Chun-Wei Tung

Computational identification of ubiquitylation sites from protein sequences

BackgroundUbiquitylation plays an important role in regulating protein functions. Recently, experimental methods were developed toward effective identification of ubiquitylation sites. To efficiently explore more undiscovered ubiquitylation sites, this study aims to develop an accurate sequence-based prediction method to identify promising ubiquitylation sites.ResultsWe established an ubiquitylation dataset consisting of 157 ubiquitylation sites and 3676 putative non-ubiquitylation sites extracted from 105 proteins in the UbiProt database. This study first evaluates promising sequence-based features and classifiers for the prediction of ubiquitylation sites by assessing three kinds of features (amino acid identity, evolutionary information, and physicochemical property) and three classifiers (support vector machine, k-nearest neighbor, and NaïveBayes). Results show that the set of used 531 physicochemical properties and support vector machine (SVM) are the best kind of features and classifier respectively that their combination has a prediction accuracy of 72.19% using leave-one-out cross-validation.Consequently, an informative physicochemical property mining algorithm (IPMA) is proposed to select an informative subset of 531 physicochemical properties. A prediction system UbiPred was implemented by using an SVM with the feature set of 31 informative physicochemical properties selected by IPMA, which can improve the accuracy from 72.19% to 84.44%. To further analyze the informative physicochemical properties, a decision tree method C5.0 was used to acquire if-then rule-based knowledge of predicting ubiquitylation sites. UbiPred can screen promising ubiquitylation sites from putative non-ubiquitylation sites using prediction scores. By applying UbiPred, 23 promising ubiquitylation sites were identified from an independent dataset of 3424 putative non-ubiquitylation sites, which were also validated by using the obtained prediction rules.ConclusionWe have proposed an algorithm IPMA for mining informative physicochemical properties from protein sequences to build an SVM-based prediction system UbiPred. UbiPred can predict ubiquitylation sites accompanied with a prediction score each to help biologists in identifying promising sites for experimental verification. UbiPred has been implemented as a web server and is available at http://iclab.life.nctu.edu.tw/ubipred.

ProLoc-GO: utilizing informative Gene Ontology terms for sequence-based prediction of protein subcellular localization.

BackgroundGene Ontology (GO) annotation, which describes the function of genes and gene products across species, has recently been used to predict protein subcellular and subnuclear localization. Existing GO-based prediction methods for protein subcellular localization use the known accession numbers of query proteins to obtain their annotated GO terms. An accurate prediction method for predicting subcellular localization of novel proteins without known accession numbers, using only the input sequence, is worth developing.ResultsThis study proposes an efficient sequence-based method (named ProLoc-GO) by mining informative GO terms for predicting protein subcellular localization. For each protein, BLAST is used to obtain a homology with a known accession number to the protein for retrieving the GO annotation. A large number n of all annotated GO terms that have ever appeared are then obtained from a large set of training proteins. A novel genetic algorithm based method (named GOmining) combined with a classifier of support vector machine (SVM) is proposed to simultaneously identify a small number m out of the n GO terms as input features to SVM, where m <<n. The m informative GO terms contain the essential GO terms annotating subcellular compartments such as GO:0005634 (Nucleus), GO:0005737 (Cytoplasm) and GO:0005856 (Cytoskeleton). Two existing data sets SCL12 (human protein with 12 locations) and SCL16 (Eukaryotic proteins with 16 locations) with <25% sequence identity are used to evaluate ProLoc-GO which has been implemented by using a single SVM classifier with the m = 44 and m = 60 informative GO terms, respectively. ProLoc-GO using input sequences yields test accuracies of 88.1% and 83.3% for SCL12 and SCL16, respectively, which are significantly better than the SVM-based methods, which achieve < 35% test accuracies using amino acid composition (AAC) with acid pairs and AAC with dipedtide composition. For comparison, ProLoc-GO using known accession numbers of query proteins yields test accuracies of 90.6% and 85.7%, which is also better than Hum-PLoc (85.0%) and Euk-OET-PLoc (83.7%) using ensemble classifiers with hybridization of GO terms and amphiphilic pseudo amino acid composition for SCL12 and SCL16, respectively.ConclusionThe growth of Gene Ontology in size and popularity has increased the effectiveness of GO-based features. GOmining can serve as a tool for selecting informative GO terms in solving sequence-based prediction problems. The prediction system using ProLoc-GO with input sequences of query proteins for protein subcellular localization has been implemented (see Availability).

