基于概率神经网络的蛋白质亚细胞定位

Protein Subcellular Localization based on Probabilistic Neural Network

文章通过对氨基酸词频的分析,应用概率神经网络来自动地进行蛋白质亚细胞定位.对于真核生物蛋白质的预测精度达到了82%,对于原核生物的预测精度则达到了92%.而且对于蛋白质序列N端缺失的情况有很好的鲁棒性.

There describes a new based on the one rank amino acid frequency analysis of the sequence. This new approach provides better predictions than existing methods. The total prediction accuracies on Reinhardt and Hubbard's dataset reach 92.4% for prokaryotic protein sequences and 82.2 % for eukaryotic protein sequences with 5-fold cross validation. The model shows robust against N-terminal errors in the sequences.