Sum-h2, enabling genetic discovery for deep learning-derived phenotypes through a fast evaluation framework and arena of performance
- 1Yale University
Abstract
In the recent growing interest of AI research toward biology, genetic association studies of AI- derived phenotypes from high-content modalities such as images emerges as a powerful means for biological discovery. However, such AI-phenotyping methods still lacks a good optimization target and an efficient evaluation framework. The number of discovered loci was the major criterion for evaluating the quality of AI-derived phenotypes. However, the time and computational resources required for running the GWAS and subsequent loci-clumping are substantial, limiting the rapid development and iteration of deep learning representation algorithms. Here we present a 1000x faster and lightweight framework, sum-h2, than traditional GWAS framework for evaluating genetic discovery through total heritability. We revisit tr(P^(-1) G), previously proposed in the context of evolutionary studies, as a measure of multi-phenotype heritability. We showed that sum-h2, the sum of heritability over phenotypic Principal Components (PCs), is equivalent to the linear transformation-invariant tr(P^(-1) G), through both theoretical proof and simulation studies. Moreover, sum-h2 can be estimated rapidly with minimal information loss over a relatedness-enriched sample, while preserving the relative ranking of endophenotypes by GWAS loci counts. Based on selected UKB data and sum-h2, we set up a Genetic Discovery Arena, enabling rapid and fair comparisons for the development and optimization of deep learning-derived phenotyping methods.
Related
- Structure-Based Discovery of GTP-Enhanced Rab10 Modulators and Their Effects on Alzheimer Disease-Relevant Cellular Phenotypes
- The ethical and regulatory framework of medical artificial intelligence (AI) system’s behavioral performance for image-based diagnostics: An ethical evaluation of the International and European Union Scope
- Optimizing Cognitive Phenotyping for Genetic Discovery in Alzheimer's Disease: A Simulation-Based Evaluation of Mini-Mental State Examination-Based Decline Measures
- Capturing Spatial Heterogeneity Using UAV-Derived Multispectral Phenotypes and Random Regression Models Improves Genetic Evaluation in Alfalfa Breeding Trials
- Cholesterol-Induced Senescent Macrophages and Evaluation of Cellular Senescence Phenotypes
BibTeX
@misc{xia2026sumh2,
title = {{Sum-h2, enabling genetic discovery for deep learning-derived phenotypes through a fast evaluation framework and arena of performance}},
author = {T. Xia and Z. Xie and X. Zhao and S. M. S. Islam and A. Naseri and Z. Fan and H. Chen and D. Zhi},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.24.753959},
url = {https://www.biorxiv.org/content/10.64898/2026.09.24.753959v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - Sum-h2, enabling genetic discovery for deep learning-derived phenotypes through a fast evaluation framework and arena of performance
AU - T. Xia
AU - Z. Xie
AU - X. Zhao
AU - S. M. S. Islam
AU - A. Naseri
AU - Z. Fan
AU - H. Chen
AU - D. Zhi
PY - 2026
DA - 2026/09/24
PB - bioRxiv
DO - 10.64898/2026.09.24.753959
UR - https://www.biorxiv.org/content/10.64898/2026.09.24.753959v1
AB - In the recent growing interest of AI research toward biology, genetic association studies of AI- derived phenotypes from high-content modalities such as images emerges as a powerful means for biological discovery. However, such AI-phenotyping methods still lacks a good optimization target and an efficient evaluation framework. The number of discovered loci was the major criterion for evaluating the quality of AI-derived phenotypes. However, the time and computational resources required for running the GWAS and subsequent loci-clumping are substantial, limiting the rapid development and iteration of deep learning representation algorithms. Here we present a 1000x faster and lightweight framework, sum-h2, than traditional GWAS framework for evaluating genetic discovery through total heritability. We revisit tr(P^(-1) G), previously proposed in the context of evolutionary studies, as a measure of multi-phenotype heritability. We showed that sum-h2, the sum of heritability over phenotypic Principal Components (PCs), is equivalent to the linear transformation-invariant tr(P^(-1) G), through both theoretical proof and simulation studies. Moreover, sum-h2 can be estimated rapidly with minimal information loss over a relatedness-enriched sample, while preserving the relative ranking of endophenotypes by GWAS loci counts. Based on selected UKB data and sum-h2, we set up a Genetic Discovery Arena, enabling rapid and fair comparisons for the development and optimization of deep learning-derived phenotyping methods.
ER -