@inproceedings{59510145afb947c590d1699ffaf72352,
title = "A pipeline for identifying integration sites of mobile elements in the genome using next-generation sequencing",
abstract = "Next Generation Sequencing (NGS) reads obtained by sequencing of the junction of a mobile element and the host flanking region from individuals in a population are typically mapped to a reference genome to determine the location of the mobile element-host junction. We propose a clustering pipeline for grouping such NGS data into clusters corresponding to the locations of integration sites in the genome. Our pipeline relies on the UCLUST clustering software, which clusters reads into groups using a clustering threshold, to cluster the integration sites NGS reads into groups based on their site of origin. An optimal clustering threshold is chosen based on a proposed clustering measure, I - index. We evaluate our pipeline on simulated integration sites data from the human genome and compare its performance to UCLUST clustering. Our pipeline is more accurate in recovering both the number and the correct sequence of the integration sites when compared to the other method. This pipeline can be beneficial in detecting the mobile element-host junctions in a population for species with no reference genome.",
author = "Raunaq Malhotra and Daniel Elleder and Le Bao and Hunter, {David R.} and Mary Poss and Raj Acharya",
note = "Funding Information: This work was supported, in part, by the National Science Foundation Awards 1421908, 1533797, the United States Geological Survey award 06HQAG0131 and by the Czech Ministry of Education, Youth and Sports grant LK11215. Publisher Copyright: Copyright ISCA.; 8th International Conference on Bioinformatics and Computational Biology, BICOB 2016 ; Conference date: 04-04-2016 Through 06-04-2016",
year = "2016",
language = "English (US)",
series = "Proceedings of the 8th International Conference on Bioinformatics and Computational Biology, BICOB 2016",
publisher = "The International Society for Computers and Their Applications (ISCA)",
pages = "63--68",
editor = "Nurit Haspel and Thomas Ioerger",
booktitle = "Proceedings of the 8th International Conference on Bioinformatics and Computational Biology, BICOB 2016",
}