A deep learning classifier for local ancestry inference

TL;DR

This paper introduces a novel deep learning approach for local ancestry inference by framing it as an image segmentation task, achieving accuracy comparable to established methods.

Contribution

It develops a deep convolutional neural network with an encoder-decoder architecture for LAI, a new formulation not previously explored.

Findings

Model achieves near-gold standard accuracy

Learns admixture as a zero-shot task

Effective on simulated admixed data

Abstract

Local ancestry inference (LAI) identifies the ancestry of each segment of an individual's genome and is an important step in medical and population genetic studies of diverse cohorts. Several techniques have been used for LAI, including Hidden Markov Models and Random Forests. Here, we formulate the LAI task as an image segmentation problem and develop a new LAI tool using a deep convolutional neural network with an encoder-decoder architecture. We train our model using complete genome sequences from 982 unadmixed individuals from each of five continental ancestry groups, and we evaluate it using simulated admixed data derived from an additional 279 individuals selected from the same populations. We show that our model is able to learn admixture as a zero-shot task, yielding ancestry assignments that are nearly as accurate as those from the existing gold standard tool, RFMix.