A novel features ranking metric with application to scalable visual and bioinformatics data classification

Combining Sequence Entropy and Subgraph Topology for Complex Prediction in Protein Protein Interaction (PPI) Network

Background:

Complex prediction from interaction network of proteins has become a challenging task. Most of the computational approaches focus on topological structures of protein complexes and fewer of them consider important biological information contained within amino acid sequences.

Objective:

To capture the essence of information contained within protein sequences we have computed sequence entropy and length. Proteins interact with each other and form different sub graph topologies.

Methods:

We integrate biological features with sub graph topological features and model complexes by using a Logistic Model Tree.

Results:

The experimental results demonstrated that our method out performs other four state-ofart computational methods in terms of the number of detecting known protein complexes correctly.

Conclusion:

In addition, our framework provides insights into future biological study and might be helpful in predicting other types of sub graph topologies.

Developing a Multi-Dose Computational Model for Drug-Induced Hepatotoxicity Prediction Based on Toxicogenomics Data

Drug-induced hepatotoxicity may cause acute and chronic liver disease, leading to great concern for patient safety. It is also one of the main reasons for drug withdrawal from the market. Toxicogenomics data has been widely used in hepatotoxicity prediction. In our study, we proposed a multi-dose computational model to predict the drug-induced hepatotoxicity based on gene expression and toxicity data. The dose/concentration information after drug treatment is fully utilized in our study based on the dose-response curve, thus a more informative representative of the dose-response relationship is considered. We also proposed a new feature selection method, named MEMO, which is also one important aspect of our multi-dose model in our study, to deal with the high-dimensional toxicogenomics data. We validated the proposed model using the TG-GATEs, which is a large database recording toxicogenomics data from multiple views. The experimental results show that the drug-induced hepatotoxicity can be predicted with high accuracy and efficiency using the proposed predictive model.

Computational Prediction of Sigma-54 Promoters in Bacterial Genomes by Integrating Motif Finding and Machine Learning Strategies

Sigma factor, as a unit of RNA polymerase holoenzyme, is a critical factor in the process of gene transcriptional regulation. It recognizes the specific DNA sites and brings the core enzyme of RNA polymerase to the upstream regions of target genes. Therefore, the prediction of the promoters for a particular sigma factor is essential for interpreting functional genomic data and observation. This paper develops a new method to predict sigma-54 promoters in bacterial genomes. The new method organically integrates motif finding and machine learning strategies to capture the intrinsic features of sigma-54 promoters. The experiments on E. coli benchmark test set show that our method has good capability to distinguish sigma-54 promoters from surrounding or randomly selected DNA sequences. The applications of the other three bacterial genomes indicate the potential robustness and applicative power of our method on a large number of bacterial genomes. The source code of our method can be freely downloaded at https://github.com/maqin2001/PromotePredictor.

Identification of Intrinsically Disordered Proteins and Regions by Length-Dependent Predictors Based on Conditional Random Fields

Accurate identification of intrinsically disordered proteins/regions (IDPs/IDRs) is critical for predicting protein structure and function. Previous studies have shown that IDRs of different lengths have different characteristics, and several classification-based predictors have been proposed for predicting different types of IDRs. Compared with these classification-based predictors, the previously proposed predictor IDP-CRF exhibits state-of-the-art performance for predicting IDPs/IDRs, which is a sequence labeling model based on conditional random fields (CRFs). Motivated by these methods, we propose a predictor called IDP-FSP, which is an ensemble of three CRF-based predictors called IDP-FSP-L, IDP-FSP-S, and IDP-FSP-G. These three predictors are specially designed to predict long, short, and generic disordered regions, respectively, and they are constructed based on different features. To the best of our knowledge, IDP-FSP is the first predictor that combines a sequence labeling algorithm with IDRs of different lengths. Experimental results using two independent test datasets show that IDP-FSP achieves better or at least comparable predictive performance with 26 existing state-of-the-art methods in this field, proving the effectiveness of IDP-FSP.

iProEP: A Computational Predictor for Predicting Promoter

Promoter is a fundamental DNA element located around the transcription start site (TSS) and could regulate gene transcription. Promoter recognition is of great significance in determining transcription units, studying gene structure, analyzing gene regulation mechanisms, and annotating gene functional information. Many models have already been proposed to predict promoters. However, the performances of these methods still need to be improved. In this work, we combined pseudo k-tuple nucleotide composition (PseKNC) with position-correlation scoring function (PCSF) to formulate promoter sequences of Homo sapiens (H. sapiens), Drosophila melanogaster (D. melanogaster), Caenorhabditis elegans (C. elegans), Bacillus subtilis (B. subtilis), and Escherichia coli (E. coli). Minimum Redundancy Maximum Relevance (mRMR) algorithm and increment feature selection strategy were then adopted to find out optimal feature subsets. Support vector machine (SVM) was used to distinguish between promoters and non-promoters. In the 10-fold cross-validation test, accuracies of 93.3%, 93.9%, 95.7%, 95.2%, and 93.1% were obtained for H. sapiens, D. melanogaster, C. elegans, B. subtilis, and E. coli, with the areas under receiver operating curves (AUCs) of 0.974, 0.975, 0.981, 0.988, and 0.976, respectively. Comparative results demonstrated that our method outperforms existing methods for identifying promoters. An online web server was established that can be freely accessed (http://lin-group.cn/server/iProEP/).

A critical assessment of the feature selection methods used for biomarker discovery in current metaproteomics studies

Microbial community (MC) has great impact on mediating complex disease indications, biogeochemical cycling and agricultural productivities, which makes metaproteomics powerful technique for quantifying diverse and dynamic composition of proteins or peptides. The key role of biostatistical strategies in MC study is reported to be underestimated, especially the appropriate application of feature selection method (FSM) is largely ignored. Although extensive efforts have been devoted to assessing the performance of FSMs, previous studies focused only on their classification accuracy without considering their ability to correctly and comprehensively identify the spiked proteins. In this study, the performances of 14 FSMs were comprehensively assessed based on two key criteria (both sample classification and spiked protein discovery) using a variety of metaproteomics benchmarks. First, the classification accuracies of those 14 FSMs were evaluated. Then, their abilities in identifying the proteins of different spiked concentrations were assessed. Finally, seven FSMs (FC, LMEB, OPLS-DA, PLS-DA, SAM, SVM-RFE and T-Test) were identified as performing consistently superior or good under both criteria with the PLS-DA performing consistently superior. In summary, this study served as comprehensive analysis on the performances of current FSMs and could provide a valuable guideline for researchers in metaproteomics.

