Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.

Metabolomic data processing pipelines have been improving in recent years, allowing for greater feature extraction and identification. Lately, machine learning and robust statistical techniques to control false discoveries are being incorporated into metabolomic data analysis. In this paper, we intr...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shoaib Bin Masud, Conor Jenkins, Erika Hussey, Seth Elkin-Frankston, Phillip Mach, Elizabeth Dhummakupt, Shuchin Aeron
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/ff97c7d7b98d40f8b88205d0084b8322
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:ff97c7d7b98d40f8b88205d0084b8322
record_format dspace
spelling oai:doaj.org-article:ff97c7d7b98d40f8b88205d0084b83222021-12-02T20:08:56ZUtilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.1932-620310.1371/journal.pone.0255240https://doaj.org/article/ff97c7d7b98d40f8b88205d0084b83222021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0255240https://doaj.org/toc/1932-6203Metabolomic data processing pipelines have been improving in recent years, allowing for greater feature extraction and identification. Lately, machine learning and robust statistical techniques to control false discoveries are being incorporated into metabolomic data analysis. In this paper, we introduce one such recently developed technique called aggregate knockoff filtering to untargeted metabolomic analysis. When applied to a publicly available dataset, aggregate knockoff filtering combined with typical p-value filtering improves the number of significantly changing metabolites by 25% when compared to conventional untargeted metabolomic data processing. By using this method, features that would normally not be extracted under standard processing would be brought to researchers' attention for further analysis.Shoaib Bin MasudConor JenkinsErika HusseySeth Elkin-FrankstonPhillip MachElizabeth DhummakuptShuchin AeronPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 7, p e0255240 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Shoaib Bin Masud
Conor Jenkins
Erika Hussey
Seth Elkin-Frankston
Phillip Mach
Elizabeth Dhummakupt
Shuchin Aeron
Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
description Metabolomic data processing pipelines have been improving in recent years, allowing for greater feature extraction and identification. Lately, machine learning and robust statistical techniques to control false discoveries are being incorporated into metabolomic data analysis. In this paper, we introduce one such recently developed technique called aggregate knockoff filtering to untargeted metabolomic analysis. When applied to a publicly available dataset, aggregate knockoff filtering combined with typical p-value filtering improves the number of significantly changing metabolites by 25% when compared to conventional untargeted metabolomic data processing. By using this method, features that would normally not be extracted under standard processing would be brought to researchers' attention for further analysis.
format article
author Shoaib Bin Masud
Conor Jenkins
Erika Hussey
Seth Elkin-Frankston
Phillip Mach
Elizabeth Dhummakupt
Shuchin Aeron
author_facet Shoaib Bin Masud
Conor Jenkins
Erika Hussey
Seth Elkin-Frankston
Phillip Mach
Elizabeth Dhummakupt
Shuchin Aeron
author_sort Shoaib Bin Masud
title Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
title_short Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
title_full Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
title_fullStr Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
title_full_unstemmed Utilizing machine learning with knockoff filtering to extract significant metabolites in Crohn's disease with a publicly available untargeted metabolomics dataset.
title_sort utilizing machine learning with knockoff filtering to extract significant metabolites in crohn's disease with a publicly available untargeted metabolomics dataset.
publisher Public Library of Science (PLoS)
publishDate 2021
url https://doaj.org/article/ff97c7d7b98d40f8b88205d0084b8322
work_keys_str_mv AT shoaibbinmasud utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT conorjenkins utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT erikahussey utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT sethelkinfrankston utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT phillipmach utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT elizabethdhummakupt utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
AT shuchinaeron utilizingmachinelearningwithknockofffilteringtoextractsignificantmetabolitesincrohnsdiseasewithapubliclyavailableuntargetedmetabolomicsdataset
_version_ 1718375160892882944