A novel data mining approach for the accurate prediction of translation initiation sites

摘要: In an mRNA sequence, the prediction of exact codon where process translation starts (Translation Initiation Site – TIS) is a particularly important problem. So far it has been tackled by several researchers that apply various statistical and machine learning techniques, achieving high accuracy levels, often over 90%. this paper we propose mahine approach can further improve accuracy. First, provide concise review literature in field. Then novel feature set. We perform extensive experiments on publicly available, real world dataset for vertebrate organisms using variety features classification setups. evaluate our results compare them with reference study show involves new combination Ribosome Scanning Model meta-classifier shows higher most cases.