Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach

Shivakumar Keerthikumar, Sahely Bhadra, Kumaran Kandasamy, Rajesh Raju, Y. L. Ramachandra, Chiranjib Bhattacharyya, Kohsuke Imai, Osamu Ohara, Sujatha Mohan, Akhilesh Pandey

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Screening and early identification of primary immunodeficiency disease (PID) genes is a major challenge for physicians. Many resources have catalogued molecular alterations in known PID genes along with their associated clinical and immunological phenotypes. However, these resources do not assist in identifying candidate PID genes. We have recently developed a platform designated Resource of Asian PDIs, which hosts information pertaining to molecular alterations, protein-protein interaction networks, mouse studies and microarray gene expression profiling of all known PID genes. Using this resource as a discovery tool, we describe the development of an algorithm for prediction of candidate PID genes. Using a support vector machine learning approach, we have predicted 1442 candidate PID genes using 69 binary features of 148 known PID genes and 3162 non-PID genes as a training data set. The power of this approach is illustrated by the fact that six of the predicted genes have recently been experimentally confirmed to be PID genes. The remaining genes in this predicted data set represent attractive candidates for testing in patients where the etiology cannot be ascribed to any of the known PID genes.

Original languageEnglish (US)
Pages (from-to)345-351
Number of pages7
JournalDNA Research
Volume16
Issue number6
DOIs
StatePublished - Dec 1 2009
Externally publishedYes

Fingerprint

Genes
Support Vector Machine
Machine Learning
Protein Interaction Maps
Gene Expression Profiling
Physicians
Phenotype
Proteins
Datasets

Keywords

  • HPRD
  • Human Proteinpedia
  • NetPath
  • RAPID
  • SVM

ASJC Scopus subject areas

  • Molecular Biology
  • Genetics

Cite this

Keerthikumar, S., Bhadra, S., Kandasamy, K., Raju, R., Ramachandra, Y. L., Bhattacharyya, C., ... Pandey, A. (2009). Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach. DNA Research, 16(6), 345-351. https://doi.org/10.1093/dnares/dsp019

Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach. / Keerthikumar, Shivakumar; Bhadra, Sahely; Kandasamy, Kumaran; Raju, Rajesh; Ramachandra, Y. L.; Bhattacharyya, Chiranjib; Imai, Kohsuke; Ohara, Osamu; Mohan, Sujatha; Pandey, Akhilesh.

In: DNA Research, Vol. 16, No. 6, 01.12.2009, p. 345-351.

Research output: Contribution to journalArticle

Keerthikumar, S, Bhadra, S, Kandasamy, K, Raju, R, Ramachandra, YL, Bhattacharyya, C, Imai, K, Ohara, O, Mohan, S & Pandey, A 2009, 'Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach', DNA Research, vol. 16, no. 6, pp. 345-351. https://doi.org/10.1093/dnares/dsp019
Keerthikumar S, Bhadra S, Kandasamy K, Raju R, Ramachandra YL, Bhattacharyya C et al. Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach. DNA Research. 2009 Dec 1;16(6):345-351. https://doi.org/10.1093/dnares/dsp019
Keerthikumar, Shivakumar ; Bhadra, Sahely ; Kandasamy, Kumaran ; Raju, Rajesh ; Ramachandra, Y. L. ; Bhattacharyya, Chiranjib ; Imai, Kohsuke ; Ohara, Osamu ; Mohan, Sujatha ; Pandey, Akhilesh. / Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach. In: DNA Research. 2009 ; Vol. 16, No. 6. pp. 345-351.
@article{c9a9b75abfd4461cbc077428bc786e66,
title = "Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach",
abstract = "Screening and early identification of primary immunodeficiency disease (PID) genes is a major challenge for physicians. Many resources have catalogued molecular alterations in known PID genes along with their associated clinical and immunological phenotypes. However, these resources do not assist in identifying candidate PID genes. We have recently developed a platform designated Resource of Asian PDIs, which hosts information pertaining to molecular alterations, protein-protein interaction networks, mouse studies and microarray gene expression profiling of all known PID genes. Using this resource as a discovery tool, we describe the development of an algorithm for prediction of candidate PID genes. Using a support vector machine learning approach, we have predicted 1442 candidate PID genes using 69 binary features of 148 known PID genes and 3162 non-PID genes as a training data set. The power of this approach is illustrated by the fact that six of the predicted genes have recently been experimentally confirmed to be PID genes. The remaining genes in this predicted data set represent attractive candidates for testing in patients where the etiology cannot be ascribed to any of the known PID genes.",
keywords = "HPRD, Human Proteinpedia, NetPath, RAPID, SVM",
author = "Shivakumar Keerthikumar and Sahely Bhadra and Kumaran Kandasamy and Rajesh Raju and Ramachandra, {Y. L.} and Chiranjib Bhattacharyya and Kohsuke Imai and Osamu Ohara and Sujatha Mohan and Akhilesh Pandey",
year = "2009",
month = "12",
day = "1",
doi = "10.1093/dnares/dsp019",
language = "English (US)",
volume = "16",
pages = "345--351",
journal = "DNA Research",
issn = "1340-2838",
publisher = "Oxford University Press",
number = "6",

