Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Advancing biomolecular understanding and design following human instructions

Nature Machine Intelligence volume 7, pages 1154–1167 (2025)Cite this article

Subjects

A preprint version of the article is available at arXiv.

Abstract

Understanding and designing biomolecules, such as proteins and small molecules, is central to advancing drug discovery, synthetic biology and enzyme engineering. Recent breakthroughs in artificial intelligence have revolutionized biomolecular research, achieving remarkable accuracy in biomolecular prediction and design. However, a critical gap remains between artificial intelligence’s computational capabilities and researchers’ intuitive goals, particularly in using natural language to bridge complex tasks with human intentions. Large language models have shown potential to interpret human intentions, yet their application to biomolecular research remains nascent due to challenges including specialized knowledge requirements, multimodal data integration, and semantic alignment between natural language and biomolecules. To address these limitations, we present InstructBioMol, a large language model designed to bridge natural language and biomolecules through a comprehensive any-to-any alignment of natural language, molecules and proteins. This model can integrate multimodal biomolecules as the input, and enable researchers to articulate design goals in natural language, providing biomolecular outputs that meet precise biological needs. Experimental results demonstrate that InstructBioMol can understand and design biomolecules following human instructions. In particular, it can generate drug molecules with a 10% improvement in binding affinity and design enzymes that achieve an enzyme–substrate pair prediction score of 70.4. This highlights its potential to transform real-world biomolecular research.

Access through your institution
Buy or subscribe

This is a preview of subscription content, access via your institution

Access options

Access through your institution

Buy this article

  • Purchase on SpringerLink
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Overview of InstructBioMol.
Fig. 2: Model performance on protein understanding and design benchmarks.
Fig. 3: Model performance on drug discovery and enzyme design.
Fig. 4: Performance on description-based protein–molecule pair generation.

Similar content being viewed by others

Data availability

The dataset used in this study is available via Zenodo at https://doi.org/10.5281/zenodo.15303508 (ref. 81).

Code availability

The source code of this study is available via GitHub at https://github.com/HICAI-ZJU/InstructBioMol and via Zenodo at https://doi.org/10.5281/zenodo.15335654 (ref. 82).

References

  1. Kim, J., Park, S., Min, D. & Kim, W. Comprehensive survey of recent drug discovery using deep learning. Int. J. Mol. Sci. 22, 9983 (2021).

    Article  Google Scholar 

  2. Volk, MichaelJeffrey et al. Biosystems design by machine learning. ACS Synth. Biol. 9, 1514–1533 (2020).

    Article  Google Scholar 

  3. Mazurenko, S., Prokop, Z. & Damborsky, J. Machine learning in enzyme engineering. ACS Catal. 10, 1210–1223 (2019).

    Article  Google Scholar 

  4. Abramson, J. et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature 630, 493–500 (2024).

    Article  Google Scholar 

  5. Krishna, R. et al. Generalized biomolecular modeling and design with RoseTTAFold All-Atom. Science 384, eadl2528 (2024).

    Article  Google Scholar 

  6. Zhou, C. et al. A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT. Int. J. Mach. Learn. Cybern. https://doi.org/10.1007/s13042-024-02443-6 (2024).

  7. Touvron, H. et al. Llama 2: open foundation and fine-tuned chat models. Preprint at https://arxiv.org/abs/2307.09288 (2023).

  8. OpenAI. GPT-4 technical report. Preprint at https://arxiv.org/abs/2303.08774 (2023).

  9. Zhang, Q. et al. Scientific large language models: a survey on biological & chemical domains. ACM Comput. Surv. 57, 161 (2025).

    Article  Google Scholar 

  10. Weininger, D. SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J. Chem. Inf. Comput. Sci. 28, 31–36 (1988).

    Article  Google Scholar 

  11. Krenn, M., Häse, F., Nigam, AkshatKumar, Friederich, P. & Aspuru-Guzik, Alán Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation. Mach. Learn. Sci. Technol. 1, 45024 (2020).

    Article  Google Scholar 

  12. Pearson, W. R. in Computer Analysis of Sequence Data: Part I 307–331 (Humana Press, 1994).

  13. Jumper, J. et al. Highly accurate protein structure prediction with AlphaFold. Nature 596, 583–589 (2021).

    Article  Google Scholar 

  14. Ouyang, L. et al. Training language models to follow instructions with human feedback. In Advances in Neural Information Processing Systems 27730–27744 (Curran Associates, 2022).

