随机森林方法预测膜蛋白类型

膜蛋白的类型与其功能是密切相关的，因此膜蛋白类型的预测是研究其功能的重要手段，从蛋白质的氨基酸序列出发对膜蛋白的类型进行预测有重要意义。文章基于蛋白质的氨基酸序列，将组合离散增量和伪氨基酸组分信息共同作为预测参数，采用随机森林分类器，对8类膜蛋白进行了预测。在Jackknife检验下的预测精度为86.3%，独立检验的预测精度为93.8%，取得了好于前人的预测结果。

Predicting Membrane Protein Types Using The Random Forests Algorithm

There is a close relationship between the function and types of membrane proteins, so the prediction of membrane protein types is an important means in the research of protein function, and it has significance to predict the membrane protein types from the protein amino acid sequence. Based on the amino-acid sequence in protein, eight types of membrane proteins were predicted by using the algorithm of random forests with the increment of diversity and the pseudo amino acid composition information. The overall prediction accuracy was 93.8% for independent test and 86.3% for jackknife test respectively, better than results of previous prediction.