DrugGen 2: A disease-aware language model for enhancing drug discovery
Summary
DrugGen-2 fine-tunes GPT-2 using supervised learning and reinforcement learning (GRPO) to generate small molecules conditioned on both disease ontology and target protein sequences, achieving superior diversity and binding affinity for drug discovery.
View Cached Full Text
Cached at: 07/10/26, 10:10 AM
Paper page - DrugGen 2: A disease-aware language model for enhancing drug discovery
Source: https://huggingface.co/papers/2607.08404
Abstract
DrugGen-2 generates small molecules conditioned on disease ontology and target protein sequences through fine-tuning GPT-2 with supervised learning and reinforcement learning using GRPO, achieving superior molecular diversity and binding affinity compared to baseline models.
Current computational approaches for drug design typically focus on generating molecules conditioned on specific targets or general molecular properties, often neglecting the influence of disease context on target behavior and therapeutic outcomes. To address this gap, we introduce DrugGen-2, a novel generative model that designs small molecules conditioned on both disease ontology and target protein sequences. DrugGen-2 was developed by fine-tuning a pre-trainedGPT-2model on a curated dataset of approved drugs linked to their diseases and targets, using a two-step strategy ofsupervised fine-tuningfollowed byreinforcement learningviagroup relative policy optimization(GRPO). This process was guided by reward functions optimizing forchemical validity, novelty, diversity, and high predictedbinding affinity. When evaluated on five protein targets relevant to diabetic nephropathy, DrugGen-2 significantly outperformed baseline models (DrugGPT and DrugGen). It demonstrated a superior capacity to generate unique molecules, exhibited greater structural similarity to approved drugs, and achieved improved predicted binding affinities across all targets.Molecular dockinganalyses further supported these findings, identifying candidate ligands with strong binding potential, including compounds with predicted affinities (-9.917, -9.485, and -9.367) exceeding those of reference drugs such as enalapril for angiotensin-converting enzyme (-8.283). By integrating disease-specific context intomolecular generation, DrugGen-2 advances AI-assisted drug discovery, offering a powerful tool for de novo design and drug repurposing that accounts for the complex interplay between diseases and molecular targets.
View arXiv pageView PDFProject pageGitHub0Add to collection
Get this paper in your agent:
hf papers read 2607\.08404
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper1
#### alimotahharynia/DrugGen-2 Text Generation• 0.1B• Updatedabout 2 hours ago • 182
Datasets citing this paper1
#### alimotahharynia/approved_disease_target_drug Viewer• Updatedabout 2 hours ago • 154k • 47
Spaces citing this paper1
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimization
This paper introduces a novel diffusion-based generative model for structure-based drug design that decouples pocket and ligand representation learning and incorporates multi-scale interaction signals and property-aware optimization to generate developable 3D molecules with improved binding affinity and ADMET properties.
Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design
This paper proposes JoPMol, a jointly controlled precision molecular generative model that integrates gene expression profiles, molecular structure text, and chemical properties to generate personalized drug candidates, outperforming state-of-the-art methods.
DrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
DrugSAGE is a framework that accumulates and reuses cross-task memory to build state-of-the-art drug discovery models efficiently, outperforming baseline agents by 10-30% on held-out tasks.
Turning scattered evidence into discovery decisions for life sciences
OpenAI’s new life-science model “GPT-Rosalind” inside Codex autonomously ranks asthma drug targets by orchestrating specialist sub-agents that merge genetics, transcriptomics, safety and IP data into a single evidence-backed decision.
Introducing new capabilities to GPT-Rosalind
OpenAI introduces an updated GPT-Rosalind model purpose-built for life sciences research, with improved performance in medicinal chemistry, genomics, and drug-discovery workflows, and new benchmarks like LifeSciBench and MedChemBench.