Towards better accuracy for missing value estimation of epistatic miniarray profiling data by a novel ensemble approach

A comprehensive survey on computational learning methods for analysis of gene expression data

Computational analysis methods including machine learning have a significant impact in the fields of genomics and medicine. High-throughput gene expression analysis methods such as microarray technology and RNA sequencing produce enormous amounts of data. Traditionally, statistical methods are used for comparative analysis of gene expression data. However, more complex analysis for classification of sample observations, or discovery of feature genes requires sophisticated computational approaches. In this review, we compile various statistical and computational tools used in analysis of expression microarray data. Even though the methods are discussed in the context of expression microarrays, they can also be applied for the analysis of RNA sequencing and quantitative proteomics datasets. We discuss the types of missing values, and the methods and approaches usually employed in their imputation. We also discuss methods of data normalization, feature selection, and feature extraction. Lastly, methods of classification and class discovery along with their evaluation parameters are described in detail. We believe that this detailed review will help the users to select appropriate methods for preprocessing and analysis of their data based on the expected outcome.

SAWRPI: A Stacking Ensemble Framework With Adaptive Weight for Predicting ncRNA-Protein Interactions Using Sequence Information

Non-coding RNAs (ncRNAs) take essential effects on biological processes, like gene regulation. One critical way of ncRNA executing biological functions is interactions between ncRNA and RNA binding proteins (RBPs). Identifying proteins, involving ncRNA-protein interactions, can well understand the function ncRNA. Many high-throughput experiment have been applied to recognize the interactions. As a consequence of these approaches are time- and labor-consuming, currently, a great number of computational methods have been developed to improve and advance the ncRNA-protein interactions research. However, these methods may be not available to all RNAs and proteins, particularly processing new RNAs and proteins. Additionally, most of them cannot process well with long sequence. In this work, a computational method SAWRPI is proposed to make prediction of ncRNA-protein through sequence information. More specifically, the raw features of protein and ncRNA are firstly extracted through the k-mer sparse matrix with SVD reduction and learning nucleic acid symbols by natural language processing with local fusion strategy, respectively. Then, to classify easily, Hilbert Transformation is exploited to transform raw feature data to the new feature space. Finally, stacking ensemble strategy is adopted to learn high-level abstraction features automatically and generate final prediction results. To confirm the robustness and stability, three different datasets containing two kinds of interactions are utilized. In comparison with state-of-the-art methods and other results classifying or feature extracting strategies, SAWRPI achieved high performance on three datasets, containing two kinds of lncRNA-protein interactions. Upon our finding, SAWRPI is a trustworthy, robust, yet simple and can be used as a beneficial supplement to the task of predicting ncRNA-protein interactions.

LncRBase V.2: an updated resource for multispecies lncRNAs and ClinicLSNP hosting genetic variants in lncRNAs for cancer patients

The recent discovery of long non-coding RNA as a regulatory molecule in the cellular system has altered the concept of the functional aptitude of the genome. Since our publication of the first version of LncRBase in 2014, there has been an enormous increase in the number of annotated lncRNAs of multiple species other than Human and Mouse. LncRBase V.2 hosts information of 549,648 lncRNAs corresponding to six additional species besides Human and Mouse, viz. Rat, Fruitfly, Zebrafish, Chicken, Cow and C.elegans. It provides additional distinct features such as (i) Transcription Factor Binding Site (TFBS) in the lncRNA promoter region, (ii) sub-cellular localization pattern of lncRNAs (iii) lnc-pri-miRNAs (iv) Possible small open reading frames (sORFs) within lncRNA. (v) Manually curated information of interacting target molecules and disease association of lncRNA genes (vi) Distribution of lncRNAs across multiple tissues of all species. Moreover, we have hosted ClinicLSNP within LncRBase V.2. ClinicLSNP has a comprehensive catalogue of lncRNA variants present within breast, ovarian, and cervical cancer inferred from 561 RNA-Seq data corresponding to these cancers. Further, we have checked whether these lncRNA variants overlap with (i)Repeat elements,(ii)CGI, (iii)TFBS within lncRNA loci (iv)SNP localization in trait-associated Linkage Disequilibrium(LD) region, (v)predicted the potentially pathogenic variants and (vi)effect of SNP on lncRNA secondary structure. Overall, LncRBaseV.2 is a user-friendly database to survey, search and retrieve information about multi-species lncRNAs. Further, ClinicLSNP will serve as a useful resource for cancer specific lncRNA variants and their related information. The database is freely accessible and available at http://dibresources.jcbose.ac.in/zhumur/lncrbase2/.

