causal

Cross-Ancestry Predictor Decay Is a Tagging Problem

Polygenic predictors trained on one ancestry group (mostly European data) lose accuracy when applied to a more distant ancestry group, likely because the predictor uses non-causal SNPs that merely tag the truly causal variant via population-specific correlation structure, and these tags decay across populations even if the underlying causal architecture is shared—a hypothesis solvable with machine learning once non-European biobanks come online.

causalpending

Speaker

Steve Hsu

Evidence Quote

“the predictor, which is just using statistical power to figure things out, will grab one of these SNPs as a tag for the truly causal SNP in there. It doesn't know which one is genuinely causal... but the tagging quality falls off if you go to another population”

Source

Steve Hsu - Intelligence, Embryo Selection, & The Future of Humanity— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:37:09 AM

Your notes

Loading notes...