Back

New machine learning method identifies subtle fine-scale genetic stratification in diverse populations

Qin, X.; Jia, P.

2023-08-08 genomics
10.1101/2023.08.07.552391 bioRxiv
Show abstract

Fine-scale genetic structure impacts genetic risk predictions and furthers the understanding of the demography of populations. Current approaches (e.g., PCA, DAPC, t-SNE, and UMAP) either produce coarse and ambiguous cluster divisions or fail to preserve the correct genetic distance between populations. We proposed a new machine learning algorithm named ALFDA. ALFDA considers both local and global genetic affinity between individuals and also preserves the multimodal structure within populations. ALFDA outperformed the existing approaches in identifying fine-scale genetic structure and in retaining population geogenetic distance, providing a valuable tool for geographic ancestry inference as well as correction for spatial stratification in population health studies.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.