Deep learning in biology faces a transferability crisis

PLoS Biology 2026 Open access

Read full text
Authors: Thomas A. O’Shea-Wheller, Katie I. Murray
DOI: 10.1371/journal.pbio.3003656
Cited by: 2
References: 5

Abstract

Creating generalizable models is a conserved aim in deep learning-however, misleading claims of transferability threaten to obfuscate reliable performance evaluation. We outline the severity of this issue in the biosciences, and suggest potential solutions.

Fields of Study & Subjects

Machine Learning in Bioinformatics Cell Image Analysis Techniques Single-cell and spatial transcriptomics

Publication details

Journal / source
PLoS Biology
Publisher
Public Library of Science (PLoS)
Volume
24
Issue
3
Pages
e3003656–e3003656
Publication date
3 March 2026
Language
EN