Chuen-Der Huang

Feature Selection and Combination Criteria for Improving Accuracy in Protein Structure Prediction

The classification of protein structures is essential for their function determination in bioinformatics. At present, a reasonably high rate of prediction accuracy has been achieved in classifying proteins into four classes in the SCOP database according to their primary amino acid sequences. However, for further classification into fine-grained folding categories, especially when the number of possible folding patterns as those defined in the SCOP database is large, it is still quite a challenge. In our previous work, we have proposed a two-level classification strategy called hierarchical learning architecture (HLA) using neural networks and two indirect coding features to differentiate proteins according to their classes and folding patterns, which achieved an accuracy rate of 65.5%. In this paper, we use a combinatorial fusion technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying various criteria in combinatorial fusion to the protein fold prediction approach using neural networks with HLA and the radial basis function network (RBFN), the resulting classification has an overall prediction accuracy rate of 87% for four classes and 69.6% for 27 folding categories. These rates are significantly higher than the accuracy rate of 56.5% previously obtained by Ding and Dubchak. Our results demonstrate that data fusion is a viable method for feature selection and combination in the prediction and classification of protein structure.

Hierarchical learning architecture with automatic feature selection for multiclass protein fold classification

The structure classification of proteins plays a very important role in bioinformatics, since the relationships and characteristics among those known proteins can be exploited to predict the structure of new proteins. The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications, the role of appropriate features has not been paid adequate importance. In this investigation we use three novel ideas for multiclass protein fold classification. First, we use the gating neural network, where each input node is associated with a gate. This network can select important features in an online manner when the learning goes on. At the beginning of the training, all gates are almost closed, i.e., no feature is allowed to enter the network. Through the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly, and some gates may be partially open. The second novel idea is to use a hierarchical learning architecture (HLA). The classifier in the first level of HLA classifies the protein features into four major classes: all alpha, all beta, alpha + beta, and alpha/beta. And in the next level we have another set of classifiers, which further classifies the protein features into 27 folds. The third novel idea is to induce the indirect coding features from the amino-acid composition sequence of proteins based on the N-gram concept. This provides us with more representative and discriminative new local features of protein sequences for multiclass protein fold classification. The proposed HLA with new indirect coding features increases the protein fold classification accuracy by about 12%. Moreover, the gating neural network is found to reduce the number of features drastically. Using only half of the original features selected by the gating neural network can reach comparable test accuracy as that using all the original features. The gating mechanism also helps us to get a better insight into the folding process of proteins. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it also reduces the computation time.

Recognition of structure classification of protein folding by NN and SVM hierarchical learning architecture

Classifying the structure of protein is a very important task in biological data. By means of the classification, the relationships and characteristics among known proteins can be exploited to predict the structure of new proteins. The study of the protein structures is based on the sequences and their similarity. It is a difficult task. Recently, due to the ability of machine learning techniques, many researchers have applied them to probe into this protein classification problem. We also apply here machine learning methods for multi-class protein fold recognition problem by proposing a novel hierarchical learning architecture. This novel hierarchical learning architecture can be formed by NN (neural networks) or SVM (support vector machine) as basic building blocks. Our results show that both of them can perform well. We use this new architecture to attack the multi-class protein fold recognition problem as proposed by Dubchak and Ding in 2001. With the same set of features our method can not only obtain better prediction accuracy and lower computation time, but also can avoid the use of the stochastic voting process in the original approach.

PROTEIN METAL BINDING RESIDUE PREDICTION BASED ON NEURAL NETWORKS

Over one-third of protein structures contain metal ions, which are the necessary elements in life systems. Traditionally, structural biologists were used to investigate properties of metalloproteins (proteins which bind with metal ions) by physical means and interpreting the function formation and reaction mechanism of enzyme by their structures and observations from experiments in vitro. Most of proteins have primary structures (amino acid sequence information) only; however, the 3-dimension structures are not always available. In this paper, a direct analysis method is proposed to predict the protein metal-binding amino acid residues from its sequence information only by neural networks with sliding window-based feature extraction and biological feature encoding techniques. In four major bulk elements (Calcium, Potassium, Magnesium, and Sodium), the metal-binding residues are identified by the proposed method with higher than 90% sensitivity and very good accuracy under 5-fold cross validation. With such promising results, it can be extended and used as a powerful methodology for metal-binding characterization from rapidly increasing protein sequences in the future.

