Compressed learning and its applications to subcellular localization

One of the main challenges faced by biological applications is to predict protein subcellular localization in automatic fashion accurately. To achieve this in these applications, a wide variety of machine learning methods have been proposed in recent years. Most of them focus on finding the optimal classification scheme and less of them take the simplifying the complexity of biological systems into account. Traditionally, such bio-data are analyzed by first performing a feature selection before classification. Motivated by CS (Compressed Sensing) theory, we propose the methodology which performs compressed learning with a sparseness criterion such that feature selection and dimension reduction are merged into one analysis. The proposed methodology decreases the complexity of biological system, while increases protein subcellular localization accuracy. Experimental results are quite encouraging, indicating that the aforementioned sparse methods are quite promising in dealing with complicated biological problems, such as predicting the subcellular localization of Gram-negative bacterial proteins.     

基于多层次稀疏编码预测蛋白质亚细胞定位

文中提出了一种简单有效的蛋白质亚细胞区间定位预测方法,为进一步了解蛋白质的功能和性质提供理论基础。运用稀疏编码,结合氨基酸组成信息提取蛋白质序列特征,基于不同字典大小对得到的特征进行多层次池化整合,并送入支持向量机进行分类。经Jackknife检验,在数据集ZD98、CH317和Gram1253上的预测成功率分别达到95.9%、93.4%和94.7%。实验证明基于多层次稀疏编码的分类预测算法能显著提高蛋白质亚细胞区间定位的预测精度。     

Using pseudo amino acid composition to predict protein subcellular location: approached with amino acid composition distribution

In the Post Genome Age, there is an urgent need to develop the reliable and effective computational methods to predict the subcellular localization for the explosion of newly found proteins. Here, a novel method of pseudo amino acid (PseAA) composition, the so-called “amino acid composition distribution” (AACD), is introduced. First, a protein sequence is divided equally into multiple segments. Then, amino acid composition of each segment is calculated in series. After that, each protein sequence can be represented by a feature vector. Finally, the feature vectors of all sequences thus obtained are further input into the multi-class support vector machines to predict the subcellular localization. The results show that AACD is quite effective in representing protein sequences for the purpose of predicting protein subcellular localization.     

真核蛋白质的亚细胞位点预测研究进展

研究真核蛋白质的亚细胞位点是了解真核蛋白质功能,深入研究蛋白质相关信号通路内在机制的基础。同时,可以为了解 疾病发病机制及为新药研发提供帮助。因此,研究真核蛋白质的亚细胞位点意义十分重大。随着基因组测序的完成,真核蛋白质 序列信息增长迅速,为真核蛋白质亚细胞位点的研究提出了更多的挑战。传统的实验法难以满足蛋白质信息量迅速增长的需求。 而采用生物信息学手段处理大规模数据的计算预测方法,可在较短时间内获得大量真核蛋白质亚细胞位点信息,弥补了实验法 的不足。因此,运用计算预测法预测真核蛋白质的亚细胞位点成为生物信息学领域的研究热点之一。本文主要从提取真核蛋白质 的特征信息、计算预测方法及预测效果的评价三个方面,介绍近年来真核蛋白质亚细胞位点预测的研究进展。     

Predicting protein subcellular location with network embedding and enrichment features

The subcellular location of a protein is highly related to its function. Identifying the location of a given protein is an essential step for investigating its related problems. Traditional experimental methods can produce solid determination. However, their limitations, such as high cost and low efficiency, are evident. Computational methods provide an alternative means to address these problems. Most previous methods constantly extract features from protein sequences or structures for building prediction models. In this study, we use two types of features and combine them to construct the model. The first feature type is extracted from a protein–protein interaction network to abstract the relationship between the encoded protein and other proteins. The second type is obtained from gene ontology and biological pathways to indicate the existing functions of the encoded protein. These features are analyzed using some feature selection methods. The final optimum features are adopted to build the model with recurrent neural network as the classification algorithm. Such model yields good performance with Matthews correlation coefficient of 0.844. A decision tree is used as a rule learning classifier to extract decision rules. Although the performance of decision rules is poor, they are valuable in revealing the molecular mechanism of proteins with different subcellular locations. The final analysis confirms the reliability of the extracted rules. The source code of the propose method is freely available at https://github.com/xypan1232/rnnloc     

