TransportTP: A two-phase classification approach for membrane transporter prediction and characterization
<p>Abstract</p> <p>Background</p> <p>Membrane transporters play crucial roles in living cells. Experimental characterization of transporters is costly and time-consuming. Current computational methods for transporter characterization still require extensive curation eff...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2009-12-01
|
Series: | BMC Bioinformatics |
Online Access: | http://www.biomedcentral.com/1471-2105/10/418 |
id |
doaj-2484516b257d4f92abb8e04630e14cf5 |
---|---|
record_format |
Article |
spelling |
doaj-2484516b257d4f92abb8e04630e14cf52020-11-24T21:59:46ZengBMCBMC Bioinformatics1471-21052009-12-0110141810.1186/1471-2105-10-418TransportTP: A two-phase classification approach for membrane transporter prediction and characterizationUdvardi Michael KBenedito Vagner ALi HaiquanZhao Patrick<p>Abstract</p> <p>Background</p> <p>Membrane transporters play crucial roles in living cells. Experimental characterization of transporters is costly and time-consuming. Current computational methods for transporter characterization still require extensive curation efforts, especially for eukaryotic organisms. We developed a novel genome-scale transporter prediction and characterization system called TransportTP that combined homology-based and machine learning methods in a two-phase classification approach. First, traditional homology methods were employed to predict novel transporters based on sequence similarity to known classified proteins in the Transporter Classification Database (TCDB). Second, machine learning methods were used to integrate a variety of features to refine the initial predictions. A set of rules based on transporter features was developed by machine learning using well-curated proteomes as guides.</p> <p>Results</p> <p>In a cross-validation using the yeast proteome for training and the proteomes of ten other organisms for testing, TransportTP achieved an equivalent recall and precision of 81.8%, based on TransportDB, a manually annotated transporter database. In an independent test using the Arabidopsis proteome for training and four recently sequenced plant proteomes for testing, it achieved a recall of 74.6% and a precision of 73.4%, according to our manual curation.</p> <p>Conclusions</p> <p>TransportTP is the most effective tool for eukaryotic transporter characterization up to date.</p> http://www.biomedcentral.com/1471-2105/10/418 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Udvardi Michael K Benedito Vagner A Li Haiquan Zhao Patrick |
spellingShingle |
Udvardi Michael K Benedito Vagner A Li Haiquan Zhao Patrick TransportTP: A two-phase classification approach for membrane transporter prediction and characterization BMC Bioinformatics |
author_facet |
Udvardi Michael K Benedito Vagner A Li Haiquan Zhao Patrick |
author_sort |
Udvardi Michael K |
title |
TransportTP: A two-phase classification approach for membrane transporter prediction and characterization |
title_short |
TransportTP: A two-phase classification approach for membrane transporter prediction and characterization |
title_full |
TransportTP: A two-phase classification approach for membrane transporter prediction and characterization |
title_fullStr |
TransportTP: A two-phase classification approach for membrane transporter prediction and characterization |
title_full_unstemmed |
TransportTP: A two-phase classification approach for membrane transporter prediction and characterization |
title_sort |
transporttp: a two-phase classification approach for membrane transporter prediction and characterization |
publisher |
BMC |
series |
BMC Bioinformatics |
issn |
1471-2105 |
publishDate |
2009-12-01 |
description |
<p>Abstract</p> <p>Background</p> <p>Membrane transporters play crucial roles in living cells. Experimental characterization of transporters is costly and time-consuming. Current computational methods for transporter characterization still require extensive curation efforts, especially for eukaryotic organisms. We developed a novel genome-scale transporter prediction and characterization system called TransportTP that combined homology-based and machine learning methods in a two-phase classification approach. First, traditional homology methods were employed to predict novel transporters based on sequence similarity to known classified proteins in the Transporter Classification Database (TCDB). Second, machine learning methods were used to integrate a variety of features to refine the initial predictions. A set of rules based on transporter features was developed by machine learning using well-curated proteomes as guides.</p> <p>Results</p> <p>In a cross-validation using the yeast proteome for training and the proteomes of ten other organisms for testing, TransportTP achieved an equivalent recall and precision of 81.8%, based on TransportDB, a manually annotated transporter database. In an independent test using the Arabidopsis proteome for training and four recently sequenced plant proteomes for testing, it achieved a recall of 74.6% and a precision of 73.4%, according to our manual curation.</p> <p>Conclusions</p> <p>TransportTP is the most effective tool for eukaryotic transporter characterization up to date.</p> |
url |
http://www.biomedcentral.com/1471-2105/10/418 |
work_keys_str_mv |
AT udvardimichaelk transporttpatwophaseclassificationapproachformembranetransporterpredictionandcharacterization AT beneditovagnera transporttpatwophaseclassificationapproachformembranetransporterpredictionandcharacterization AT lihaiquan transporttpatwophaseclassificationapproachformembranetransporterpredictionandcharacterization AT zhaopatrick transporttpatwophaseclassificationapproachformembranetransporterpredictionandcharacterization |
_version_ |
1725847249028644864 |