  15. Edwards, C. et al. Translation between molecules and natural language. In Proc. 2022 Conference on Empirical Methods in Natural Language Processing 375–413 (Association for Computational Linguistics, 2022).

  16. Wang, Z. et al. InstructProtein: aligning human and protein language via knowledge instruction. In Proc. 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 1114–1136 (Association for Computational Linguistics, 2024).

  17. Pei, Q. et al. Biot5: enriching cross-modal integration in biology with chemical knowledge and natural language associations. In 2023 Conference on Empirical Methods in Natural Language Processing 1102–1123 (Association for Computational Linguistics, 2023).

  18. Fang, Y. et al. Mol-Instructions: a large-scale biomolecular instruction dataset for large language models. In The Twelfth International Conference on Learning Representations (ICLR, 2024).

  19. Pei, Q. et al. Biot5+: towards generalized biological understanding with IUPAC integration and multi-task tuning. In ACL (Findings) 1216–1240 (Association for Computational Linguistics, 2024).

  20. Luo, Y. et al. BioMedGPT: open multimodal generative pre-trained transformer for biomedicine. Preprint at https://arxiv.org/abs/2308.09442 (2023).

  21. Liu, S. et al. Conversational drug editing using retrieval and domain feedback. In The Twelfth International Conference On Learning Representations (ICLR, 2024).

  22. Kroll, A., Ranjan, S., Engqvist, MartinK. M. & Lercher, M. J. A general model to predict small molecule substrates of enzymes based on machine and deep learning. Nat. Commun. 14, 2787 (2023).

    Article  Google Scholar 

  23. Vaswani, A. et al. Attention is all you need. In 31st Conference on Neural Information Processing Systems (NIPS 2017) https://papers.nips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf (2017).

  24. Hastings, J. et al. ChEBI in 2016: improved services and an expanding collection of metabolites. Nucleic Acids Res. 44, D1214–D1219 (2016).

    Article  Google Scholar 

  25. Li, J. et al. Empowering molecule discovery for molecule-caption translation with large language models: a ChatGPT perspective. IEEE Trans. Knowl. Data Eng. https://doi.ieeecomputersociety.org/10.1109/TKDE.2024.3393356 (2024).

  26. Zhao, Z. et al. ChemDFM: dialogue foundation model for chemistry. Preprint at https://arxiv.org/abs/2401.14818 (2024).

  27. Cao, H., Liu, Z., Lu, X., Yao, Y. & Li, Y. InstructMol: multi-modal integration for building a versatile and reliable molecular assistant in drug discovery. In Proc. 31st International Conference on Computational Linguistics 354–379 (Association for Computational Linguistics, 2025).

  28. Liu, Z. et al. Prott3: protein-to-text generation for text-based protein understanding. In Proc. 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 5949–5966 (Association for Computational Linguistics, 2024).

  29. Liu, S. et al. A text-guided protein design framework. Nat. Mach. Intell. 7, 580–591 (2025).

    Article  Google Scholar 

  30. Anderson, A. C. The process of structure-based drug design. Chem. Biol. 10, 787–797 (2003).

    Article  Google Scholar 

  31. Peng, X. et al. Pocket2Mol: efficient molecular sampling based on 3D protein pockets. In Proc. Machine Learning Research 17644–17655 (PMLR, 2022).

  32. Luo, S., Guan, J., Ma, J. & Peng, J. A 3D generative model for structure-based drug design. In Advances in Neural Information Processing Systems 6229–6239 (Curran Associates, 2021).

  33. Guan, J. et al. 3D equivariant diffusion for target-aware molecule generation and affinity prediction. In The Eleventh International Conference on Learning Representations https://openreview.net/pdf?id=kJqXEPXMsE0 (ICLR, 2023).

  34. Li, Y. et al. DrugGPT: a GPT-based strategy for designing potential ligands targeting specific proteins. Preprint at bioRxiv https://doi.org/10.1101/2023.06.29.543848 (2023).

  35. Bar-Even, A. et al. The moderately efficient enzyme: evolutionary and physicochemical trends shaping enzyme parameters. Biochemistry 50, 4402–4410 (2011).

    Article  Google Scholar 

  36. Hu, E. J. et al. LoRA: low-rank adaptation of large language models. In International Conference on Learning Representations https://openreview.net/pdf?id=nZeVKeeFYf9 (ICLR, 2022).