Prediction of protein subcellular localization by support vector machines using multi-scale energy and pseudo amino acid composition

As more and more genomes have been discovered in recent years, there is an urgent need to develop a reliable method to predict the subcellular localization for the explosion of newly found proteins. However, many well-known prediction methods based on amino acid composition have problems utilizing the sequence-order information. Here, based on the concept of Chou's pseudo amino acid composition (PseAA), a new feature extraction method, the multi-scale energy (MSE) approach, is introduced to incorporate the sequence-order information. First, a protein sequence was mapped to a digital signal using the amino acid index. Then, by wavelet transform, the mapped signal was broken down into several scales in which the energy factors were calculated and further formed into an MSE feature vector. Following this, combining this MSE feature vector with amino acid composition (AA), we constructed a series of MSEPseAA feature vectors to represent the protein subcellular localization sequences. Finally, according to a new kind of normalization approach, the MSEPseAA feature vectors were normalized to form the improved MSEPseAA vectors, named as IEPseAA. Using the technique of IEPseAA, C-support vector machine (C-SVM) and three multi-class SVMs strategies, quite promising results were obtained, indicating that MSE is quite effective in reflecting the sequence-order effects and might become a useful tool for predicting the other attributes of proteins as well.     

Using protein-protein interaction network information to predict the subcellular locations of proteins in budding yeast

The information of protein subcellular localization is vitally important for in-depth understanding the intricate pathways that regulate biological processes at the cellular level. With the rapidly increasing number of newly found protein sequence in the Post-Genomic Age, many automated methods have been developed attempting to help annotate their subcellular locations in a timely manner. However, very few of them were developed using the protein-protein interaction (PPI) network information. In this paper, we have introduced a new concept called "tethering potential" by which the PPI information can be effectively fused into the formulation for protein samples. Based on such a network frame, a new predictor called Yeast-PLoc has been developed for identifying budding yeast proteins among their 19 subcellular location sites. Meanwhile, a purely sequence-based approach, called the "hybrid-property" method, is integrated into Yeast-PLoc as a fall-back to deal with those proteins without sufficient PPI information. The overall success rate by the jackknife test on the 4,683 yeast proteins in the training dataset was 70.25%. Furthermore, it was shown that the success rate by Yeast- PLoc on an independent dataset was remarkably higher than those by some other existing predictors, indicating that the current approach by incorporating the PPI information is quite promising. As a user-friendly web-server, Yeast-PLoc is freely accessible at http://yeastloc.biosino.org/.     

Prediction of subcellular location apoptosis proteins with ensemble classifier and feature selection

Apoptosis proteins have a central role in the development and the homeostasis of an organism. These proteins are very important for understanding the mechanism of programmed cell death. The function of an apoptosis protein is closely related to its subcellular location. It is crucial to develop powerful tools to predict apoptosis protein locations for rapidly increasing gap between the number of known structural proteins and the number of known sequences in protein databank. In this study, amino acids pair compositions with different spaces are used to construct feature sets for representing sample of protein feature selection approach based on binary particle swarm optimization, which is applied to extract effective feature. Ensemble classifier is used as prediction engine, of which the basic classifier is the fuzzy K-nearest neighbor. Each basic classifier is trained with different feature sets. Two datasets often used in prior works are selected to validate the performance of proposed approach. The results obtained by jackknife test are quite encouraging, indicating that the proposed method might become a potentially useful tool for subcellular location of apoptosis protein, or at least can play a complimentary role to the existing methods in the relevant areas. The supplement information and software written in Matlab are available by contacting the corresponding author.     

Protein location prediction using atomic composition and global features of the amino acid sequence

Subcellular location of protein is constructive information in determining its function, screening for drug candidates, vaccine design, annotation of gene products and in selecting relevant proteins for further studies. Computational prediction of subcellular localization deals with predicting the location of a protein from its amino acid sequence. For a computational localization prediction method to be more accurate, it should exploit all possible relevant biological features that contribute to the subcellular localization. In this work, we extracted the biological features from the full length protein sequence to incorporate more biological information. A new biological feature, distribution of atomic composition is effectively used with, multiple physiochemical properties, amino acid composition, three part amino acid composition, and sequence similarity for predicting the subcellular location of the protein. Support Vector Machines are designed for four modules and prediction is made by a weighted voting system. Our system makes prediction with an accuracy of 100, 82.47, 88.81 for self-consistency test, jackknife test and independent data test respectively. Our results provide evidence that the prediction based on the biological features derived from the full length amino acid sequence gives better accuracy than those derived from N-terminal alone. Considering the features as a distribution within the entire sequence will bring out underlying property distribution to a greater detail to enhance the prediction accuracy.     

