Dataset Information

Predicting regulatory variants using a dense epigenomic mapped CNN model elucidated the molecular basis of trait-tissue associations.

ABSTRACT: Assessing the causal tissues of human complex diseases is important for the prioritization of trait-associated genetic variants. Yet, the biological underpinnings of trait-associated variants are extremely difficult to infer due to statistical noise in genome-wide association studies (GWAS), and because >90% of genetic variants from GWAS are located in non-coding regions. Here, we collected the largest human epigenomic map from ENCODE and Roadmap consortia and implemented a deep-learning-based convolutional neural network (CNN) model to predict the regulatory roles of genetic variants across a comprehensive list of epigenomic modifications. Our model, called DeepFun, was built on DNA accessibility maps, histone modification marks, and transcription factors. DeepFun can systematically assess the impact of non-coding variants in the most functional elements with tissue or cell-type specificity, even for rare variants or de novo mutations. By applying this model, we prioritized trait-associated loci for 51 publicly-available GWAS studies. We demonstrated that CNN-based analyses on dense and high-resolution epigenomic annotations can refine important GWAS associations in order to identify regulatory loci from background signals, which yield novel insights for better understanding the molecular basis of human complex disease. We anticipate our approaches will become routine in GWAS downstream analysis and non-coding variant evaluation.

SUBMITTER: Pei G

PROVIDER: S-EPMC7797043 | biostudies-literature | 2021 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting regulatory variants using a dense epigenomic mapped CNN model elucidated the molecular basis of trait-tissue associations.

Pei Guangsheng G Hu Ruifeng R Dai Yulin Y Manuel Astrid Marilyn AM Zhao Zhongming Z Jia Peilin P

Nucleic acids research 20210101 1

Assessing the causal tissues of human complex diseases is important for the prioritization of trait-associated genetic variants. Yet, the biological underpinnings of trait-associated variants are extremely difficult to infer due to statistical noise in genome-wide association studies (GWAS), and because >90% of genetic variants from GWAS are located in non-coding regions. Here, we collected the largest human epigenomic map from ENCODE and Roadmap consortia and implemented a deep-learning-based c ...[more]

PMID: 33300042

Similar Datasets

Project description:Zinc-finger, MYND-type containing 10 (ZMYND10), or more commonly called BLU, expression is frequently downregulated in nasopharyngeal carcinoma (NPC) and many other tumors due to promoter hypermethylation. Functional evidence shows that the BLU gene inhibits tumor growth in animal assays, but the detailed molecular mechanism responsible for this is still not well understood. In current studies, we find that 93.5% of early-stage primary NPC tumors show downregulated BLU expression. Using a PCR array, overexpression of the BLU gene was correlated to the angiogenesis network in NPC cells. Moreover, expression changes of the MMP family, VEGF and TSP1, were often detected in different stages of NPC, suggesting the possibility that BLU may be directly involved in the microenvironment and anti-angiogenic activity in NPC development. Compared with vector-alone control cells, BLU stable transfectants, derived from poorly-differentiated NPC HONE1 cells, suppress VEGF165, VEGF189 and TSP1 expression at both the RNA and protein levels, and significantly reduce the secreted VEGF protein in these cells, reflecting an unknown regulatory mechanism mediated by the BLU gene in NPC. Cells expressing BLU inhibited cellular invasion, migration and tube formation. These in vitro results were further confirmed by in vivo tumor suppression and a matrigel plug angiogenesis assay in nude mice. Tube-forming ability was clearly inhibited, when the BLU gene is expressed in these cells. Up to 70-90% of injected tumor cells expressing increased exogenous BLU underwent cell death in animal assays. Overexpressed BLU only inhibited VEGF165 expression in differentiated squamous NPC HK1 cells, but also showed an anti-angiogenic effect in the animal assay, revealing a complicated mechanism regulating angiogenesis and the microenvironment in different NPC cell lines. Results of these studies indicate that alteration of BLU gene expression influences anti-angiogenesis pathways and is important for the development of NPC.

Dataset Information

Predicting regulatory variants using a dense epigenomic mapped CNN model elucidated the molecular basis of trait-tissue associations.

Publications

Predicting regulatory variants using a dense epigenomic mapped CNN model elucidated the molecular basis of trait-tissue associations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets