Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

multiclassPairs: An R package to train multiclass pair-based classifier

Marzouka, Nour-Al-Dain LU and Eriksson, Pontus LU (2021) In Bioinformatics 37(18). p.3043-3044
Abstract
Motivation
k–Top Scoring Pairs (kTSP) algorithms utilize in-sample gene expression feature pair rules for class prediction, and have demonstrated excellent performance and robustness. The available packages and tools primarily focus on binary prediction (i.e. two classes). However, many real-world classification problems e.g., tumor subtype prediction, are multiclass tasks.
Results
Here, we present multiclassPairs, an R package to train pair-based single sample classifiers for multiclass problems. multiclassPairs offers two main methods to build multiclass prediction models, either using a one-vs-rest kTSP scheme or through a novel pair-based Random Forest approach. The package also provides options for dealing with class... (More)
Motivation
k–Top Scoring Pairs (kTSP) algorithms utilize in-sample gene expression feature pair rules for class prediction, and have demonstrated excellent performance and robustness. The available packages and tools primarily focus on binary prediction (i.e. two classes). However, many real-world classification problems e.g., tumor subtype prediction, are multiclass tasks.
Results
Here, we present multiclassPairs, an R package to train pair-based single sample classifiers for multiclass problems. multiclassPairs offers two main methods to build multiclass prediction models, either using a one-vs-rest kTSP scheme or through a novel pair-based Random Forest approach. The package also provides options for dealing with class imbalances, multiplatform training, missing features in test data, and visualization of training and test results.
Availability
‘multiclassPairs’ package is available on CRAN servers and GitHub: https://github.com/NourMarzouka/multiclassPairs
Supplementary information
Supplementary data are available at Bioinformatics online. (Less)
Please use this url to cite or link to this publication:
author
and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Bioinformatics
volume
37
issue
18
article number
btab088
pages
3043 - 3044
publisher
Oxford University Press
external identifiers
  • pmid:33543757
  • scopus:85119084997
ISSN
1367-4803
DOI
10.1093/bioinformatics/btab088
language
English
LU publication?
yes
id
046f029e-97c1-423e-aee5-77c9ec34cbfd
date added to LUP
2021-02-08 13:34:49
date last changed
2023-05-17 10:33:45
@misc{046f029e-97c1-423e-aee5-77c9ec34cbfd,
  abstract     = {{Motivation<br/>k–Top Scoring Pairs (kTSP) algorithms utilize in-sample gene expression feature pair rules for class prediction, and have demonstrated excellent performance and robustness. The available packages and tools primarily focus on binary prediction (i.e. two classes). However, many real-world classification problems e.g., tumor subtype prediction, are multiclass tasks.<br/>Results<br/>Here, we present multiclassPairs, an R package to train pair-based single sample classifiers for multiclass problems. multiclassPairs offers two main methods to build multiclass prediction models, either using a one-vs-rest kTSP scheme or through a novel pair-based Random Forest approach. The package also provides options for dealing with class imbalances, multiplatform training, missing features in test data, and visualization of training and test results.<br/>Availability<br/>‘multiclassPairs’ package is available on CRAN servers and GitHub: https://github.com/NourMarzouka/multiclassPairs<br/>Supplementary information<br/>Supplementary data are available at Bioinformatics online.}},
  author       = {{Marzouka, Nour-Al-Dain and Eriksson, Pontus}},
  issn         = {{1367-4803}},
  language     = {{eng}},
  month        = {{02}},
  number       = {{18}},
  pages        = {{3043--3044}},
  publisher    = {{Oxford University Press}},
  series       = {{Bioinformatics}},
  title        = {{multiclassPairs: An R package to train multiclass pair-based classifier}},
  url          = {{http://dx.doi.org/10.1093/bioinformatics/btab088}},
  doi          = {{10.1093/bioinformatics/btab088}},
  volume       = {{37}},
  year         = {{2021}},
}