Genetic Contexts Characterize Dynamic Histone Modification Patterns Among Cell Types

Histone modifications play critical roles in mammalian development, regulating chromatin structure and gene expression. Dynamic histone modifications among cell types have been shown to associate with changes in mammalian development. However, how to quantitatively measure the histone modification alterations and how histone modifications vary across cell types under different genetic contexts remain largely unexplored and whether these changes are related to the primary DNA sequence remains limited. Here, we employed an entropy-based method to measure histone modification alterations in six definite genomic regions across five cell types and identified lineage-specific histone modification genes. We observed that histone modification alterations prefer to enrich in 5'-UTR exons, and also in 3'-UTR exons and its downstream. Then we built a model to predict the histone modification patterns from the primary DNA sequence. We found that the frequencies of k-mer sequence compositions are predictive of histone modification patterns, suggesting that the primary DNA sequence correlated with the histone modification alterations among cell types. Additionally, the lineage-specific histone modification genes display a higher conservation and lower GC-content. Together, we performed a systematic analysis for histone modification alterations and demonstrated how to identify genomic region-specific elements of epigenetic and genetic regulation and histone modification patterns across different cell types.

Survey of Machine Learning Techniques for Prediction of the Isoform Specificity of Cytochrome P450 Substrates

Background:

Determination or prediction of the Absorption, Distribution, Metabolism, and Excretion (ADME) properties of drug candidates and drug-induced toxicity plays crucial roles in drug discovery and development. Metabolism is one of the most complicated pharmacokinetic properties to be understood and predicted. However, experimental determination of the substrate binding, selectivity, sites and rates of metabolism is time- and recourse- consuming. In the phase I metabolism of foreign compounds (i.e., most of drugs), cytochrome P450 enzymes play a key role. To help develop drugs with proper ADME properties, computational models are highly desired to predict the ADME properties of drug candidates, particularly for drugs binding to cytochrome P450.

Objective:

This narrative review aims to briefly summarize machine learning techniques used in the prediction of the cytochrome P450 isoform specificity of drug candidates.

Results:

Both single-label and multi-label classification methods have demonstrated good performance on modelling and prediction of the isoform specificity of substrates based on their quantitative descriptors.

Conclusion:

This review provides a guide for researchers to develop machine learning-based methods to predict the cytochrome P450 isoform specificity of drug candidates.

The Development of Machine Learning Methods in Cell-Penetrating Peptides Identification: A Brief Review

Background:

Cell-penetrating Peptides (CPPs) are important short peptides that facilitate cellular intake or uptake of various molecules. CPPs can transport drug molecules through the plasma membrane and send these molecules to different cellular organelles. Thus, CPP identification and related mechanisms have been extensively explored. In order to reveal the penetration mechanisms of a large number of CPPs, it is necessary to develop convenient and fast methods for CPPs identification.

Methods:

Biochemical experiments can provide precise details for accurately identifying CPP, but these methods are expensive and laborious. To overcome these disadvantages, several computational methods have been developed to identify CPPs. We have performed review on the development of machine learning methods in CPP identification. This review provides an insight into CPP identification.

Results:

We summarized the machine learning-based CPP identification methods and compared the construction strategies of 11 different computational methods. Furthermore, we pointed out the limitations and difficulties in predicting CPPs.

Conclusion:

In this review, the last studies on CPP identification using machine learning method were reported. We also discussed the future development direction of CPP recognition with computational methods.

Predicting Ion Channels Genes and Their Types With Machine Learning Techniques

Motivation: The number of ion channels is increasing rapidly. As many of them are associated with diseases, they are the targets of more than 700 drugs. The discovery of new ion channels is facilitated by computational methods that predict ion channels and their types from protein sequences. Methods: We used the SVMProt and the k-skip-n-gram methods to extract the feature vectors of ion channels, and obtained 188- and 400-dimensional features, respectively. The 188- and 400-dimensional features were combined to obtain 588-dimensional features. We then employed the maximum-relevance-maximum-distance method to reduce the dimensions of the 588-dimensional features. Finally, the support vector machine and random forest methods were used to build the prediction models to evaluate the classification effect. Results: Different methods were employed to extract various feature vectors, and after effective dimensionality reduction, different classifiers were used to classify the ion channels. We extracted the ion channel data from the Universal Protein Resource (UniProt, http://www.uniprot.org/) and Ligand-Gated Ion Channel databases (http://www.ebi.ac.uk/compneur-srv/LGICdb/LGICdb.php), and then verified the performance of the classifiers after screening. The findings of this study could inform the research and development of drugs.

A Machine Learning Approach for Identifying Gene Biomarkers Guiding the Treatment of Breast Cancer

Genomic profiles among different breast cancer survivors who received similar treatment may provide clues about the key biological processes involved in the cells and finding the right treatment. More specifically, such profiling may help personalize the treatment based on the patients' gene expression. In this paper, we present a hierarchical machine learning system that predicts the 5-year survivability of the patients who underwent though specific therapy; The classes are built on the combination of two parts that are the survivability information and the given therapy. For the survivability information part, it defines whether the patient survives the 5-years interval or deceased. While the therapy part denotes the therapy has been taken during that interval, which includes hormone therapy, radiotherapy, or surgery, which totally forms six classes. The Model classifies one class vs. the rest at each node, which makes the tree-based model creates five nodes. The model is trained using a set of standard classifiers based on a comprehensive study dataset that includes genomic profiles and clinical information of 347 patients. A combination of feature selection methods and a prediction method are applied on each node to identify the genes that can predict the class at that node, the identified genes for each class may serve as potential biomarkers to the class's treatment for better survivability. The results show that the model identifies the classes with high-performance measurements. An exhaustive analysis based on relevant literature shows that some of the potential biomarkers are strongly related to breast cancer survivability and cancer in general.

