mlsanityData to 14 Oct 2026

Improving Targeted Molecule Generation through Language Model Fine-Tuning Via Reinforcement Learning

arXiv 2405.06836 ↗First posted 10 May 2024q-bio.BM cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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 language models 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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 10 of its 53 references that are in the map. First posted on arXiv 10 May 2024.

Builds on

10 of 53 references.

References · 10

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
  4. 2015An Introduction to Convolutional Neural Networkscited by 514
  5. 2015Adversarial Autoencoderscited by 364
  6. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 275
  7. 2022Translation between Molecules and Natural Languagecited by 177
  8. 2017Deep Reinforcement Learning for De-Novo Drug Designcited by 161
  9. 2022Deep learning for drug repurposing: methods, databases, and applicationscited by 16
  10. 2024Is Crowdsourcing Breaking Your Bank? Cost-Effective Fine-Tuning of Pre-trained Language Models with Proximal Policy Optimizationcited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024SmileyLlama: Modifying Large Language Models for Directed Chemical Space Explorationcited by 14

Similar, not cited

Close in wording, no citation either way

  1. 2025DrugImproverGPT: A Large Language Model for Drug Optimization with Fine-Tuning via Structured Policy Optimization
  2. 2025ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design
  3. 2026Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design
  4. 2026DrugGen 2: A disease-aware language model for enhancing drug discovery
  5. 2026Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation
  6. 2024Diversity-Aware Reinforcement Learning for de novo Drug Design
  7. 2025REINFORCE-ING Chemical Language Models for Drug Discovery
  8. 2025De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learning