Predicting RNA-protein binding sites and motifs through combining local and global deep convolutional neural networks

Motivation

RNA-binding proteins (RBPs) take over 5-10% of the eukaryotic proteome and play key roles in many biological processes, e.g. gene regulation. Experimental detection of RBP binding sites is still time-intensive and high-costly. Instead, computational prediction of the RBP binding sites using patterns learned from existing annotation knowledge is a fast approach. From the biological point of view, the local structure context derived from local sequences will be recognized by specific RBPs. However, in computational modeling using deep learning, to our best knowledge, only global representations of entire RNA sequences are employed. So far, the local sequence information is ignored in the deep model construction process.

Results

In this study, we present a computational method iDeepE to predict RNA-protein binding sites from RNA sequences by combining global and local convolutional neural networks (CNNs). For the global CNN, we pad the RNA sequences into the same length. For the local CNN, we split a RNA sequence into multiple overlapping fixed-length subsequences, where each subsequence is a signal channel of the whole sequence. Next, we train deep CNNs for multiple subsequences and the padded sequences to learn high-level features, respectively. Finally, the outputs from local and global CNNs are combined to improve the prediction. iDeepE demonstrates a better performance over state-of-the-art methods on two large-scale datasets derived from CLIP-seq. We also find that the local CNN runs 1.8 times faster than the global CNN with comparable performance when using GPUs. Our results show that iDeepE has captured experimentally verified binding motifs.

Availability and implementation

https://github.com/xypan1232/iDeepE.

Supplementary information

Supplementary data are available at Bioinformatics online.

The lncLocator: a subcellular localization predictor for long non-coding RNAs based on a stacked ensemble classifier

Motivation

The long non-coding RNA (lncRNA) studies have been hot topics in the field of RNA biology. Recent studies have shown that their subcellular localizations carry important information for understanding their complex biological functions. Considering the costly and time-consuming experiments for identifying subcellular localization of lncRNAs, computational methods are urgently desired. However, to the best of our knowledge, there are no computational tools for predicting the lncRNA subcellular locations to date.

Results

In this study, we report an ensemble classifier-based predictor, lncLocator, for predicting the lncRNA subcellular localizations. To fully exploit lncRNA sequence information, we adopt both k-mer features and high-level abstraction features generated by unsupervised deep models, and construct four classifiers by feeding these two types of features to support vector machine (SVM) and random forest (RF), respectively. Then we use a stacked ensemble strategy to combine the four classifiers and get the final prediction results. The current lncLocator can predict five subcellular localizations of lncRNAs, including cytoplasm, nucleus, cytosol, ribosome and exosome, and yield an overall accuracy of 0.59 on the constructed benchmark dataset.

Availability and implementation

The lncLocator is available at www.csbio.sjtu.edu.cn/bioinf/lncLocator.

Supplementary information

Supplementary data are available at Bioinformatics online.

BGFE: A Deep Learning Model for ncRNA-Protein Interaction Predictions Based on Improved Sequence Information

The interactions between ncRNAs and proteins are critical for regulating various cellular processes in organisms, such as gene expression regulations. However, due to limitations, including financial and material consumptions in recent experimental methods for predicting ncRNA and protein interactions, it is essential to propose an innovative and practical approach with convincing performance of prediction accuracy. In this study, based on the protein sequences from a biological perspective, we put forward an effective deep learning method, named BGFE, to predict ncRNA and protein interactions. Protein sequences are represented by bi-gram probability feature extraction method from Position Specific Scoring Matrix (PSSM), and for ncRNA sequences, k-mers sparse matrices are employed to represent them. Furthermore, to extract hidden high-level feature information, a stacked auto-encoder network is employed with the stacked ensemble integration strategy. We evaluate the performance of the proposed method by using three datasets and a five-fold cross-validation after classifying the features through the random forest classifier. The experimental results clearly demonstrate the effectiveness and the prediction accuracy of our approach. In general, the proposed method is helpful for ncRNA and protein interacting predictions and it provides some serviceable guidance in future biological research.

