Related Experiment Video
Updated: Aug 5, 2026
03:08
Using Human Differentially Expressed Gene Lists to Perform Downstream Pathway Enrichment Analysis and Target Prioritization
Published on: October 3, 2025
From GWAS Signals to Molecular Mechanisms: Explainable AI for Causal Gene Prioritization and Biomolecular Target
Mia Yang Ang1,2,3, Li Chen3,4, Lanni Song3,4
1Department of Biomedical Sciences, Jeffrey Cheah Sunway Medical School, Faculty of Medical and Life Sciences, Sunway University, Sunway City, Petaling Jaya 47500, Selangor, Malaysia.
Biomolecules
|July 28, 2026
Summary
Explainable artificial intelligence (XAI) can link genome-wide association study (GWAS) signals to biological mechanisms. This approach aids in identifying causal variants and therapeutic targets for complex diseases.
Area of Science:
- Genomics
- Artificial Intelligence
- Precision Medicine
Background:
- Genome-wide association studies (GWAS) identify thousands of disease-associated loci, but most are in non-coding regions, obscuring causal variants and effector genes.
- Interpreting GWAS findings requires integrating diverse molecular data, including expression quantitative trait loci and single-cell multi-omics.
- Current artificial intelligence (AI) models often act as black boxes, limiting biological reproducibility and experimental validation.
Purpose of the Study:
- This review evaluates explainable artificial intelligence (XAI) as a framework for translating GWAS signals into molecularly testable hypotheses.
- The study emphasizes XAI's role in linking genetic associations to biological mechanisms, causal genes, and therapeutic targets.
- The focus is on accelerating the functional interpretation of GWAS outputs for complex diseases using AI.
Main Methods:
- The review synthesizes current approaches in post-GWAS interpretation, including fine-mapping and multi-omics data integration.
- It critically assesses the limitations of 'black-box' AI models in biological research.
- The core method involves evaluating XAI's potential to provide transparent, reproducible evidence paths from genetic variants to biological insights.
Main Results:
- Explainability is proposed as a biological requirement for AI models in genomics.
- XAI can expose evidence pathways from disease-associated variants to regulatory elements, genes, proteins, and pathways.
- Transparent evidence provenance, ancestry-aware interpretation, and functional validation are key components of effective XAI.
Conclusions:
- XAI offers a promising framework for biologically interpreting GWAS findings.
- By ensuring transparency and testability, XAI can facilitate target prioritization and precision molecular medicine.
- This approach supports the translation of genetic discoveries into actionable insights for complex human diseases.
Related Concept Videos
01:29Pharmacogenomics: Identification of New Drug Targets
Advances in genomics have profoundly influenced drug discovery by increasing both the speed and accuracy of pharmaceutical development. Pharmacogenomics, which examines how genetic variation influences drug response, facilitates the identification of novel therapeutic targets and enables patient stratification for personalized treatment. These strategies contribute to improved drug efficacy, minimized adverse effects, and more efficient clinical trial design.Mapping genetic differences...
01:11Genome-wide Association Studies-GWAS
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
01:19Interactions Between Signaling Pathways
Signaling cascades usually lack linearity. Multiple pathways interact and regulate one another, allowing cells to integrate and respond to diverse environmental stimuli.
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...
Convergence and divergence, and cross-talk between signaling pathways
Two distinct signaling pathways can converge on a single functional unit, which may either be a single protein or a complex of proteins. The response is either functionally distinct or synergistic between the two pathways but different from the response...