Improving Local Ancestry Inference through Neural Networks

Abstract Motivation Local Ancestry Inference (LAI) allows us to study evolutionary processes in admixed populations[1], uncover ancestry-specific disease risk factors[2], and to better understand the demographic history of these populations[3]. Many methods for LAI exist, however, these methods usually focus on cases of intercontinental admixture. In this work, we evaluate both existing and novel methods in challenging scenarios, such as downsampled reference panels, intracontinental admixture, and distant admixture events. Results We present four novel LAI implementations based on neural network architectures, including Bidirectional Long Short-Term Memory and Transformer networks which have not previously been used for LAI. We compare these novel implementations to existing methods for LAI across a variety of scenarios using the 1 Thousand Genomes dataset and other synthetic datasets. We find that while all networks achieve high performance for intercontinental admixture scenarios, inference power is comparatively low for scenarios of intracontinental or distant admixture. We further show how our implementations achieve the best performance of all methods through specialized preprocessing and inference smoothing steps. Availability All implementations and benchmarking code available at https://github.com/Jazpy/LAINNs .