Identification of the copy number variant biomarkers for breast cancer subtypes

Breast cancer is a common and threatening malignant disease with multiple biological and clinical subtypes. It can be categorized into subtypes of luminal A, luminal B, Her2 positive, and basal-like. Copy number variants (CNVs) have been reported to be a potential and even better biomarker for cancer diagnosis than mRNA biomarkers, because it is considerably more stable and robust than gene expression. Thus, it is meaningful to detect CNVs of different cancers. To identify the CNV biomarker for breast cancer subtypes, we integrated the CNV data of more than 2000 samples from two large breast cancer databases, METABRIC and The Cancer Genome Atlas (TCGA). A Monte Carlo feature selection-based and incremental feature selection-based computational method was proposed and tested to identify the distinctive core CNVs in different breast cancer subtypes. We identified the CNV genes that may contribute to breast cancer tumorigenesis as well as built a set of quantitative distinctive rules for recognition of the breast cancer subtypes. The tenfold cross-validation Matthew's correlation coefficient (MCC) on METABRIC training set and the independent test on TCGA dataset were 0.515 and 0.492, respectively. The CNVs of PGAP3, GRB7, MIR4728, PNMT, STARD3, TCAP and ERBB2 were important for the accurate diagnosis of breast cancer subtypes. The findings reported in this study may further uncover the difference between different breast cancer subtypes and improve the diagnosis accuracy.

An Algorithm for Creating Virtual Controls Using Integrated and Harmonized Longitudinal Data

We introduce a strategy for creating virtual control groups-cases generated through computer algorithms that, when aggregated, may serve as experimental comparators where live controls are difficult to recruit, such as when programs are widely disseminated and randomization is not feasible. We integrated and harmonized data from eight archived longitudinal adolescent-focused data sets spanning the decades from 1980 to 2010. Collectively, these studies examined numerous psychosocial variables and assessed past 30-day alcohol, cigarette, and marijuana use. Additional treatment and control group data from two archived randomized control trials were used to test the virtual control algorithm. Both randomized controlled trials (RCTs) assessed intentions, normative beliefs, and values as well as past 30-day alcohol, cigarette, and marijuana use. We developed an algorithm that used percentile scores from the integrated data set to create age- and gender-specific latent psychosocial scores. The algorithm matched treatment case observed psychosocial scores at pretest to create a virtual control case that figuratively "matured" based on age-related changes, holding the virtual case's percentile constant. Virtual controls matched treatment case occurrence, eliminating differential attrition as a threat to validity. Virtual case substance use was estimated from the virtual case's latent psychosocial score using logistic regression coefficients derived from analyzing the treatment group. Averaging across virtual cases created group estimates of prevalence. Two criteria were established to evaluate the adequacy of virtual control cases: (1) virtual control group pretest drug prevalence rates should match those of the treatment group and (2) virtual control group patterns of drug prevalence over time should match live controls. The algorithm successfully matched pretest prevalence for both RCTs. Increases in prevalence were observed, although there were discrepancies between live and virtual control outcomes. This study provides an initial framework for creating virtual controls using a step-by-step procedure that can now be revised and validated using other prevention trial data.

A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information

The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach

Background

RNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation.

Results

In viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications.

Conclusion

The iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1561-8) contains supplementary material, which is available to authorized users.

IPMiner: hidden ncRNA-protein interaction sequential pattern mining with stacked autoencoder for accurate computational prediction

BACKGROUND

Non-coding RNAs (ncRNAs) play crucial roles in many biological processes, such as post-transcription of gene regulation. ncRNAs mainly function through interaction with RNA binding proteins (RBPs). To understand the function of a ncRNA, a fundamental step is to identify which protein is involved into its interaction. Therefore it is promising to computationally predict RBPs, where the major challenge is that the interaction pattern or motif is difficult to be found.

RESULTS

In this study, we propose a computational method IPMiner (Interaction Pattern Miner) to predict ncRNA-protein interactions from sequences, which makes use of deep learning and further improves its performance using stacked ensembling. One of the IPMiner's typical merits is that it is able to mine the hidden sequential interaction patterns from sequence composition features of protein and RNA sequences using stacked autoencoder, and then the learned hidden features are fed into random forest models. Finally, stacked ensembling is used to integrate different predictors to further improve the prediction performance. The experimental results indicate that IPMiner achieves superior performance on the tested lncRNA-protein interaction dataset with an accuracy of 0.891, sensitivity of 0.939, specificity of 0.831, precision of 0.945 and Matthews correlation coefficient of 0.784, respectively. We further comprehensively investigate IPMiner on other RNA-protein interaction datasets, which yields better performance than the state-of-the-art methods, and the performance has an increase of over 20 % on some tested benchmarked datasets. In addition, we further apply IPMiner for large-scale prediction of ncRNA-protein network, that achieves promising prediction performance.