Using complexity measure factor to predict protein subcellular location

Summary. Recent advances in large-scale genome sequencing have led to the rapid accumulation of amino acid sequences of proteins whose functions are unknown. Because the functions of these proteins are closely correlated with their subcellular localizations, it is vitally important to develop an automated method as a high-throughput tool to timely identify their subcellular location. Based on the concept of the pseudo amino acid composition by which a considerable amount of sequence-order effects can be incorporated into a set of discrete numbers (Chou, K. C., Proteins: Structure, Function, and Genetics, 2001, 43: 246–255), the complexity measure approach is introduced. The advantage by incorporating the complexity measure factor as one of the pseudo amino acid components for a protein is that it can more effectively reflect its overall sequence-order feature than the conventional correlation factors. With such a formulation frame to represent the samples of protein sequences, the covariant-discriminant predictor (Chou, K. C. and Elrod, D. W., Protein Engineering, 1999, 12: 107–118) was adopted to conduct prediction. High success rates were obtained by both the jackknife cross-validation test and independent dataset test, suggesting that introduction of the concept of the complexity measure into prediction of protein subcellular location is quite promising, and might also hold a great potential as a useful vehicle for the other areas of molecular biology.     

PLPD: reliable protein localization prediction from imbalanced and overlapped datasets

Subcellular localization is one of the key functional characteristics of proteins. An automatic and efficient prediction method for the protein subcellular localization is highly required owing to the need for large-scale genome analysis. From a machine learning point of view, a dataset of protein localization has several characteristics: the dataset has too many classes (there are more than 10 localizations in a cell), it is a multi-label dataset (a protein may occur in several different subcellular locations), and it is too imbalanced (the number of proteins in each localization is remarkably different). Even though many previous works have been done for the prediction of protein subcellular localization, none of them tackles effectively these characteristics at the same time. Thus, a new computational method for protein localization is eventually needed for more reliable outcomes. To address the issue, we present a protein localization predictor based on D-SVDD (PLPD) for the prediction of protein localization, which can find the likelihood of a specific localization of a protein more easily and more correctly. Moreover, we introduce three measurements for the more precise evaluation of a protein localization predictor. As the results of various datasets which are made from the experiments of Huh et al. (2003), the proposed PLPD method represents a different approach that might play a complimentary role to the existing methods, such as Nearest Neighbor method and discriminate covariant method. Finally, after finding a good boundary for each localization using the 5184 classified proteins as training data, we predicted 138 proteins whose subcellular localizations could not be clearly observed by the experiments of Huh et al. (2003).     

Predicting protein localization in budding yeast

MOTIVATION: Most of the existing methods in predicting protein subcellular location were used to deal with the cases limited within the scope from two to five localizations, and only a few of them can be effectively extended to cover the cases of 12-14 localizations. This is because the more the locations involved are, the poorer the success rate would be. Besides, some proteins may occur in several different subcellular locations, i.e. bear the feature of 'multiplex locations'. So far there is no method that can be used to effectively treat the difficult multiplex location problem. The present study was initiated in an attempt to address (1) how to efficiently identify the localization of a query protein among many possible subcellular locations, and (2) how to deal with the case of multiplex locations. RESULTS: By hybridizing gene ontology, functional domain and pseudo amino acid composition approaches, a new method has been developed that can be used to predict subcellular localization of proteins with multiplex location feature. A global analysis of the proteins in budding yeast classified into 22 locations was performed by jack-knife cross-validation with the new method. The overall success identification rate thus obtained is 70%. In contrast to this, the corresponding rates obtained by some other existing methods were only 13-14%, indicating that the new method is very powerful and promising. Furthermore, predictions were made for the four proteins whose localizations could not be determined by experiments, as well as for the 236 proteins whose localizations in budding yeast were ambiguous according to experimental observations. However, according to our predicted results, many of these 'ambiguous proteins' were found to have the same score and ranking for several different subcellular locations, implying that they may simultaneously exist, or move around, in these locations. This finding is intriguing because it reflects the dynamic feature of these proteins in a cell that may be associated with some special biological functions.     

