Generalized query-based active learning to identify differentially methylated regions in DNA.

Active learning is a supervised learning technique that reduces the number of examples required for building a successful classifier, because it can choose the data it learns from. This technique holds promise for many biological domains in which classified examples are expensive and time-consuming to obtain. Most traditional active learning methods ask very specific queries to the Oracle (e.g., a human expert) to label an unlabeled example. The example may consist of numerous features, many of which are irrelevant. Removing such features will create a shorter query with only relevant features, and it will be easier for the Oracle to answer. We propose a generalized query-based active learning (GQAL) approach that constructs generalized queries based on multiple instances. By constructing appropriately generalized queries, we can achieve higher accuracy compared to traditional active learning methods. We apply our active learning method to find differentially DNA methylated regions (DMRs). DMRs are DNA locations in the genome that are known to be involved in tissue differentiation, epigenetic regulation, and disease. We also apply our method on 13 other data sets and show that our method is better than another popular active learning technique.

Environmentally induced epigenetic transgenerational inheritance of altered Sertoli cell transcriptome and epigenome: molecular etiology of male infertility.

Environmental toxicants have been shown to induce the epigenetic transgenerational inheritance of adult onset disease, including testis disease and male infertility. The current study was designed to determine the impact of an altered sperm epigenome on the subsequent development of an adult somatic cell (Sertoli cell) that influences the onset of a specific disease (male infertility). A gestating female rat (F0 generation) was exposed to the agriculture fungicide vinclozolin during gonadal sex determination and then the subsequent F3 generation progeny used for the isolation of Sertoli cells and assessment of testis disease. As previously observed, enhanced spermatogenic cell apoptosis was observed. The Sertoli cells provide the physical and nutritional support for the spermatogenic cells. Over 400 genes were differentially expressed in the F3 generation control versus vinclozolin lineage Sertoli cells. A number of specific cellular pathways were identified to be transgenerationally altered. One of the key metabolic processes affected was pyruvate/lactate production that is directly linked to spermatogenic cell viability. The Sertoli cell epigenome was also altered with over 100 promoter differential DNA methylation regions (DMR) modified. The genomic features and overlap with the sperm DMR were investigated. Observations demonstrate that the transgenerational sperm epigenetic alterations subsequently alters the development of a specific somatic cell (Sertoli cell) epigenome and transcriptome that correlates with adult onset disease (male infertility). The environmentally induced epigenetic transgenerational inheritance of testis disease appears to be a component of the molecular etiology of male infertility.