Abstract:Nowadays, experiments have shown that some special types of RNA may control gene expressing and phenotype, besides their traditional role of allowing the protein synthesis. 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, several computational methods have been proposed to distinguish mRNAs from ncRNAs, using different theories and models. Self-Organizing Maps (SOM), a neural network model, is very efficient in time for the training step, and can be easily implemented, besides allowing to increase the number of classes for grouping the input data in a straightforward way.<BR/>We proposed and implemented a method for identifying non-coding RNAs using SOMs, named SOM-PORTRAIT. In order to accelerate the use of SOM-PORTRAIT for thousands of sequences, we propose Dist-SOM-PORTRAIT, in the context of the EELA-2 project. Basically, the Dist-SOM-PORTRAIT method will work as follows. First, the FASTA input file will be divided in as many parts as requested by the user, and each one of these portions will be stored on a separate file. Then, a job will be created for all these separated files, and will be automatically executed.