Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees

MicroRNAs (miRNAs) are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predic...

Full description

Saved in:
Bibliographic Details
Main Authors: Philip H. Williams, Rod Eyles, Georg Weiller
Format: Article
Language:English
Published: Wiley 2012-01-01
Series:Journal of Nucleic Acids
Online Access:http://dx.doi.org/10.1155/2012/652979
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832548543387140096
author Philip H. Williams
Rod Eyles
Georg Weiller
author_facet Philip H. Williams
Rod Eyles
Georg Weiller
author_sort Philip H. Williams
collection DOAJ
description MicroRNAs (miRNAs) are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predicted miRNA precursors, mature miRNAs, and other nonprotein coding sequences. MirTools, mirDeep2, and miRanalyzer require “read count” to be included with the input sequences, which restricts their use to deep-sequencing data. Our aim was to train a predictor using a cross-section of different species to accurately predict miRNAs outside the training set. We wanted a system that did not require read-count for prediction and could therefore be applied to short sequences extracted from genomic, EST, or RNA-seq sources. A miRNA-predictive decision-tree model has been developed by supervised machine learning. It only requires that the corresponding genome or transcriptome is available within a sequence window that includes the precursor candidate so that the required sequence features can be collected. Some of the most critical features for training the predictor are the miRNA:miRNA∗ duplex energy and the number of mismatches in the duplex. We present a cross-species plant miRNA predictor with 84.08% sensitivity and 98.53% specificity based on rigorous testing by leave-one-out validation.
format Article
id doaj-art-6ac5ceea3fba4c87b371be843c3242d9
institution Kabale University
issn 2090-0201
2090-021X
language English
publishDate 2012-01-01
publisher Wiley
record_format Article
series Journal of Nucleic Acids
spelling doaj-art-6ac5ceea3fba4c87b371be843c3242d92025-02-03T06:13:48ZengWileyJournal of Nucleic Acids2090-02012090-021X2012-01-01201210.1155/2012/652979652979Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision TreesPhilip H. Williams0Rod Eyles1Georg Weiller2Division of Plant Sciences, Research School of Biology, College of Medicine, Biology & Environment, The Australian National University, Canberra, ACT 0200, AustraliaDivision of Plant Sciences, Research School of Biology, College of Medicine, Biology & Environment, The Australian National University, Canberra, ACT 0200, AustraliaDivision of Plant Sciences, Research School of Biology, College of Medicine, Biology & Environment, The Australian National University, Canberra, ACT 0200, AustraliaMicroRNAs (miRNAs) are nonprotein coding RNAs between 20 and 22 nucleotides long that attenuate protein production. Different types of sequence data are being investigated for novel miRNAs, including genomic and transcriptomic sequences. A variety of machine learning methods have successfully predicted miRNA precursors, mature miRNAs, and other nonprotein coding sequences. MirTools, mirDeep2, and miRanalyzer require “read count” to be included with the input sequences, which restricts their use to deep-sequencing data. Our aim was to train a predictor using a cross-section of different species to accurately predict miRNAs outside the training set. We wanted a system that did not require read-count for prediction and could therefore be applied to short sequences extracted from genomic, EST, or RNA-seq sources. A miRNA-predictive decision-tree model has been developed by supervised machine learning. It only requires that the corresponding genome or transcriptome is available within a sequence window that includes the precursor candidate so that the required sequence features can be collected. Some of the most critical features for training the predictor are the miRNA:miRNA∗ duplex energy and the number of mismatches in the duplex. We present a cross-species plant miRNA predictor with 84.08% sensitivity and 98.53% specificity based on rigorous testing by leave-one-out validation.http://dx.doi.org/10.1155/2012/652979
spellingShingle Philip H. Williams
Rod Eyles
Georg Weiller
Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
Journal of Nucleic Acids
title Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
title_full Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
title_fullStr Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
title_full_unstemmed Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
title_short Plant MicroRNA Prediction by Supervised Machine Learning Using C5.0 Decision Trees
title_sort plant microrna prediction by supervised machine learning using c5 0 decision trees
url http://dx.doi.org/10.1155/2012/652979
work_keys_str_mv AT philiphwilliams plantmicrornapredictionbysupervisedmachinelearningusingc50decisiontrees
AT rodeyles plantmicrornapredictionbysupervisedmachinelearningusingc50decisiontrees
AT georgweiller plantmicrornapredictionbysupervisedmachinelearningusingc50decisiontrees