Cargando…

A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains

Motivation: Peripheral membrane-targeting domain (MTD) families, such as C1-, C2- and PH domains, play a key role in signal transduction and membrane trafficking by dynamically translocating their parent proteins to specific plasma membranes when changes in lipid composition occur. It is, however, d...

Descripción completa

Detalles Bibliográficos
Autores principales: Källberg, Morten, Bhardwaj, Nitin, Langlois, Robert, Lu, Hui
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2012
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3436836/
https://www.ncbi.nlm.nih.gov/pubmed/22962463
http://dx.doi.org/10.1093/bioinformatics/bts409
_version_ 1782242708960575488
author Källberg, Morten
Bhardwaj, Nitin
Langlois, Robert
Lu, Hui
author_facet Källberg, Morten
Bhardwaj, Nitin
Langlois, Robert
Lu, Hui
author_sort Källberg, Morten
collection PubMed
description Motivation: Peripheral membrane-targeting domain (MTD) families, such as C1-, C2- and PH domains, play a key role in signal transduction and membrane trafficking by dynamically translocating their parent proteins to specific plasma membranes when changes in lipid composition occur. It is, however, difficult to determine the subset of domains within families displaying this property, as sequence motifs signifying the membrane binding properties are not well defined. For this reason, procedures based on sequence similarity alone are often insufficient in computational identification of MTDs within families (yielding less than 65% accuracy even with a sequence identity of 70%). Results: We present a machine learning protocol for determining membrane-targeting properties achieving 85–90% accuracy in separating binding and non-binding domains within families. Our model is based on features from both sequence and structure, thereby incorporation statistics obtained from the entire domain family and domain-specific physical quantities such as surface electrostatics. In addition, by using the enriched rules in alternating decision tree classifiers, we are able to determine the meaning of the assigned function labels in terms of biological mechanisms. Conclusions: The high accuracy of the learned models and good agreement between the rules discovered using the ADtree classifier and mechanisms reported in the literature reflect the value of machine learning protocols in both prediction and biological knowledge discovery. Our protocol can thus potentially be used as a general function annotation and knowledge mining tool for other protein domains. Availability: metador.bioengr.uic.edu Contact: huilu@uic.edu
format Online
Article
Text
id pubmed-3436836
institution National Center for Biotechnology Information
language English
publishDate 2012
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-34368362012-12-12 A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains Källberg, Morten Bhardwaj, Nitin Langlois, Robert Lu, Hui Bioinformatics Original Papers Motivation: Peripheral membrane-targeting domain (MTD) families, such as C1-, C2- and PH domains, play a key role in signal transduction and membrane trafficking by dynamically translocating their parent proteins to specific plasma membranes when changes in lipid composition occur. It is, however, difficult to determine the subset of domains within families displaying this property, as sequence motifs signifying the membrane binding properties are not well defined. For this reason, procedures based on sequence similarity alone are often insufficient in computational identification of MTDs within families (yielding less than 65% accuracy even with a sequence identity of 70%). Results: We present a machine learning protocol for determining membrane-targeting properties achieving 85–90% accuracy in separating binding and non-binding domains within families. Our model is based on features from both sequence and structure, thereby incorporation statistics obtained from the entire domain family and domain-specific physical quantities such as surface electrostatics. In addition, by using the enriched rules in alternating decision tree classifiers, we are able to determine the meaning of the assigned function labels in terms of biological mechanisms. Conclusions: The high accuracy of the learned models and good agreement between the rules discovered using the ADtree classifier and mechanisms reported in the literature reflect the value of machine learning protocols in both prediction and biological knowledge discovery. Our protocol can thus potentially be used as a general function annotation and knowledge mining tool for other protein domains. Availability: metador.bioengr.uic.edu Contact: huilu@uic.edu Oxford University Press 2012-09-15 2012-09-03 /pmc/articles/PMC3436836/ /pubmed/22962463 http://dx.doi.org/10.1093/bioinformatics/bts409 Text en © The Author(s) (2012). Published by Oxford University Press. http://creativecommons.org/licenses/by/3.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Original Papers
Källberg, Morten
Bhardwaj, Nitin
Langlois, Robert
Lu, Hui
A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title_full A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title_fullStr A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title_full_unstemmed A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title_short A structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
title_sort structure-based protocol for learning the family-specific mechanisms of membrane-binding domains
topic Original Papers
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3436836/
https://www.ncbi.nlm.nih.gov/pubmed/22962463
http://dx.doi.org/10.1093/bioinformatics/bts409
work_keys_str_mv AT kallbergmorten astructurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT bhardwajnitin astructurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT langloisrobert astructurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT luhui astructurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT kallbergmorten structurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT bhardwajnitin structurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT langloisrobert structurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains
AT luhui structurebasedprotocolforlearningthefamilyspecificmechanismsofmembranebindingdomains