CONCLUSION

By integrating deep neural network and stacked ensembling, from simple sequence composition features, IPMiner can automatically learn high-level abstraction features, which had strong discriminant ability for RNA-protein detection. IPMiner achieved high performance on our constructed lncRNA-protein benchmark dataset and other RNA-protein datasets. IPMiner tool is available at http://www.csbio.sjtu.edu.cn/bioinf/IPMiner .

A hybrid imputation approach for microarray missing value estimation

BACKGROUND

Missing data is an inevitable phenomenon in gene expression microarray experiments due to instrument failure or human error. It has a negative impact on performance of downstream analysis. Technically, most existing approaches suffer from this prevalent problem. Imputation is one of the frequently used methods for processing missing data. Actually many developments have been achieved in the research on estimating missing values. The challenging task is how to improve imputation accuracy for data with a large missing rate.

METHODS

In this paper, induced by the thought of collaborative training, we propose a novel hybrid imputation method, called Recursive Mutual Imputation (RMI). Specifically, RMI exploits global correlation information and local structure in the data, captured by two popular methods, Bayesian Principal Component Analysis (BPCA) and Local Least Squares (LLS), respectively. Mutual strategy is implemented by sharing the estimated data sequences at each recursive process. Meanwhile, we consider the imputation sequence based on the number of missing entries in the target gene. Furthermore, a weight based integrated method is utilized in the final assembling step.

RESULTS

We evaluate RMI with three state-of-art algorithms (BPCA, LLS, Iterated Local Least Squares imputation (ItrLLS)) on four publicly available microarray datasets. Experimental results clearly demonstrate that RMI significantly outperforms comparative methods in terms of Normalized Root Mean Square Error (NRMSE), especially for datasets with large missing rates and less complete genes.

CONCLUSIONS

It is noted that our proposed hybrid imputation approach incorporates both global and local information of microarray genes, which achieves lower NRMSE values against to any single approach only. Besides, this study highlights the need for considering the imputing sequence of missing entries for imputation methods.

Data Imputation in Epistatic MAPs by Network-Guided Matrix Completion

Epistatic miniarray profile (E-MAP) is a popular large-scale genetic interaction discovery platform. E-MAPs benefit from quantitative output, which makes it possible to detect subtle interactions with greater precision. However, due to the limits of biotechnology, E-MAP studies fail to measure genetic interactions for up to 40% of gene pairs in an assay. Missing measurements can be recovered by computational techniques for data imputation, in this way completing the interaction profiles and enabling downstream analysis algorithms that could otherwise be sensitive to missing data values. We introduce a new interaction data imputation method called network-guided matrix completion (NG-MC). The core part of NG-MC is low-rank probabilistic matrix completion that incorporates prior knowledge presented as a collection of gene networks. NG-MC assumes that interactions are transitive, such that latent gene interaction profiles inferred by NG-MC depend on the profiles of their direct neighbors in gene networks. As the NG-MC inference algorithm progresses, it propagates latent interaction profiles through each of the networks and updates gene network weights toward improved prediction. In a study with four different E-MAP data assays and considered protein-protein interaction and gene ontology similarity networks, NG-MC significantly surpassed existing alternative techniques. Inclusion of information from gene networks also allowed NG-MC to predict interactions for genes that were not included in original E-MAP assays, a task that could not be considered by current imputation approaches.

PredcircRNA: computational classification of circular RNA from other long non-coding RNA using hybrid features

PredcircRNA presents computational classification of circularRNA from other lncRNA using hybrid features based on multiple kernel learning.

Searching for synergies: matrix algebraic approaches for efficient pair screening

Functionally interacting perturbations, such as synergistic drugs pairs or synthetic lethal gene pairs, are of key interest in both pharmacology and functional genomics. However, to find such pairs by traditional screening methods is both time consuming and costly. We present a novel computational-experimental framework for efficient identification of synergistic target pairs, applicable for screening of systems with sizes on the order of current drug, small RNA or SGA (Synthetic Genetic Array) libraries (>1000 targets). This framework exploits the fact that the response of a drug pair in a given system, or a pair of genes' propensity to interact functionally, can be partly predicted by computational means from (i) a small set of experimentally determined target pairs, and (ii) pre-existing data (e.g. gene ontology, PPI) on the similarities between targets. Predictions are obtained by a novel matrix algebraic technique, based on cyclical projections onto convex sets. We demonstrate the efficiency of the proposed method using drug-drug interaction data from seven cancer cell lines and gene-gene interaction data from yeast SGA screens. Our protocol increases the rate of synergism discovery significantly over traditional screening, by up to 7-fold. Our method is easy to implement and could be applied to accelerate pair screening for both animal and microbial systems.