Prediction and Characterization of Intrinsically Unstructured Proteins

More and more disordered regions have been discovered in protein sequences, and many of them are found to be functionally significant. Previous studies reveal that disordered regions of a protein can be predicted by its primary structure, i.e. the amino acid sequence. One observation that has been widely accepted is that disordered regions are toward charged amino acids, while ordered regions usually have compositional bias toward hydrophobic amino acids. Recent studies further show that employing evolutionary information such as position specific scoring matrices (PSSMs) improves the prediction accuracy of protein disorder. As more and more machine learning techniques have been introduced to protein disorder detection, extracting more useful features with biological insights should attracts attention.
This thesis first studies the effect of a condensed position specific scoring matrix with respect to physicochemical properties (PSSMP) on the prediction accuracy, where the PSSMP is derived by merging several amino acid columns of a PSSM belonging to a certain property into a single column. Next, we decompose each conventional physicochemical property of amino acids into two disjoint groups which have a propensity for order and disorder respectively, and show by experiments that some of the new properties perform better than their parent properties in predicting protein disorder. In order to get an effective and compact feature set on this problem, we propose a hybrid feature selection method that inherits the efficiency of uni-variant analysis and the effectiveness of the stepwise feature selection that explores combinations of multiple features. The results of the proposed experiments results show that the selected feature set improves the performance of a classifier built with Radial Basis Function Networks (RBFN) in comparison with the feature set constructed with PSSMs or PSSMPs that adopt simply the conventional physicochemical properties. Distinguishing disordered regions from ordered regions in protein sequences facilitates the exploration of protein structures and functions. However, the proposed predictor still suffers a large amount of false positives when facing real data. Therefore, we introduce a two-stage RBNF classifier, named DisPSSMP2, to improve the performance of DisPSSMP by reducing a large amount of false positives.
This thesis finally presents the web server iPDA which integrates the proposed classifier with several other sequence predictors in order to investigate the functional role of the detected disordered region. In iPDA, a pattern mining package for detecting sequence conservation is embedded for discovering potential binding regions of the query protein, which is really helpful to uncovering the relationship between protein function and its primary sequence.