POPI: predicting immunogenicity of MHC class I binding peptides by mining informative physicochemical properties

MOTIVATION Both modeling of antigen-processing pathway including major histocompatibility complex (MHC) binding and immunogenicity prediction of those MHC-binding peptides are essential to develop a computer-aided system of peptide-based vaccine design that is one goal of immunoinformatics. Numerous studies have dealt with modeling the immunogenic pathway but not the intractable problem of immunogenicity prediction due to complex effects of many intrinsic and extrinsic factors. Moderate affinity of the MHC-peptide complex is essential to induce immune responses, but the relationship between the affinity and peptide immunogenicity is too weak to use for predicting immunogenicity. This study focuses on mining informative physicochemical properties from known experimental immunogenicity data to understand immune responses and predict immunogenicity of MHC-binding peptides accurately. RESULTS This study proposes a computational method to mine a feature set of informative physicochemical properties from MHC class I binding peptides to design a support vector machine (SVM) based system (named POPI) for the prediction of peptide immunogenicity. High performance of POPI arises mainly from an inheritable bi-objective genetic algorithm, which aims to automatically determine the best number m out of 531 physicochemical properties, identify these m properties and tune SVM parameters simultaneously. The dataset consisting of 428 human MHC class I binding peptides belonging to four classes of immunogenicity was established from MHCPEP, a database of MHC-binding peptides (Brusic et al., 1998). POPI, utilizing the m = 23 selected properties, performs well with the accuracy of 64.72% using leave-one-out cross-validation, compared with two sequence alignment-based prediction methods ALIGN (54.91%) and PSI-BLAST (53.23%). POPI is the first computational system for prediction of peptide immunogenicity based on physicochemical properties. AVAILABILITY A web server for prediction of peptide immunogenicity (POPI) and the used dataset of MHC class I binding peptides (PEPMHCI) are available at http://iclab.life.nctu.edu.tw/POPI

ProLoc: Prediction of protein subnuclear localization using SVM with automatic selection from physicochemical composition features

Accurate prediction methods of protein subnuclear localizations rely on the cooperation between informative features and classifier design. Support vector machine (SVM) based learning methods are shown effective for predictions of protein subcellular and subnuclear localizations. This study proposes an evolutionary support vector machine (ESVM) based classifier with automatic selection from a large set of physicochemical composition (PCC) features to design an accurate system for predicting protein subnuclear localization, named ProLoc. ESVM using an inheritable genetic algorithm combined with SVM can automatically determine the best number m of PCC features and identify m out of 526 PCC features simultaneously. To evaluate ESVM, this study uses two datasets SNL6 and SNL9, which have 504 proteins localized in 6 subnuclear compartments and 370 proteins localized in 9 subnuclear compartments. Using a leave-one-out cross-validation, ProLoc utilizing the selected m=33 and 28 PCC features has accuracies of 56.37% for SNL6 and 72.82% for SNL9, which are better than 51.4% for the SVM-based system using k-peptide composition features applied on SNL6, and 64.32% for an optimized evidence-theoretic k-nearest neighbor classifier utilizing pseudo amino acid composition applied on SNL9, respectively.