Identification of Phage Viral Proteins With Hybrid Sequence Features

The uniqueness of bacteriophages plays an important role in bioinformatics research. In real applications, the function of the bacteriophage virion proteins is the main area of interest. Therefore, it is very important to classify bacteriophage virion proteins and non-phage virion proteins accurately. Extracting comprehensive and effective sequence features from proteins plays a vital role in protein classification. In order to more fully represent protein information, this paper is more comprehensive and effective by combining the features extracted by the feature information representation algorithm based on sequence information (CCPA) and the feature representation algorithm based on sequence and structure information. After extracting features, the Max-Relevance-Max-Distance (MRMD) algorithm is used to select the optimal feature set with the strongest correlation between class labels and low redundancy between features. Given the randomness of the samples selected by the random forest classification algorithm and the randomness features for producing each node variable, a random forest method is employed to perform 10-fold cross-validation on the bacteriophage protein classification. The accuracy of this model is as high as 93.5% in the classification of phage proteins in this study. This study also found that, among the eight physicochemical properties considered, the charge property has the greatest impact on the classification of bacteriophage proteins These results indicate that the model discussed in this paper is an important tool in bacteriophage protein research.

XGBPRH: Prediction of Binding Hot Spots at Protein⁻RNA Interfaces Utilizing Extreme Gradient Boosting

Hot spot residues at protein⁻RNA complexes are vitally important for investigating the underlying molecular recognition mechanism. Accurately identifying protein⁻RNA binding hot spots is critical for drug designing and protein engineering. Although some progress has been made by utilizing various available features and a series of machine learning approaches, these methods are still in the infant stage. In this paper, we present a new computational method named XGBPRH, which is based on an eXtreme Gradient Boosting (XGBoost) algorithm and can effectively predict hot spot residues in protein⁻RNA interfaces utilizing an optimal set of properties. Firstly, we download 47 protein⁻RNA complexes and calculate a total of 156 sequence, structure, exposure, and network features. Next, we adopt a two-step feature selection algorithm to extract a combination of 6 optimal features from the combination of these 156 features. Compared with the state-of-the-art approaches, XGBPRH achieves better performances with an area under the ROC curve (AUC) score of 0.817 and an F1-score of 0.802 on the independent test set. Meanwhile, we also apply XGBPRH to two case studies. The results demonstrate that the method can effectively identify novel energy hotspots.

Identification of Triple-Negative Breast Cancer Genes and a Novel High-Risk Breast Cancer Prediction Model Development Based on PPI Data and Support Vector Machines

Triple-negative breast cancer (TNBC) is a special subtype of breast cancer that is difficult to treat. It is crucial to identify breast cancer-related genes that could provide new biomarkers for breast cancer diagnosis and potential treatment goals. In the development of our new high-risk breast cancer prediction model, seven raw gene expression datasets from the NCBI gene expression omnibus (GEO) database (GSE31519, GSE9574, GSE20194, GSE20271, GSE32646, GSE45255, and GSE15852) were used. Using the maximum relevance minimum redundancy (mRMR) method, we selected significant genes. Then, we mapped transcripts of the genes on the protein-protein interaction (PPI) network from the Search Tool for the Retrieval of Interacting Genes (STRING) database, as well as traced the shortest path between each pair of proteins. Genes with higher betweenness values were selected from the shortest path proteins. In order to ensure validity and precision, a permutation test was performed. We randomly selected 248 proteins from the PPI network for shortest path tracing and repeated the procedure 100 times. We also removed genes that appeared more frequently in randomized results. As a result, 54 genes were selected as potential TNBC-related genes. Using 14 out the 54 genes, which are potential TNBC associated genes, as input features into a support vector machine (SVM), a novel model was trained to predict high-risk breast cancer. The prediction accuracy of normal tissues and TNBC tissues reached 95.394%, and the predictions of Stage II and Stage III TNBC reached 86.598%, indicating that such genes play important roles in distinguishing breast cancers, and that the method could be promising in practical use. According to reports, some of the 54 genes we identified from the PPI network are associated with breast cancer in the literature. Several other genes have not yet been reported but have functional resemblance with known cancer genes. These may be novel breast cancer-related genes and need further experimental validation. Gene ontology (GO) enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed to appraise the 54 genes. It was indicated that cellular response to organic cyclic compounds has an influence in breast cancer, and most genes may be related with viral carcinogenesis.

Prediction of aptamer-protein interacting pairs based on sparse autoencoder feature extraction and an ensemble classifier

Aptamer-protein interacting pairs play important roles in physiological functions and structural characterization. Identifying aptamer-protein interacting pairs is challenging and limited, despite of the tremendous applications of aptamers. Therefore, it is vital to construct a high prediction performance model for identifying aptamer-target interacting pairs. In this study, a novel ensemble method is presented to predict aptamer-protein interacting pairs by integrating sequence characteristics derived from aptamers and the target proteins. The features extracted for aptamers were the compositions of amino acids and pseudo K-tuple nucleotides. In addition, a sparse autoencoder was used to characterize features for the target protein sequences. To remove redundant features, gradient boosting decision tree (GBDT) and incremental feature selection (IFS) methods were used to obtain the optimum combination of sequence characters. Based on 616 selected features, an ensemble of three sub- support vector machine (SVM) classifiers was used to construct our prediction model. Evaluated on an independent dataset, our predictor obtained an accuracy of 75.7%, Matthew's Correlation Coefficient of 0.478, and Youden's Index of 0.538, which were superior to the values reached using other existing predictors. The results show that our model can be used to distinguishing novel aptamer-protein interacting pairs and revealing the interrelation between aptamers and proteins.

