蛋白质亚细胞定位与其功能密切相关。蛋白质在细胞中的正确定位是细胞系统高度有序运转的前提保障。研究细胞中蛋白质定位的机制和规律,预测蛋白质的亚细胞定位,对于了解蛋白质的性质和功能,了解蛋白质之间的相互作用,探索生命的规律和奥秘具有重要意义。基于机器学习方法的蛋白质亚细胞定位预测是生物信息学研究的热点之一。从数据集的建立、蛋白质序列特征刻画和蛋白质亚细胞定位预测算法3个方面,总结和评述了在过去十几年里机器学习方法在蛋白质亚细胞定位研究中的应用情况和取得的成果,分析了机器学习方法在蛋白质亚细胞定位预测方面存在的问题和面临的挑战,指出了蛋白质亚细胞定位研究的主要方向。
Subcellular localization of protein is closely related to its function,properly localization of protein in the cell is the precondition for the cell system to operate orderly, Probing into the mechanism and principle of protein sorting and predicting its subcellular localization can provide insight into the protein's properties and functional annotation of proteins, and it is significant meaningful to apprehend the nature of life. Predicting the subcelllular localization of protein has become a hot research field in the recent year. The development of constructing datasets, representing protein sequences, as well as classification algorithm in the area of protein subcellular localization prediction were reviewed and commented, and the challenge of machine learning methods faced in this field was then pointed out, in the end, perspectives in this realm were also proposed.