Robust Microbial Markers for Non-Invasive Inflammatory Bowel Disease Identification

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Inflammatory Bowel Disease (IBD) is an umbrella term for a group of inflammatory diseases of the gastrointestinal tract, including Crohn’s Disease and ulcerative colitis. Changes to the intestinal microbiome, the community of micro-organisms that resides in the human gut, have been shown to contribute to the pathogenesis of IBD. IBD diagnosis is often delayed due its non-specific symptoms and because an invasive colonoscopy is required for confirmation, which leads to poor growth in children and worse treatment outcomes. Feature selection algorithms are often applied to microbial communities to identify bacterial groups that drive disease. It has been shown that aggregating Ensemble Feature Selection (EFS) can improve the robustness of feature selection algorithms, which is defined as the variation of feature selector output caused by small changes to the dataset. In this work we apply a two-step filter and an EFS process to generate robust feature subsets that can non-invasively predict IBD subtypes from high-resolution microbiome data. The predictive power of the robust feature subsets is the highest reported in literature to date. Furthermore, we identify five biologically plausible bacterial species that have not previously been implicated in IBD aetiology.
LanguageEnglish
Number of pages12
JournalIEEE Transactions on Computational Biology and Bioinformatics
Early online date30 Apr 2018
DOIs
Publication statusE-pub ahead of print - 30 Apr 2018

Fingerprint

Inflammatory Bowel Diseases
Microbiota
Colonoscopy
Ulcerative Colitis
Crohn Disease
Gastrointestinal Tract
Growth

Cite this

@article{d75afa32a1b84be69852d6db636302dd,
title = "Robust Microbial Markers for Non-Invasive Inflammatory Bowel Disease Identification",
abstract = "Inflammatory Bowel Disease (IBD) is an umbrella term for a group of inflammatory diseases of the gastrointestinal tract, including Crohn’s Disease and ulcerative colitis. Changes to the intestinal microbiome, the community of micro-organisms that resides in the human gut, have been shown to contribute to the pathogenesis of IBD. IBD diagnosis is often delayed due its non-specific symptoms and because an invasive colonoscopy is required for confirmation, which leads to poor growth in children and worse treatment outcomes. Feature selection algorithms are often applied to microbial communities to identify bacterial groups that drive disease. It has been shown that aggregating Ensemble Feature Selection (EFS) can improve the robustness of feature selection algorithms, which is defined as the variation of feature selector output caused by small changes to the dataset. In this work we apply a two-step filter and an EFS process to generate robust feature subsets that can non-invasively predict IBD subtypes from high-resolution microbiome data. The predictive power of the robust feature subsets is the highest reported in literature to date. Furthermore, we identify five biologically plausible bacterial species that have not previously been implicated in IBD aetiology.",
author = "Benjamin Wingfield and Sonya Coleman and T.Martin McGinnity and AJ Bjourson",
year = "2018",
month = "4",
day = "30",
doi = "10.1109/TCBB.2018.2831212",
language = "English",
journal = "IEEE/ACM Transactions on Computational Biology and Bioinformatics",
issn = "1545-5963",

}

TY - JOUR

T1 - Robust Microbial Markers for Non-Invasive Inflammatory Bowel Disease Identification

AU - Wingfield, Benjamin

AU - Coleman, Sonya

AU - McGinnity, T.Martin

AU - Bjourson, AJ

PY - 2018/4/30

Y1 - 2018/4/30

N2 - Inflammatory Bowel Disease (IBD) is an umbrella term for a group of inflammatory diseases of the gastrointestinal tract, including Crohn’s Disease and ulcerative colitis. Changes to the intestinal microbiome, the community of micro-organisms that resides in the human gut, have been shown to contribute to the pathogenesis of IBD. IBD diagnosis is often delayed due its non-specific symptoms and because an invasive colonoscopy is required for confirmation, which leads to poor growth in children and worse treatment outcomes. Feature selection algorithms are often applied to microbial communities to identify bacterial groups that drive disease. It has been shown that aggregating Ensemble Feature Selection (EFS) can improve the robustness of feature selection algorithms, which is defined as the variation of feature selector output caused by small changes to the dataset. In this work we apply a two-step filter and an EFS process to generate robust feature subsets that can non-invasively predict IBD subtypes from high-resolution microbiome data. The predictive power of the robust feature subsets is the highest reported in literature to date. Furthermore, we identify five biologically plausible bacterial species that have not previously been implicated in IBD aetiology.

AB - Inflammatory Bowel Disease (IBD) is an umbrella term for a group of inflammatory diseases of the gastrointestinal tract, including Crohn’s Disease and ulcerative colitis. Changes to the intestinal microbiome, the community of micro-organisms that resides in the human gut, have been shown to contribute to the pathogenesis of IBD. IBD diagnosis is often delayed due its non-specific symptoms and because an invasive colonoscopy is required for confirmation, which leads to poor growth in children and worse treatment outcomes. Feature selection algorithms are often applied to microbial communities to identify bacterial groups that drive disease. It has been shown that aggregating Ensemble Feature Selection (EFS) can improve the robustness of feature selection algorithms, which is defined as the variation of feature selector output caused by small changes to the dataset. In this work we apply a two-step filter and an EFS process to generate robust feature subsets that can non-invasively predict IBD subtypes from high-resolution microbiome data. The predictive power of the robust feature subsets is the highest reported in literature to date. Furthermore, we identify five biologically plausible bacterial species that have not previously been implicated in IBD aetiology.

U2 - 10.1109/TCBB.2018.2831212

DO - 10.1109/TCBB.2018.2831212

M3 - Article

JO - IEEE/ACM Transactions on Computational Biology and Bioinformatics

T2 - IEEE/ACM Transactions on Computational Biology and Bioinformatics

JF - IEEE/ACM Transactions on Computational Biology and Bioinformatics

SN - 1545-5963

ER -