CoChat
Sign Up
Cited by 3Protein Structure and DynamicsMachine Learning in BioinformaticsComputational Drug Discovery Methods

The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.

Ab-initio amino acid sequence design from protein text description with ProtDAT

Open access
Guo, Xiao-Yu, Li, Yi-Fan, Liu, Yuan, Pan, Xiaoyong, Shen, Hong-Bin·2025·Nature Communications
DOI 10.1038/s41467-025-65562-w

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Protein design has become a critical method in advancing significant potential for various applications such as drug development and enzyme engineering. However, protein design methods utilizing large language models with solely pretraining and fine-tuning struggle to capture relationships in multi-modal protein data. To address this, we propose ProtDAT, a de novo fine-grained multi-modal data interaction framework capable of designing proteins from descriptive protein text input. ProtDAT builds upon the inherent characteristics of protein data to unify sequences and text as a cohesive whole rather than separate entities. It leverages a novel Multi-modal Cross-attention, integrating protein sequences and textual information for a foundational level and seamless integration. Evaluation metrics such as pLDDT, TM-score and RMSD are implemented to evaluate the structural plausibility, functionality, structural similarity, and validity of protein sequences. Experiments on 20,000 text-sequence pairs from Swiss-Prot within the ProtDAT framework demonstrate higher accuracy compared to the performance of the best method in the experiments, with a 23.34% increase in pLDDT, a 76.45% increase in TM-score, and a 24.41% reduction in RMSD.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-025-65562-w