Supervised Brain Tumor Segmentation Based on Gradient and Context-Sensitive Features

Gliomas have the highest mortality rate and prevalence among the primary brain tumors. In this study, we proposed a supervised brain tumor segmentation method which detects diverse tumoral structures of both high grade gliomas and low grade gliomas in magnetic resonance imaging (MRI) images based on two types of features, the gradient features and the context-sensitive features. Two-dimensional gradient and three-dimensional gradient information was fully utilized to capture the gradient change. Furthermore, we proposed a circular context-sensitive feature which captures context information effectively. These features, totally 62, were compressed and optimized based on an mRMR algorithm, and random forest was used to classify voxels based on the compact feature set. To overcome the class-imbalanced problem of MRI data, our model was trained on a class-balanced region of interest dataset. We evaluated the proposed method based on the 2015 Brain Tumor Segmentation Challenge database, and the experimental results show a competitive performance.

MinE-RFE: determine the optimal subset from RFE by minimizing the subset-accuracy–defined energy

Recursive feature elimination (RFE), as one of the most popular feature selection algorithms, has been extensively applied to bioinformatics. During the training, a group of candidate subsets are generated by iteratively eliminating the least important features from the original features. However, how to determine the optimal subset from them still remains ambiguous. Among most current studies, either overall accuracy or subset size (SS) is used to select the most predictive features. Using which one or both and how they affect the prediction performance are still open questions. In this study, we proposed MinE-RFE, a novel RFE-based feature selection approach by sufficiently considering the effect of both factors. Subset decision problem was reflected into subset-accuracy space and became an energy-minimization problem. We also provided a mathematical description of the relationship between the overall accuracy and SS using Gaussian Mixture Models together with spline fitting. Besides, we comprehensively reviewed a variety of state-of-the-art applications in bioinformatics using RFE. We compared their approaches of deciding the final subset from all the candidate subsets with MinE-RFE on diverse bioinformatics data sets. Additionally, we also compared MinE-RFE with some well-used feature selection algorithms. The comparative results demonstrate that the proposed approach exhibits the best performance among all the approaches. To facilitate the use of MinE-RFE, we further established a user-friendly web server with the implementation of the proposed approach, which is accessible at http://qgking.wicp.net/MinE/. We expect this web server will be a useful tool for research community.

A Brief Survey of Machine Learning Methods in Protein Sub-Golgi Localization

Background:

The location of proteins in a cell can provide important clues to their functions in various biological processes. Thus, the application of machine learning method in the prediction of protein subcellular localization has become a hotspot in bioinformatics. As one of key organelles, the Golgi apparatus is in charge of protein storage, package, and distribution.

Objective:

The identification of protein location in Golgi apparatus will provide in-depth insights into their functions. Thus, the machine learning-based method of predicting protein location in Golgi apparatus has been extensively explored. The development of protein sub-Golgi apparatus localization prediction should be reviewed for providing a whole background for the fields.

Method:

The benchmark dataset, feature extraction, machine learning method and published results were summarized.

Results:

We briefly introduced the recent progresses in protein sub-Golgi apparatus localization prediction using machine learning methods and discussed their advantages and disadvantages.

Conclusion:

We pointed out the perspective of machine learning methods in protein sub-Golgi localization prediction.

Identification of S-nitrosylation sites based on multiple features combination

Protein S-nitrosylation (SNO) is a typical reversible, redox-dependent and post-translational modification that involves covalent modification of cysteine residues with nitric oxide (NO) for the thiol group. Numerous experiments have shown that SNO plays a major role in cell function and pathophysiology. In order to rapidly analysis the big sets of data, the computing methods for identifying the SNO sites are being considered as necessary auxiliary tools. In this study, multiple features including Parallel correlation pseudo amino acid composition (PC-PseAAC), Basic kmer1 (kmer1), Basic kmer2 (kmer2), General parallel correlation pseudo amino acid composition (PC-PseAAC_G), Adapted Normal distribution Bi-Profile Bayes (ANBPB), Double Bi-Profile Bayes (DBPB), Bi-Profile Bayes (BPB), Incorporating Amino Acid Pairwise (IAAPair) and Position-specific Tri-Amino Acid Propensity(PSTAAP) were employed to extract the sequence information. To remove information redundancy, information gain (IG) was applied to evaluate the importance of amino acids, which is the information entropy of class after subtracting the conditional entropy for the given amino acid. The prediction performance of the SNO sites was found to be best by using the cross-validation and independent tests. In addition, we also calculated four commonly used performance measurements, i.e. Sensitivity (Sn), Specificity (Sp), Accuracy (Acc), and the Matthew's Correlation Coefficient (MCC). For the training dataset, the overall Acc was 83.11%, the MCC was 0.6617. For an independent test dataset, Acc was 73.17%, and MCC was 0.3788. The results indicate that our method is likely to complement the existing prediction methods and is a useful tool for effective identification of the SNO sites.

Construction of Complex Features for Computational Predicting ncRNA-Protein Interaction

Non-coding RNA (ncRNA) plays important roles in many critical regulation processes. Many ncRNAs perform their regulatory functions by the form of RNA-protein complexes. Therefore, identifying the interaction between ncRNA and protein is fundamental to understand functions of ncRNA. Under pressures from expensive cost of experimental techniques, developing an accuracy computational predictive model has become an indispensable way to identify ncRNA-protein interaction. A powerful predicting model of ncRNA-protein interaction needs a good feature set of characterizing the interaction. In this paper, a novel method is put forward to generate complex features for characterizing ncRNA-protein interaction (named CFRP). To obtain a comprehensive description of ncRNA-protein interaction, complex features are generated by non-linear transformations from the traditional k-mer features of ncRNA and protein sequences. To further reduce the dimensions of complex features, a group of discriminative features are selected by random forest. To validate the performances of the proposed method, a series of experiments are carried on several widely-used public datasets. Compared with the traditional k-mer features, the CFRP complex features can boost the performances of ncRNA-protein interaction prediction model. Meanwhile, the CFRP-based prediction model is compared with several state-of-the-art methods, and the results show that the proposed method achieves better performances than the others in term of the evaluation metrics. In conclusion, the complex features generated by CFRP are beneficial for building a powerful predicting model of ncRNA-protein interaction.