POPISK: T-cell reactivity prediction using support vector machines and string kernels

BackgroundAccurate prediction of peptide immunogenicity and characterization of relation between peptide sequences and peptide immunogenicity will be greatly helpful for vaccine designs and understanding of the immune system. In contrast to the prediction of antigen processing and presentation pathway, the prediction of subsequent T-cell reactivity is a much harder topic. Previous studies of identifying T-cell receptor (TCR) recognition positions were based on small-scale analyses using only a few peptides and concluded different recognition positions such as positions 4, 6 and 8 of peptides with length 9. Large-scale analyses are necessary to better characterize the effect of peptide sequence variations on T-cell reactivity and design predictors of a peptides T-cell reactivity (and thus immunogenicity). The identification and characterization of important positions influencing T-cell reactivity will provide insights into the underlying mechanism of immunogenicity.ResultsThis work establishes a large dataset by collecting immunogenicity data from three major immunology databases. In order to consider the effect of MHC restriction, peptides are classified by their associated MHC alleles. Subsequently, a computational method (named POPISK) using support vector machine with a weighted degree string kernel is proposed to predict T-cell reactivity and identify important recognition positions. POPISK yields a mean 10-fold cross-validation accuracy of 68% in predicting T-cell reactivity of HLA-A2-binding peptides. POPISK is capable of predicting immunogenicity with scores that can also correctly predict the change in T-cell reactivity related to point mutations in epitopes reported in previous studies using crystal structures. Thorough analyses of the prediction results identify the important positions 4, 6, 8 and 9, and yield insights into the molecular basis for TCR recognition. Finally, we relate this finding to physicochemical properties and structural features of the MHC-peptide-TCR interaction.ConclusionsA computational method POPISK is proposed to predict immunogenicity with scores which are useful for predicting immunogenicity changes made by single-residue modifications. The web server of POPISK is freely available at http://iclab.life.nctu.edu.tw/POPISK.

PupDB: a database of pupylated proteins

BackgroundProkaryotic ubiquitin-like protein (Pup), the firstly identified post-translational protein modifier in prokaryotes, is an important signal for the selective degradation of proteins. Recently, large-scale proteomics technology has been applied to identify a large number of pupylated proteins. The development of a database for managing pupylated proteins and pupylation sites is important for further analyses.DescriptionA database named PupDB is constructed by collecting experimentally identified pupylated proteins and pupylation sites from published studies and integrating the information of pupylated proteins with corresponding structures and functional annotations. PupDB is a web-based database with tools for browses and searches of pupylated proteins and interactive displays of protein structures and pupylation sites.ConclusionsThe structured and searchable database PupDB is expected to provide a useful resource for further analyzing the substrate specificity, identifying pupylated proteins in other organisms and developing computational tools for predicting pupylation sites. PupDB is freely available at http://cwtung.kmu.edu.tw/pupdb.

Predicting protein subnuclear localization using GO-amino-acid composition features

The nucleus guides life processes of cells. Many of the nuclear proteins participating in the life processes tend to concentrate on subnuclear compartments. The subnuclear localization of nuclear proteins is hence important for deeply understanding the construction and functions of the nucleus. Recently, Gene Ontology (GO) annotation has been used for prediction of subnuclear localization. However, the effective use of GO terms in solving sequence-based prediction problems remains challenging, especially when query protein sequences have no accession number or annotated GO term. This study obtains homologies of query proteins with known accession numbers using BLAST to retrieve GO terms for sequence-based subnuclear localization prediction. A prediction method PGAC, which involves mining informative GO terms associated with amino acid composition features, is proposed to design a support vector machine-based classifier. PGAC yields 55 informative GO terms with training and test accuracies of 85.7% and 76.3%, respectively, using a data set SNL_35 (561 proteins in 9 localizations) with 35% sequence identity. Upon comparison with Nuc-PLoc, which combines amphiphilic pseudo amino acid composition of a protein with its position-specific scoring matrix, PGAC using the data set SNL_80 yields a leave-one-out cross-validation accuracy of 81.1%, which is better than that of Nuc-PLoc, 67.4%. Experimental results show that the set of informative GO terms are effective features for protein subnuclear localization. The prediction server based on PGAC has been implemented at http://iclab.life.nctu.edu.tw/prolocgac.

