Journal of Advances in Artificial Intelligence and Machine Learning

Journal of Advances in Artificial Intelligence and Machine Learning

Open Access
ISSN: 3069-8316
Research Article

Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm

Authors: Ju-Yuan Chang, Kuan-Tsung Li, Yu-Shen Tsai, Michael Kubal, Aaron M Hamby, Naomi Thomson, Jonathan Sheridan, Shiloh Barfield, Randy Rutz, Frank S Ong, Ramon Felciano, Scott Kahn, ShaoMin Wu.

DOI: 10.33425/3069-8316.1008


Abstract

This study presents a comprehensive benchmark analysis of InheriNext®, a domain-specific, AI-powered tool designed for phenotype-driven pathogenic variant prioritization. For this study, 7,244 whole exome test cases were generated using phenotype and genotype data from Phenopackets, along with pools of variants from healthy individuals to serve as genomic backgrounds. Performance was evaluated across diverse testing scenarios and compared against four established tools. The results show InheriNext® achieving a 98.6% sensitivity in identifying pathogenic variants and consistent performance across diverse tests for variant types, phenotype counts, and disease groups—supporting the robustness and adaptability of its methodology. Sharing these benchmarking results and samples is intended to drive progress by assisting clinicians and researchers in evaluating interpretation tools and identifying areas for improvement.

View / Download PDF
Citation: Ju-Yuan Chang, Kuan-Tsung Li, Yu-Shen Tsai, et al. Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm. 2025; 1(1). DOI: 10.33425/3069-8316.1008
Editor-in-Chief
Jose Luis Verdegay Galdeano
Jose Luis Verdegay Galdeano
Department of Computer Science and Artificial Intelligence | University of Granada

View full editorial board →
Journal Metrics
Impact Factor 2.4*
Acceptance Rate 75%
Time to first decision 6-10 Days
Submission to acceptance 12-15 Days