Target Identification and Prioritization

Target identification is a decision under uncertainty. AI systems help organize evidence, but the scientific risk is confusing association with therapeutic tractability.

Learning Objectives

• Separate target association, causal support, tractability, and safety.
• Use genetics and functional genomics as evidence layers.
• Evaluate knowledge graph outputs as prioritization, not proof.

TL;DR

AI-assisted target selection is useful when it integrates evidence transparently. The winning target is not the top-ranked node. It is the target with a testable mechanism, feasible modality, safety rationale, and disease-relevant assay path.

Introduction

The Open Targets Platform integrates genetics, genomics, chemistry, literature, and drug evidence to support systematic target-disease prioritization (Ochoa et al., 2021). AI adds ranking and representation learning, but the underlying problem remains biological evidence integration.

Demonstrated

Demonstrated capability includes evidence aggregation, target-disease scoring, literature mining, and genetics-informed prioritization. Open Targets provides a transparent public example of systematic target prioritization infrastructure (Ochoa et al., 2021). FDA also recognizes AI and machine learning use across drug development submissions and discussion papers (FDA, 2026).

Evidence Anchor	What It Supports	Practical Constraint
Open Targets	Integrated target-disease evidence	Scores require biological interpretation
FDA drug AI materials	Regulatory attention to AI in drug development	Regulatory acceptance depends on context of use
Geneformer	Gene-network modeling from single-cell data	Network prediction is not target validation

Theoretical

Theoretical capability includes target selection models that forecast efficacy, toxicity, patient subgroup, and modality fit before a program begins. The causal and translational links remain difficult, especially when disease biology is heterogeneous.

Beyond Current Capabilities

Beyond current capabilities includes reliable target discovery without wet-lab or human genetics validation. Computational ranking alone does not establish disease causality or therapeutic window.

Practice Notes

• Separate evidence for disease association from evidence for intervention.
• Require a modality hypothesis before program launch.
• Use orthogonal evidence layers rather than one graph score.
• Record why lower-ranked targets were rejected.