Understanding the Role of (Advanced) Machine Learning in Metagenomic Workflows

Thomas Krause, Bruno G. N. Andrade, Haithem Afli, Haiying Wang, Huiru Zheng, Matthias L. Hemmje

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

With the rapid decrease in sequencing costs there is an increased research interest in metagenomics, the study of the genomic content of microbial communities. Machine learning has also seen a revolution with regards to versatility and performance in the last decade using techniques like “Deep Learning”. Classical as well as modern machine learning (ML) techniques are already used in key areas within metagenomics. There are however several challenges that may impede broader use of ML and especially deep learning.

This paper provides an overview of machine learning in metagenomics, its challenges and its relationship to biomedical pipelines. Special focus is put on modern techniques such as deep learning. The results are then discussed again in the context of the AI2VIS4BigData reference model to validate its relevancy in this research area.
Original languageEnglish
Title of host publicationLecture Notes in Computer Science
Subtitle of host publicationAdvanced Visual Interfaces. Supporting Artificial Intelligence and Big Data Applications. AVI-BDA 2020, ITAVIS 2020
PublisherSpringer Cham
Pages56-82
Number of pages27
Volume12585
ISBN (Print)978-3-030-68006-0
DOIs
Publication statusPublished - 3 Feb 2021

Publication series

NameAdvanced Visual Interfaces. Supporting Artificial Intelligence and Big Data Applications
Volume12585
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Keywords

  • Machine learning
  • Deep learning
  • Metagenomics
  • Big data
  • AI2VIS4BigData

Fingerprint

Dive into the research topics of 'Understanding the Role of (Advanced) Machine Learning in Metagenomic Workflows'. Together they form a unique fingerprint.

Cite this