THRONE: A New Approach for Accurate Prediction of Human RNA N7-Methylguanosine Sites

N⁷-methylguanosine (m7G) is an essential, ubiquitous, and positively charged modification at the 5′ cap of eukaryotic mRNA, modulating its export, translation, and splicing processes. Although several machine learning (ML)-based computational predictors for m7G have been developed, all utilized specific computational framework. This study is the first instance we explored four different computational frameworks and identified the best approach. Based on that we developed a novel predictor, THRONE (A three-layer ensemble predictor for identifying human RNA N7-methylguanosine sites) to accurately identify m7G sites from the human genome. THRONE employs a wide range of sequence-based features inputted to several ML classifiers and combines these models through ensemble learning. The three-step ensemble learning is as follows: 54 baseline models were constructed in the first layer and the predicted probability of m7G was considered as a new feature vector for the sequential step. Subsequently, six meta-models were created using the new feature vector and their predicted probability was yet again considered as novel features. Finally, random forest was deemed as the best super classifier learner for the final prediction using a systematic approach incorporated with novel features. Interestingly, THRONE outperformed other existing methods in the prediction of m7G sites on both cross-validation analysis and independent evaluation. The proposed method is publicly accessible at: http://thegleelab.org/THRONE/ and expects to help the scientific community identify the putative m7G sites and formulate a novel testable biological hypothesis.     

Machine learning study of classifiers trained with biophysiochemical properties of amino acids to predict fibril forming Peptide motifs

It is important to understand the cause of amyloid illnesses by predicting the short protein fragments capable of forming amyloid-like fibril motifs aiding in the discovery of sequence-targeted anti-aggregation drugs. It is extremely desirable to design computational tools to provide affordable in silico predictions owing to the limitations of molecular techniques for their identification. In this research article, we tried to study, from a machine learning perspective, the performance of several machine learning classifiers that use heterogenous features based on biochemical and biophysical properties of amino acids to discriminate between amyloidogenic and non-amyloidogenic regions in peptides. Four conventional machine learning classifiers namely Support Vector Machine, Neural network, Decision tree and Random forest were trained and tested to find the best classifier that fits the problem domain well. Prior to classification, novel implementations of two biologically-inspired feature optimization techniques based on evolutionary algorithms and methodologies that mimic social life and a multivariate method based on projection are utilized in order to remove the unimportant and uninformative features. Among the dimenionality reduction algorithms considered under the study, prediction results show that algorithms based on evolutionary computation is the most effective. SVM best suits the problem domain in its fitment among the classifiers considered. The best classifier is also compared with an online predictor to evidence the equilibrium maintained between true positive rates and false positive rates in the proposed classifier. This exploratory study suggests that these methods are promising in providing amyloidogenity prediction and may be further extended for large-scale proteomic studies.     

A novel algorithm for network-based prediction of cancer recurrence

To develop accurate prognostic models is one of the biggest challenges in “omics”-based cancer research. Here, we propose a novel computational method for identifying dysregulated gene subnetworks as biomarkers to predict cancer recurrence. Applying our method to the DNA methylome of endometrial cancer patients, we identified a subnetwork consisting of differentially methylated (DM) genes, and non-differentially methylated genes, termed Epigenetic Connectors (EC), that are topologically important for connecting the DM genes in a protein-protein interaction network. The ECs are statistically significantly enriched in well-known tumorgenesis and metastasis pathways, and include known epigenetic regulators. Importantly, combining the DMs and ECs as features using a novel random walk procedure, we constructed a support vector machine classifier that significantly improved the prediction accuracy of cancer recurrence and outperformed several alternative methods, demonstrating the effectiveness of our network-based approach.     

DROP: an SVM domain linker predictor trained with optimal features selected by random forest

MOTIVATION: Biologically important proteins are often large, multidomain proteins, which are difficult to characterize by high-throughput experimental methods. Efficient domain/boundary predictions are thus increasingly required in diverse area of proteomics research for computationally dissecting proteins into readily analyzable domains. RESULTS: We constructed a support vector machine (SVM)-based domain linker predictor, DROP (Domain linker pRediction using OPtimal features), which was trained with 25 optimal features. The optimal combination of features was identified from a set of 3000 features using a random forest algorithm complemented with a stepwise feature selection. DROP demonstrated a prediction sensitivity and precision of 41.3 and 49.4%, respectively. These values were over 19.9% higher than those of control SVM predictors trained with non-optimized features, strongly suggesting the efficiency of our feature selection method. In addition, the mean NDO-Score of DROP for predicting novel domains in seven CASP8 FM multidomain proteins was 0.760, which was higher than any of the 12 published CASP8 DP servers. Overall, these results indicate that the SVM prediction of domain linkers can be improved by identifying optimal features that best distinguish linker from non-linker regions.     

