Research Interest

 
We are interested in the broad area of bioinformatics, systems biology and artificial intelligence. We are developing new tools and methodologies for taking on new challenges in genomic and proteomic fields.
Our current research topics are:
 
An Intelligent System for Bioinformatics Organized Resources
We design and develop a Knowledge-based Decision Support System (KDSS) that offers not only support in the choice of the proper strategy, tool and algorithm, but it helps the user to configure and to run them, step by step. For this reason, this system can be seen as an ideal crossover between classical DSS and emerging WFMS. In addition we define for this KDSS an ontology, called Data-Problem-Solver (DPS), able to model the expertise provided by domain experts and knowledge engineers. We take advantage of using this system for idenitifying protein complexes showing biological functions, from the saccharomyces cerevisiae protein-protein interaction dataset.

 

Analysis of DNA Barcode sequences based on compression-based techniques
We aim at introducing the use of an alignment-free approach in order to make taxonomic analysis of barcode sequences. Our approach is based on the use of two compression-based versions of non-computable Universal Similarity Metric (USM) class of distances. This way we try to overcome some flaws of classic techniques, such as the time-consuming and parameter-dependent alignment procedure and the use of stochastic evolutionary distance models, that do not represent a distance metric.

 

Genomic sequence classification using alignment-free techniques

As regarind bacteria taxonomy classification using 16S rRNA gene sequences, we introduce a novel alignment-free genomic classification approach based on probabilistic topic modeling. We build a classifier, using a kmer (small fragments of length k) decomposition of DNA sequences and the LDA algorithm.

As regarding animalia species classification using COI-5 rRNA gene sequences, we propose a novel method based on the identification of distinctive words, extracted from the spectral representation of DNA sequences. In particular, we performed an unsupervised clustering using neural gas algorithm, for iteratively calculating those fingerprints that are characteristics of DNA sequences at different taxonomic levels.

 

Self Organizing Maps for the Visual Exploration of Biological Data
Facilitating the visual exploration of scientific data has received increasing attention in the past decade or so. Especially in life science related application areas the amount of available data has grown at a breath taking pace. We describe an approach that allows for visual inspection of large collections of molecular compounds. This goal has been carried out using an artificial intelligent neural network, the Self Organizing Map (SOM). In addition to standard method, we introduce a fast learning algorithm that uses the simluated annealing heuristic, in order to reduce both the execution time and the quality of visualization.