Robust and stable feature selection by integrating ranking methods and wrapper technique in genetic data classification

High dimensional data increase the dimension of space and consequently the computational complexity and result in lower generalization. From these types of classification problems microarray data classification can be mentioned. Microarrays contain genetic and biological data which can be used to diagnose diseases including various types of cancers and tumors. Having intractable dimensions, dimension reduction process is necessary on these data. The main goal of this paper is to provide a method for dimension reduction and classification of genetic data sets. The proposed approach includes different stages. In the first stage, several feature ranking methods are fused for enhancing the robustness and stability of feature selection process. Wrapper method is combined with the proposed hybrid ranking method to embed the interaction between genes. Afterwards, the classification process is applied using support vector machine. Before feeding the data to the SVM classifier the problem of imbalance classes of data in the training phase should be overcame. The experimental results of the proposed approach on five microarray databases show that the robustness metric of the feature selection process is in the interval of [0.70, 0.88]. Also the classification accuracy is in the range of [91%, 96%].     

Classification of motor imagery tasks for BCI with multiresolution analysis and multiobjective feature selection

Background

Brain-computer interfacing (BCI) applications based on the classification of electroencephalographic (EEG) signals require solving high-dimensional pattern classification problems with such a relatively small number of training patterns that curse of dimensionality problems usually arise. Multiresolution analysis (MRA) has useful properties for signal analysis in both temporal and spectral analysis, and has been broadly used in the BCI field. However, MRA usually increases the dimensionality of the input data. Therefore, some approaches to feature selection or feature dimensionality reduction should be considered for improving the performance of the MRA based BCI.

Methods

This paper investigates feature selection in the MRA-based frameworks for BCI. Several wrapper approaches to evolutionary multiobjective feature selection are proposed with different structures of classifiers. They are evaluated by comparing with baseline methods using sparse representation of features or without feature selection.

Results and conclusion

The statistical analysis, by applying the Kolmogorov-Smirnoff and Kruskal–Wallis tests to the means of the Kappa values evaluated by using the test patterns in each approach, has demonstrated some advantages of the proposed approaches. In comparison with the baseline MRA approach used in previous studies, the proposed evolutionary multiobjective feature selection approaches provide similar or even better classification performances, with significant reduction in the number of features that need to be computed.

     

Predicting protein subcellular localization by pseudo amino acid composition with a segment-weighted and features-combined approach

Information of protein subcellular location plays an important role in molecular cell biology. Prediction of the subcellular location of proteins will help to understand their functions and interactions. In this paper, a different mode of pseudo amino acid composition was proposed to represent protein samples for predicting their subcellular localization via the following procedures: based on the optimal splice site of each protein sequence, we divided a sequence into sorting signal part and mature protein part, and extracted sequence features from each part separately. Then, the combined features were fed into the SVM classifier to perform the prediction. By the jackknife test on a benchmark dataset in which none of proteins included has more than 90% pairwise sequence identity to any other, the overall accuracies achieved by the method are 94.5% and 90.3% for prokaryotic and eukaryotic proteins, respectively. The results indicate that the prediction quality by our method is quite satisfactory. It is anticipated that the current method may serve as an alternative approach to the existing prediction methods.     

A neural network model with feature selection for Korean speech act classification

A speech act is a linguistic action intended by a speaker. Speech act classification is an essential part of a dialogue understanding system because the speech act of an utterance is closely tied with the user's intention in the utterance. We propose a neural network model for Korean speech act classification. In addition, we propose a method that extracts morphological features from surface utterances and selects effective ones among the morphological features. Using the feature selection method, the proposed neural network can partially increase precision and decrease training time. In the experiment, the proposed neural network showed better results than other models using comparatively high-level linguistic features. Based on the experimental result, we believe that the proposed neural network model is suitable for real field applications because it is easy to expand the neural network model into other domains. Moreover, we found that neural networks can be useful in speech act classification if we can convert surface sentences into vectors with fixed dimensions by using an effective feature selection method.     