Identifying Plant Pentatricopeptide Repeat Coding Gene/Protein Using Mixed Feature Extraction Methods

Motivation: Pentatricopeptide repeat (PPR) is a triangular pentapeptide repeat domain that plays a vital role in plant growth. In this study, we seek to identify PPR coding genes and proteins using a mixture of feature extraction methods. We use four single feature extraction methods focusing on the sequence, physical, and chemical properties as well as the amino acid composition, and mix the features. The Max-Relevant-Max-Distance (MRMD) technique is applied to reduce the feature dimension. Classification uses the random forest, J48, and naïve Bayes with 10-fold cross-validation. Results: Combining two of the feature extraction methods with the random forest classifier produces the highest area under the curve of 0.9848. Using MRMD to reduce the dimension improves this metric for J48 and naïve Bayes, but has little effect on the random forest results. Availability and Implementation: The webserver is available at: http://server.malab.cn/MixedPPR/index.jsp.

i6mA-Pred: identifying DNA N6-methyladenine sites in the rice genome

Motivation

DNA N6-methyladenine (6mA) is associated with a wide range of biological processes. Since the distribution of 6mA site in the genome is non-random, accurate identification of 6mA sites is crucial for understanding its biological functions. Although experimental methods have been proposed for this regard, they are still cost-ineffective for detecting 6mA site in genome-wide scope. Therefore, it is desirable to develop computational methods to facilitate the identification of 6mA site.

Results

In this study, a computational method called i6mA-Pred was developed to identify 6mA sites in the rice genome, in which the optimal nucleotide chemical properties obtained by the using feature selection technique were used to encode the DNA sequences. It was observed that the i6mA-Pred yielded an accuracy of 83.13% in the jackknife test. Meanwhile, the performance of i6mA-Pred was also superior to other methods.

Availability and implementation

A user-friendly web-server, i6mA-Pred is freely accessible at http://lin-group.cn/server/i6mA-Pred.

Robust Pulmonary Nodule Segmentation in CT Image for Juxta-pleural and Juxta-vascular Case

Background:

Lung cancer is a greatest threat to people's health and life. CT image leads to unclear boundary segmentation. Segmentation of irregular nodules and complex structure, boundary information is not well considered and lung nodules have always been a hot topic.

Objective:

In this study, the pulmonary nodule segmentation is accomplished with the new graph cut algorithm. The problem of segmenting the juxta-pleural and juxta-vascular nodules was investigated which is based on graph cut algorithm.

Methods:

Firstly, the inflection points by the curvature was decided. Secondly, we used kernel graph cut to segment the nodules for the initial edge. Thirdly, the seeds points based on cast raying method is performed; lastly, a novel geodesic distance function is proposed to improve the graph cut algorithm and applied in lung nodules segmentation.

Results:

The new algorithm has been tested on total 258 nodules. Table 1 summarizes the morphologic features of all the nodules and given the results between the successful segmentation group and the poor/failed segmentation group. Figure 1 to Fig. (12) shows segmentation effect of Juxta-vascular nodules, Juxta-pleural nodules, and comparted with the other interactive segmentation methods.

Conclusion:

The experimental verification shows better results with our algorithm, the results will measure the volume numerical approach to nodule volume. The results of lung nodules segmentation in this study are as good as the results obtained by the other methods.

Tumor origin detection with tissue-specific miRNA and DNA methylation markers

Motivation

A clear identification of the primary site of tumor is of great importance to the next targeted site-specific treatments and could efficiently improve patient's overall survival. Even though many classifiers based on gene expression had been proposed to predict the tumor primary, only a few studies focus on using DNA methylation (DNAm) profiles to develop classifiers, and none of them compares the performance of classifiers based on different profiles.

Results

We introduced novel selection strategies to identify highly tissue-specific CpG sites and then used the random forest approach to construct the classifiers to predict the origin of tumors. We also compared the prediction performance by applying similar strategy on miRNA expression profiles. Our analysis indicated that these classifiers had an accuracy of 96.05% (Maximum-Relevance-Maximum-Distance: 90.02-99.99%) or 95.31% (principal component analysis: 79.82-99.91%) on independent DNAm datasets, and an overall accuracy of 91.30% (range 79.33-98.74%) on independent miRNA test sets for predicting tumor origin. This suggests that our feature selection methods are very effective to identify tissue-specific biomarkers and the classifiers we developed can efficiently predict the origin of tumors. We also developed a user-friendly webserver that helps users to predict the tumor origin by uploading miRNA expression or DNAm profile of their interests.

Availability and implementation

The webserver, and relative data, code are accessible at http://server.malab.cn/MMCOP/.

Contact

zouquan@nclab.net or a.teschendorff@ucl.ac.uk.

Supplementary information

Supplementary data are available at Bioinformatics online.

Sequence-based bacterial small RNAs prediction using ensemble learning strategies

Background

Bacterial small non-coding RNAs (sRNAs) have emerged as important elements in diverse physiological processes, including growth, development, cell proliferation, differentiation, metabolic reactions and carbon metabolism, and attract great attention. Accurate prediction of sRNAs is important and challenging, and helps to explore functions and mechanism of sRNAs.

Results

In this paper, we utilize a variety of sRNA sequence-derived features to develop ensemble learning methods for the sRNA prediction. First, we compile a balanced dataset and four imbalanced datasets. Then, we investigate various sRNA sequence-derived features, such as spectrum profile, mismatch profile, reverse compliment k-mer and pseudo nucleotide composition. Finally, we consider two ensemble learning strategies to integrate all features for building ensemble learning models for the sRNA prediction. One is the weighted average ensemble method (WAEM), which uses the linear weighted sum of outputs from the individual feature-based predictors to predict sRNAs. The other is the neural network ensemble method (NNEM), which trains a deep neural network by combining diverse features. In the computational experiments, we evaluate our methods on these five datasets by using 5-fold cross validation. WAEM and NNEM can produce better results than existing state-of-the-art sRNA prediction methods.

Conclusions

WAEM and NNEM have great potential for the sRNA prediction, and are helpful for understanding the biological mechanism of bacteria.

