Deep learning of 2D-Restructured gene expression representations for improved low-sample therapeutic response prediction

Clinical outcome prediction is important for stratified therapeutics. Machine learning (ML) and deep learning (DL) methods facilitate therapeutic response prediction from transcriptomic profiles of cells and clinical samples. Clinical transcriptomic DL is challenged by the low-sample sizes (34–286 s...

Full description

Saved in:
Bibliographic Details
Published in:Computers in biology and medicine 2023-09, Vol.164, p.107245-107245, Article 107245
Main Authors: Cheng, Kai Ping, Shen, Wan Xiang, Jiang, Yu Yang, Chen, Yan, Chen, Yu Zong, Tan, Ying
Format: Article
Language:English
Subjects:
Algorithms
Biomarkers
Cancer therapies
Datasets
Deep learning
Gene expression
Low-sample
Machine learning
Metastasis
Predictions
Representations
Robustness
Therapeutic response prediction
Transcriptome
Transcriptomics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Clinical outcome prediction is important for stratified therapeutics. Machine learning (ML) and deep learning (DL) methods facilitate therapeutic response prediction from transcriptomic profiles of cells and clinical samples. Clinical transcriptomic DL is challenged by the low-sample sizes (34–286 subjects), high-dimensionality (up to 21,653 genes) and unordered nature of clinical transcriptomic data. The established methods rely on ML algorithms at accuracy levels of 0.6–0.8 AUC/ACC values. Low-sample DL algorithms are needed for enhanced prediction capability. Here, an unsupervised manifold-guided algorithm was employed for restructuring transcriptomic data into ordered image-like 2D-representations, followed by efficient DL of these 2D-representations with deep ConvNets. Our DL models significantly outperformed the state-of-the-art (SOTA) ML models on 82% of 17 low-sample benchmark datasets (53% with >0.05 AUC/ACC improvement). They are more robust than the SOTA models in cross-cohort prediction tasks, and in identifying robust biomarkers and response-dependent variational patterns consistent with experimental indications. •An unsupervised manifold-guided algorithm was used for image-like 2D-GERs generation.•Our DL models significantly outperformed the SOTA ML models on 82% of 17 low-sample benchmark datasets.•Gene expression biomarkers were captured by feature importance saliency-map from deep learning models.•Our DL models are more robust than the SOTA models in cross-cohort prediction tasks.
ISSN:0010-4825
1879-0534
DOI:10.1016/j.compbiomed.2023.107245