期刊
CURRENT ORGANIC CHEMISTRY
卷 23, 期 15, 页码 1671-1680出版社
BENTHAM SCIENCE PUBL LTD
DOI: 10.2174/1385272823666190718145613
关键词
Antifreeze protein; classification; machine learning; computational protcomics; cold-adapted organisms; cell fluids
Lots of cold-adapted organisms could produce antifreeze proteins (AFPs) to counter the freezing of cell fluids by controlling the growth of ice crystal. AFPs have been found in various species such as in vertebrates, invertebrates, plants, bacteria, and fungi. These AFPs from fish, insects and plants displayed a high diversity. Thus, the identification of the AFPs is a challenging task in computational proteomics. With the accumulation of AFPs and development of machine meaning methods, it is possible to construct a high-throughput tool to timely identify the AFPs. In this review, we briefly reviewed the application of machine learning methods in antifreeze proteins identification flow difference section, including published benchmark dataset, sequence descriptor, classification algorithms and published methods. We hope that this review will produce new ideas and directions for the researches in identifying antifreeze proteins.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据