PECB: prediction of enzyme catalytic residues based on Naive Bayes classification

摘要: In the post-genome era, huge numbers of protein structures accumulate, but little is known about their function. It time consuming and labour intensive to investigate them, e.g., enzyme catalytic properties, through in vivo or vitro work. So silico predictions could be a promising strategy greatly shrink list potential targets. This work incorporated both structural physico-chemical information into Naive Bayes classification system, gained much better performance. The ten-fold cross validation results this method reach 88.6% sensitivity 93.7% specificity. improvement prediction accuracy detailed paper. PECB also applied predict other important sites.