AggMapNet: enhanced and explainable low-sample omics deep learning with feature-aggregated multi-channel networks. Issue 8 (31st January 2022)

• Record Type: Journal Article
• Authors: Shen, Wan Xiang; Liu, Yu; Chen, Yan; Zeng, Xian; Tan, Ying; Jiang, Yu Yang; Chen, Yu Zong
• Is Part Of: Nucleic acids research. Volume 50:Issue 8(2022)
• Page Start: e45
• Page End: e45
• Publication Date: 2022-01-31
• Subjects: Nucleic acids -- Periodicals; Molecular biology -- Periodicals; 572.805
• DOI: 10.1093/nar/gkac010
• Languages: English
• ISSNs: 0305-1048

Abstract

Abstract: Omics-based biomedical learning frequently relies on data of high-dimensions (up to thousands) and low-sample sizes (dozens to hundreds), which challenges efficient deep learning (DL) algorithms, particularly for low-sample omics investigations. Here, an unsupervised novel feature aggregation tool AggMap was developed to Agg regate and Map omics features into multi-channel 2D spatial-correlated image-like feature maps (Fmaps) based on their intrinsic correlations. AggMap exhibits strong feature reconstruction capabilities on a randomized benchmark dataset, outperforming existing methods. With AggMap multi-channel Fmaps as inputs, newly-developed multi-channel DL AggMapNet models outperformed the state-of-the-art machine learning models on 18 low-sample omics benchmark tasks. AggMapNet exhibited better robustness in learning noisy data and disease classification. The AggMapNet explainable module Simply-explainer identified key metabolites and proteins for COVID-19 detections and severity predictions. The unsupervised AggMap algorithm of good feature restructuring abilities combined with supervised explainable AggMapNet architecture establish a pipeline for enhanced learning and interpretability of low-sample omics data.