Predicting subcellular location of apoptosis proteins based on wavelet transform and support vector machine

Apoptosis proteins have a central role in the development and homeostasis of an organism. These proteins are very important for understanding the mechanism of programmed cell death. As a result of genome and other sequencing projects, the gap between the number of known apoptosis protein sequences and the number of known apoptosis protein structures is widening rapidly. Because of this extremely unbalanced state, it would be worthwhile to develop a fast and reliable method to identify their subcellular locations so as to gain better insight into their biological functions. In view of this, a new method, in which the support vector machine combines with discrete wavelet transform, has been developed to predict the subcellular location of apoptosis proteins. The results obtained by the jackknife test were quite promising, and indicated that the proposed method can remarkably improve the prediction accuracy of subcellular locations, and might also become a useful high-throughput tool in characterizing other attributes of proteins, such as enzyme class, membrane protein type, and nuclear receptor subfamily according to their sequences.     

Gene ontology based transfer learning for protein subcellular localization

Background  

Prediction of protein subcellular localization generally involves many complex factors, and using only one or two aspects of data information may not tell the true story. For this reason, some recent predictive models are deliberately designed to integrate multiple heterogeneous data sources for exploiting multi-aspect protein feature information. Gene ontology, hereinafter referred to as GO, uses a controlled vocabulary to depict biological molecules or gene products in terms of biological process, molecular function and cellular component. With the rapid expansion of annotated protein sequences, gene ontology has become a general protein feature that can be used to construct predictive models in computational biology. Existing models generally either concatenated the GO terms into a flat binary vector or applied majority-vote based ensemble learning for protein subcellular localization, both of which can not estimate the individual discriminative abilities of the three aspects of gene ontology.     

Face Recognition Using Sparse Representation-Based Classification on K-Nearest Subspace

The sparse representation-based classification (SRC) has been proven to be a robust face recognition method. However, its computational complexity is very high due to solving a complex -minimization problem. To improve the calculation efficiency, we propose a novel face recognition method, called sparse representation-based classification on k-nearest subspace (SRC-KNS). Our method first exploits the distance between the test image and the subspace of each individual class to determine the nearest subspaces and then performs SRC on the selected classes. Actually, SRC-KNS is able to reduce the scale of the sparse representation problem greatly and the computation to determine the nearest subspaces is quite simple. Therefore, SRC-KNS has a much lower computational complexity than the original SRC. In order to well recognize the occluded face images, we propose the modular SRC-KNS. For this modular method, face images are partitioned into a number of blocks first and then we propose an indicator to remove the contaminated blocks and choose the nearest subspaces. Finally, SRC is used to classify the occluded test sample in the new feature space. Compared to the approach used in the original SRC work, our modular SRC-KNS can greatly reduce the computational load. A number of face recognition experiments show that our methods have five times speed-up at least compared to the original SRC, while achieving comparable or even better recognition rates.     

Esub8: A novel tool to predict protein subcellular localizations in eukaryotic organisms

Background

Subcellular localization of a new protein sequence is very important and fruitful for understanding its function. As the number of new genomes has dramatically increased over recent years, a reliable and efficient system to predict protein subcellular location is urgently needed.

Results

Esub8 was developed to predict protein subcellular localizations for eukaryotic proteins based on amino acid composition. In this research, the proteins are classified into the following eight groups: chloroplast, cytoplasm, extracellular, Golgi apparatus, lysosome, mitochondria, nucleus and peroxisome. We know subcellular localization is a typical classification problem; consequently, a one-against-one (1-v-1) multi-class support vector machine was introduced to construct the classifier. Unlike previous methods, ours considers the order information of protein sequences by a different method. Our method is tested in three subcellular localization predictions for prokaryotic proteins and four subcellular localization predictions for eukaryotic proteins on Reinhardt's dataset. The results are then compared to several other methods. The total prediction accuracies of two tests are both 100% by a self-consistency test, and are 92.9% and 84.14% by the jackknife test, respectively. Esub8 also provides excellent results: the total prediction accuracies are 100% by a self-consistency test and 87% by the jackknife test.

Conclusions

Our method represents a different approach for predicting protein subcellular localization and achieved a satisfactory result; furthermore, we believe Esub8 will be a useful tool for predicting protein subcellular localizations in eukaryotic organisms.