DeepFun is a deep learning based model for functional evaluation of genetic variants with single-base resolution. Specifically, we collected comprehensive chromatin profiles from ENCODE and Roadmap projects to construct the feature space, including 1548 DNase I accessibility, 1536 histone mark, and 4795 transcription factor binding profiles, and these profiles covered 225 tissues or cell lines. With such comprehensive epi-genomics annotations and pre-trained model, this web-server provides an online service to quickly assess the impact of genetic variants in tissue- or cell type-specific manner..
Compute SNP activity (accessibility or binding probability) difference (SAD) or relative log fold changes of odds (log-odds) difference between two alleles for a list of query variants across all chromatin features.
Ruifeng Hu, Guangsheng Pei, Peilin Jia, Zhongming Zhao @ CPH, UTHealth-Houston SBMI.
DeepFun is free and open to all users and there is no login requirement.