  37. Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O. & Dahl, G. E. Neural message passing for quantum chemistry. In Proc. Machine Learning Research 1263–1272 (PMLR, 2017).

  38. Zhou, G. et al. Uni-Mol: a universal 3D molecular representation learning framework. In The Eleventh International Conference on Learning Representations https://openreview.net/pdf?id=6K2RM6wVqKu (ICLR, 2023).

  39. Lin, Z. et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 1123–1130 (2023).

    Article  MathSciNet  Google Scholar 

  40. Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In International Conference on Learning Representations https://openreview.net/pdf?id=ryGs6iA5Km (ICLR, 2019).

  41. Hu, W. et al. Strategies for pre-training graph neural networks. In International Conference on Learning Representations https://openreview.net/pdf?id=HJlWWJSFDH (2020).

  42. Wang, Y. et al. Geometric transformer with interatomic positional encoding. In Advances in Neural Information Processing Systems 55981–55994 (Curran Associates, 2023).

  43. Su, J. et al. SaProt: protein language modeling with structure-aware vocabulary. In The Twelfth International Conference on Learning Representations https://openreview.net/pdf?id=6MRm3G4NiU (ICLR, 2024).

  44. Zhang, Z., Liu, Q., Wang, H., Lu, C. & Lee, C. K. Motif-based graph self-supervised learning for molecular property prediction. In Advances in Neural Information Processing Systems 15870–15882 (Curran Associates, 2021).

  45. Li, H. et al. A knowledge-guided pre-training framework for improving molecular representation learning. Nat. Commun. 14, 7568 (2023).

    Article  Google Scholar 

  46. Grant, C. E., Bailey, T. L. & Noble, WilliamStafford FIMO: scanning for occurrences of a given motif. Bioinformatics 27, 1017–1018 (2011).

    Article  Google Scholar 

  47. Rogers, D. & Hahn, M. Extended-connectivity fingerprints. J. Chem. Inf. Model. 50, 742–754 (2010).

    Article  Google Scholar 

  48. Boeckmann, B. et al. The SWISS-PROT protein knowledgebase and its supplement TrEMBL in 2003. Nucleic Acids Res. 31, 365–370 (2003).

    Article  Google Scholar 

  49. Radford, A. et al. Improving language understanding by generative pre-training. OpenAI https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf (2018).

  50. Kim, S. Pubchem substance and compound databases. Nucleic Acids Res. 44, D1202–D1213 (2016).

    Article  Google Scholar 

  51. Suzek, B. E., Huang, H., McGarvey, P., Mazumder, R. & Wu, C. H. Uniref: comprehensive and non-redundant uniprot reference clusters. Bioinformatics 23, 1282–1288 (2007).

    Article  Google Scholar 

  52. White, J. PubMed 2.0. Med. Ref. Serv. Q. 39, 382–387 (2020).

    Article  Google Scholar 

  53. Sever, R. et al. bioRxiv: the preprint server for biology. Preprint at bioRxiv https://doi.org/10.1101/833400 (2019).

  54. Mudrak, B. et al. Five years of ChemRxiv: where we are and where we go from here. Angew. Chem. Int. Ed. 62, e202215847 (2023).

  55. McNaught, A. D. et al. Compendium of Chemical Terminology Vol. 1669 (Blackwell Science Oxford, 1997).

  56. The UniProt Consortium. UniProt: the universal protein knowledgebase. Nucleic Acids Res. 46, 2699–2699 (2018).

    Article  Google Scholar 

  57. Gilson, M. K. et al. BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res. 44, D1045–D1053 (2016).

    Article  Google Scholar 

  58. Uludoğan, G., Ozkirimli, E., Ulgen, K. O., Karalí, N. & Özgür, A. Exploiting pretrained biochemical language models for targeted drug design. Bioinformatics 38, ii155–ii161 (2022).

    Article  Google Scholar 

  59. Bansal, P. et al. Rhea, the reaction knowledgebase in 2022. Nucleic Acids Res. 50, D693–D700 (2022).

    Article  Google Scholar 

  60. Landrum, G. RDKit: a software suite for cheminformatics, computational chemistry, and predictive modeling. Greg Landrum 8, 5281 (2013).

    Google Scholar 

  61. Riniker, S. & Landrum, G. A. Better informed distance geometry: using what we know to improve conformation generation. J. Chem. Inf. Model. 55, 2562–2574 (2015).