Feature selection and combination criteria for improving predictive accuracy in protein structure classification

The classification of protein structures is essential for their function determination in bioinformatics. The success of the protein structure classification depends on two factors: the computational methods used and the features selected. In this paper, we use a combinatorial fusion analysis technique to facilitate feature selection and combination for improving predictive accuracy in protein structure classification. When applying these criteria to our previous work, the resulting classification has an overall prediction accuracy rate of 87% for four classes and 69.6% for 27 folding categories. These rates are significantly higher than our previous work and demonstrate that combinatorial fusion is a valuable method for protein structure classification.

A comparison of mutual and fuzzy-mutual information-based feature selection strategies

It is very important to select a small set of relevant features from a high dimensional data set and useful to design either an effective classification or prediction model. This procedure involves a series of estimations of the relationship between each pair of variables and between each variable and class labels. Mutual information is widely used to estimate these relationships. However, alternative strategies may be useful to estimate the mutual information with continuous or hybrid data. In this study, we attempt to evaluate the difference between the selection strategies involved with mutual information and fuzzy mutual information. The results indicate that using fuzzy mutual information is more helpful to obtain more stable feature sets and more accurate estimations of the relationship between two variables.

Machine learning for multi-class protein fold classification based on neural networks with feature gating

The success of a classification system depends heavily on two things: the tools being used and the features considered. For the bioinformatics applications the role of appropriate features has not been paid adequate importance. In this investigation we use two novel ideas. First, we use neural networks where each input node is associated with a gate. At the beginning of the training all gates are almost closed, i.e., no feature is allowed to enter the network. During the training, depending on the requirements, gates are either opened or closed. At the end of the training, gates corresponding to good features are completely opened while gates corresponding to bad features are closed more tightly. And of course, some gates may be partially open. So the network can not only select features in an online manner when the learning goes on, it also does some feature extraction. The second novel idea is to use a hierarchical machine learning architecture. Where at the first level the network classifies the data into four major folds : all alpha, all beta, alpha + beta and alpha / beta. And in the next level we have another set of networks, which further classifies the data into twenty seven folds. This approach helps us to achieve the following. The gating network is found to reduce the number of features drastically. It is interesting to observe that for the first level using just 50 features selected by the gating network we can get a comparable test accuracy as that using 125 features using neural classifiers. The process also helps us to get a better insight into the folding process. For example, tracking the evolution of different gates we can find which characteristics (features) of the data are more important for the folding process. And, of course, it reduces the computation time. The use of the hierarchical architecture helps us to get a better performance also.

A STUDY OF OPTIMAL HANDLE SHAPE AND MUSCLE STRENGTH DISTRIBUTION ON LOWER ARM WHEN HOLDING A FOIL

The strength of five working muscle groups of the lower arms of 8 male fencers, including adductor pollicis, extensor carpi radialis, flexor carpi radialis, extensor carpi ulnaris, and flexor carpi ulnaris, were examined during competition. Root mean square values of muscular electromyographic signals indicated that the shape of foil handles significantly influenced distribution of working strength of each muscle group. Use of the Pistol-Viscounti type of foil handle showed better distribution of strength among the 5 muscle groups than did other types of foils. Using the Pistol-Viscounti foil handle not only reduced muscular fatigue but also lessened cumulative trauma symptoms while holding a foil for a long duration.

A modified fuzzy co-clustering (MFCC) approach for microarray data analysis

Biologically a gene or a sample could participate in multiple biological pathways, and only few genes are concurrently involved in a cellular process under some specific experimental conditions. Hence, identification of a subset of genes showing similar regulations under subsets of condition in microarray data has become an important research issue. Many investigators develop bi-clustering methods to attack this problem. In this study, we adopt fuzzy co-clustering concept and design a procedure to iteratively extract bi-clusters with co-expressed gene patterns (here the entire proposed process is called a modified fuzzy co-clustering (MFCC) approach). We have applied synthetic data and compared our MFCCs performance with four well-known state-of-the-art methods. Here we have not only shown that our MFCC approach can successfully extract each designed bi-clusters in the synthetic data sets, but also have demonstrated the better performance by our MFCC approach.

Leisure Activities for the Elderly–The Influence of Visual Working Memory on Mahjong and Its Video Game Version

Mahjong is not only a traditional game for recreation but an important leisure activity for elderly people in Chinese society. In this study, 8 elderly people of age 65 in average are selected as testees, their visual senses are sufficiently capable to continuously play mahjong for more than 1 hour. In addition, the testees all have more than one year of experience in playing mahjong. Also, a self-developed working memory inspection system is used to detect the influences of the working memory corrective ratio of version for elderly people under 350 Lux, the mahjong play duration as the variable. The study also may serve as a reference in designing environmental illumination and the duration for elderly people while playing mahjong.