Marginalised Stack Denoising Autoencoders for Metagenomic Data Binning

Kouchaki, S., Tirunagari, S., Tapinos, A. and Robertson, D. L. (2017) Marginalised Stack Denoising Autoencoders for Metagenomic Data Binning. In: 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Manchester, UK, 23-25 Aug 2017, ISBN 9781467389884 (doi: 10.1109/CIBCB.2017.8058552)

Abstract

Shotgun sequencing has facilitated the analysis of complex microbial communities. Recently we have shown how local binary patterns (LBP) from image processing can be used to analyse the sequenced samples. LBP codes represent the data in a sparse high dimensional space. To improve the performance of our pipeline, marginalised stacked autoencoders are used here to learn frequent LBP codes and map the high dimensional space to a lower dimension dense space. We demonstrate its performance using both low and high complexity simulated metagenomic data and compare the performance of our method with several existing techniques including principal component analysis (PCA) in the dimension reduction step and fc-mer frequency in feature extraction step.

• Item Type: Conference Proceedings
• Additional Information: SK is supported by the VIROGENESIS project. The VIROGENESIS project receives funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 634650. AT is supported by a BBSRC project grant, BB/M001121/1.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Robertson, Professor David
• Authors: Kouchaki, S., Tirunagari, S., Tapinos, A., and Robertson, D. L.
• College/School: College of Medical Veterinary and Life Sciences > School of Infection & Immunity; College of Medical Veterinary and Life Sciences > School of Infection & Immunity > Centre for Virus Research
• ISBN: 9781467389884
• Published Online: 05 October 2017
• Copyright Holders: Copyright © 2017 IEEE
• First Published: First published in 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
• Publisher Policy: Reproduced in accordance with the publisher copyright policy