Identification of Key Genes and Potential Therapeutic Targets in Sepsis-Associated Acute Kidney Injury Using Transformer and Machine Learning Approaches

Identification of Key Genes and Potential Therapeutic Targets in Sepsis-Associated Acute Kidney Injury Using Transformer and Machine Learning Approaches

Sepsis-associated acute kidney injury (SA-AKI) is a life-threatening complication of sepsis, characterized by high mortality and prolonged hospitalization. Early diagnosis and effective therapy remain difficult despite extensive investigation. To address this, we developed an AI-driven integrative f...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhendong Zhai, JunZhe Peng, Wenjun Zhong, Jun Tao, Yaqi Ao, Bailin Niu, Li Zhu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Bioengineering
Subjects:
sepsis
acute kidney injury
transformer
machine learning
diagnostic model
Online Access:https://www.mdpi.com/2306-5354/12/5/536
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Sepsis-associated acute kidney injury (SA-AKI) is a life-threatening complication of sepsis, characterized by high mortality and prolonged hospitalization. Early diagnosis and effective therapy remain difficult despite extensive investigation. To address this, we developed an AI-driven integrative framework that combines a Transformer-based deep learning model with established machine learning techniques (LASSO, SVM-RFE, Random Forest and neural networks) to uncover complex, nonlinear interactions among gene-expression biomarkers. Analysis of normalized microarray data from GEO (GSE95233 and GSE69063) identified differentially expressed genes (DEGs), and KEGG/GO enrichment via clusterProfiler revealed key pathways in immune response, protein synthesis, and antigen presentation. By integrating multiple transcriptomic cohorts, we pinpointed 617 SA-AKI-associated DEGs—21 of which overlapped between sepsis and AKI datasets. Our Transformer-based classifier ranked five genes (<i>MYL12B, RPL10</i>, <i>PTBP1</i>, <i>PPIA</i>, and <i>TOMM7</i>) as top diagnostic markers, with AUC values ranging from 0.9395 to 0.9996 (MYL12B yielding 0.9996). Drug–gene interaction mining using DGIdb (FDR < 0.05) nominated 19 candidate therapeutics for SA-AKI. Together, these findings demonstrate that melding deep learning with classical machine learning not only sharpens early SA-AKI detection but also systematically uncovers actionable drug targets, laying groundwork for precision intervention in critical care settings.
ISSN:2306-5354

Similar Items