Subcellular location prediction of apoptosis proteins using two novel feature extraction methods based on evolutionary information and LDA

摘要

Apoptosis, also known as programmed cell death, is a basic biological phenomenon that is associated with the occurrence of a wide variety of diseases, such as a tumor, autoimmune disease, Alzheimer’s disease and so on. It plays an important role in animal development and homeostasis [ ]. Studies have shown that apoptosis proteins are essential in this process. The subcellular location of a protein is closely related to its function. And only in the specific subcellular location, can the protein work [ ]. Subcellular localization information of apoptosis proteins contributes to exploring the internal mechanism of programmed cell death and designing new drugs [ ]. However, the number of apoptosis proteins with clear subcellular location markers is limited in the database, and it is time-consuming and costly to label samples by traditional experimental methods. Therefore, exploring feasible computational methods to predict the subcellular location of the given protein has been a hotspot for nearly two decades.