Yen-Wei Chu

iStable: off-the-shelf predictor integration for predicting protein stability changes

BackgroundMutation of a single amino acid residue can cause changes in a protein, which could then lead to a loss of protein function. Predicting the protein stability changes can provide several possible candidates for the novel protein designing. Although many prediction tools are available, the conflicting prediction results from different tools could cause confusion to users.ResultsWe proposed an integrated predictor, iStable, with grid computing architecture constructed by using sequence information and prediction results from different element predictors. In the learning model, several machine learning methods were evaluated and adopted the support vector machine as an integrator, while not just choosing the majority answer given by element predictors. Furthermore, the role of the sequence information played was analyzed in our model, and an 11-window size was determined. On the other hand, iStable is available with two different input types: structural and sequential. After training and cross-validation, iStable has better performance than all of the element predictors on several datasets. Under different classifications and conditions for validation, this study has also shown better overall performance in different types of secondary structures, relative solvent accessibility circumstances, protein memberships in different superfamilies, and experimental conditions.ConclusionsThe trained and validated version of iStable provides an accurate approach for prediction of protein stability changes. iStable is freely available online at: http://predictor.nchu.edu.tw/iStable.

siPRED: predicting siRNA efficacy using various characteristic methods.

Small interfering RNA (siRNA) has been used widely to induce gene silencing in cells. To predict the efficacy of an siRNA with respect to inhibition of its target mRNA, we developed a two layer system, siPRED, which is based on various characteristic methods in the first layer and fusion mechanisms in the second layer. Characteristic methods were constructed by support vector regression from three categories of characteristics, namely sequence, features, and rules. Fusion mechanisms considered combinations of characteristic methods in different categories and were implemented by support vector regression and neural networks to yield integrated methods. In siPRED, the prediction of siRNA efficacy through integrated methods was better than through any method that utilized only a single method. Moreover, the weighting of each characteristic method in the context of integrated methods was established by genetic algorithms so that the effect of each characteristic method could be revealed. Using a validation dataset, siPRED performed better than other predictive systems that used the scoring method, neural networks, or linear regression. Finally, siPRED can be improved to achieve a correlation coefficient of 0.777 when the threshold of the whole stacking energy is ≥−34.6 kcal/mol. siPRED is freely available on the web at http://predictor.nchu.edu.tw/siPRED.

Illumination Invariant Color Model for Image Matching and Object Recognition

In this paper we present a new illumination invariant color model for image matching and object recognition. The color model is defined as the ratios of the color differences between neighboring pixels for each color component. Based on the dichromatic reflection color model, it is shown that the proposed color model is invariant to lighting geometry, illumination color, specularity, and diffuse lighting. Experimental results show robust image matching and recognition of using the new color model on objects that are illuminated under different illumination colors and lighting geometry.

Regularity of secondary protein structures: a genetic algorithm approach

Instead of putting too much focus on current approaches to protein secondary structure prediction, the authors look at the natural instincts of protein secondary structures, and propose a schema representation which are offered for identifying regular patterns among various types of secondary protein structures. The schemas employ genetic algorithms base on a steady-state strategy and two disjunctive data sets are used to verify the fitness function for our approach. In this study, 904 schemas are found, and nearly half of the said schemas reach a confidence of 70% and higher. Finally, the paper concludes with some illustrations of significant schemas produced as part of this study, with brief explanations of their significance.

2-DE combined with two-layer feature selection accurately establishes the origin of oolong tea.

Taiwan is known for its high quality oolong tea. Because of high consumer demand, some tea manufactures mix lower quality leaves with genuine Taiwan oolong tea in order to increase profits. Robust scientific methods are, therefore, needed to verify the origin and quality of tea leaves. In this study, we investigated whether two-dimensional gel electrophoresis (2-DE) and nanoscale liquid chromatography/tandem mass spectroscopy (nano-LC/MS/MS) coupled with a two-layer feature selection mechanism comprising information gain attribute evaluation (IGAE) and support vector machine feature selection (SVM-FS) are useful in identifying characteristic proteins that can be used as markers of the original source of oolong tea. Samples in this study included oolong tea leaves from 23 different sources. We found that our method had an accuracy of 95.5% in correctly identifying the origin of the leaves. Overall, our method is a novel approach for determining the origin of oolong tea leaves.

