Publications of Giovanni Felici

This page shows all publications that appeared in the IASI annual research reports. Authors currently affiliated with the Institute are always listed with the full name.

You can browse through them using either the links of the following line or those associated with author names.

Show all publications of the year  2013, with author Felici G., in the category IASI Research Reports (or show them all):


IASI Research Report n. 13-15  (Next)  

Weitschek E., Polychronopoulos D, Almirantis Y, Giovanni Felici

Conserved non coding elements classification

ABSTRACT
Conserved non coding elements (CNEs) are non-coding DNA regions that are evolutionarily conserved in different organisms. The functionality of conserved non coding elements (CNEs) is actually unknown and large efforts have to be done for getting insights of their role in several organisms genomes. In this work we take into consideration a particular type of CNEs analysis: their classification. CNEs classification is difficult and cannot be obtained via common alignment based techniques. Therefore, an alignment free method based on a feature vector representations of the sequences is adopted in this work. The feature vector representation is combined and given as input to rule based supervised machine learning algorithms for CNEs classification. These methodology (composition of the methods) is tested on different public available data sets obtained from up to date CNEs data bases and on CNEs of new sequenced organisms. The classification results are sound and the reader is provided with classification models (if then rules), that are able to successfully distinguish the different functional classes present in the different datasets. The classification accuracies are compared with a state of the art sequence analysis method, the genomic signature. It is shown, that the proposed methodology has better classification performances: the distinction of CNEs and other sequences is obtained with success and with accurate and compact classification models.
back
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -