METCC: METric learning for Confounder Control Making distance matter in high dimensional biological analysis

TL;DR

METCC employs contrastive metric learning with a triplet network to effectively distinguish biological signals in high-dimensional genomic data while reducing confounding effects from technical and irrelevant biological variations, even without detailed metadata.

Contribution

This work introduces a non-linear contrastive metric learning approach, METCC, that improves confounder control in biological data analysis beyond traditional linear methods, especially when metadata is limited.

Findings

METCC matches or exceeds linear methods in classification performance.

METCC reduces confounding from technical variables like batch and institution.

The approach performs well without requiring detailed metadata.

Abstract

High-dimensional data acquired from biological experiments such as next generation sequencing are subject to a number of confounding effects. These effects include both technical effects, such as variation across batches from instrument noise or sample processing, or institution-specific differences in sample acquisition and physical handling, as well as biological effects arising from true but irrelevant differences in the biology of each sample, such as age biases in diseases. Prior work has used linear methods to adjust for such batch effects. Here, we apply contrastive metric learning by a non-linear triplet network to optimize the ability to distinguish biologically distinct sample classes in the presence of irrelevant technical and biological variation. Using whole-genome cell-free DNA data from 817 patients, we demonstrate that our approach, METric learning for Confounder Control (METCC), is able to match or exceed the classification performance achieved using a best-in-class linear method (HCP) or no normalization. Critically, results from METCC appear less confounded by irrelevant technical variables like institution and batch than those from other methods even without access to high quality metadata information required by many existing techniques; offering hope for improved generalization.