Publications

@article{Rodríguez-Baena2013,

title = {Extracting and validating biclusters from binary datasets},

author = {D. Rodríguez-Baena},

doi = {10.3233/AIC-130570},

year  = {2013},

date = {2013-05-01},

journal = {AI Communications},

volume = {26},

number = {4},

pages = {417-418},

abstract = {This work proposes a novel algorithm to extract biclusters from binary datasets: the Bit-Pattern Biclustering Algorithm (BiBit). The selective search performed by BiBit, based on a very fast bits words processing technique, provides very satisfactory results in quality and computational cost. Besides, a new software tool, named CarGene (Characterization of Genes), that helps scientists to validate sets of genes using biological knowledge is introduced too.},

keywords = {Biclustering, Binary dataset, Biological validation},

pubstate = {published},

tppubtype = {article}

}

@article{Rodríguez-Baena2011,

title = {A biclustering algorithm for extracting bit-patterns from binary datasets},

author = {D. Rodríguez-Baena and A. J. Pérez-Pulido and J. Aguilar-Ruiz},

url = {https://doi.org/10.1093/bioinformatics/btr464

https://academic.oup.com/bioinformatics/article-pdf/27/19/2738/16900447/btr464.pdf},

doi = {10.1093/bioinformatics/btr464},

issn = {1367-4803},

year  = {2011},

date = {2011-08-08},

journal = {Bioinformatics},

volume = {27},

number = {19},

pages = {2738-2745},

abstract = {Motivation: Binary datasets represent a compact and simple way to store data about the relationships between a group of objects and their possible properties. In the last few years, different biclustering algorithms have been specially developed to be applied to binary datasets. Several approaches based on matrix factorization, suffix trees or divide-and-conquer techniques have been proposed to extract useful biclusters from binary data, and these approaches provide information about the distribution of patterns and intrinsic correlations.



Results: A novel approach to extracting biclusters from binary datasets, BiBit, is introduced here. The results obtained from different experiments with synthetic data reveal the excellent performance and the robustness of BiBit to density and size of input data. Also, BiBit is applied to a central nervous system embryonic tumor gene expression dataset to test the quality of the results. A novel gene expression preprocessing methodology, based on expression level layers, and the selective search performed by BiBit, based on a very fast bit-pattern processing technique, provide very satisfactory results in quality and computational cost. The power of biclustering in finding genes involved simultaneously in different cancer processes is also shown. Finally, a comparison with Bimax, one of the most cited binary biclustering algorithms, shows that BiBit is faster while providing essentially the same results.},

keywords = {Biclustering, Binary dataset},

pubstate = {published},

tppubtype = {article}

}