TargetMiner: MicroRNA target prediction with systematic identification of tissue specific negative examples Export

@article{citeulike:5489191, abstract = {Motivation: Prediction of microRNA (miRNA) target mRNAs using machine learning approaches is an important area of research. However, most of the methods suffer from either high false positive or false negative rates. One reason for this is the marked deficiency of negative examples or miRNA-non target pairs. Systematic identification of non-target mRNAs is still not addressed properly, and therefore, current machine learning approaches are compelled to rely on artificially generated negative examples for training. Results: In this paper we have identified [\~{}]300 tissue specific negative examples using a novel approach that involves expression profiling of both miRNAs and mRNAs, miRNA-mRNA structural interactions and seed site conservation. The newly generated negative examples are validated with pSILAC data set (Selbach et al., 2008) that elucidate the fact that the identified non-targets are indeed non-targets.These high throughput tissue specific negative examples and a set of experimentally verified positive examples are then used to build a system called TargetMiner, a support vector machine (SVM) based classifier. In addition to assessing the prediction accuracy on cross-validation experiments, TargetMiner has been validated with a completely independent experimental test data set. Our method outperforms 10 existing target prediction algorithms and provides a good balance between sensitivity and specificity that is not reflected in the existing methods. We achieve a significantly higher sensitivity and specificity of 69\% and 67.8\% based on a pool of 90 feature set and 76.5\% and 66.1\% using a set of 30 selected feature set on the completely independent test data set. In order to establish the effectiveness of the systematically generated negative examples, the SVM is trained using a different set of negative data generated using the method in (Yousef et al., 2007). A significantly higher false positive rate (70.6\%) is observed when tested on the independent set, while all other factors are kept the same. Again, when an existing method (NBmiRTar) is executed with the our proposed negative data, we observe an improvement in its performance. These clearly establish the effectiveness of the proposed approach of selecting the negative examples systematically. Availability: TargetMiner is now available as an online tool at www.isical.ac.in/\~{}bioinfo\_miu Supplementarymaterials: Supplementarymaterials are available at www.isical.ac.in/\~{}bioinfo\_miu/Download.html Contact: sanghami@isical.ac.in, rmitra\_t@isical.ac.in 10.1093/bioinformatics/btp503}, author = {Bandyopadhyay, Sanghamitra and Mitra, Ramkrishna}, booktitle = {Bioinformatics}, citeulike-article-id = {5489191}, citeulike-linkout-0 = {http://dx.doi.org/10.1093/bioinformatics/btp503}, citeulike-linkout-1 = {http://bioinformatics.oxfordjournals.org/content/25/20/2625.abstract}, citeulike-linkout-2 = {http://bioinformatics.oxfordjournals.org/content/25/20/2625.full.pdf}, citeulike-linkout-3 = {http://view.ncbi.nlm.nih.gov/pubmed/19692556}, citeulike-linkout-4 = {http://www.hubmed.org/display.cgi?uids=19692556}, day = {19}, doi = {10.1093/bioinformatics/btp503}, issn = {1460-2059}, journal = {Bioinformatics}, keywords = {examples, identification, microrna, negative, prediction, specific, systematic, target, tissue}, month = {August}, number = {20}, pages = {btp503--2631}, posted-at = {2009-10-12 11:19:32}, priority = {2}, title = {TargetMiner: MicroRNA target prediction with systematic identification of tissue specific negative examples}, url = {http://dx.doi.org/10.1093/bioinformatics/btp503}, volume = {25}, year = {2009} }

TY - JOUR ID - citeulike:5489191 L3 - citeulike-article-id:5489191 N2 - Motivation: Prediction of microRNA (miRNA) target mRNAs using machine learning approaches is an important area of research. However, most of the methods suffer from either high false positive or false negative rates. One reason for this is the marked deficiency of negative examples or miRNA-non target pairs. Systematic identification of non-target mRNAs is still not addressed properly, and therefore, current machine learning approaches are compelled to rely on artificially generated negative examples for training. Results: In this paper we have identified [~]300 tissue specific negative examples using a novel approach that involves expression profiling of both miRNAs and mRNAs, miRNA-mRNA structural interactions and seed site conservation. The newly generated negative examples are validated with pSILAC data set (Selbach et al., 2008) that elucidate the fact that the identified non-targets are indeed non-targets.These high throughput tissue specific negative examples and a set of experimentally verified positive examples are then used to build a system called TargetMiner, a support vector machine (SVM) based classifier. In addition to assessing the prediction accuracy on cross-validation experiments, TargetMiner has been validated with a completely independent experimental test data set. Our method outperforms 10 existing target prediction algorithms and provides a good balance between sensitivity and specificity that is not reflected in the existing methods. We achieve a significantly higher sensitivity and specificity of 69% and 67.8% based on a pool of 90 feature set and 76.5% and 66.1% using a set of 30 selected feature set on the completely independent test data set. In order to establish the effectiveness of the systematically generated negative examples, the SVM is trained using a different set of negative data generated using the method in (Yousef et al., 2007). A significantly higher false positive rate (70.6%) is observed when tested on the independent set, while all other factors are kept the same. Again, when an existing method (NBmiRTar) is executed with the our proposed negative data, we observe an improvement in its performance. These clearly establish the effectiveness of the proposed approach of selecting the negative examples systematically. Availability: TargetMiner is now available as an online tool at www.isical.ac.in/~bioinfo_miu Supplementarymaterials: Supplementarymaterials are available at www.isical.ac.in/~bioinfo_miu/Download.html Contact: sanghami@isical.ac.in, rmitra_t@isical.ac.in 10.1093/bioinformatics/btp503 IS - 20 JF - Bioinformatics SN - 1460-2059 EP - 2631 TI - TargetMiner: MicroRNA target prediction with systematic identification of tissue specific negative examples VL - 25 T2 - Bioinformatics SP - btp503 KW - examples KW - identification KW - microrna KW - negative KW - prediction KW - specific KW - systematic KW - target KW - tissue AU - Bandyopadhyay, Sanghamitra AU - Mitra, Ramkrishna PY - 2009/08/19/ UR - http://dx.doi.org/10.1093/bioinformatics/btp503 ER -