Self-organization and associative memory: 3rd edition
Self-organization and associative memory: 3rd edition
BSB'07 Proceedings of the 2nd Brazilian conference on Advances in bioinformatics and computational biology
ISBRA'11 Proceedings of the 7th international conference on Bioinformatics research and applications
| Hi-index | 0.00 |
Recent experiments have shown that some types of RNA may control gene expression and phenotype by themselves, besides their traditional role of allowing the protein synthesis. Roughly speaking, RNAs can be divided into two classes: mRNAs, that are translated into proteins, and non-coding RNAs (ncRNAs), which play several cellular important roles besides protein coding. In recent years, many computational methods based on different theories and models have been proposed to distinguish mRNAs from ncRNAs. Particularly, Self-Organizing Maps (SOM), a neural network model, is time efficient for the training step, and present a straightforward implementation that allow easily increasing of the number of classes for clustering the input data. In this work, we propose a method for identifying non-coding RNAs using Self Organizing Maps, named SOM-PORTRAIT. We implemented the method and applied it to a data set containing Assembled ESTs of the Paracoccidioides brasiliensis fungus transcriptome. The obtained results were promising, with the advantage that the time and memory requirements needed to our SOM-PORTRAIT are much less than those needed for methods based on the Support Vector Machine (SVM) paradigm, like PORTRAIT.