MRI-based radiomics signature for tumor grading of rectal carcinoma using random forest model

The present study aimed to construct prospective models for tumor grading of rectal carcinoma by using magnetic resonance (MR)-based radiomics features. A set of 118 patients with rectal carcinoma was analyzed. After imbalance-adjustments of the data using Synthetic Minority Oversampling Technique (SMOTE), the final data set was randomized into the training set and validation set at the ratio of 3:1. The radiomics features were captured from manually segmented lesion of magnetic resonance imaging (MRI). The most related radiomics features were selected using the random forest model by calculating the Gini importance of initial extracted characteristics. A random forest classifier model was constructed using the top important features. The classifier model performance was evaluated via receive operator characteristic curve and area under the curve (AUC). A total of 1,131 radiomics features were extracted from segmented lesion. The top 50 most important features were selected to construct a random forest classifier model. The AUC values of grade 1, 2, 3, and 4 for training set were 0.918, 0.822, 0.775, and 1.000, respectively, and the corresponding AUC values for testing set were 0.717, 0.683, 0.690, and 0.827 separately. The developed feature selection method and machine learning-based prediction models using radiomics features of MRI show a relatively acceptable performance in tumor grading of rectal carcinoma and could distinguish the tumor subjects from the healthy ones, which is important for the prognosis of cancer patients.     

Prediction of membrane proteins using split amino acid and ensemble classification

Knowledge of the types of membrane protein provides useful clues in deducing the functions of uncharacterized membrane proteins. An automatic method for efficiently identifying uncharacterized proteins is thus highly desirable. In this work, we have developed a novel method for predicting membrane protein types by exploiting the discrimination capability of the difference in amino acid composition at the N and C terminus through split amino acid composition (SAAC). We also show that the ensemble classification can better exploit this discriminating capability of SAAC. In this study, membrane protein types are classified using three feature extraction and several classification strategies. An ensemble classifier Mem-EnsSAAC is then developed using the best feature extraction strategy. Pseudo amino acid (PseAA) composition, discrete wavelet analysis (DWT), SAAC, and a hybrid model are employed for feature extraction. The nearest neighbor, probabilistic neural network, support vector machine, random forest, and Adaboost are used as individual classifiers. The predicted results of the individual learners are combined using genetic algorithm to form an ensemble classifier, Mem-EnsSAAC yielding an accuracy of 92.4 and 92.2% for the Jackknife and independent dataset test, respectively. Performance measures such as MCC, sensitivity, specificity, F-measure, and Q-statistics show that SAAC-based prediction yields significantly higher performance compared to PseAA- and DWT-based systems, and is also the best reported so far. The proposed Mem-EnsSAAC is able to predict the membrane protein types with high accuracy and consequently, can be very helpful in drug discovery. It can be accessed at http://111.68.99.218/membrane.     

miRSel: Automated extraction of associations between microRNAs and genes from the biomedical literature

Background  

MicroRNAs have been discovered as important regulators of gene expression. To identify the target genes of microRNAs, several databases and prediction algorithms have been developed. Only few experimentally confirmed microRNA targets are available in databases. Many of the microRNA targets stored in databases were derived from large-scale experiments that are considered not very reliable. We propose to use text mining of publication abstracts for extracting microRNA-gene associations including microRNA-target relations to complement current repositories.     

