One of the fundamental goals in cell biology and proteomics is to identify the subcellular locations. Information of the subcellular locations for proteins can provide useful clues about their functions. Another area of which has received little attention in the literature is the submitochondria locations. Mitochondria are subcellular organelles that appear only in eukaryotic cells. The mitochondrion is the ‘‘power generator’’ playing a critical role in generating energy in the eukaryotic cell. Mitochondria are surrounded by two layers of membrane, the inner membrane and the outer membrane. Proteins which are localized within mitochondria play important roles in energy metabolism process. Inner membrane, outer membrane and matrix contain proteins which do contribute to different procedures in energy metabolism. The use of a reliable automatic submitochondria localizer could speed up the drugs design for over 100 kinds of complex diseases related to mitochondria like programmed cell death and ionic homeostasis. In this thesis, we construct predictors for protein submitochondria locations based on various features of sequence. We have used 11 representation model of protein samples that include amino acid composition, dipeptide composition, higher order dipeptide composition, compositions of amino acid properties, Chou-pseudo amino acid composition, functional domain composition, model based on prediction of solvent accessibility, model based on prediction of secondary structure elements, the combination discrete model based on prediction of solvent accessibility and secondary structure elements, discrete model of pairwise sequence alignment, and improved discrete model of pairwise sequence alignment. Each biological feature is selected as input to multi In addition, we have selected Ordered Weighted Averaging (OWA) which is one of fusion data operators to apply on the 11 best SVM-based Key Words: Mitochondria, Protein Localization, Support Vector Machine, Data Fusion, Ordered Weighted Averaging , Pairwise-Alignment
