Genetic variation: Putting causal variants on the map

sscNOVA: a semi-supervised convolutional neural network for predicting functional regulatory variants in autoimmune diseases

Genome-wide association studies (GWAS) have identified thousands of variants in the human genome with autoimmune diseases. However, identifying functional regulatory variants associated with autoimmune diseases remains challenging, largely because of insufficient experimental validation data. We adopt the concept of semi-supervised learning by combining labeled and unlabeled data to develop a deep learning-based algorithm framework, sscNOVA, to predict functional regulatory variants in autoimmune diseases and analyze the functional characteristics of these regulatory variants. Compared to traditional supervised learning methods, our approach leverages more variants' data to explore the relationship between functional regulatory variants and autoimmune diseases. Based on the experimentally curated testing dataset and evaluation metrics, we find that sscNOVA outperforms other state-of-the-art methods. Furthermore, we illustrate that sscNOVA can help to improve the prioritization of functional regulatory variants from lead single-nucleotide polymorphisms and the proxy variants in autoimmune GWAS data.

Epigenetic reprogramming of immune cells in injury, repair, and resolution

Immune cells are pivotal in the reaction to injury, whereupon, under ideal conditions, repair and resolution phases restore homeostasis following initial acute inflammation. Immune cell activation and reprogramming require transcriptional changes that can only be initiated if epigenetic alterations occur. Recently, accelerated deciphering of epigenetic mechanisms has extended knowledge of epigenetic regulation, including long-distance chromatin remodeling, DNA methylation, posttranslational histone modifications, and involvement of small and long noncoding RNAs. Epigenetic changes have been linked to aspects of immune cell development, activation, and differentiation. Furthermore, genome-wide epigenetic landscapes have been established for some immune cells, including tissue-resident macrophages, and blood-derived cells including T cells. The epigenetic mechanisms underlying developmental steps from hematopoietic stem cells to fully differentiated immune cells led to development of epigenetic technologies and insights into general rules of epigenetic regulation. Compared with more advanced research areas, epigenetic reprogramming of immune cells in injury remains in its infancy. While the early epigenetic mechanisms supporting activation of the immune response to injury have been studied, less is known about resolution and repair phases and cell type-specific changes. We review prominent recent findings concerning injury-mediated epigenetic reprogramming, particularly in stroke and myocardial infarction. Lastly, we illustrate how single-cell technologies will be crucial to understanding epigenetic reprogramming in the complex sequential processes following injury.