Discriminating acidic and alkaline enzymes using a random forest model with secondary structure amino acid composition

Understating the adaptation mechanism of enzymes to pH extremes and discriminating them is a challenging task and would help to design stable enzymes. In this work, we have systematically analyzed the secondary structure amino acid compositions of 105 acidic and 111 alkaline enzymes, respectively. We found that the propensity of the individual residues to participate in different secondary structures might be a general stability mechanism for their adaptation to pH extremes. Based on it, we present a secondary structure amino acid composition method for extracting useful features from sequence, and a novel ensemble classifier named random forest was used. The overall prediction accuracy evaluated by the 10-fold cross-validation reached 90.7%. Comparing our method with other feature extraction methods, the improvement of the overall prediction accuracy ranged from 5.5% to 21.2%. The random forests algorithm also outperformed other machine learning techniques with an improvement ranging from 3.2% to 19.9%.     

Predicting potential cancer genes by integrating network properties, sequence features and functional annotations

The discovery of novel cancer genes is one of the main goals in cancer research. Bioinformatics methods can be used to accelerate cancer gene discovery, which may help in the understanding of cancer and the development of drug targets. In this paper, we describe a classifier to predict potential cancer genes that we have developed by integrating multiple biological evidence, including protein-protein interaction network properties, and sequence and functional features. We detected 55 features that were significantly different between cancer genes and non-cancer genes. Fourteen cancer-associated features were chosen to train the classifier. Four machine learning methods, logistic regression, support vector machines (SVMs), BayesNet and decision tree, were explored in the classifier models to distinguish cancer genes from non-cancer genes. The prediction power of the different models was evaluated by 5-fold cross-validation. The area under the receiver operating characteristic curve for logistic regression, SVM, Baysnet and J48 tree models was 0.834, 0.740, 0.800 and 0.782, respectively. Finally, the logistic regression classifier with multiple biological features was applied to the genes in the Entrez database, and 1976 cancer gene candidates were identified. We found that the integrated prediction model performed much better than the models based on the individual biological evidence, and the network and functional features had stronger powers than the sequence features in predicting cancer genes.     

Plant microRNA-Target Interaction Identification Model Based on the Integration of Prediction Tools and Support Vector Machine

Background

Confident identification of microRNA-target interactions is significant for studying the function of microRNA (miRNA). Although some computational miRNA target prediction methods have been proposed for plants, results of various methods tend to be inconsistent and usually lead to more false positive. To address these issues, we developed an integrated model for identifying plant miRNA–target interactions.

Results

Three online miRNA target prediction toolkits and machine learning algorithms were integrated to identify and analyze Arabidopsis thaliana miRNA-target interactions. Principle component analysis (PCA) feature extraction and self-training technology were introduced to improve the performance. Results showed that the proposed model outperformed the previously existing methods. The results were validated by using degradome sequencing supported Arabidopsis thaliana miRNA-target interactions. The proposed model constructed on Arabidopsis thaliana was run over Oryza sativa and Vitis vinifera to demonstrate that our model is effective for other plant species.

Conclusions

The integrated model of online predictors and local PCA-SVM classifier gained credible and high quality miRNA-target interactions. The supervised learning algorithm of PCA-SVM classifier was employed in plant miRNA target identification for the first time. Its performance can be substantially improved if more experimentally proved training samples are provided.     

Feature Selection for high Dimensional DNA Microarray data using hybrid approaches

Feature selection from DNA microarray data is a major challenge due to high dimensionality in expression data. The number of samples in the microarray data set is much smaller compared to the number of genes. Hence the data is improper to be used as the training set of a classifier. Therefore it is important to select features prior to training the classifier. It should be noted that only a small subset of genes from the data set exhibits a strong correlation with the class. This is because finding the relevant genes from the data set is often non-trivial. Thus there is a need to develop robust yet reliable methods for gene finding in expression data. We describe the use of several hybrid feature selection approaches for gene finding in expression data. These approaches include filtering (filter out the best genes from the data set) and wrapper (best subset of genes from the data set) phases. The methods use information gain (IG) and Pearson Product Moment Correlation (PPMC) as the filtering parameters and biogeography based optimization (BBO) as the wrapper approach. K nearest neighbour algorithm (KNN) and back propagation neural network are used for evaluating the fitness of gene subsets during feature selection. Our analysis shows that an impressive performance is provided by the IG-BBO-KNN combination in different data sets with high accuracy (>90%) and low error rate.     

