An accurate regression of developmental stages for breast cancer based on transcriptomic biomarkers.

AIM: Breast cancers at different stages have tremendous differences on both phenotypic and molecular patterns. The developmental stage is an essential factor in the clinical decision of treatment plans, but was usually formulated as a classification problem, which ignored the consecutive relationships among them. MATERIALS & METHODS: This study proposed a regression-based procedure to detect the stage biomarkers of breast cancers. Biomarkers were detected by the Lasso and Ridge algorithms. RESULTS & CONCLUSION: A collaboration duet of Lasso and Ridge regression algorithms achieved the best performances, with classification accuracy (Acc) equal to 0.8294 and regression goodness-of-fit (R2) equal to 0.7810. The 265 biomarker genes were enriched with the signal peptide-based secretion function with the Bonferroni-corrected p-value equal to 6.9408e-3 and false discovery rate (FDR) equal to 1.1614e-2.

Detecting Methylomic Biomarkers of Pediatric Autism in the Peripheral Blood Leukocytes.

Autism was a spectrum of multiple complex diseases that required an interdisciplinary group of experts to make a diagnostic decision. Both genetic and environmental factors play essential roles in causing the onset of Autism. Therefore, this study hypothesized that methylomic biomarkers may facilitate the accurate Autism detection. A comprehensive series of biomarker detection algorithms were utilized to find the best methylomic biomarkers for the Autism detection using the methylomic data of the peripheral blood samples. The best model achieved 99.70% in accuracy with 678 methylomic biomarkers and a tenfold cross validation strategy. Some of the methylomic biomarkers were experimentally confirmed to be associated with the onset or development of Autism.