A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems

ABSTRACT Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made toward developing ML models that predict health out...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Begüm D. Topçuoğlu, Nicholas A. Lesniak, Mack T. Ruffin, Jenna Wiens, Patrick D. Schloss
Formato: article
Lenguaje:EN
Publicado: American Society for Microbiology 2020
Materias:
Acceso en línea:https://doaj.org/article/47b3a3d71e7741b48a1bbd42dbb2aeb9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:47b3a3d71e7741b48a1bbd42dbb2aeb9
record_format dspace
spelling oai:doaj.org-article:47b3a3d71e7741b48a1bbd42dbb2aeb92021-11-15T15:56:47ZA Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems10.1128/mBio.00434-202150-7511https://doaj.org/article/47b3a3d71e7741b48a1bbd42dbb2aeb92020-06-01T00:00:00Zhttps://journals.asm.org/doi/10.1128/mBio.00434-20https://doaj.org/toc/2150-7511ABSTRACT Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made toward developing ML models that predict health outcomes using bacterial abundances, but inconsistent adoption of training and evaluation methods call the validity of these models into question. Furthermore, there appears to be a preference by many researchers to favor increased model complexity over interpretability. To overcome these challenges, we trained seven models that used fecal 16S rRNA sequence data to predict the presence of colonic screen relevant neoplasias (SRNs) (n = 490 patients, 261 controls and 229 cases). We developed a reusable open-source pipeline to train, validate, and interpret ML models. To show the effect of model selection, we assessed the predictive performance, interpretability, and training time of L2-regularized logistic regression, L1- and L2-regularized support vector machines (SVM) with linear and radial basis function kernels, a decision tree, random forest, and gradient boosted trees (XGBoost). The random forest model performed best at detecting SRNs with an area under the receiver operating characteristic curve (AUROC) of 0.695 (interquartile range [IQR], 0.651 to 0.739) but was slow to train (83.2 h) and not inherently interpretable. Despite its simplicity, L2-regularized logistic regression followed random forest in predictive performance with an AUROC of 0.680 (IQR, 0.625 to 0.735), trained faster (12 min), and was inherently interpretable. Our analysis highlights the importance of choosing an ML approach based on the goal of the study, as the choice will inform expectations of performance and interpretability. IMPORTANCE Diagnosing diseases using machine learning (ML) is rapidly being adopted in microbiome studies. However, the estimated performance associated with these models is likely overoptimistic. Moreover, there is a trend toward using black box models without a discussion of the difficulty of interpreting such models when trying to identify microbial biomarkers of disease. This work represents a step toward developing more-reproducible ML practices in applying ML to microbiome research. We implement a rigorous pipeline and emphasize the importance of selecting ML models that reflect the goal of the study. These concepts are not particular to the study of human health but can also be applied to environmental microbiology studies.Begüm D. TopçuoğluNicholas A. LesniakMack T. RuffinJenna WiensPatrick D. SchlossAmerican Society for Microbiologyarticle16S rRNA genecolon cancermachine learningmicrobial ecologymicrobiomeMicrobiologyQR1-502ENmBio, Vol 11, Iss 3 (2020)
institution DOAJ
collection DOAJ
language EN
topic 16S rRNA gene
colon cancer
machine learning
microbial ecology
microbiome
Microbiology
QR1-502
spellingShingle 16S rRNA gene
colon cancer
machine learning
microbial ecology
microbiome
Microbiology
QR1-502
Begüm D. Topçuoğlu
Nicholas A. Lesniak
Mack T. Ruffin
Jenna Wiens
Patrick D. Schloss
A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
description ABSTRACT Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made toward developing ML models that predict health outcomes using bacterial abundances, but inconsistent adoption of training and evaluation methods call the validity of these models into question. Furthermore, there appears to be a preference by many researchers to favor increased model complexity over interpretability. To overcome these challenges, we trained seven models that used fecal 16S rRNA sequence data to predict the presence of colonic screen relevant neoplasias (SRNs) (n = 490 patients, 261 controls and 229 cases). We developed a reusable open-source pipeline to train, validate, and interpret ML models. To show the effect of model selection, we assessed the predictive performance, interpretability, and training time of L2-regularized logistic regression, L1- and L2-regularized support vector machines (SVM) with linear and radial basis function kernels, a decision tree, random forest, and gradient boosted trees (XGBoost). The random forest model performed best at detecting SRNs with an area under the receiver operating characteristic curve (AUROC) of 0.695 (interquartile range [IQR], 0.651 to 0.739) but was slow to train (83.2 h) and not inherently interpretable. Despite its simplicity, L2-regularized logistic regression followed random forest in predictive performance with an AUROC of 0.680 (IQR, 0.625 to 0.735), trained faster (12 min), and was inherently interpretable. Our analysis highlights the importance of choosing an ML approach based on the goal of the study, as the choice will inform expectations of performance and interpretability. IMPORTANCE Diagnosing diseases using machine learning (ML) is rapidly being adopted in microbiome studies. However, the estimated performance associated with these models is likely overoptimistic. Moreover, there is a trend toward using black box models without a discussion of the difficulty of interpreting such models when trying to identify microbial biomarkers of disease. This work represents a step toward developing more-reproducible ML practices in applying ML to microbiome research. We implement a rigorous pipeline and emphasize the importance of selecting ML models that reflect the goal of the study. These concepts are not particular to the study of human health but can also be applied to environmental microbiology studies.
format article
author Begüm D. Topçuoğlu
Nicholas A. Lesniak
Mack T. Ruffin
Jenna Wiens
Patrick D. Schloss
author_facet Begüm D. Topçuoğlu
Nicholas A. Lesniak
Mack T. Ruffin
Jenna Wiens
Patrick D. Schloss
author_sort Begüm D. Topçuoğlu
title A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
title_short A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
title_full A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
title_fullStr A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
title_full_unstemmed A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems
title_sort framework for effective application of machine learning to microbiome-based classification problems
publisher American Society for Microbiology
publishDate 2020
url https://doaj.org/article/47b3a3d71e7741b48a1bbd42dbb2aeb9
work_keys_str_mv AT begumdtopcuoglu aframeworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT nicholasalesniak aframeworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT macktruffin aframeworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT jennawiens aframeworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT patrickdschloss aframeworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT begumdtopcuoglu frameworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT nicholasalesniak frameworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT macktruffin frameworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT jennawiens frameworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
AT patrickdschloss frameworkforeffectiveapplicationofmachinelearningtomicrobiomebasedclassificationproblems
_version_ 1718427085450510336