@article{Huang01122020,
author = {Huang, Dandan and Yi, Xianfu and Zhou, Yao and Yao, Hongcheng and Xu, Hang and Wang, Jianhua and Zhang, Shijie and Nong, Wenyan and Wang, Panwen and Shi, Lei and Xuan, Chenghao and Li, Miaoxin and Wang, Junwen and Li, Weidong and Kwan, Hoi Shan and Sham, Pak Chung and Wang, Kai and Li, Mulin Jun}, 
title = {Ultrafast and scalable variant annotation and prioritization with big functional genomics data},
volume = {30}, 
number = {12}, 
pages = {1789-1801}, 
year = {2020}, 
doi = {10.1101/gr.267997.120}, 
abstract ={The advances of large-scale genomics studies have enabled compilation of cell type–specific, genome-wide DNA functional elements at high resolution. With the growing volume of functional annotation data and sequencing variants, existing variant annotation algorithms lack the efficiency and scalability to process big genomic data, particularly when annotating whole-genome sequencing variants against a huge database with billions of genomic features. Here, we develop VarNote to rapidly annotate genome-scale variants in large and complex functional annotation resources. Equipped with a novel index system and a parallel random-sweep searching algorithm, VarNote shows substantial performance improvements (two to three orders of magnitude) over existing algorithms at different scales. It supports both region-based and allele-specific annotations and introduces advanced functions for the flexible extraction of annotations. By integrating massive base-wise and context-dependent annotations in the VarNote framework, we introduce three efficient and accurate pipelines to prioritize the causal regulatory variants for common diseases, Mendelian disorders, and cancers.}, 
URL = {http://genome.cshlp.org/content/30/12/1789.abstract}, 
eprint = {http://genome.cshlp.org/content/30/12/1789.full.pdf+html}, 
journal = {Genome Research} 
}