    Article  Google Scholar 

  62. Halgren, T. A. Merck molecular force field. I. Basis, form, scope, parameterization, and performance of MMFF94. J. Comput. Chem. 17, 490–519 (1996).

    Article  Google Scholar 

  63. Varadi, M. AlphaFold protein structure database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic Acids Res. 50, D439–D444 (2022).

    Article  Google Scholar 

  64. Paszke, A. et al. PyTorch: an imperative style, high-performance deep learning library. In 33rd Conference on Neural Information Processing Systems (NeurIPS 2019) https://papers.nips.cc/paper_files/paper/2019/file/bdbca288fee7f92f2bfa9f7012727740-Paper.pdf (NeurIPS, 2019).

  65. Rajbhandari, S., Rasley, J., Ruwase, O. & He, Y. ZeRO: memory optimizations toward training trillion parameter models. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis 1–16 (IEEE, 2020).

  66. Papineni, K., Roukos, S., Ward, T. & Zhu, W.J. Bleu: a method for automatic evaluation of machine translation. In Proc. 40th Annual Meeting of the Association for Computational Linguistics 311–318 (ACL, 2002).

  67. Lin, C. Y. in Text Summarization Branches Out 74–81 (2004).

  68. Banerjee, S. & Lavie, A. METEOR: an automatic metric for MT evaluation with improved correlation with human judgments. In Proc. ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translationand/or Summarization 65–72 (Association for Computational Linguistics, 2005).

  69. Miller, F. P., Vandome, A. F. & McBrewster, J. Levenshtein Distance: Information Theory, Computer Science, String (Computer Science), String Metric, Damerau? Levenshtein Distance, Spell Checker, Hamming Distance (Alpha Press, 2009).

  70. Durant, J. L., Leland, B. A., Henry, D. R. & Nourse, J. G. Reoptimization of MDL keys for use in drug discovery. J. Chem. Inf. Comput. Sci. 42, 1273–1280 (2002).

    Article  Google Scholar 

  71. Schneider, N., Sayle, R. A. & Landrum, G. A. Get your atoms in order an open-source implementation of a novel and robust molecular canonicalization algorithm. J. Chem. Inf. Model. 55, 2111–2120 (2015).

    Article  Google Scholar 

  72. Bajusz, D., Rácz, A. & Héberger, K. Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations? J. Cheminform. 7, 20 (2015).

    Article  Google Scholar 

  73. Preuer, K., Renz, P., Unterthiner, T., Hochreiter, S. & Klambauer, G. Fréchet ChemNet distance: a metric for generative models for molecules in drug discovery. J. Chem. Inf. Model. 58, 1736–1741 (2018).

    Article  Google Scholar 

  74. Smith, T. F. Identification of common molecular subsequences. J. Mol. Biol. 147, 195–197 (1981).

    Article  Google Scholar 

  75. Henikoff, S. & Henikoff, J. G. Amino acid substitution matrices from protein blocks. Proc. Natl Acad. Sci. USA 89, 10915–10919 (1992).

    Article  Google Scholar 

  76. Qu, Y. et al. MolCRAFT: structure-based drug design in continuous parameter space. In Proc. Forty-first International Conference on Machine Learning https://openreview.net/pdf?id=KaAQu5rNU1 (2024).

  77. Corso, G. et al. Deep confident steps to new pockets: strategies for docking generalization. In International Conference on Learning Representations https://openreview.net/pdf?id=UfBIxpTK10 (ICLR, 2024).

  78. Alhossary, A., Handoko, S. D., Mu, Y. & Kwoh, C.-K. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics 31, 2214–2216 (2015).

    Article  Google Scholar 

  79. Bickerton, G. R., Paolini, G. V., Besnard, J., Muresan, S. & Hopkins, A. L. Quantifying the chemical beauty of drugs. Nat. Chem. 4, 90–98 (2012).

    Article  Google Scholar 

  80. Ertl, P. & Schuffenhauer, A. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J. Cheminform. 1, 8 (2009).

    Article  Google Scholar 

  81. Zhuang, X. Dataset for the paper ‘advancing biomolecule understanding and design following human instructions’. Zenodo https://doi.org/10.5281/zenodo.15303508 (2025).

