Uncovering hub genes and immunological characteristics for heart failure utilizing RRA, WGCNA and Machine learning

• DOI: 10.1016/j.ijcha.2024.101335
• Publication Date: 2024-02-09T19:04:55Z
• Authors: Dingyuan Tu; Qiang Xu; Xiaoli Zuo; Chaoqun Ma
• Keywords: Immune infiltration; Original Paper; 0303 health sciences; 03 medical and health sciences; RC666-701; Weighted gene co-expression network analysis; Machine learning; Diseases of the circulatory (Cardiovascular) system; Heart failure; Robust rank aggregation

Heart failure (HF) is a major public health issue with high mortality and morbidity. This study aimed to find potential diagnostic markers for HF by the combination of bioinformatics analysis machine learning, as well analyze role immune infiltration in pathological process HF. The gene expression profiles 124 patients 135 nonfailing donors (NFDs) were obtained from six datasets NCBI Gene Expression Omnibus (GEO) database. We applied robust rank aggregation (RRA) weighted co-expression network (WGCNA) method identify critical genes To discover novel HF, three learning methods employed, including best subset regression, regularization technique, support vector machine-recursive feature elimination (SVM-RFE). Besides, was investigated single-sample set enrichment (ssGSEA). Combining RRA WGCNA method, we recognized 39 associated Through integrating methods, FCN3 SMOC2 determined Differences signature also found between NFDs. Moreover, explored associations two response pathogenesis In summary, can be used plays an important initiation progression