Classification of Widely and Rarely Expressed Genes with Recurrent Neural Network

A tissue-specific gene expression shapes the formation of tissues, while gene expression changes reflect the immune response of the human body to environmental stimulations or pressure, particularly in disease conditions, such as cancers. A few genes are commonly expressed across tissues or various cancers, while others are not. To investigate the functional differences between widely and rarely expressed genes, we defined the genes that were expressed in 32 normal tissues/cancers (i.e., called widely expressed genes; FPKM >1 in all samples) and those that were not detected (i.e., called rarely expressed genes; FPKM <1 in all samples) based on the large gene expression data set provided by Uhlen et al. Each gene was encoded using the gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment scores. Minimum redundancy maximum relevance (mRMR) was used to measure and rank these features on the mRMR feature list. Thereafter, we applied the incremental feature selection method with a supervised classifier recurrent neural network (RNN) to select the discriminate features for classifying widely expressed genes from rarely expressed genes and construct an optimum RNN classifier. The Youden's indexes generated by the optimum RNN classifier and evaluated using a 10-fold cross validation were 0.739 for normal tissues and 0.639 for cancers. Furthermore, the underlying mechanisms of the key discriminate GO and KEGG features were analyzed. Results can facilitate the identification of the expression landscape of genes and elucidation of how gene expression shapes tissues and the microenvironment of cancers.

•

Some genes are widely expressed across tissues or various cancers.

•

A number of genes are rarely expressed across tissues or various cancers.

•

The functional differences between widely and rarely expressed genes were studied.

•

Several GO terms and KEGG pathways were extracted and analyzed.

Recent Advances on the Machine Learning Methods in Identifying DNA Replication Origins in Eukaryotic Genomics

The initiate site of DNA replication is called origins of replication (ORI) which is regulated by a set of regulatory proteins and plays important roles in the basic biochemical process during cell growth and division in all living organisms. Therefore, the study of ORIs is essential for understanding the cell-division cycle and gene expression regulation so that scholars can develop a new strategy against genetic diseases by using the knowledge of DNA replication. Thus, the accurate identification of ORIs will provide key clues for DNA replication research and clinical medicine. Although, the conventional experiments could provide accurate results, they are time-consuming and cost ineffective. On the contrary, bioinformatics-based methods can overcome these shortcomings. Especially, with the emergence of DNA sequences in the post-genomic era, it is highly expected to develop high throughput tools to identify ORIs based on sequence information. In this review, we will summarize the current progress in computational prediction of eukaryotic ORIs including the collection of benchmark dataset, the application of machine learning-based techniques, the results obtained by these methods, and the construction of web servers. Finally, we gave the future perspectives on ORIs prediction. The review provided readers with a whole background of ORIs prediction based on machine learning methods, which will be helpful for researchers to study DNA replication in-depth and drug therapy of genetic defect.

HIV infection alters the human epigenetic landscape

Many complex diseases or traits are the results of both genetic and environmental factors. The environmental factors affect the human body by modifying its epigenetics, which controls the activity of genomes without mutating it. Viral infection is one of the common environmental factors for complex diseases. For example, the human immunodeficiency virus (HIV) infection can cause acquired immune deficiency syndrome (AIDS), HBV, and HCV infections are associated with hepatocellular carcinoma, and human papillomavirus infection is a causal factor in cervical carcinoma. In this study, to investigate how HIV infection affects DNA methylation, we analyzed the blood DNA methylation data of 485 512 sites in 44 HIV- and 142 HIV + patients. Several advanced computational methods were applied to identify the core distinctive features that were different between the HIV patients and the healthy controls. These methods can be used for differentiating HIV-infected patients from uninfected ones. These core distinctive DNA methylation features were confirmed to be functionally connected to premature aging and abnormal immune regulation, two typical pathological symptoms of HIV infection, revealing the potential regulatory mechanisms of HIV infection on the DNA methylation status of the host cells and provided novel insights on the pathogenesis of HIV infection and AIDS.

Predicting Diabetes Mellitus With Machine Learning Techniques

Diabetes mellitus is a chronic disease characterized by hyperglycemia. It may cause many complications. According to the growing morbidity in recent years, in 2040, the world’s diabetic patients will reach 642 million, which means that one of the ten adults in the future is suffering from diabetes. There is no doubt that this alarming figure needs great attention. With the rapid development of machine learning, machine learning has been applied to many aspects of medical health. In this study, we used decision tree, random forest and neural network to predict diabetes mellitus. The dataset is the hospital physical examination data in Luzhou, China. It contains 14 attributes. In this study, five-fold cross validation was used to examine the models. In order to verity the universal applicability of the methods, we chose some methods that have the better performance to conduct independent test experiments. We randomly selected 68994 healthy people and diabetic patients’ data, respectively as training set. Due to the data unbalance, we randomly extracted 5 times data. And the result is the average of these five experiments. In this study, we used principal component analysis (PCA) and minimum redundancy maximum relevance (mRMR) to reduce the dimensionality. The results showed that prediction with random forest could reach the highest accuracy (ACC = 0.8084) when all the attributes were used.

Comparative analysis and prediction of quorum-sensing peptides using feature representation learning and machine learning algorithms

Quorum-sensing peptides (QSPs) are the signal molecules that are closely associated with diverse cellular processes, such as cell-cell communication, and gene expression regulation in Gram-positive bacteria. It is therefore of great importance to identify QSPs for better understanding and in-depth revealing of their functional mechanisms in physiological processes. Machine learning algorithms have been developed for this purpose, showing the great potential for the reliable prediction of QSPs. In this study, several sequence-based feature descriptors for peptide representation and machine learning algorithms are comprehensively reviewed, evaluated and compared. To effectively use existing feature descriptors, we used a feature representation learning strategy that automatically learns the most discriminative features from existing feature descriptors in a supervised way. Our results demonstrate that this strategy is capable of effectively capturing the sequence determinants to represent the characteristics of QSPs, thereby contributing to the improved predictive performance. Furthermore, wrapping this feature representation learning strategy, we developed a powerful predictor named QSPred-FL for the detection of QSPs in large-scale proteomic data. Benchmarking results with 10-fold cross validation showed that QSPred-FL is able to achieve better performance as compared to the state-of-the-art predictors. In addition, we have established a user-friendly webserver that implements QSPred-FL, which is currently available at http://server.malab.cn/QSPred-FL. We expect that this tool will be useful for the high-throughput prediction of QSPs and the discovery of important functional mechanisms of QSPs.

