MOTIVATION: Self-organizing maps (SOMs) are readily available bioinformatics methods for clustering and visualizing high-dimensional data, provided that such biological information is previously transformed to fixed-size, metric-based vectors. To increase the usefulness of SOM-based approaches for the analysis of genomic sequence data, novel representation methods are required that automatically and objectively transform aligned nucleotide sequences into numeric vectors, dealing with both nucleotide ambiguity and gaps derived from sequence alignment. RESULTS: Six different codification variants based on Euclidean space, just like SOM processing, have been tested using two SOM models: the classical Kohonen's SOM and growing cell structures. They have been applied to two different sets of sequences: 32 sequences of small sub-unit ribosomal RNA from organisms belonging to the three domains of life, and 44 sequences of the reverse transcriptase region of the pol gene of human immunodeficiency virus type 1 belonging to different groups and sub-types. Our results show that the most important factor affecting the accuracy of sequence clustering is the assignment of an extra weight to the presence of alignment-derived gaps. Although each of the codification variants shows a different level of taxonomic consistency, the results are in agreement with sequence-based phylogenetic reconstructions and anticipate a broad applicability of this codification method.

In this paper, self-organizing maps (SOM) with growing capability are proposed to evaluate the goodness of multispectral training areas selection that would be used in supervised classification processes. The SOM model used in this study is the Growing Cell Structures (GCS) neural network. Some modifications of the original GCS training algorithm are proposed in order to make easy the physical interpretation of their parameters. In addition, several visualization methods have been implemented with the aim of displaying the trained GCS networks. The performances of the modified GCS model have been investigated through a large number of experiments. They have been carried out using multispectral data registered by ETM+ sensor (Landsat 7), to discriminate land cover categories. The results confirm the excellent behavior of the GCS modified training algorithm to evaluate the quality of the selected training patterns, their viability for feeding supervised classification models and their refining.