ODBAE: a high-performance model identifying complex phenotypes in high-dimensional biological datasets

TL;DR

ODBAE is a novel machine learning approach that detects complex, multi-parameter phenotypes in high-dimensional biological data by capturing latent relationships and identifying influential and high leverage outliers.

Contribution

This paper introduces ODBAE, a new autoencoder-based method with a revised loss function for detecting complex outliers in biological datasets, revealing joint abnormalities and novel gene associations.

Findings

ODBAE successfully identifies knockout mice with abnormal multi-indicator phenotypes.

The method uncovers new metabolism-related genes linked to complex phenotypes.

It reveals coordinated abnormalities across multiple metabolic indicators.

Abstract

Identifying complex phenotypes from high-dimensional biological data is challenging due to the intricate interdependencies among different physiological indicators. Traditional approaches often focus on detecting outliers in single variables, overlooking the broader network of interactions that contribute to phenotype emergence. Here, we introduce ODBAE (Outlier Detection using Balanced Autoencoders), a machine learning method designed to uncover both subtle and extreme outliers by capturing latent relationships among multiple physiological parameters. ODBAE's revised loss function enhances its ability to detect two key types of outliers: influential points (IP), which disrupt latent correlations between dimensions, and high leverage points (HLP), which deviate from the norm but go undetected by traditional autoencoder-based methods. Using data from the International Mouse Phenotyping Consortium (IMPC), we show that ODBAE can identify knockout mice with complex, multi-indicator phenotypes - normal in individual traits, but abnormal when considered together. In addition, this method reveals novel metabolism-related genes and uncovers coordinated abnormalities across metabolic indicators. Our results highlight the utility of ODBAE in detecting joint abnormalities and advancing our understanding of homeostatic perturbations in biological systems.