scCaT: An explainable capsulating architecture for sepsis diagnosis transferring from single-cell RNA sequencing

• Published in: PLoS computational biology Vol. 20; no. 10; p. e1012083
• Main Authors: Zheng, Xubin, Meng, Dian, Chen, Duo, Wong, Wan-Ki, To, Ka-Ho, Zhu, Lei, Wu, JiaFei, Liang, Yining, Leung, Kwong-Sak, Wong, Man-Hon, Cheng, Lixin
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 21.10.2024
• Subjects: Biology and Life Sciences; Computational Biology - methods; Computer and Information Sciences; Deep Learning; Diagnosis; Genetic aspects; Humans; Medicine and Health Sciences; Methods; Research and Analysis Methods; RNA sequencing; Sepsis; Sepsis - diagnosis; Sepsis - genetics; Sequence Analysis, RNA - methods; Single-Cell Analysis - methods; China
• ISSN: 1553-7358; 1553-734X; 1553-7358
• DOI: 10.1371/journal.pcbi.1012083

Sepsis is a life-threatening condition characterized by an exaggerated immune response to pathogens, leading to organ damage and high mortality rates in the intensive care unit. Although deep learning has achieved impressive performance on prediction and classification tasks in medicine, it requires large amounts of data and lacks explainability, which hinder its application to sepsis diagnosis. We introduce a deep learning framework, called scCaT, which blends the capsulating architecture with Transformer to develop a sepsis diagnostic model using single-cell RNA sequencing data and transfers it to bulk RNA data. The capsulating architecture effectively groups genes into capsules based on biological functions, which provides explainability in encoding gene expressions. The Transformer serves as a decoder to classify sepsis patients and controls. Our model achieves high accuracy with an AUROC of 0.93 on the single-cell test set and an average AUROC of 0.98 on seven bulk RNA cohorts. Additionally, the capsules can recognize different cell types and distinguish sepsis from control samples based on their biological pathways. This study presents a novel approach for learning gene modules and transferring the model to other data types, offering potential benefits in diagnosing rare diseases with limited subjects.