Published on July 16, 2018

Eukaryotic cells contain diverse subcellular organelles. These organelles form distinct

functional cellular compartments where different biological processes and functions are

carried out. The accurate translocation of a protein is crucial to establish and maintain

cellular organization and function. Newly synthesized proteins are transported to different

cellular components with the assistance of protein transport machineries and complex

targeting signals. Mis-localization of proteins is often associated with metabolic disorders

and diseases. Compared with experimental methods, computational prediction of protein

localization, utilizing different machine learning methods, provides an efficient and

effective way for studying the protein subcellular localization on the whole-proteome level.

Here, we present in this dissertation the bioinformatics methods for studying protein

subcellular localization. We reviewed the studies of protein subcellular transport and

machine learning methods in bioinformatics, presented our work on mitochondrial protein

targeting prediction in plants, summarized the ongoing development of a web-resource for

protein subcellular localization, and discussed the future work and development.