M6AMRFS: Robust Prediction of N6-Methyladenosine Sites With Sequence-Based Features in Multiple Species

As one of the well-studied RNA methylation modifications, N6-methyladenosine (m6A) plays important roles in various biological progresses, such as RNA splicing and degradation, etc. Identification of m6A sites is fundamentally important for better understanding of their functional mechanisms. Recently, machine learning based prediction methods have emerged as an effective approach for fast and accurate identification of m6A sites. In this paper, we proposed "M6AMRFS", a new machine learning based predictor for the identification of m6A sites. In this predictor, we exploited a new feature representation algorithm to encode RNA sequences with two feature descriptors (dinucleotide binary encoding and Local position-specific dinucleotide frequency), and used the F-score algorithm combined with SFS (Sequential Forward Search) to enhance the feature representation ability. To predict m6A sites, we employed the eXtreme Gradient Boosting (XGBoost) algorithm to build a predictive model. Benchmarking results showed that the proposed predictor is competitive with the state-of-the art predictors. Importantly, robust predictions for multiple species by our predictor demonstrate that our predictive models have strong generalization ability. To the best of our knowledge, M6AMRFS is the first tool that can be used for the identification of m6A sites in multiple species. To facilitate the use of our predictor, we have established a user-friendly webserver with the implementation of M6AMRFS, which is currently available in http://server.malab.cn/M6AMRFS/. We anticipate that it will be a useful tool for the relevant research of m6A sites.

Machine Learning Approaches for Protein⁻Protein Interaction Hot Spot Prediction: Progress and Comparative Assessment

Hot spots are the subset of interface residues that account for most of the binding free energy, and they play essential roles in the stability of protein binding. Effectively identifying which specific interface residues of protein–protein complexes form the hot spots is critical for understanding the principles of protein interactions, and it has broad application prospects in protein design and drug development. Experimental methods like alanine scanning mutagenesis are labor-intensive and time-consuming. At present, the experimentally measured hot spots are very limited. Hence, the use of computational approaches to predicting hot spots is becoming increasingly important. Here, we describe the basic concepts and recent advances of machine learning applications in inferring the protein–protein interaction hot spots, and assess the performance of widely used features, machine learning algorithms, and existing state-of-the-art approaches. We also discuss the challenges and future directions in the prediction of hot spots.

Classifying Included and Excluded Exons in Exon Skipping Event Using Histone Modifications

Alternative splicing (AS) not only ensures the diversity of gene expression products, but also closely correlated with genetic diseases. Therefore, knowledge about regulatory mechanisms of AS will provide useful clues for understanding its biological functions. In the current study, a random forest based method was developed to classify included and excluded exons in exon skipping event. In this method, the samples in the dataset were encoded by using optimal histone modification features which were optimized by using the Maximum Relevance Maximum Distance (MRMD) feature selection technique. The proposed method obtained an accuracy of 72.91% in 10-fold cross validation test and outperformed existing methods. Meanwhile, we also systematically analyzed the distribution of histone modifications between included and excluded exons and discovered their preference in both kinds of exons, which might provide insights into researches on the regulatory mechanisms of alternative splicing.

Enhanced Prediction of Hot Spots at Protein-Protein Interfaces Using Extreme Gradient Boosting

Identification of hot spots, a small portion of protein-protein interface residues that contribute the majority of the binding free energy, can provide crucial information for understanding the function of proteins and studying their interactions. Based on our previous method (PredHS), we propose a new computational approach, PredHS2, that can further improve the accuracy of predicting hot spots at protein-protein interfaces. Firstly we build a new training dataset of 313 alanine-mutated interface residues extracted from 34 protein complexes. Then we generate a wide variety of 600 sequence, structure, exposure and energy features, together with Euclidean and Voronoi neighborhood properties. To remove redundant and irrelevant information, we select a set of 26 optimal features utilizing a two-step feature selection method, which consist of a minimum Redundancy Maximum Relevance (mRMR) procedure and a sequential forward selection process. Based on the selected 26 features, we use Extreme Gradient Boosting (XGBoost) to build our prediction model. Performance of our PredHS2 approach outperforms other machine learning algorithms and other state-of-the-art hot spot prediction methods on the training dataset and the independent test set (BID) respectively. Several novel features, such as solvent exposure characteristics, second structure features and disorder scores, are found to be more effective in discriminating hot spots. Moreover, the update of the training dataset and the new feature selection and classification algorithms play a vital role in improving the prediction quality.

IDP⁻CRF: Intrinsically Disordered Protein/Region Identification Based on Conditional Random Fields

Accurate prediction of intrinsically disordered proteins/regions is one of the most important tasks in bioinformatics, and some computational predictors have been proposed to solve this problem. How to efficiently incorporate the sequence-order effect is critical for constructing an accurate predictor because disordered region distributions show global sequence patterns. In order to capture these sequence patterns, several sequence labelling models have been applied to this field, such as conditional random fields (CRFs). However, these methods suffer from certain disadvantages. In this study, we proposed a new computational predictor called IDP⁻CRF, which is trained on an updated benchmark dataset based on the MobiDB database and the DisProt database, and incorporates more comprehensive sequence-based features, including PSSMs (position-specific scoring matrices), kmer, predicted secondary structures, and relative solvent accessibilities. Experimental results on the benchmark dataset and two independent datasets show that IDP⁻CRF outperforms 25 existing state-of-the-art methods in this field, demonstrating that IDP⁻CRF is a very useful tool for identifying IDPs/IDRs (intrinsically disordered proteins/regions). We anticipate that IDP⁻CRF will facilitate the development of protein sequence analysis.

iRNA-2OM: A Sequence-Based Predictor for Identifying 2'-O-Methylation Sites in Homo sapiens

2'-O-methylation plays an important biological role in gene expression. Owing to the explosive increase in genomic sequencing data, it is necessary to develop a method for quickly and efficiently identifying whether a sequence contains the 2'-O-methylation site. As an additional method to the experimental technique, a computational method may help to identify 2'-O-methylation sites. In this study, based on the experimental 2'-O-methylation data of Homo sapiens, we proposed a support vector machine-based model to predict 2'-O-methylation sites in H. sapiens. In this model, the RNA sequences were encoded with the optimal features obtained from feature selection. In the fivefold cross-validation test, the accuracy reached 97.95%.

