Open AccessThe ability to classify patients based on gene-expression data varies by algorithm and performance metric
Author(s) -
Stephen Piccolo,
Avery Mecham,
Nathan P Golightly,
Jérémie L Johnson,
Dustin Miller
Publication year - 2022
Publication title -
plos computational biology/plos computational biology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.628
H-Index - 182
eISSN - 1553-7358
pISSN - 1553-734X
DOI - 10.1371/journal.pcbi.1009926
Subject(s) - metric (unit) , gene expression , algorithm , computer science , gene expression profiling , expression (computer science) , computational biology , artificial intelligence , pattern recognition (psychology) , bioinformatics , gene , biology , genetics , programming language , operations management , economics
By classifying patients into subgroups, clinicians can provide more effective care than using a uniform approach for all patients. Such subgroups might include patients with a particular disease subtype, patients with a good (or poor) prognosis, or patients most (or least) likely to respond to a particular therapy. Transcriptomic measurements reflect the downstream effects of genomic and epigenomic variations. However, high-throughput technologies generate thousands of measurements per patient, and complex dependencies exist among genes, so it may be infeasible to classify patients using traditional statistical models. Machine-learning classification algorithms can help with this problem. However, hundreds of classification algorithms exist—and most support diverse hyperparameters—so it is difficult for researchers to know which are optimal for gene-expression biomarkers. We performed a benchmark comparison, applying 52 classification algorithms to 50 gene-expression datasets (143 class variables). We evaluated algorithms that represent diverse machine-learning methodologies and have been implemented in general-purpose, open-source, machine-learning libraries. When available, we combined clinical predictors with gene-expression data. Additionally, we evaluated the effects of performing hyperparameter optimization and feature selection using nested cross validation. Kernel- and ensemble-based algorithms consistently outperformed other types of classification algorithms; however, even the top-performing algorithms performed poorly in some cases. Hyperparameter optimization and feature selection typically improved predictive performance, and univariate feature-selection algorithms typically outperformed more sophisticated methods. Together, our findings illustrate that algorithm performance varies considerably when other factors are held constant and thus that algorithm selection is a critical step in biomarker studies.