An integrative approach to identifying biologically relevant genes

摘要: Gene selection aims at detecting biologically relevant genes to assist biologists’ research. The cDNA Microarray data used in gene is usually “wide”. With more than several thousand genes, but only less a hundred of samples, many irrelevant can gain their statistical relevance by sheer randomness. Addressing this problem goes beyond what the offer and necessitates use additional information. Recent developments bioinformatics have made various knowledge sources available, such as KEGG pathway repository Ontology database. Integrating different types could provide information about samples. In work, we propose novel approach integrate for identifying genes. converts external its internal knowledge, which be rank Upon obtaining ranking lists, it aggregates them via probabilistic model generates final list. Experimental results from our study on acute lymphoblastic leukemia demonstrate efficacy proposed show that using together help detect