Identifying Phage Virion Proteins by Using Two-Step Feature Selection Methods

Accurate identification of phage virion protein is not only a key step for understanding the function of the phage virion protein but also helpful for further understanding the lysis mechanism of the bacterial cell. Since traditional experimental methods are time-consuming and costly for identifying phage virion proteins, it is extremely urgent to apply machine learning methods to accurately and efficiently identify phage virion proteins. In this work, a support vector machine (SVM) based method was proposed by mixing multiple sets of optimal g-gap dipeptide compositions. The analysis of variance (ANOVA) and the minimal-redundancy-maximal-relevance (mRMR) with an increment feature selection (IFS) were applied to single out the optimal feature set. In the five-fold cross-validation test, the proposed method achieved an overall accuracy of 87.95%. We believe that the proposed method will become an efficient and powerful method for scientists concerning phage virion proteins.

Imbalance learning for the prediction of N6-Methylation sites in mRNAs

Background

N⁶-methyladenosine (m⁶A) is an important epigenetic modification which plays various roles in mRNA metabolism and embryogenesis directly related to human diseases. To identify m⁶A in a large scale, machine learning methods have been developed to make predictions on m⁶A sites. However, there are two main drawbacks of these methods. The first is the inadequate learning of the imbalanced m⁶A samples which are much less than the non-m⁶A samples, by their balanced learning approaches. Second, the features used by these methods are not outstanding to represent m⁶A sequence characteristics.

Results

We propose to use cost-sensitive learning ideas to resolve the imbalance data issues in the human mRNA m⁶A prediction problem. This cost-sensitive approach applies to the entire imbalanced dataset, without random equal-size selection of negative samples, for an adequate learning. Along with site location and entropy features, top-ranked positions with the highest single nucleotide polymorphism specificity in the window sequences are taken as new features in our imbalance learning. On an independent dataset, our overall prediction performance is much superior to the existing predictors. Our method shows stronger robustness against the imbalance changes in the tests on 9 datasets whose imbalance ratios range from 1:1 to 9:1. Our method also outperforms the existing predictors on 1226 individual transcripts. It is found that the new types of features are indeed of high significance in the m⁶A prediction. The case studies on gene c-Jun and CBFB demonstrate the detailed prediction capacity to improve the prediction performance.

Conclusion

The proposed cost-sensitive model and the new features are useful in human mRNA m⁶A prediction. Our method achieves better correctness and robustness than the existing predictors in independent test and case studies. The results suggest that imbalance learning is promising to improve the performance of m⁶A prediction.

Electronic supplementary material

The online version of this article (10.1186/s12864-018-4928-y) contains supplementary material, which is available to authorized users.

M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning

N6-methyladenosine (m⁶A) modification is the most abundant RNA methylation modification and involves various biological processes, such as RNA splicing and degradation. Recent studies have demonstrated the feasibility of identifying m⁶A peaks using high-throughput sequencing techniques. However, such techniques cannot accurately identify specific methylated sites, which is important for a better understanding of m⁶A functions. In this study, we develop a novel machine learning-based predictor called M6APred-EL for the identification of m⁶A sites. To predict m⁶A sites accurately within genomic sequences, we trained an ensemble of three support vector machine classifiers that explore the position-specific information and physical chemical information from position-specific k-mer nucleotide propensity, physical-chemical properties, and ring-function-hydrogen-chemical properties. We examined and compared the performance of our predictor with other state-of-the-art methods of benchmarking datasets. Comparative results showed that the proposed M6APred-EL performed more accurately for m⁶A site identification. Moreover, a user-friendly web server that implements the proposed M6APred-EL is well established and is currently available at http://server.malab.cn/M6APred-EL/. It is expected to be a practical and effective tool for the investigation of m⁶A functional mechanisms.

Feature Selection via Swarm Intelligence for Determining Protein Essentiality

Protein essentiality is fundamental to comprehend the function and evolution of genes. The prediction of protein essentiality is pivotal in identifying disease genes and potential drug targets. Since the experimental methods need many investments in time and funds, it is of great value to predict protein essentiality with high accuracy using computational methods. In this study, we present a novel feature selection named Elite Search mechanism-based Flower Pollination Algorithm (ESFPA) to determine protein essentiality. Unlike other protein essentiality prediction methods, ESFPA uses an improved swarm intelligence⁻based algorithm for feature selection and selects optimal features for protein essentiality prediction. The first step is to collect numerous features with the highly predictive characteristics of essentiality. The second step is to develop a feature selection strategy based on a swarm intelligence algorithm to obtain the optimal feature subset. Furthermore, an elite search mechanism is adopted to further improve the quality of feature subset. Subsequently a hybrid classifier is applied to evaluate the essentiality for each protein. Finally, the experimental results show that our method is competitive to some well-known feature selection methods. The proposed method aims to provide a new perspective for protein essentiality determination.

Rough sets and Laplacian score based cost-sensitive feature selection

Cost-sensitive feature selection learning is an important preprocessing step in machine learning and data mining. Recently, most existing cost-sensitive feature selection algorithms are heuristic algorithms, which evaluate the importance of each feature individually and select features one by one. Obviously, these algorithms do not consider the relationship among features. In this paper, we propose a new algorithm for minimal cost feature selection called the rough sets and Laplacian score based cost-sensitive feature selection. The importance of each feature is evaluated by both rough sets and Laplacian score. Compared with heuristic algorithms, the proposed algorithm takes into consideration the relationship among features with locality preservation of Laplacian score. We select a feature subset with maximal feature importance and minimal cost when cost is undertaken in parallel, where the cost is given by three different distributions to simulate different applications. Different from existing cost-sensitive feature selection algorithms, our algorithm simultaneously selects out a predetermined number of “good” features. Extensive experimental results show that the approach is efficient and able to effectively obtain the minimum cost subset. In addition, the results of our method are more promising than the results of other cost-sensitive feature selection algorithms.