Computational identification of human long intergenic non-coding RNAs using a GA–SVM algorithm

Long intergenic non-coding RNAs (lincRNAs) are a new type of non-coding RNAs and are closely related with the occurrence and development of diseases. In previous studies, most lincRNAs have been identified through next-generation sequencing. Because lincRNAs exhibit tissue-specific expression, the reproducibility of lincRNA discovery in different studies is very poor. In this study, not including lincRNA expression, we used the sequence, structural and protein-coding potential features as potential features to construct a classifier that can be used to distinguish lincRNAs from non-lincRNAs. The GA–SVM algorithm was performed to extract the optimized feature subset. Compared with several feature subsets, the five-fold cross validation results showed that this optimized feature subset exhibited the best performance for the identification of human lincRNAs. Moreover, the LincRNA Classifier based on Selected Features (linc-SF) was constructed by support vector machine (SVM) based on the optimized feature subset. The performance of this classifier was further evaluated by predicting lincRNAs from two independent lincRNA sets. Because the recognition rates for the two lincRNA sets were 100% and 99.8%, the linc-SF was found to be effective for the prediction of human lincRNAs.     

Aspect-Object Alignment with Integer Linear Programming in Opinion Mining

Target extraction is an important task in opinion mining. In this task, a complete target consists of an aspect and its corresponding object. However, previous work has always simply regarded the aspect as the target itself and has ignored the important "object" element. Thus, these studies have addressed incomplete targets, which are of limited use for practical applications. This paper proposes a novel and important sentiment analysis task, termed aspect-object alignment, to solve the "object neglect" problem. The objective of this task is to obtain the correct corresponding object for each aspect. We design a two-step framework for this task. We first provide an aspect-object alignment classifier that incorporates three sets of features, namely, the basic, relational, and special target features. However, the objects that are assigned to aspects in a sentence often contradict each other and possess many complicated features that are difficult to incorporate into a classifier. To resolve these conflicts, we impose two types of constraints in the second step: intra-sentence constraints and inter-sentence constraints. These constraints are encoded as linear formulations, and Integer Linear Programming (ILP) is used as an inference procedure to obtain a final global decision that is consistent with the constraints. Experiments on a corpus in the camera domain demonstrate that the three feature sets used in the aspect-object alignment classifier are effective in improving its performance. Moreover, the classifier with ILP inference performs better than the classifier without it, thereby illustrating that the two types of constraints that we impose are beneficial.     

Mito-GSAAC: mitochondria prediction using genetic ensemble classifier and split amino acid composition

Mitochondria are all-important organelles of eukaryotic cells since they are involved in processes associated with cellular mortality and human diseases. Therefore, trustworthy techniques are highly required for the identification of new mitochondrial proteins. We propose Mito-GSAAC system for prediction of mitochondrial proteins. The aim of this work is to investigate an effective feature extraction strategy and to develop an ensemble approach that can better exploit the advantages of this feature extraction strategy for mitochondria classification. We investigate four kinds of protein representations for prediction of mitochondrial proteins: amino acid composition, dipeptide composition, pseudo amino acid composition, and split amino acid composition (SAAC). Individual classifiers such as support vector machine (SVM), k-nearest neighbor, multilayer perceptron, random forest, AdaBoost, and bagging are first trained. An ensemble classifier is then built using genetic programming (GP) for evolving a complex but effective decision space from the individual decision spaces of the trained classifiers. The highest prediction performance for Jackknife test is 92.62% using GP-based ensemble classifier on SAAC features, which is the highest accuracy, reported so far on the Mitochondria dataset being used. While on the Malaria Parasite Mitochondria dataset, the highest accuracy is obtained by SVM using SAAC and it is further enhanced to 93.21% using GP-based ensemble. It is observed that SAAC has better discrimination power for mitochondria prediction over the rest of the feature extraction strategies. Thus, the improved prediction performance is largely due to the better capability of SAAC for discriminating between mitochondria and non-mitochondria proteins at the N and C terminus and the effective combination capability of GP. Mito-GSAAC can be accessed at . It is expected that the novel approach and the accompanied predictor will have a major impact to Molecular Cell Biology, Proteomics, Bioinformatics, System Biology, and Drug Development.     