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 44

  1. Lin, Z. et al. Language models of protein sequences at the scale of evolution enable accurate structure prediction. BioRxiv 2022, 500902 (2022).
  2. Orengo, C. A., Todd, A. E. & Thornton, J. M. From protein structure to function. Curr. Opin. Struct. Biol. 9, 374–382 (1999). · DOI
  3. Garagić, D. et al. Machine Learning Multi-Modality Fusion Approaches Outperform Single-Modality & Traditional Approaches. IEEE Aerospace Conference (pp. 1–9), 2021. · DOI
  4. Samish, I., MacDermaid, C. M., Perez-Aguilar, J. M. & Saven, J. G. Theoretical and computational protein design. Annu. Rev. Phys. Chem. 62, 129–149 (2011). · DOI
  5. Mizuguchi, K., Deane, C. M., Blundell, T. L., Johnson, M. S. & Overington, J. P. JOY: protein sequence-structure representation and analysis. Bioinformatics (Oxford, England) 14, 617–623 (1998). · DOI
  6. Sadowski, M. & Jones, D. The sequence–structure relationship and protein function prediction. Curr. Opin. Struct. Biol. 19, 357–362 (2009). · DOI
  7. Hesslow, D., Zanichelli, N., Notin, P., Poli, I. & Marks, D. Rita: a study on scaling up generative protein sequence models. arXiv Preprint arXiv:2205.05789 (2022). · arXiv
  8. Ferruz, N., Schmidt, S. & Höcker, B. ProtGPT2 is a deep unsupervised language model for protein design. Nat. Commun. 13, 4348 (2022). · DOI · Paper page
  9. Alamdari, S. et al. Protein generation with evolutionary diffusion: sequence is all you need. Preprint at BioRxiv, 2023.09.11.556673 (2023). · DOI · Paper page
  10. Hayes, T. et al. Simulating 500 million years of evolution with a language model. Science, 387, eads0018 (2025). · DOI · Paper page
  11. Liu, S. et al. A text-guided protein design framework. Nature Machine Intelligence, 7, 580–591 (2025). · DOI
  12. Wang, S., You, R., Liu, Y., Xiong, Y. & Zhu, S. NetGO 3.0: protein language model improves large-scale functional annotations. Genomics, Proteomics & Bioinformatics, 2, 349–358. (2023). · DOI
  13. Xu, M. et al. Protst: Multi-modality learning of protein sequences and biomedical texts. International Conference on Machine Learning. pp. 38749–38767 (2023).
  14. Su, J., He, Y., You, S. et al. A trimodal protein language model enables advanced protein searches. Nat. Biotechnol. https://doi.org/10.1038/s41587-025-02836-0 (2025). · DOI
  15. Zhang, N. et al. Ontoprotein: protein pretraining with gene ontology embedding. International Conference on Machine Learning. 2022: 1786–1803.
  16. Törönen, P. & Holm, L. PANNZER—a practical tool for protein function prediction. Protein Sci. 31, 118–128 (2022). · DOI
  17. Lv, L. et al. Prollama: A protein large language model for multi-task protein language processing. IEEE Transactions on Artificial Intelligence, 1–12, https://doi.org/10.1109/TAI.2025.3564914 (2025). · DOI
  18. Chen, Z. et al. Unifying sequences, structures, and descriptions for any-to-any protein generation with the large multimodal model HelixProtX. arXiv Preprint arXiv:2407.09274 (2024). · arXiv
  19. Xu, H., Woicik, A., Poon, H., Altman, R. B. & Wang, S. Multilingual translation for zero-shot biomedical classification using BioTranslator. Nat. Commun. 14, 738 (2023). · DOI
  20. Pei, Q. et al. BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (pp. 1102–1123). Association for Computational Linguistics. (2023). · DOI
  21. Harshvardhan, G., Gourisaria, M. K., Pandey, M. & Rautaray, S. S. A comprehensive survey and analysis of generative models in machine learning. Computer Sci. Rev. 38, 100285 (2020). · DOI
  22. Liu, X. et al. GPT understands, too. AI Open, 208–215 (2023). · DOI
  23. Touvron, H. et al. Llama 2: Open foundation and fine-tuned chat models. arXiv Preprint arXiv:2307.09288 (2023). · arXiv
  24. Boeckmann, B. et al. The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003. Nucleic acids Res. 31, 365–370 (2003). · DOI
  25. Gu, Y. et al. Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthc. (HEALTH) 3, 1–23 (2021).
  26. Rives, A. et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. 118, e2016239118 (2021). · DOI · Paper page
  27. Hunter, S. et al. InterPro: the integrative protein signature database. Nucleic Acids Res. 37, D211–D215 (2008). · DOI · Paper page
  28. Sapundzhi, F., Popstoilov, M. & Lazarova, M. RMSD Calculations for Comparing Protein Three-Dimensional Structures. International Conference on Numerical Methods and Applications. 279–288. Cham: Springer Nature Switzerland, 2022. · DOI
  29. Berman, H. M. et al. The protein data bank. Acta Crystallogr. Sect. D: Biol. Crystallogr. 58, 899–907 (2002). · DOI
  30. Zhang, Y. & Skolnick, J. TM-align: a protein structure alignment algorithm based on the TM-score. Nucleic acids Res. 33, 2302–2309 (2005). · DOI · Paper page
  31. Ødum, M. T. et al. DeepLoc 2.1: multi-label membrane protein type prediction using protein language models. Nucleic Acids Research, gkae237 (2024). · DOI
  32. Steinegger, M. & Söding, J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat. Biotechnol. 35, 1026–1028 (2017). · DOI · Paper page
  33. Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Systems 30, 5998–6008 (2017).
  34. Macqueen, J. et al. Some methods for classification and analysis of multivariate observations. Proceedings of 5-th Berkeley Symposium on Mathematical Statistics and Probability/University of California Press. 281–297. (1967)
  35. Consortium, U. UniProt: a worldwide hub of protein knowledge. Nucleic acids Res. 47, D506–D515 (2019). · DOI · Paper page
  36. Van Erven, T. & Harremos, P. Rényi divergence and Kullback-Leibler divergence. IEEE Trans. Inf. Theory 60, 3797–3820 (2014). · DOI
  37. May, A. C. Percent sequence identity: the need to be explicit. Structure 12, 737–738 (2004). · DOI
  38. Hamamsy, T. et al. Protein remote homology detection and structural alignment using deep learning. Nat. Biotechnol. 42, 975–985 (2024). · DOI
  39. Tanabe, L. & Wilbur, W. J. Tagging gene and protein names in biomedical text. Bioinformatics 18, 1124–1132 (2002). · DOI
  40. Radford, A. et al. Language models are unsupervised multitask learners. OpenAI blog 1, 9 (2019).
  41. Chickering, D. M. Optimal structure identification with greedy search. J. Mach. Learn. Res. 3, 507–554 (2002).
  42. Freitag, M. & Al-Onaizan, Y. Beam search strategies for neural machine translation. Proceedings of the First Workshop on Neural Machine Translation (pp. 56–60). Association for Computational Linguistics. https://doi.org/10.18653/v1/W17-3207 (2017). · DOI
  43. Holtzman, A., Buys, J., Du, L., Forbes, M. & Choi, Y. The curious case of neural text degeneration. arXiv Preprint arXiv:1904.09751 (2019). · arXiv
  44. Yacouby, R. & Axman, D. Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models. Proceedings of the first workshop on evaluation and comparison of NLP systems. 79–91. (2020) · DOI

Metadata

Authors
Guo, X.-Y., Li, Y.-F., Liu, Y., Pan, X., & Shen, H.-B.
Affiliations
Shanghai Jiao Tong University (CN)
Corresponding author
Shen, Hong-Bin
ORCID
Venue
Nature Communications
Publisher
Springer Science and Business Media LLC
Published
2025-11-26
Volume
16
Issue
1
Pages
10544-10544
ISSN
2041-1723 (ISSN-L)
DOI
10.1038/s41467-025-65562-w
OpenAlex
W4416721989
Cited by
3
References
8
Citations by year
2026: 3
FWCI
0.90
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by-nc-nd)
  • Research Square (acceptedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Science and Technology Commission of Shanghai Municipality ((24510714300)
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 › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
Keywords
de novo protein design, Swiss-Prot
MeSH terms
Amino Acid Sequence, Proteins, Software, Protein Engineering, Computational Biology, Sequence Analysis, Protein, Databases, Protein

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.

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