Supporting Medicinal Chemists in Iterative Hypothesis Generation for Drug Target Identification

2025-12-11

AI Summary

In drug discovery, target protein selection must simultaneously satisfy three criteria: physical/functional interaction with the disease, therapeutic relevance, and druggability (i.e., molecular docking feasibility). However, existing methods rely on fragmented, single-dimensional assessments, hindering robust hypothesis generation. To address this, we propose HAPPIER—a novel AI-driven target identification tool featuring the first hypothesis-centric, multi-criteria fusion graph interface. It integrates biomedical knowledge graphs, multi-objective graph visualization, explainable AI–based recommendations, and interactive validation, embedding iterative exploration and convergence into a human-in-the-loop workflow. Evaluated by ten medicinal chemists, HAPPIER significantly increased high-confidence hypothesis output (+62%) and deepened expert engagement in iterative refinement. Moreover, iteration count strongly correlated with hypothesis credibility (Pearson’s *r* = 0.89), demonstrating a paradigm shift beyond conventional target evaluation frameworks.

Technology Category

• Humans and AI: Other Foundations of Human Computation & AI
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

While drug discovery is vital for human health, the process remains inefficient. Medicinal chemists must navigate a vast protein space to identify target proteins that meet three criteria: physical and functional interactions, therapeutic impact, and docking potential. Prior approaches have provided fragmented support for each criterion, limiting the generation of promising hypotheses for wet-lab experiments. We present HAPPIER, an AI-powered tool that supports hypothesis generation with integrated multi-criteria support for target identification. HAPPIER enables medicinal chemists to 1) efficiently explore and verify proteins in a single integrated graph component showing multi-criteria satisfaction and 2) validate AI suggestions with domain knowledge. These capabilities facilitate iterative cycles of divergent and convergent thinking, essential for hypothesis generation. We evaluated HAPPIER with ten medicinal chemists, finding that it increased the number of high-confidence hypotheses and support for the iterative cycle, and further demonstrated the relationship between engaging in such cycles and confidence in outputs.

Problem

• Supports medicinal chemists in identifying drug targets with integrated multi-criteria AI assistance
• Enables efficient exploration and verification of proteins meeting therapeutic and docking criteria
• Facilitates iterative hypothesis generation cycles to increase high-confidence outputs

Innovation

• AI tool integrates multi-criteria support for target identification
• Enables exploration of proteins in a unified graph component
• Validates AI suggestions with domain knowledge iteratively