Machine Learning Based Network Analysis Determined Clinically Relevant miRNAs in Breast Cancer

BACKGROUND AND AIMS: MicroRNAs (miRNAs) have been shown to play important roles in many cancers, including breast cancer. The majority of previous studies employed network analysis to identify key miRNAs in cancer progression. However, most of dysregulated miRNA networks were constructed based on the expression variation of miRNAs and target genes. METHODS: The relations between miRNAs and target genes were computed by Spearman correlation separately in breast cancer and normal breast samples. We calculated dysregulated scores based on the dysregulation of miRNA-mRNA regulatory relations. A dysregulated miRNA target network (DMTN) was constructed from the miRNA-mRNA pairs with significant dysregulated scores. SVM classifier was employed to predict breast cancer risk miRNAs from the DMTN. Hypermetric test was utilized to calculate the significance of overlap between different gene sets. Pearson correlation was used to evaluate associations between miRNAs/genes and drug response. RESULTS: The DMTN comprised 511 miRNAs and was similar to common biological networks. Based on miRNAs and target genes in DMTN, we predicted 90 breast cancer risk miRNAs by using SVM classifier. Predicted risk miRNAs and one-step neighbor genes were significantly overlapping with differential miRNAs, cancer-related and housekeeping genes in breast cancer. These risk miRNAs were involved in many cancer-related and immune-related processes. In addition, most risk miRNAs were able to predict survival of breast cancer patients. More interestingly, some risk miRNAs and one-step neighbor genes were remarkably associated with immune cell infiltration. For example, high expression of hsa-miR-155 indicates high abundance of activated CD4+ T cells but low level of M2 macrophage infiltration. Furthermore, we identified 588 miRNA-drug and 3,146 gene-drug pairs, wherein the expression level of miRNAs/genes could indicate the sensitivity of cancer cells to anti-cancer drugs. CONCLUSION: We predicted 90 breast cancer risk miRNAs based on proposed DMTN by using SVM classifier. Predicted risk miRNAs are biologically and clinically relevant in breast cancer. Risk miRNAs and one-step neighbor genes could serve as biomarkers for immune cell infiltration and anti-cancer drug response, which sheds lights on immunotherapy or targeted therapy for patients with breast cancer.