure prediction [6],[7], functional annotation and signal peptide recognition.”
The use of artificial intelligence in advancing molecular biology in Africa: a narrative review
Awuah, D., Hounkpe, A., Anane-Asamoah, J., Dakubo, W. K., Adu, I. K., Barnie, P. A., Ansah, E. O., Fosu, K., Aidoo, C. O., Essien, V., et al. (2026) · Molecular Genetics and Genomics · doi:10.1007/s00438-026-02492-2
Siegert, J. A. J., Kelber, F., Vogginger, B., Eisenhuth, P., Beining, M., Ehrlich, V., Partzsch, J., Mayr, C., & Meiler, J. (2026) · Communications Chemistry · doi:10.1038/s42004-026-02122-3
Synthetic Biology: An Overview
Li, Z., Petersen, N. M., & Young, E. M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-24738-5.00099-9
Thai, K., Duong, C. Q., Nguyen, T. T. T., Tran, V.-T., Mai, Q.-M., & Le, M.-T. (2026) · Royal Society of Chemistry eBooks · doi:10.1039/9781837070206-00001 · Cited by 1
Machine Learning in Protein Structure Prediction
Thai, K., Nguyen, D.-N., Vo, T.-P., & Le, M.-T. (2026) · Royal Society of Chemistry eBooks · doi:10.1039/9781837070206-00064
Machine Learning in Molecular Dynamics Applications in Medicinal Chemistry
Amin, S. A., Kar, S., & Piotto, S. (2026) · Royal Society of Chemistry eBooks · doi:10.1039/9781837070206-00153
Huang, L., Li, Z.-M., Gao, L., Wang, S., Wu, Z., & Li, Z. (2026) · Life · doi:10.3390/life16071212
“In addition, AlphaFold and RoseTTAFold were used to predict the three-dimensional structure of Cs AcOAT for comparison and validation of the modeled structure [21,22].”
Methods for the establishment of enzymatic mechanisms – from QM to ML
Neves, R. P. P., Coimbra, J. T. S., Paiva, P., Raucci, U., Das, S., Calixto, A. R., Ribeiro, A. J. M., Sousa, J. P. M., Ferreira, P., Trizio, E., et al. (2026) · Chemical Science · doi:10.1039/d6sc02180h
Machine Learning Applications in Vaccine Design
Parvathy, P. S., Kumar, V. A., Biswas, R., & Mohan, C. G. (2026) · Royal Society of Chemistry eBooks · doi:10.1039/9781837070206-00682
Amrina, A., Mufti, A., & Khan, M. (2025) · Lingeduca Journal of Language and Education Studies · doi:10.70177/lingeduca.v4i2.3280
Shaminth Prasad, P., & Rao, R. (2026) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2026.2708778
Nam, K. H. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27156553
“This observation suggests that AI prediction tools do not simply replicate existing PDB structures; rather, they infer structurally and functionally plausible conformations based on broadly learned structural features, consistent with previous reports [26,29].”
Lu, S., Li, Y.-G., Tian, Z., Nan, X.-F., Zhou, Q., & Zhang, S.-T. (2026) · Computational and Structural Biotechnology Journal · doi:10.34133/csbj.0200
DirectContacts2: a wiring diagram of human physical protein interactions
Claussen, E. R., Woodcock-Girard, M. D., Fischer, S. M., & Drew, K. (2026) · Nature Communications · doi:10.1038/s41467-026-75863-3 · Cited by 2
In Silico Design and Quality Assessment of Rep Protein Models for African Cassava Mosaic Virus
Estrada‐Tejedor, R., Djida, A. P., & Closa, J. T. (2026) · Afinidad · doi:10.55815/980000013745
Echave, J., & Carpentier, M. (2026) · Molecular Biology and Evolution · doi:10.1093/molbev/msag162
The evolutionary processes of bacterial aromatic polyketide ketosynthases
Wang, X., Gao, Q., Ge, L., & Qin, Z. (2026) · Genome biology · doi:10.1186/s13059-026-04215-7
Carbonara: a SAXS-guided seeding framework for exploring protein solution-state dynamicsPreprint
Mckeown, J. J. C., Brown, C., Bale, A., Fisher, H., Rambo, R. P., Essex, J. W., Degiacomi, M. T., & Prior, C. B. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.25.740665
Discovery of a phenazine–thiol conjugase from sparse data using genome-informed machine learning
Shan, X., Trindade, I. B., Glasser, N. R., Thalhammer, K. O., Scurria, M., Mora, A., Conway, S. J., & Newman, D. K. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2607571123
Marien, J., Sritharan, S., Caviglia, B., Versini, R., Auclair, L., Barraud, P., Tisné, C., Reguei, A., Murail, S., Leclerc, F., et al. (2026) · Journal of Chemical Information and Modeling · doi:10.64898/2026.07.24.740587
Proteolytic activation of c-MYC facilitated by DOT1L
Sepulveda, G. P., Nawalaniec, K., Nikorich, I., Gushchanskaia, E. S., Mora-Martin, A., Esse, R., Ceballos, A., Xia, C., Kwan, J., Blum, B. C., et al. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2525603123
Zhang, Z., Cao, R., Sun, J., Chen, L., Xiang, L., Shen, Z., Lv, B., Qin, L., & Li, C. (2026) · Chinese Journal of Chemical Engineering · doi:10.1016/j.cjche.2026.07.004
WASP: a pipeline for functional annotation prediction based on AlphaFold structural models
Missier, G. D., Shabestary, K., & Ledesma‐Amaro, R. (2026) · Nature Communications · doi:10.1038/s41467-026-75956-z
Diffraction-quality, ultraflexible protein single crystals engineered with DNA
Han, Z., & Mirkin, C. A. (2026) · Science Advances · doi:10.1126/sciadv.aeh2948
“Given the empirical and often unpredictable nature of protein crystallization, an early application of this approach may involve using computational structure prediction tools, such as AlphaFold ( 42 , 43 ), to guide DNA modification at sites likely to promote DNA-directed crystallization.”
