REALoc: Reliable and effective methods to assist predicting human protein subcellular localization

REALoc About Help

REALoc: Reliable and effective methods to assist predicting human protein subcellular localization

Drug development and investigation of protein function both require an understanding of protein subcellular localization. We developed a system, REALoc, that can predict the subcellular localization of singleplex and multiplex proteins in humans. This system consists of two systematic frameworks that integrate one-to-one and many-to-many machine learning methods and use se-quence-based features, including amino acid composition, surface accessibility, weighted sign aa index, and sequence similarity profile, as well as gene ontology function-based features.

REALoc can be used to predict localization to six subcellular compartments (cell membrane, cytoplasm, endoplasmic reticulum/Golgi, mitochondrion, nucleus, and extracellular). REALoc yielded a 75.3% absolute true success rate during five-fold cross-validation and a 57.1% absolute true success rate in an independent database test, which was >10% higher than four other prediction systems. Lastly, we analyzed the effects of Vote and GANN models on singleplex and multiplex localization prediction efficacy.

Reference:
Chi-Hua Tung, Chi-Wei Chen, Han-Hao Sun, Yen-Wei Chu* (2017) Predicting human protein subcellular localization by heterogeneous and comprehensive approaches, PLoS ONE, 12(6):e0178832. doi: 10.1371/journal.pone.0178832.Download dataset

REALoc: Reliable and effective methods to assist predicting human protein subcellular localization

Home