Abstract | ||
---|---|---|
Different microRNA target prediction tools produce different results. Motivated by this fact, here we present an ensemble-learning approach that combines the outcomes from multiple tools to reduce prediction error. We test this approach with a dataset derived from a public database containing human microRNAs and microRNA-mRNA pairs. According to our experimental result, using the proposed method tends to be significantly better than using individual prediction tools in terms of increasing the area under curve (AUC) defined on a receiver operating characteristic curve. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/BIGCOMP.2014.6741403 | BigComp |
Keywords | Field | DocType |
ensemble-learning approach,area under curve,robust microrna-mrna interaction prediction,learning (artificial intelligence),human micrornas,receiver operating characteristic curve,prediction error reduction,microrna-mrna pairs,auc,bioinformatics,rna,microrna target prediction tools,public database,learning artificial intelligence | Data mining,Mean squared prediction error,Receiver operating characteristic,Computer science,Artificial intelligence,Ensemble learning,Machine learning | Conference |
ISSN | Citations | PageRank |
2375-933X | 0 | 0.34 |
References | Authors | |
8 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Seunghak Yu | 1 | 0 | 0.34 |
Juho Kim | 2 | 632 | 68.72 |
Hyeyoung Min | 3 | 29 | 5.34 |
Sungroh Yoon | 4 | 566 | 78.80 |