HyperADRs: A Hierarchical Hypergraph Framework for Drug-Gene-ADR Prediction

TL;DR

HyperADRs is a hierarchical hypergraph framework that predicts drug-gene-ADR interactions, integrating multi-source data and advanced embedding techniques to improve pharmacogenomic decision making and interpretability.

Contribution

It introduces a novel hierarchical hypergraph model with a contrastive learning module for accurate, transferable drug-gene-ADR prediction and interpretability in pharmacogenomics.

Findings

Outperforms baseline models on ranking metrics in PharmGKB evaluations.

Maintains ranking advantage on unseen DrugBank triplets, demonstrating transferability.

Supports mechanistically grounded pharmacogenomic hypothesis generation.

Abstract

Adverse drug reactions (ADRs) are a major barrier to safe and effective pharmacotherapy and increasingly reflect higher order interactions between drugs, genetic background, and clinical phenotypes. Existing graph based approaches usually predict ADRs as properties of drugs or drug pairs, leaving the causal gene implicit and limiting their value for pharmacogenomic decision making. We introduce HyperADRs, a hierarchical hypergraph framework that predicts ADR risk at the level of drug-gene-ADR triads. Starting from curated pharmacogenomic annotations in PharmGKB and the pharmacogenomics subdatabase of DrugBank, we construct high confidence triplets and integrate them with auxiliary molecular, functional, and disease relations from precision-medicine-oriented knowledge graphs. Drugs, genes, and ADR concepts are embedded with modality appropriate pretrained models (UniMol, ESM2, SapBERT) and propagated through a hypergraph convolutional network. A FiLM based, query conditioned contrastive learning module learns context specific representations so that, given any two entities, the model retrieves the correct third entity against many candidates. To improve robustness and interpretability, we propose a nine category ADR macro system scheme that reduces large heterogeneous "other" bins while aligning with organ system reasoning in clinical pharmacology. Across drug-, gene-, and ADR-held-out evaluations on PharmGKB, HyperADRs matches or exceeds strong baselines on ranking based metrics. When trained on PharmGKB and tested on unseen DrugBank triplets, HyperADRs maintains its ranking advantage, indicating that the learned representations capture transferable biological mechanisms and can support mechanistically grounded pharmacogenomic hypothesis generation.