Machine Learning-Based Identification of Candidate Serum miRNA Features for Pan-Cancer and Cancer Type Classification

MicroRNA (miRNA) regulation plays a pivotal role in intracellular gene expression. Analysis of miRNA profiles can provide critical insights into disease states. As cancer-associated molecules reported in previous studies, miRNAs may serve as candidate classificatory features for exploratory cancer classification. This research analyzed serum miRNA data from patients with 13 solid cancer types and individuals without cancer. The study comprised two distinct analyses: first, stratifying the dataset into cancer and non-cancer groups to identify miRNAs differentially represented in cancer patients; and second, subdividing the cancer patient data into 13 predefined solid-cancer types to identify candidate miRNA features that discriminate among these cancer types. We employed seven feature-ranking algorithms to evaluate miRNA contributions in both analyses and generate feature lists. Each list was examined using an incremental feature selection method to extract essential miRNAs and build good-performing classification models. Several candidate miRNAs were identified for distinguishing pan-cancer samples from non-cancer ones: miR-4783-3p has been linked to associated with the regulation of endocrine cell differentiation, and miR-663a has been reported in hepatocellular carcinoma and thyroid carcinoma. The analysis also highlighted miRNAs that differentiate solid cancer types, including miR-629-3p, reported to be upregulated in lung and breast cancer, and miR-6087, reported to be downregulated in osteosarcoma and bladder cancer.