A Hybrid Genetic Algorithm Approach for Protein Secondary Structures

The importance of secondary protein structures is to help us to recognize many biological features, such as the structure and function of a protein, the evolutionary relation between proteins, and protein classification. Unfortunately, the secondary protein structures are hard to get from experimental analysis, and most researchers usually use predictive information instead of real structures. However, we want to look at the natures of protein secondary structures rather than putting too much focus on current approaches to protein secondary structure prediction. For the regularity of secondary protein structures, we define a schema and adopt an approach of evolutionary computation. The approach combines a clustering method and genetic algorithms to produce the schemata for the visible natures of protein secondary structures. There are two major roles of clustering algorithm, one is to generate part of the initial chromosomes in the genetic algorithms and the other is to assist schemata in predicting secondary protein structures. By performing the new approach, the accuracy of Q3 can be improved 12% more than the previous researches. Finally, we will demonstrate some schemata with interesting biological meaning

SUMOgo: Prediction of sumoylation sites on lysines by motif screening models and the effects of various post-translational modifications

Most modern tools used to predict sites of small ubiquitin-like modifier (SUMO) binding (referred to as SUMOylation) use algorithms, chemical features of the protein, and consensus motifs. However, these tools rarely consider the influence of post-translational modification (PTM) information for other sites within the same protein on the accuracy of prediction results. This study applied the Random Forest machine learning method, as well as motif screening models and a feature selection combination mechanism, to develop a SUMOylation prediction system, referred to as SUMOgo. With regard to prediction method, PTM sites were coded as new functional features in addition to structural features, such as sequence-based binary coding, encoded chemical features of proteins, and encoded secondary structure information that is important for PTM. Twenty cycles of prediction were conducted with a 1:1 combination of positive test data and random negative data. Matthew’s correlation coefficient of SUMOgo reached 0.511, which is higher than that of current commonly used tools. This study further verified the important role of PTM in SUMOgo and includes a case study on CREB binding protein (CREBBP). The website for the final tool is http://predictor.nchu.edu.tw/SUMOgo.

Predicting human protein subcellular localization by heterogeneous and comprehensive approaches

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, based on comprehensive strategy, consists of two heterogeneous systematic frameworks that integrate one-to-one and many-to-many machine learning methods and use sequence-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 six other prediction systems. Lastly, we analyzed the effects of Vote and GANN models on singleplex and multiplex localization prediction efficacy. REALoc is freely available at http://predictor.nchu.edu.tw/REALoc.

QuaBingo: A Prediction System for Protein Quaternary Structure Attributes Using Block Composition

Background. Quaternary structures of proteins are closely relevant to gene regulation, signal transduction, and many other biological functions of proteins. In the current study, a new method based on protein-conserved motif composition in block format for feature extraction is proposed, which is termed block composition. Results. The protein quaternary assembly states prediction system which combines blocks with functional domain composition, called QuaBingo, is constructed by three layers of classifiers that can categorize quaternary structural attributes of monomer, homooligomer, and heterooligomer. The building of the first layer classifier uses support vector machines (SVM) based on blocks and functional domains of proteins, and the second layer SVM was utilized to process the outputs of the first layer. Finally, the result is determined by the Random Forest of the third layer. We compared the effectiveness of the combination of block composition, functional domain composition, and pseudoamino acid composition of the model. In the 11 kinds of functional protein families, QuaBingo is 23% of Matthews Correlation Coefficient (MCC) higher than the existing prediction system. The results also revealed the biological characterization of the top five block compositions. Conclusions. QuaBingo provides better predictive ability for predicting the quaternary structural attributes of proteins.

Selecting High Efficacy siRNAs by Computational Models

Wei-Jie Pan1, Chi-Wei Chen1, Heng-Hao Liang1, Yen-Wei Chu1,2,3,4 1Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan 2Biotechnology Center, National Chung Hsing University, Taichung, Taiwan 3Institute of Molecular Biology, National Chung Hsing University, Taichung, Taiwan 4Graduate Institute of Biotechnology, National Chung Hsing University, Taichung, Taiwan