Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
131 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning (2405.06836v2)

Published 10 May 2024 in q-bio.BM and cs.LG

Abstract: Developing new drugs is laborious and costly, demanding extensive time investment. In this paper, we introduce a de-novo drug design strategy, which harnesses the capabilities of LLMs to devise targeted drugs for specific proteins. Employing a Reinforcement Learning (RL) framework utilizing Proximal Policy Optimization (PPO), we refine the model to acquire a policy for generating drugs tailored to protein targets. The proposed method integrates a composite reward function, combining considerations of drug-target interaction and molecular validity. Following RL fine-tuning, the proposed method demonstrates promising outcomes, yielding notable improvements in molecular validity, interaction efficacy, and critical chemical properties, achieving 65.37 for Quantitative Estimation of Drug-likeness (QED), 321.55 for Molecular Weight (MW), and 4.47 for Octanol-Water Partition Coefficient (logP), respectively. Furthermore, out of the generated drugs, only 0.041% do not exhibit novelty.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Deep learning in drug target interaction prediction: current and future perspectives. Current Medicinal Chemistry, 28(11):2100–2113.
  2. Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data. Molecular pharmaceutics, 13(7):2524–2530.
  3. Application advances of deep learning methods for de novo drug design and molecular dynamics simulation. Wiley Interdisciplinary Reviews: Computational Molecular Science, 12(3):e1581.
  4. Protein Data Bank. 1971. Protein data bank. Nature New Biol, 233(223):10–1038.
  5. Reinvent 2.0: an ai tool for de novo drug design. Journal of chemical information and modeling, 60(12):5918–5922.
  6. A proximal policy optimization with curiosity algorithm for virtual drone navigation. Engineering Research Express, 6(1):015057.
  7. Chembl web services: streamlining access to drug discovery data and utilities. Nucleic acids research, 43(W1):W612–W620.
  8. A multimodal deep learning framework for predicting drug–drug interaction events. Bioinformatics, 36(15):4316–4322.
  9. Translation between molecules and natural language. arXiv preprint arXiv:2204.11817.
  10. Padme: A deep learning-based framework for drug-target interaction prediction. arXiv preprint arXiv:1807.09741.
  11. Generative recurrent networks for de novo drug design. Molecular informatics, 37(1-2):1700111.
  12. Predicting protein–protein interactions through sequence-based deep learning. Bioinformatics, 34(17):i802–i810.
  13. A multimodal deep learning-based drug repurposing approach for treatment of covid-19. Molecular diversity, 25:1717–1730.
  14. Deep learning frameworks for protein–protein interaction prediction. Computational and Structural Biotechnology Journal, 20:3223–3233.
  15. Deeppurpose: a deep learning library for drug–target interaction prediction. Bioinformatics, 36(22-23):5545–5547.
  16. Machine and deep learning approaches for cancer drug repurposing. In Seminars in cancer biology, volume 68, pages 132–142. Elsevier.
  17. Optimizing parameters in swarm intelligence using reinforcement learning: An application of proximal policy optimization to the isoma algorithm. Swarm and Evolutionary Computation, 85:101487.
  18. Accelerating de novo drug design against novel proteins using deep learning. Journal of Chemical Information and Modeling, 61(2):621–630.
  19. De novo structure-based drug design using deep learning. Journal of Chemical Information and Modeling, 62(21):5100–5109.
  20. Efficient prediction of drug–drug interaction using deep learning models. IET Systems Biology, 14(4):211–216.
  21. Greg Landrum. 2013. Rdkit documentation. Release, 1(1-79):4.
  22. Chun Yen Lee and Yi-Ping Phoebe Chen. 2021. New insights into drug repurposing for covid-19 using deep learning. IEEE Transactions on Neural Networks and Learning Systems, 32(11):4770–4780.
  23. Novel deep learning model for more accurate prediction of drug-drug interaction effects. BMC bioinformatics, 20:1–8.
  24. Minhyeok Lee. 2023. Recent advances in deep learning for protein-protein interaction analysis: A comprehensive review. Molecules, 28(13):5169.
  25. Bindingdb: a web-accessible database of experimentally determined protein–ligand binding affinities. Nucleic acids research, 35(suppl_1):D198–D201.
  26. Fsm-ddtr: End-to-end feedback strategy for multi-objective de novo drug design using transformers. Computers in Biology and Medicine, 164:107285.
  27. Ferruccio Palazzesi and Alfonso Pozzan. 2022. Deep learning applied to ligand-based de novo drug design. Artificial intelligence in drug design, pages 273–299.
  28. Deep learning for drug repurposing: Methods, databases, and applications. Wiley interdisciplinary reviews: Computational molecular science, 12(4):e1597.
  29. Yifan Peng and Zhiyong Lu. 2017. Deep learning for extracting protein-protein interactions from biomedical literature. arXiv preprint arXiv:1706.01556.
  30. Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models. Frontiers in Pharmacology.
  31. Deep reinforcement learning for de novo drug design. Science advances, 4(7):eaap7885.
  32. A comprehensive review of computational methods for drug-drug interaction detection. IEEE/ACM transactions on computational biology and bioinformatics, 19(4):1968–1985.
  33. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347.
  34. Sequence-based prediction of protein protein interaction using a deep-learning algorithm. BMC bioinformatics, 18:1–8.
  35. Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of machine learning research, 9(11).
  36. Attention is all you need. Advances in neural information processing systems, 30.
  37. Trl: Transformer reinforcement learning. https://github.com/huggingface/trl.
  38. Deep learning approaches for de novo drug design: An overview. Current opinion in structural biology, 72:135–144.
  39. A deep learning-based method for drug-target interaction prediction based on long short-term memory neural network. BMC medical informatics and decision making, 20:1–9.
  40. Deep-learning-based drug–target interaction prediction. Journal of proteome research, 16(4):1401–1409.
  41. Shuo Yang and Gjergji Kasneci. 2024. Is crowdsourcing breaking your bank? cost-effective fine-tuning of pre-trained language models with proximal policy optimization. arXiv preprint arXiv:2402.18284.
  42. Proximal policy optimization-based controller for chaotic systems. International Journal of Robust and Nonlinear Control, 34(1):586–601.
  43. Predicting drug-target interaction network using deep learning model. Computational biology and chemistry, 80:90–101.
  44. Deep learning for drug–drug interaction extraction from the literature: a review. Briefings in bioinformatics, 21(5):1609–1627.
  45. Universal approach to de novo drug design for target proteins using deep reinforcement learning. ACS omega, 8(6):5464–5474.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets