Related Experiment Videos

Identification of lactylation-related genes associated with heart failure via bioinformatics and machine learning

Yan Zhang1, Haixia Luo1, Xiaojie Jia1

  • 1Department of Cardiology, Tangdu Hospital, Fourth Military Medical University, Xi'an, 710000, China.

Insights

Researchers identified four lactylation-related genes (HLTF, HMGN2, ARGLU1, LSP1) as potential heart failure (HF) biomarkers. Machine learning models accurately diagnosed HF, offering new avenues for early detection and treatment.

Area of Science:

  • Biomolecular mechanisms
  • Cardiovascular disease research
  • Computational biology

Background:

  • Heart failure (HF) represents the advanced stage of cardiovascular disease, characterized by high global incidence and unfavorable outcomes.
  • Identifying novel diagnostic biomarkers is crucial for improving HF patient prognosis and management.

Purpose of the Study:

  • To pinpoint lactylation-related genes (LRGs) as potential diagnostic biomarkers for heart failure (HF).
  • To develop and validate a machine learning-based diagnostic model for HF using identified LRGs.

Main Methods:

  • Utilized gene expression data from the GEO database for HF patients and healthy controls.
  • Integrated LRGs from existing literature with differential gene expression analysis and Weighted Gene Co-expression Network Analysis (WGCNA) to identify HF-specific LRGs.
  • Constructed and validated diagnostic models using machine learning techniques, including external datasets and animal models.

Main Results:

  • Identified four key upregulated genes in HF patients: HLTF, HMGN2, ARGLU1, and LSP1.
  • Developed nine machine learning models with Area Under the Curve (AUC) values exceeding 0.9, indicating high diagnostic accuracy.
  • Validated gene expression trends in an external dataset (GSE84796) and in a mouse model of cardiac hypertrophy (TAC), confirming upregulation of the four hub genes.
  • Gene Set Enrichment Analysis (GSEA) associated these hub genes with critical metabolic and disease-related pathways.

Conclusions:

  • The identified LRGs (HLTF, HMGN2, ARGLU1, LSP1) show promise as novel diagnostic biomarkers for heart failure.
  • The machine learning diagnostic model demonstrates significant accuracy and potential for clinical application in the early diagnosis and treatment of HF.
Abstract

Related Concept Videos