Genetic prediction of quantitative traits: a machine learner's guide focused on height

TL;DR

This paper offers a comprehensive guide for machine learning researchers on predicting complex traits like height from genetic data, highlighting current models, challenges, and best practices.

Contribution

It provides an overview of state-of-the-art models and essential considerations for phenotype prediction from genetics, focusing on height as a case study.

Findings

Summarizes current models for genetic trait prediction

Discusses key subtleties in genetic data analysis

Provides benchmark datasets and evaluation metrics

Abstract

Machine learning and deep learning have been celebrating many successes in the application to biological problems, especially in the domain of protein folding. Another equally complex and important question has received relatively little attention by the machine learning community, namely the one of prediction of complex traits from genetics. Tackling this problem requires in-depth knowledge of the related genetics literature and awareness of various subtleties associated with genetic data. In this guide, we provide an overview for the machine learning community on current state of the art models and associated subtleties which need to be taken into consideration when developing new models for phenotype prediction. We use height as an example of a continuous-valued phenotype and provide an introduction to benchmark datasets, confounders, feature selection, and common metrics.