Kiran, H., Anwar, M. A., Ahmad, W., Jawad, I., Siddiqa, A., Imran, M., Rahman, M., & Saleem, M. S. (2026) · Biologia · doi:10.1007/s11756-026-02294-2
“Initially, three dimensional structures for AwGTF1, AwGTF2, AwGTF3, and GTFG2-F1 were explored using multiple protein structure prediction platforms, including Phyre2 (Kelley et al. 2015), SWISS-MODEL (Waterhouse et al. 2018), RosettaFold (Baek et al. 2021), and AlphaFold2 (Jumper et al. 2021) to compare model quality…”
Escaping our own biases: AI, scientific reasoning, and discovery in molecular biology
Costa, T. R. D., & Penadés, J. R. (2026) · Molecular Cell · doi:10.1016/j.molcel.2026.07.002 · Cited by 1
Teixeira, T. D. O., da Silva, R. C. C., Alves, M. C. S., Silva, R. D. A., Echeverria, J. E. S., & Simionatto, S. (2026) · Journal of Computer-Aided Molecular Design · doi:10.1007/s10822-026-00905-3
“Notable tools in this domain include AlphaFold2 [17, 18] and RoseTTAFold [19].”
Na, J., Jeong, M., & Kim, J. H. (2026) · Structural Dynamics · doi:10.1063/4.0001219
Li, W., Cadet, X. F., Medina-Ortiz, D., Davari, M. D., Sowdhamini, R., Bessafi, M., Damour, C., Li, Y., Miranville, A., de Brevern, A. G., et al. (2026) · International Journal of Molecular Sciences · doi:10.3390/ijms27167151 · Cited by 1
Yoon, H., Han, R., Kim, J.-W., & Lee, Y. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag421
SIRT1 Exon 2‐Encoded IDR Gates CREB‐Dependent Transcriptional Timing During Fasting
Shukla, A., Adhikari, S., Balaji, C., Chakrabarti, S., Kaur, A., Mondal, J., & Kolthur‐Seetharam, U. (2026) · The FASEB Journal · doi:10.1096/fj.202600254r
Elucidating enzyme–substrate specificity through co-folding foundation modelPreprint
Cheng, X., Seo, S., Huh, C., Chen, J., Jiang, S., Guo, P., Weng, J., Kim, W. Y., & Jin, W. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.07.30.741672
Han, Y., Ding, H., & Cui, X. (2026) · Food Bioscience · doi:10.1016/j.fbio.2026.109664
Going high-throughput: Dynamic conformations and interactions in vivo
Gong, Z., Zhao, Q., Sun, M., Zhang, B., Zhang, X., Zhang, L., Zhang, Y., & Liu, M. (2026) · Magnetic Resonance Letters · doi:10.1016/j.mrl.2026.200306
“In recent years, artificial intelligence-based structure prediction methods, exemplified by AlphaFold, have achieved large-scale modeling of folded proteins with considerable accuracy [5,6].”
Humanized Anti-PD-1 Antibodies Generated Using The Conditional Kernel-Elastic AutoencoderPreprint
Shi, Y., Li, H., Liu, P., Bunick, C., Tang, S., Wang, J., & Batista, V. S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.08.03.742579
Self-citationHu, R.-E., & Ng, I. (2026) · Chemical Engineering Journal · doi:10.1016/j.cej.2026.180351
TriGraphQA: A Triple Graph Learning Framework for Model Quality Assessment of Protein Complexes
Liang, L., & Zhao, K. B. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.6c00829
Rhobot-Screen: an integrated robotic platform for functional screening of rhodopsin variants
Nagata, T., Konno, M., Hashimoto, D. R., & Inoue, K. (2026) · BMC Biology · doi:10.1186/s12915-026-02691-8
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.