Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm
Journal of Advances in Artificial Intelligence and Machine Learning · 31.12.2026 · 1 (2)
DOI: 10.33425/3069-8316.1008 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Advances in Artificial Intelligence and Machine Learning, online erschienen am 31.12.2026. Verfasst von Ju-Yuan Chang und 12 weiteren Autor:innen.
Abstract (Originalsprache)
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.
Zitieren
APA
Chang, J., Li, K., Tsai, Y., Kubal, M., Hamby, A. M., Thomson, N., Sheridan, J., Barfield, S., Rutz, R., Ong, F. S., Felciano, R., Kahn, S., & Wu, S. (2026). Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm. Journal of Advances in Artificial Intelligence and Machine Learning, 1(2). https://doi.org/10.33425/3069-8316.1008
Vancouver
Chang J, Li K, Tsai Y, Kubal M, Hamby AM, Thomson N, et al. Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm. Journal of Advances in Artificial Intelligence and Machine Learning. 2026;1(2). doi:10.33425/3069-8316.1008
BibTeX
@article{Chang2026,
author = {Chang, Ju-Yuan and Li, Kuan-Tsung and Tsai, Yu-Shen and Kubal, Michael and Hamby, Aaron M and Thomson, Naomi and Sheridan, Jonathan and Barfield, Shiloh and Rutz, Randy and Ong, Frank S and Felciano, Ramon and Kahn, Scott and Wu, ShaoMin},
title = {Integrating Genomic and Phenotypic Data for Gene Prioritization: AI Performance Assessment of the InheriNext® Algorithm},
journal = {Journal of Advances in Artificial Intelligence and Machine Learning},
year = {2026},
volume = {1},
number = {2},
doi = {10.33425/3069-8316.1008}
}
EUVIMED