Simplified method to predict mutual interactions of human transcription factors based on their primary structure

Handle URI:
http://hdl.handle.net/10754/325289
Title:
Simplified method to predict mutual interactions of human transcription factors based on their primary structure
Authors:
Schmeier, Sebastian; Jankovic, Boris R.; Bajic, Vladimir B. ( 0000-0001-5435-4750 )
Abstract:
Background: Physical interactions between transcription factors (TFs) are necessary for forming regulatory protein complexes and thus play a crucial role in gene regulation. Currently, knowledge about the mechanisms of these TF interactions is incomplete and the number of known TF interactions is limited. Computational prediction of such interactions can help identify potential new TF interactions as well as contribute to better understanding the complex machinery involved in gene regulation. Methodology: We propose here such a method for the prediction of TF interactions. The method uses only the primary sequence information of the interacting TFs, resulting in a much greater simplicity of the prediction algorithm. Through an advanced feature selection process, we determined a subset of 97 model features that constitute the optimized model in the subset we considered. The model, based on quadratic discriminant analysis, achieves a prediction accuracy of 85.39% on a blind set of interactions. This result is achieved despite the selection for the negative data set of only those TF from the same type of proteins, i.e. TFs that function in the same cellular compartment (nucleus) and in the same type of molecular process (transcription initiation). Such selection poses significant challenges for developing models with high specificity, but at the same time better reflects real-world problems. Conclusions: The performance of our predictor compares well to those of much more complex approaches for predicting TF and general protein-protein interactions, particularly when taking the reduced complexity of model utilisation into account. © 2011 Schmeier et al.
KAUST Department:
Computational Bioscience Research Center (CBRC)
Citation:
Schmeier S, Jankovic B, Bajic VB (2011) Simplified Method to Predict Mutual Interactions of Human Transcription Factors Based on Their Primary Structure. PLoS ONE 6: e21887. doi:10.1371/journal.pone.0021887.
Publisher:
Public Library of Science (PLoS)
Journal:
PLoS ONE
Issue Date:
5-Jul-2011
DOI:
10.1371/journal.pone.0021887
PubMed ID:
21750739
PubMed Central ID:
PMC3130058
Type:
Article
ISSN:
19326203
Appears in Collections:
Articles; Computational Bioscience Research Center (CBRC)

Full metadata record

DC FieldValue Language
dc.contributor.authorSchmeier, Sebastianen
dc.contributor.authorJankovic, Boris R.en
dc.contributor.authorBajic, Vladimir B.en
dc.date.accessioned2014-08-27T09:45:08Z-
dc.date.available2014-08-27T09:45:08Z-
dc.date.issued2011-07-05en
dc.identifier.citationSchmeier S, Jankovic B, Bajic VB (2011) Simplified Method to Predict Mutual Interactions of Human Transcription Factors Based on Their Primary Structure. PLoS ONE 6: e21887. doi:10.1371/journal.pone.0021887.en
dc.identifier.issn19326203en
dc.identifier.pmid21750739en
dc.identifier.doi10.1371/journal.pone.0021887en
dc.identifier.urihttp://hdl.handle.net/10754/325289en
dc.description.abstractBackground: Physical interactions between transcription factors (TFs) are necessary for forming regulatory protein complexes and thus play a crucial role in gene regulation. Currently, knowledge about the mechanisms of these TF interactions is incomplete and the number of known TF interactions is limited. Computational prediction of such interactions can help identify potential new TF interactions as well as contribute to better understanding the complex machinery involved in gene regulation. Methodology: We propose here such a method for the prediction of TF interactions. The method uses only the primary sequence information of the interacting TFs, resulting in a much greater simplicity of the prediction algorithm. Through an advanced feature selection process, we determined a subset of 97 model features that constitute the optimized model in the subset we considered. The model, based on quadratic discriminant analysis, achieves a prediction accuracy of 85.39% on a blind set of interactions. This result is achieved despite the selection for the negative data set of only those TF from the same type of proteins, i.e. TFs that function in the same cellular compartment (nucleus) and in the same type of molecular process (transcription initiation). Such selection poses significant challenges for developing models with high specificity, but at the same time better reflects real-world problems. Conclusions: The performance of our predictor compares well to those of much more complex approaches for predicting TF and general protein-protein interactions, particularly when taking the reduced complexity of model utilisation into account. © 2011 Schmeier et al.en
dc.language.isoenen
dc.publisherPublic Library of Science (PLoS)en
dc.rightsSchmeier et al. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.en
dc.rightsArchived with thanks to PLoS ONEen
dc.subjectregulator proteinen
dc.subjecttranscription factoren
dc.subjectaccuracyen
dc.subjectamino acid sequenceen
dc.subjectcell nucleusen
dc.subjectcontrolled studyen
dc.subjectgenetic algorithmen
dc.subjectgenetic modelen
dc.subjectintracellular spaceen
dc.subjectpredictionen
dc.subjectprocess optimizationen
dc.subjectprotein functionen
dc.subjectprotein protein interactionen
dc.subjectsensitivity and specificityen
dc.subjecttranscription initiationen
dc.subjecttranscription regulationen
dc.subjectalgorithmen
dc.subjectbinding siteen
dc.subjectbiologyen
dc.subjectgeneticsen
dc.subjectmetabolismen
dc.subjectmethodologyen
dc.subjectprotein analysisen
dc.subjectprotein bindingen
dc.subjectreproducibilityen
dc.subjectAlgorithmsen
dc.subjectBinding Sitesen
dc.subjectComputational Biologyen
dc.subjectProtein Bindingen
dc.subjectProtein Interaction Mappingen
dc.subjectReproducibility of Resultsen
dc.subjectTranscription Factorsen
dc.titleSimplified method to predict mutual interactions of human transcription factors based on their primary structureen
dc.typeArticleen
dc.contributor.departmentComputational Bioscience Research Center (CBRC)en
dc.identifier.journalPLoS ONEen
dc.identifier.pmcidPMC3130058en
dc.eprint.versionPublisher's Version/PDFen
dc.contributor.institutionUnidad Académica de Sistemas Arrecifales (Puerto Morelos), Instituto de Ciencias Del Mar y Limnología, Universidad Nacional Autõnoma de México, Puerto Morelos, QR 77580, Mexicoen
dc.contributor.institutionSchool of Natural Sciences, University of California Merced, 5200 North Lake Road, Merced, CA 95343, United Statesen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorSchmeier, Sebastianen
kaust.authorBajic, Vladimir B.en
kaust.authorJankovic, Boris R.en

Related articles on PubMed

All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.