A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data

Background  

Regularized regression methods such as principal component or partial least squares regression perform well in learning tasks on high dimensional spectral data, but cannot explicitly eliminate irrelevant features. The random forest classifier with its associated Gini feature importance, on the other hand, allows for an explicit feature elimination, but may not be optimally adapted to spectral data due to the topology of its constituent classification trees which are based on orthogonal splits in feature space.     

基于蛋白质序列的泛素化位点预测研究进展

泛素化是目前广受关注的一种翻译后修饰过程,对蛋白质降解、DNA修复等多种细胞过程都具有重要的调控作用。本文根据国内外蛋白质泛素化位点预测的研究,分析了预测泛素化位点的特征属性,总结了对这些特征进行优化的特征选择方法,并对预测过程中所使用的各种机器学习分类器进行了概述。     

Evaluation of different biological data and computational classification methods for use in protein interaction prediction

Protein–protein interactions play a key role in many biological systems. High‐throughput methods can directly detect the set of interacting proteins in yeast, but the results are often incomplete and exhibit high false‐positive and false‐negative rates. Recently, many different research groups independently suggested using supervised learning methods to integrate direct and indirect biological data sources for the protein interaction prediction task. However, the data sources, approaches, and implementations varied. Furthermore, the protein interaction prediction task itself can be subdivided into prediction of (1) physical interaction, (2) co‐complex relationship, and (3) pathway co‐membership. To investigate systematically the utility of different data sources and the way the data is encoded as features for predicting each of these types of protein interactions, we assembled a large set of biological features and varied their encoding for use in each of the three prediction tasks. Six different classifiers were used to assess the accuracy in predicting interactions, Random Forest (RF), RF similarity‐based k‐Nearest‐Neighbor, Naïve Bayes, Decision Tree, Logistic Regression, and Support Vector Machine. For all classifiers, the three prediction tasks had different success rates, and co‐complex prediction appears to be an easier task than the other two. Independently of prediction task, however, the RF classifier consistently ranked as one of the top two classifiers for all combinations of feature sets. Therefore, we used this classifier to study the importance of different biological datasets. First, we used the splitting function of the RF tree structure, the Gini index, to estimate feature importance. Second, we determined classification accuracy when only the top‐ranking features were used as an input in the classifier. We find that the importance of different features depends on the specific prediction task and the way they are encoded. Strikingly, gene expression is consistently the most important feature for all three prediction tasks, while the protein interactions identified using the yeast‐2‐hybrid system were not among the top‐ranking features under any condition. Proteins 2006. © 2006 Wiley‐Liss, Inc.     

Sequence Based Prediction of DNA-Binding Proteins Based on Hybrid Feature Selection Using Random Forest and Gaussian Na?ve Bayes

Developing an efficient method for determination of the DNA-binding proteins, due to their vital roles in gene regulation, is becoming highly desired since it would be invaluable to advance our understanding of protein functions. In this study, we proposed a new method for the prediction of the DNA-binding proteins, by performing the feature rank using random forest and the wrapper-based feature selection using forward best-first search strategy. The features comprise information from primary sequence, predicted secondary structure, predicted relative solvent accessibility, and position specific scoring matrix. The proposed method, called DBPPred, used Gaussian naïve Bayes as the underlying classifier since it outperformed five other classifiers, including decision tree, logistic regression, k-nearest neighbor, support vector machine with polynomial kernel, and support vector machine with radial basis function. As a result, the proposed DBPPred yields the highest average accuracy of 0.791 and average MCC of 0.583 according to the five-fold cross validation with ten runs on the training benchmark dataset PDB594. Subsequently, blind tests on the independent dataset PDB186 by the proposed model trained on the entire PDB594 dataset and by other five existing methods (including iDNA-Prot, DNA-Prot, DNAbinder, DNABIND and DBD-Threader) were performed, resulting in that the proposed DBPPred yielded the highest accuracy of 0.769, MCC of 0.538, and AUC of 0.790. The independent tests performed by the proposed DBPPred on completely a large non-DNA binding protein dataset and two RNA binding protein datasets also showed improved or comparable quality when compared with the relevant prediction methods. Moreover, we observed that majority of the selected features by the proposed method are statistically significantly different between the mean feature values of the DNA-binding and the non DNA-binding proteins. All of the experimental results indicate that the proposed DBPPred can be an alternative perspective predictor for large-scale determination of DNA-binding proteins.