Developing a QSAR model for hepatotoxicity screening of the active compounds in traditional Chinese medicines

The perception that natural substances are deemed safe has made traditional Chinese medicine (TCM) popular in the treatment and prevention of disease globally. However, such an assumption is often misleading owing to a lack of scientific validation. To assess the safety of TCM, in silico screening provides major advantages over the classical laboratory approaches in terms of resource- and time-saving and full reproducibility. To screen the hepatotoxicity of the active compounds of TCMs, a quantitative structure-activity relationship (QSAR) model was firstly established by utilizing drugs from the Liver Toxicity Knowledge Base. These drugs were annotated with drug-induced liver injury information obtained from clinical trials and post-marketing surveillance. The performance of the model after nested 10-fold cross-validation was 79.1%, 91.2%, 53.8% for accuracy, sensitivity, and specificity, respectively. The external validation of 91 well-known ingredients of common herbal medicines yielded a high accuracy (87%). After screening the TCM Database@Taiwan, the worlds largest TCM database, a total of 6853 (74.8%) ingredients were predicted to have hepatotoxic potential. The one-hundred chemical ingredients predicted to have the highest hepatotoxic potential by our model were further verified by published literatures. Our study indicated that this model can serve as a complementary tool to evaluate the safety of TCM.

Prediction of pupylation sites using the composition of k-spaced amino acid pairs

Pupylation is an important post-translational modification in prokaryotes. A prokaryotic ubiquitin-like protein (Pup) is attached to proteins as a signal for selective degradation by proteasome. Several proteomics methods have been developed for the identification of pupylated proteins and pupylation sites. However, pupylation sites of many experimentally identified pupylated proteins are still unknown. The development of sequence-based prediction methods can help to accelerate the identification of pupylation sites and gain insights into the substrate specificity and regulatory functions of pupylation. A novel tool iPUP is developed for the computational identification of pupylation sites. A composition of k-spaced amino acid pairs is utilized to represent a peptide sequence. Top ranked k-spaced amino acid pairs are subsequently selected by using a sequential backward feature elimination algorithm. The 10-fold cross-validation performance of iPUP trained by using the composition of 150 top ranked k-spaced amino acid pairs and support vector machines is 0.83 for the area under receiver operating characteristic curve. The importance analysis of k-spaced amino acid pairs shows that terminal space-containing pairs are useful for discriminating pupylation sites from non-pupylation sites. A sequence analysis confirms that lysines close to C-terminus tend to be pupylated. In contrast, lysines close to N-terminus are less likely to be pupylated. The iPUP tool can predict pupylation sites with probability scores for prioritizing promising pupylation sites. Both the online server and the standalone software of iPUP are freely available for academic use at http://cwtung.kmu.edu.tw/ipup.

Identification of biomarkers for esophageal squamous cell carcinoma using feature selection and decision tree methods.

Esophageal squamous cell cancer (ESCC) is one of the most common fatal human cancers. The identification of biomarkers for early detection could be a promising strategy to decrease mortality. Previous studies utilized microarray techniques to identify more than one hundred genes; however, it is desirable to identify a small set of biomarkers for clinical use. This study proposes a sequential forward feature selection algorithm to design decision tree models for discriminating ESCC from normal tissues. Two potential biomarkers of RUVBL1 and CNIH were identified and validated based on two public available microarray datasets. To test the discrimination ability of the two biomarkers, 17 pairs of expression profiles of ESCC and normal tissues from Taiwanese male patients were measured by using microarray techniques. The classification accuracies of the two biomarkers in all three datasets were higher than 90%. Interpretable decision tree models were constructed to analyze expression patterns of the two biomarkers. RUVBL1 was consistently overexpressed in all three datasets, although we found inconsistent CNIH expression possibly affected by the diverse major risk factors for ESCC across different areas.