}

TY - JOUR

T1 - Prediction of candidate primary immunodeficiency disease genes using a support vector machine learning approach

AU - Keerthikumar, Shivakumar

AU - Bhadra, Sahely

AU - Kandasamy, Kumaran

AU - Raju, Rajesh

AU - Ramachandra, Y. L.

AU - Bhattacharyya, Chiranjib

AU - Imai, Kohsuke

AU - Ohara, Osamu

AU - Mohan, Sujatha

AU - Pandey, Akhilesh

PY - 2009/12/1

Y1 - 2009/12/1

N2 - Screening and early identification of primary immunodeficiency disease (PID) genes is a major challenge for physicians. Many resources have catalogued molecular alterations in known PID genes along with their associated clinical and immunological phenotypes. However, these resources do not assist in identifying candidate PID genes. We have recently developed a platform designated Resource of Asian PDIs, which hosts information pertaining to molecular alterations, protein-protein interaction networks, mouse studies and microarray gene expression profiling of all known PID genes. Using this resource as a discovery tool, we describe the development of an algorithm for prediction of candidate PID genes. Using a support vector machine learning approach, we have predicted 1442 candidate PID genes using 69 binary features of 148 known PID genes and 3162 non-PID genes as a training data set. The power of this approach is illustrated by the fact that six of the predicted genes have recently been experimentally confirmed to be PID genes. The remaining genes in this predicted data set represent attractive candidates for testing in patients where the etiology cannot be ascribed to any of the known PID genes.

AB - Screening and early identification of primary immunodeficiency disease (PID) genes is a major challenge for physicians. Many resources have catalogued molecular alterations in known PID genes along with their associated clinical and immunological phenotypes. However, these resources do not assist in identifying candidate PID genes. We have recently developed a platform designated Resource of Asian PDIs, which hosts information pertaining to molecular alterations, protein-protein interaction networks, mouse studies and microarray gene expression profiling of all known PID genes. Using this resource as a discovery tool, we describe the development of an algorithm for prediction of candidate PID genes. Using a support vector machine learning approach, we have predicted 1442 candidate PID genes using 69 binary features of 148 known PID genes and 3162 non-PID genes as a training data set. The power of this approach is illustrated by the fact that six of the predicted genes have recently been experimentally confirmed to be PID genes. The remaining genes in this predicted data set represent attractive candidates for testing in patients where the etiology cannot be ascribed to any of the known PID genes.

KW - HPRD

KW - Human Proteinpedia

KW - NetPath

KW - RAPID

KW - SVM

UR - http://www.scopus.com/inward/record.url?scp=75349087138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=75349087138&partnerID=8YFLogxK

U2 - 10.1093/dnares/dsp019

DO - 10.1093/dnares/dsp019

M3 - Article

C2 - 19801557

AN - SCOPUS:75349087138

VL - 16

SP - 345

EP - 351

JO - DNA Research

JF - DNA Research

SN - 1340-2838

IS - 6

ER -