Abstract
The Next Generation Sequencing (NGS) technologies have provided affordable ways to generate errorful raw genetical data. To extract Variant Information from billions of NGS reads is still a daunting task which involves various hand-crafted and parameterized statistical tools. Here we propose a Deep Neural Networks (DNN) based alignment and SNV tool known as DAVI. DAVI consists of models for both global and local alignment and for Variant Calling. We have evaluated the performance of DAVI against existing state of the art tool-set and found that its accuracy and performance is comparable to existing tools used for benchmarking. We further demonstrate that while existing tools are based on data generated from a specific sequencing technology, the models proposed in DAVI are generic and can be used across different NGS technologies. Moreover, this approach is a migration from expert driven statistical models to generic, automated, self-learning models.
Footnotes
Authors’ address: Gaurav Gupta, ggupta.iitd{at}gmail.com; Shubhi Saini, saini.shubhi{at}gmail.com.
Reference Format: Gaurav Gupta and Shubhi Saini. 2019. DAVI:Deep Learning Based Tool for Alignment and Single Nucleotide Variant identification (September 2019).