Sum-h², enabling genetic discovery for deep learning-derived phenotypes through a fast evaluation framework and arena...

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 1000× faster and lightweight framework, sum-h², than traditional GWAS framework for evaluating genetic discovery through total heritability. We revisit $tr\left(P^{-1}G\right)$ , 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 $tr\left(P^{-1}G\right)$ , 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.