Naïve Bayes for microRNA target predictions—machine learning for microRNA targets

• Published in: Bioinformatics Vol. 23; no. 22; pp. 2987 - 2992
• Main Authors: Yousef, Malik, Jung, Segun, Kossenkov, Andrew V., Showe, Louise C., Showe, Michael K.
• Format: Journal Article
• Language: English
• Published: Oxford Oxford University Press 15.11.2007; Oxford Publishing Limited (England)
• Subjects: Algorithms; Artificial Intelligence; Base Sequence; Bayes Theorem; Biological and medical sciences; Fundamental and applied biological sciences. Psychology; Gene Targeting - methods; General aspects; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); MicroRNAs - genetics; Molecular Sequence Data; Pattern Recognition, Automated - methods; RNA Probes - genetics; Sequence Alignment - methods; Sequence Analysis, RNA - methods; Learning; Acquisition process; MicroRNA; Bioinformatics; Prediction
• ISSN: 1367-4803; 1367-4811; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/btm484

Motivation: Most computational methodologies for miRNA:mRNA target gene prediction use the seed segment of the miRNA and require cross-species sequence conservation in this region of the mRNA target. Methods that do not rely on conservation generate numbers of predictions, which are too large to validate. We describe a target prediction method (NBmiRTar) that does not require sequence conservation, using instead, machine learning by a naïve Bayes classifier. It generates a model from sequence and miRNA:mRNA duplex information from validated targets and artificially generated negative examples. Both the ‘seed’ and ‘out-seed’ segments of the miRNA:mRNA duplex are used for target identification. Results: The application of machine-learning techniques to the features we have used is a useful and general approach for microRNA target gene prediction. Our technique produces fewer false positive predictions and fewer target candidates to be tested. It exhibits higher sensitivity and specificity than algorithms that rely on conserved genomic regions to decrease false positive predictions. Availability: The NBmiRTar program is available at http://wotan.wistar.upenn.edu/NBmiRTar/ Contact: yousef@wistar.org Supplementary information: http://wotan.wistar.upenn.edu/NBmiRTar/