Search for: All records

DNA methylation is a process that can affect gene accessibility and therefore gene expression. In this study, a machine learning pipeline is proposed for the prediction of breast cancer and the identification of significant genes that contribute to the prediction. The current study utilized breast cancer methylation data from The Cancer Genome Atlas (TCGA), specifically the TCGA-BRCA dataset. Feature engineering techniques have been utilized to reduce data volume and make deep learning scalable. A comparative analysis of the proposed approach on Illumina 27K and 450K methylation data reveals that deep learning methodologies for cancer prediction can be coupled with feature selection models to enhance prediction accuracy. Prediction using 450K methylation markers can be accomplished in less than 13 s with an accuracy of 98.75%. Of the list of 685 genes in the feature selected 27K dataset, 578 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in five biological processes and one molecular function. Of the list of 1572 genes in the feature selected 450K data set, 1290 were mapped to Ensemble Gene IDs. This reduced set was significantly (FDR < 0.05) enriched in 95 biological processes and 17 molecular functions. Seven oncogene/tumor suppressor genes were common between the 27K and 450K feature selected gene sets. These genes were RTN4IP1, MYO18B, ANP32A, BRF1, SETBP1, NTRK1, and IGF2R. Our bioinformatics deep learning workflow, incorporating imputation and data balancing methods, is able to identify important methylation markers related to functionally important genes in breast cancer with high accuracy compared to deep learning or statistical models alone. 

Over the past several decades in the United States, incidence of pancreatic cancer (PCa) has increased, with the 5-year survival rate remaining extremely low at 10.8%. Typically, PCa is diagnosed at an advanced stage, with the consequence that there is more tumor heterogeneity and increased probability that more cells are resistant to treatments. Risk factors for PCa can serve as a way to select a high-risk population and develop biomarkers to improve early detection and treatment. We focus on blood-based methylation as an approach to identify a marker set that can be obtained in a minimally invasive way (through peripheral blood) and could be applied to a high-risk subpopulation [those with recent onset type 2 diabetes (DM)]. Blood samples were collected from 30 patients, 15 had been diagnosed with PCa and 15 had been diagnosed with recent onset DM. HumanMethylationEPIC Beadchip (Illumina, CA, United States) was used to quantify methylation of approximately 850,000 methylation sites across the genome and to analyze methylation markers associated with PCa or DM or both. Exploratory analysis conducted to propose importance of top CpG (5′—C—phosphate—G—3′) methylation site associated genes and visualized using boxplots. A methylation-based age predictor was also investigated for ability to distinguish disease groups from controls. No methylation markers were observed to be significantly associated with PCa or new onset diabetes compared with control the respective control groups. In our exploratory analysis, one methylation marker, CpG04969764, found in the Laminin Subunit Alpha 5 ( LAMA5 ) gene region was observed in both PCa and DM Top 100 methylation marker sets. Modification of LAMA5 methylation or LAMA5 gene function may be a way to distinguish those recent DM cases with and without PCa, however, additional studies with larger sample sizes and different study types (e.g., cohort) will be needed to test this hypothesis.