Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles

Clustering is carried out to identify patterns in transcriptomics profiles to determine clinically relevant subgroups of patients. Feature (gene) selection is a critical and an integral part of the process. Currently, there are many feature selection and clustering methods to identify the relevant g...

Full description

Saved in:
Bibliographic Details
Main Authors: Lawlor, Nathan, Fabbri, Alec, Guan, Peiyong, George, Joshy, Karuturi, R. Krishna Murthy
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2018
Subjects:
Online Access:https://hdl.handle.net/10356/89433
http://hdl.handle.net/10220/47077
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-89433
record_format dspace
spelling sg-ntu-dr.10356-894332022-02-16T16:31:35Z Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles Lawlor, Nathan Fabbri, Alec Guan, Peiyong George, Joshy Karuturi, R. Krishna Murthy School of Computer Science and Engineering DRNTU::Engineering::Computer science and engineering R Software Gene Selection Clustering is carried out to identify patterns in transcriptomics profiles to determine clinically relevant subgroups of patients. Feature (gene) selection is a critical and an integral part of the process. Currently, there are many feature selection and clustering methods to identify the relevant genes and perform clustering of samples. However, choosing an appropriate methodology is difficult. In addition, extensive feature selection methods have not been supported by the available packages. Hence, we developed an integrative R-package called multiClust that allows researchers to experiment with the choice of combination of methods for gene selection and clustering with ease. Using multiClust, we identified the best performing clustering methodology in the context of clinical outcome. Our observations demonstrate that simple methods such as variance-based ranking perform well on the majority of data sets, provided that the appropriate number of genes is selected. However, different gene ranking and selection methods remain relevant as no methodology works for all studies. Published version 2018-12-19T02:12:01Z 2019-12-06T17:25:23Z 2018-12-19T02:12:01Z 2019-12-06T17:25:23Z 2016 Journal Article Lawlor, N., Fabbri, A., Guan, P., George, J., & Karuturi, R. K. M. (2016). multiClust: An R-package for Identifying Biologically Relevant Clusters in Cancer Transcriptome Profiles. Cancer Informatics, 15, 103-114. doi:10.4137/CIN.S38000 https://hdl.handle.net/10356/89433 http://hdl.handle.net/10220/47077 10.4137/CIN.S38000 27330269 en Cancer Informatics © 2016 the authors, publisher and licensee Libertas Academica Limited. This is an open-access article distributed under the terms of the Creative Commons CC-BY-NC 3.0 License. 12 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
R Software
Gene Selection
spellingShingle DRNTU::Engineering::Computer science and engineering
R Software
Gene Selection
Lawlor, Nathan
Fabbri, Alec
Guan, Peiyong
George, Joshy
Karuturi, R. Krishna Murthy
Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
description Clustering is carried out to identify patterns in transcriptomics profiles to determine clinically relevant subgroups of patients. Feature (gene) selection is a critical and an integral part of the process. Currently, there are many feature selection and clustering methods to identify the relevant genes and perform clustering of samples. However, choosing an appropriate methodology is difficult. In addition, extensive feature selection methods have not been supported by the available packages. Hence, we developed an integrative R-package called multiClust that allows researchers to experiment with the choice of combination of methods for gene selection and clustering with ease. Using multiClust, we identified the best performing clustering methodology in the context of clinical outcome. Our observations demonstrate that simple methods such as variance-based ranking perform well on the majority of data sets, provided that the appropriate number of genes is selected. However, different gene ranking and selection methods remain relevant as no methodology works for all studies.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Lawlor, Nathan
Fabbri, Alec
Guan, Peiyong
George, Joshy
Karuturi, R. Krishna Murthy
format Article
author Lawlor, Nathan
Fabbri, Alec
Guan, Peiyong
George, Joshy
Karuturi, R. Krishna Murthy
author_sort Lawlor, Nathan
title Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
title_short Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
title_full Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
title_fullStr Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
title_full_unstemmed Multiclust: an R-package for identifying biologically relevant clusters in cancer transcriptome profiles
title_sort multiclust: an r-package for identifying biologically relevant clusters in cancer transcriptome profiles
publishDate 2018
url https://hdl.handle.net/10356/89433
http://hdl.handle.net/10220/47077
_version_ 1725985738200186880