  82. Zhuang, X. HICAI-ZJU/InstructBioMol: version 1.0.0. Zenodo https://doi.org/10.5281/zenodo.15335654 (2025).

  83. Probst, D. & Reymond, Jean-Louis SmilesDrawer: parsing and drawing smiles-encoded molecular structures using client-side Javascript. J. Chem. Inf. Model. 58, 1–7 (2018).

    Article  Google Scholar 

  84. Schrödinger, LLC. The PyMOL molecular graphics system, version 3.0. (2024).

Download references

Acknowledgements

This work is funded by NSFCU23B2055 (H.C.), NSFC2302433 (Q.Z.), NSFCU23A20496 (Q.Z.), the Fundamental Research Funds for the Central Universities (226-2023-00138, H.C.), Zhejiang Provincial ‘Jianbing’ ‘Lingyan’ Research and Development Program of China (2025C01097, K.D. and Q.Z.), Zhejiang Provincial Natural Science Foundation of China (LQ24F020007, Q.Z.) and Hangzhou West Lake Pearl Project Leading Innovative Youth Team Project (TD2023017, K.D.).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Zhejiang University, Hangzhou, China

    Xiang Zhuang, Yinuo Jiang, Xiaotong Li, Zeyuan Wang, Kehua Feng & Huajun Chen

  2. Zhejiang Key Laboratory of Intelligent Manufacturing for Functional Chemicals, ZJU-Hangzhou Global Scientific and Technological Innovation Center, Zhejiang University, Hangzhou, China

    Xiang Zhuang, Keyan Ding, Tianwen Lyu, Yinuo Jiang, Xiaotong Li, Zhuoyi Xiang, Zeyuan Wang, Ming Qin, Kehua Feng, Qiang Zhang & Huajun Chen

  3. Polytechnic Institute, Zhejiang University, Hangzhou, China

    Tianwen Lyu & Zhuoyi Xiang

  4. School of Software Technology, Zhejiang University, Hangzhou, China

    Ming Qin

  5. College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, China

    Jike Wang

  6. ZJU-UIUC Institute, International Campus, Zhejiang University, Haining, China

    Qiang Zhang

  7. State Key Laboratory of Ocean Sensing, Hangzhou, China

    Huajun Chen

Authors
  1. Xiang Zhuang
    View author publications

    Search author on:PubMed Google Scholar

  2. Keyan Ding
    View author publications

    Search author on:PubMed Google Scholar

  3. Tianwen Lyu
    View author publications

    Search author on:PubMed Google Scholar

  4. Yinuo Jiang
    View author publications

    Search author on:PubMed Google Scholar

  5. Xiaotong Li
    View author publications

    Search author on:PubMed Google Scholar

  6. Zhuoyi Xiang
    View author publications

    Search author on:PubMed Google Scholar

  7. Zeyuan Wang
    View author publications

    Search author on:PubMed Google Scholar

  8. Ming Qin
    View author publications

    Search author on:PubMed Google Scholar

  9. Kehua Feng
    View author publications

    Search author on:PubMed Google Scholar

  10. Jike Wang
    View author publications

    Search author on:PubMed Google Scholar

  11. Qiang Zhang
    View author publications

    Search author on:PubMed Google Scholar

  12. Huajun Chen
    View author publications

    Search author on:PubMed Google Scholar

Contributions

X.Z., K.D., Q.Z. and H.C. conceived the study. X.Z. developed the method, implemented the code and conducted the experiments. T.L. participated in benchmarking some baseline models. X.Z., Y.J., X.L. and Z.X. contributed to the dataset collection. K.D., Z.W., M.Q., K.F., J.W., Q.Z. and H.C. provided critical suggestions on the methodology and experiments. All authors wrote the paper, reviewed it and approved the final paper.

Corresponding authors

Correspondence to Keyan Ding, Qiang Zhang or Huajun Chen.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Machine Intelligence thanks Martin Min and Hongyu Guo for their contribution to the peer review of this work.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Extended data

Extended Data Table 1 Statistics of continual pretraining dataset
Full size table
Extended Data Table 2 Statistics of instruction-tuning dataset
Full size table

Supplementary information

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhuang, X., Ding, K., Lyu, T. et al. Advancing biomolecular understanding and design following human instructions. Nat Mach Intell 7, 1154–1167 (2025). https://doi.org/10.1038/s42256-025-01064-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue date:

  • DOI: https://doi.org/10.1038/s42256-025-01064-0

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing