Predicting protein subcellular location: exploiting amino acid based sequence of feature spaces and fusion of diverse classifiers

HRGPred: Prediction of herbicide resistant genes with k-mer nucleotide compositional features and support vector machine

Herbicide resistance (HR) is a major concern for the agricultural producers as well as environmentalists. Resistance to commonly used herbicides are conferred due to mutation(s) in the genes encoding herbicide target sites/proteins (GETS). Identification of these genes through wet-lab experiments is time consuming and expensive. Thus, a supervised learning-based computational model has been proposed in this study, which is first of its kind for the prediction of seven classes of GETS. The cDNA sequences of the genes were initially transformed into numeric features based on the k-mer compositions and then supplied as input to the support vector machine. In the proposed SVM-based model, the prediction occurs in two stages, where a binary classifier in the first stage discriminates the genes involved in conferring the resistance to herbicides from other genes, followed by a multi-class classifier in the second stage that categorizes the predicted herbicide resistant genes in the first stage into any one of the seven resistant classes. Overall classification accuracies were observed to be ~89% and >97% for binary and multi-class classifications respectively. The proposed model confirmed higher accuracy than the homology-based algorithms viz., BLAST and Hidden Markov Model. Besides, the developed computational model achieved ~87% accuracy, while tested with an independent dataset. An online prediction server HRGPred (http://cabgrid.res.in:8080/hrgpred) has also been established to facilitate the prediction of GETS by the scientific community.

LEARNING PARSIMONIOUS ENSEMBLES FOR UNBALANCED COMPUTATIONAL GENOMICS PROBLEMS

Prediction problems in biomedical sciences are generally quite difficult, partially due to incomplete knowledge of how the phenomenon of interest is influenced by the variables and measurements used for prediction, as well as a lack of consensus regarding the ideal predictor(s) for specific problems. In these situations, a powerful approach to improving prediction performance is to construct ensembles that combine the outputs of many individual base predictors, which have been successful for many biomedical prediction tasks. Moreover, selecting a parsimonious ensemble can be of even greater value for biomedical sciences, where it is not only important to learn an accurate predictor, but also to interpret what novel knowledge it can provide about the target problem. Ensemble selection is a promising approach for this task because of its ability to select a collectively predictive subset, often a relatively small one, of all input base predictors. One of the most well-known algorithms for ensemble selection, CES (Caruana et al.'s Ensemble Selection), generally performs well in practice, but faces several challenges due to the difficulty of choosing the right values of its various parameters. Since the choices made for these parameters are usually ad-hoc, good performance of CES is difficult to guarantee for a variety of problems or datasets. To address these challenges with CES and other such algorithms, we propose a novel heterogeneous ensemble selection approach based on the paradigm of reinforcement learning (RL), which offers a more systematic and mathematically sound methodology for exploring the many possible combinations of base predictors that can be selected into an ensemble. We develop three RL-based strategies for constructing ensembles and analyze their results on two unbalanced computational genomics problems, namely the prediction of protein function and splice sites in eukaryotic genomes. We show that the resultant ensembles are indeed substantially more parsimonious as compared to the full set of base predictors, yet still offer almost the same classification power, especially for larger datasets. The RL ensembles also yield a better combination of parsimony and predictive performance as compared to CES.

Predicting protein function and other biomedical characteristics with heterogeneous ensembles

Prediction problems in biomedical sciences, including protein function prediction (PFP), are generally quite difficult. This is due in part to incomplete knowledge of the cellular phenomenon of interest, the appropriateness and data quality of the variables and measurements used for prediction, as well as a lack of consensus regarding the ideal predictor for specific problems. In such scenarios, a powerful approach to improving prediction performance is to construct heterogeneous ensemble predictors that combine the output of diverse individual predictors that capture complementary aspects of the problems and/or datasets. In this paper, we demonstrate the potential of such heterogeneous ensembles, derived from stacking and ensemble selection methods, for addressing PFP and other similar biomedical prediction problems. Deeper analysis of these results shows that the superior predictive ability of these methods, especially stacking, can be attributed to their attention to the following aspects of the ensemble learning process: (i) better balance of diversity and performance, (ii) more effective calibration of outputs and (iii) more robust incorporation of additional base predictors. Finally, to make the effective application of heterogeneous ensembles to large complex datasets (big data) feasible, we present DataSink, a distributed ensemble learning framework, and demonstrate its sound scalability using the examined datasets. DataSink is publicly available from https://github.com/shwhalen/datasink.

Prediction of human breast and colon cancers from imbalanced data using nearest neighbor and support vector machines

This study proposes a novel prediction approach for human breast and colon cancers using different feature spaces. The proposed scheme consists of two stages: the preprocessor and the predictor. In the preprocessor stage, the mega-trend diffusion (MTD) technique is employed to increase the samples of the minority class, thereby balancing the dataset. In the predictor stage, machine-learning approaches of K-nearest neighbor (KNN) and support vector machines (SVM) are used to develop hybrid MTD-SVM and MTD-KNN prediction models. MTD-SVM model has provided the best values of accuracy, G-mean and Matthew's correlation coefficient of 96.71%, 96.70% and 71.98% for cancer/non-cancer dataset, breast/non-breast cancer dataset and colon/non-colon cancer dataset, respectively. We found that hybrid MTD-SVM is the best with respect to prediction performance and computational cost. MTD-KNN model has achieved moderately better prediction as compared to hybrid MTD-NB (Naïve Bayes) but at the expense of higher computing cost. MTD-KNN model is faster than MTD-RF (random forest) but its prediction is not better than MTD-RF. To the best of our knowledge, the reported results are the best results, so far, for these datasets. The proposed scheme indicates that the developed models can be used as a tool for the prediction of cancer. This scheme may be useful for study of any sequential information such as protein sequence or any nucleic acid sequence.

IDM-PhyChm-Ens: intelligent decision-making ensemble methodology for classification of human breast cancer using physicochemical properties of amino acids

Development of an accurate and reliable intelligent decision-making method for the construction of cancer diagnosis system is one of the fast growing research areas of health sciences. Such decision-making system can provide adequate information for cancer diagnosis and drug discovery. Descriptors derived from physicochemical properties of protein sequences are very useful for classifying cancerous proteins. Recently, several interesting research studies have been reported on breast cancer classification. To this end, we propose the exploitation of the physicochemical properties of amino acids in protein primary sequences such as hydrophobicity (Hd) and hydrophilicity (Hb) for breast cancer classification. Hd and Hb properties of amino acids, in recent literature, are reported to be quite effective in characterizing the constituent amino acids and are used to study protein foldings, interactions, structures, and sequence-order effects. Especially, using these physicochemical properties, we observed that proline, serine, tyrosine, cysteine, arginine, and asparagine amino acids offer high discrimination between cancerous and healthy proteins. In addition, unlike traditional ensemble classification approaches, the proposed 'IDM-PhyChm-Ens' method was developed by combining the decision spaces of a specific classifier trained on different feature spaces. The different feature spaces used were amino acid composition, split amino acid composition, and pseudo amino acid composition. Consequently, we have exploited different feature spaces using Hd and Hb properties of amino acids to develop an accurate method for classification of cancerous protein sequences. We developed ensemble classifiers using diverse learning algorithms such as random forest (RF), support vector machines (SVM), and K-nearest neighbor (KNN) trained on different feature spaces. We observed that ensemble-RF, in case of cancer classification, performed better than ensemble-SVM and ensemble-KNN. Our analysis demonstrates that ensemble-RF, ensemble-SVM and ensemble-KNN are more effective than their individual counterparts. The proposed 'IDM-PhyChm-Ens' method has shown improved performance compared to existing techniques.

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.

WRF-TMH: predicting transmembrane helix by fusing composition index and physicochemical properties of amino acids

Membrane protein is the prime constituent of a cell, which performs a role of mediator between intra and extracellular processes. The prediction of transmembrane (TM) helix and its topology provides essential information regarding the function and structure of membrane proteins. However, prediction of TM helix and its topology is a challenging issue in bioinformatics and computational biology due to experimental complexities and lack of its established structures. Therefore, the location and orientation of TM helix segments are predicted from topogenic sequences. In this regard, we propose WRF-TMH model for effectively predicting TM helix segments. In this model, information is extracted from membrane protein sequences using compositional index and physicochemical properties. The redundant and irrelevant features are eliminated through singular value decomposition. The selected features provided by these feature extraction strategies are then fused to develop a hybrid model. Weighted random forest is adopted as a classification approach. We have used two benchmark datasets including low and high-resolution datasets. tenfold cross validation is employed to assess the performance of WRF-TMH model at different levels including per protein, per segment, and per residue. The success rates of WRF-TMH model are quite promising and are the best reported so far on the same datasets. It is observed that WRF-TMH model might play a substantial role, and will provide essential information for further structural and functional studies on membrane proteins. The accompanied web predictor is accessible at http://111.68.99.218/WRF-TMH/ .

Mem-PHybrid: hybrid features-based prediction system for classifying membrane protein types

Membrane proteins are a major class of proteins and encoded by approximately 20% to 30% of genes in most organisms. In this work, a two-layer novel membrane protein prediction system, called Mem-PHybrid, is proposed. It is able to first identify the protein query as a membrane or nonmembrane protein. In the second level, it further identifies the type of membrane protein. The proposed Mem-PHybrid prediction system is based on hybrid features, whereby a fusion of both the physicochemical and split amino acid composition-based features is performed. This enables the proposed Mem-PHybrid to exploit the discrimination capabilities of both types of feature extraction strategy. In addition, minimum redundancy and maximum relevance has also been applied to reduce the dimensionality of a feature vector. We employ random forest, evidence-theoretic K-nearest neighbor, and support vector machine (SVM) as classifiers and analyze their performance on two datasets. SVM using hybrid features yields the highest accuracy of 89.6% and 97.3% on dataset1 and 91.5% and 95.5% on dataset2 for jackknife and independent dataset tests, respectively. The enhanced prediction performance of Mem-PHybrid is largely attributed to the exploitation of the discrimination power of the hybrid features and of the learning capability of SVM. Mem-PHybrid is accessible at http://www.111.68.99.218/Mem-PHybrid.

An ensemble classifier for eukaryotic protein subcellular location prediction using gene ontology categories and amino acid hydrophobicity

With the rapid increase of protein sequences in the post-genomic age, it is challenging to develop accurate and automated methods for reliably and quickly predicting their subcellular localizations. Till now, many efforts have been tried, but most of which used only a single algorithm. In this paper, we proposed an ensemble classifier of KNN (k-nearest neighbor) and SVM (support vector machine) algorithms to predict the subcellular localization of eukaryotic proteins based on a voting system. The overall prediction accuracies by the one-versus-one strategy are 78.17%, 89.94% and 75.55% for three benchmark datasets of eukaryotic proteins. The improved prediction accuracies reveal that GO annotations and hydrophobicity of amino acids help to predict subcellular locations of eukaryotic proteins.

Predictability of protein subcellular locations by pattern recognition techniques

An analysis of the predictability of subcellular locations is performed by using simple pattern recognition techniques in an attempt to capture the real dimensions of the problem at hand. Results show that there are some particular locations that does not need of high complexity classification models to be predicted with high accuracies, and some partial biological explanations are formulated. All the experiments were carried out over a set of Arabidopsis Thaliana proteins and classes were defined according to the plants GO slim.

On the pH-optimum of activity and stability of proteins

Biological macromolecules evolved to perform their function in specific cellular environment (subcellular compartments or tissues); therefore, they should be adapted to the biophysical characteristics of the corresponding environment, one of them being the characteristic pH. Many macromolecular properties are pH dependent, such as activity and stability. However, only activity is biologically important, while stability may not be crucial for the corresponding reaction. Here, we show that the pH-optimum of activity (the pH of maximal activity) is correlated with the pH-optimum of stability (the pH of maximal stability) on a set of 310 proteins with available experimental data. We speculate that such a correlation is needed to allow the corresponding macromolecules to tolerate small pH fluctuations that are inevitable with cellular function. Our findings rationalize the efforts of correlating the pH of maximal stability and the characteristic pH of subcellular compartments, as only pH of activity is subject of evolutionary pressure. In addition, our analysis confirmed the previous observation that pH-optimum of activity and stability are not correlated with the isoelectric point, pI, or with the optimal temperature.