Large scale identification and categorization of protein sequences using structured logistic regression

Research output: Contribution to journalJournal articlepeer-review

Standard

Large scale identification and categorization of protein sequences using structured logistic regression. / Pedersen, Bjørn Panella; Ifrim, Georgiana; Liboriussen, Poul; Axelsen, Kristian B; Palmgren, Michael Broberg; Nissen, Poul; Wiuf, Carsten Henrik; Pedersen, Christian N S.

In: PLOS ONE, Vol. 9, No. 1, e85139, 20.01.2014.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Pedersen, BP, Ifrim, G, Liboriussen, P, Axelsen, KB, Palmgren, MB, Nissen, P, Wiuf, CH & Pedersen, CNS 2014, 'Large scale identification and categorization of protein sequences using structured logistic regression', PLOS ONE, vol. 9, no. 1, e85139. https://doi.org/10.1371/journal.pone.0085139

APA

Pedersen, B. P., Ifrim, G., Liboriussen, P., Axelsen, K. B., Palmgren, M. B., Nissen, P., Wiuf, C. H., & Pedersen, C. N. S. (2014). Large scale identification and categorization of protein sequences using structured logistic regression. PLOS ONE, 9(1), [e85139]. https://doi.org/10.1371/journal.pone.0085139

Vancouver

Pedersen BP, Ifrim G, Liboriussen P, Axelsen KB, Palmgren MB, Nissen P et al. Large scale identification and categorization of protein sequences using structured logistic regression. PLOS ONE. 2014 Jan 20;9(1). e85139. https://doi.org/10.1371/journal.pone.0085139

Author

Pedersen, Bjørn Panella ; Ifrim, Georgiana ; Liboriussen, Poul ; Axelsen, Kristian B ; Palmgren, Michael Broberg ; Nissen, Poul ; Wiuf, Carsten Henrik ; Pedersen, Christian N S. / Large scale identification and categorization of protein sequences using structured logistic regression. In: PLOS ONE. 2014 ; Vol. 9, No. 1.

Bibtex

@article{3e2e68d14b43459790d4efd03708868d,
title = "Large scale identification and categorization of protein sequences using structured logistic regression",
abstract = "AbstractBackgroundStructured Logistic Regression (SLR) is a newly developed machine learning tool first proposed in the context of text categorization. Current availability of extensive protein sequence databases calls for an automated method to reliably classify sequences and SLR seems well-suited for this task. The classification of P-type ATPases, a large family of ATP-driven membrane pumps transporting essential cations, was selected as a test-case that would generate important biological information as well as provide a proof-of-concept for the application of SLR to a large scale bioinformatics problem.ResultsUsing SLR, we have built classifiers to identify and automatically categorize P-type ATPases into one of 11 pre-defined classes. The SLR-classifiers are compared to a Hidden Markov Model approach and shown to be highly accurate and scalable. Representing the bulk of currently known sequences, we analysed 9.3 million sequences in the UniProtKB and attempted to classify a large number of P-type ATPases. To examine the distribution of pumps on organisms, we also applied SLR to 1,123 complete genomes from the Entrez genome database. Finally, we analysed the predicted membrane topology of the identified P-type ATPases.ConclusionsUsing the SLR-based classification tool we are able to run a large scale study of P-type ATPases. This study provides proof-of-concept for the application of SLR to a bioinformatics problem and the analysis of P-type ATPases pinpoints new and interesting targets for further biochemical characterization and structural analysis.",
author = "Pedersen, {Bj{\o}rn Panella} and Georgiana Ifrim and Poul Liboriussen and Axelsen, {Kristian B} and Palmgren, {Michael Broberg} and Poul Nissen and Wiuf, {Carsten Henrik} and Pedersen, {Christian N S}",
year = "2014",
month = jan,
day = "20",
doi = "10.1371/journal.pone.0085139",
language = "English",
volume = "9",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "1",

}

RIS

TY - JOUR

T1 - Large scale identification and categorization of protein sequences using structured logistic regression

AU - Pedersen, Bjørn Panella

AU - Ifrim, Georgiana

AU - Liboriussen, Poul

AU - Axelsen, Kristian B

AU - Palmgren, Michael Broberg

AU - Nissen, Poul

AU - Wiuf, Carsten Henrik

AU - Pedersen, Christian N S

PY - 2014/1/20

Y1 - 2014/1/20

N2 - AbstractBackgroundStructured Logistic Regression (SLR) is a newly developed machine learning tool first proposed in the context of text categorization. Current availability of extensive protein sequence databases calls for an automated method to reliably classify sequences and SLR seems well-suited for this task. The classification of P-type ATPases, a large family of ATP-driven membrane pumps transporting essential cations, was selected as a test-case that would generate important biological information as well as provide a proof-of-concept for the application of SLR to a large scale bioinformatics problem.ResultsUsing SLR, we have built classifiers to identify and automatically categorize P-type ATPases into one of 11 pre-defined classes. The SLR-classifiers are compared to a Hidden Markov Model approach and shown to be highly accurate and scalable. Representing the bulk of currently known sequences, we analysed 9.3 million sequences in the UniProtKB and attempted to classify a large number of P-type ATPases. To examine the distribution of pumps on organisms, we also applied SLR to 1,123 complete genomes from the Entrez genome database. Finally, we analysed the predicted membrane topology of the identified P-type ATPases.ConclusionsUsing the SLR-based classification tool we are able to run a large scale study of P-type ATPases. This study provides proof-of-concept for the application of SLR to a bioinformatics problem and the analysis of P-type ATPases pinpoints new and interesting targets for further biochemical characterization and structural analysis.

AB - AbstractBackgroundStructured Logistic Regression (SLR) is a newly developed machine learning tool first proposed in the context of text categorization. Current availability of extensive protein sequence databases calls for an automated method to reliably classify sequences and SLR seems well-suited for this task. The classification of P-type ATPases, a large family of ATP-driven membrane pumps transporting essential cations, was selected as a test-case that would generate important biological information as well as provide a proof-of-concept for the application of SLR to a large scale bioinformatics problem.ResultsUsing SLR, we have built classifiers to identify and automatically categorize P-type ATPases into one of 11 pre-defined classes. The SLR-classifiers are compared to a Hidden Markov Model approach and shown to be highly accurate and scalable. Representing the bulk of currently known sequences, we analysed 9.3 million sequences in the UniProtKB and attempted to classify a large number of P-type ATPases. To examine the distribution of pumps on organisms, we also applied SLR to 1,123 complete genomes from the Entrez genome database. Finally, we analysed the predicted membrane topology of the identified P-type ATPases.ConclusionsUsing the SLR-based classification tool we are able to run a large scale study of P-type ATPases. This study provides proof-of-concept for the application of SLR to a bioinformatics problem and the analysis of P-type ATPases pinpoints new and interesting targets for further biochemical characterization and structural analysis.

U2 - 10.1371/journal.pone.0085139

DO - 10.1371/journal.pone.0085139

M3 - Journal article

C2 - 24465495

VL - 9

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 1

M1 - e85139

ER -

ID: 100977334