Powerful Tests for Multi-Marker Association Analysis Using Ensemble Learning

Multi-marker approaches have received a lot of attention recently in genome wide association studies and can enhance power to detect new associations under certain conditions. Gene-, gene-set- and pathway-based association tests are increasingly being viewed as useful supplements to the more widely used single marker association analysis which have successfully uncovered numerous disease variants. A major drawback of single-marker based methods is that they do not look at the joint effects of multiple genetic variants which individually may have weak or moderate signals. Here, we describe novel tests for multi-marker association analyses that are based on phenotype predictions obtained from machine learning algorithms. Instead of assuming a linear or logistic regression model, we propose the use of ensembles of diverse machine learning algorithms for prediction. We show that phenotype predictions obtained from ensemble learning algorithms provide a new framework for multi-marker association analysis. They can be used for constructing tests for the joint association of multiple variants, adjusting for covariates and testing for the presence of interactions. To demonstrate the power and utility of this new approach, we first apply our method to simulated SNP datasets. We show that the proposed method has the correct Type-1 error rates and can be considerably more powerful than alternative approaches in some situations. Then, we apply our method to previously studied asthma-related genes in 2 independent asthma cohorts to conduct association tests.     

Class Prediction and Feature Selection with Linear Optimization for Metagenomic Count Data

The amount of metagenomic data is growing rapidly while the computational methods for metagenome analysis are still in their infancy. It is important to develop novel statistical learning tools for the prediction of associations between bacterial communities and disease phenotypes and for the detection of differentially abundant features. In this study, we presented a novel statistical learning method for simultaneous association prediction and feature selection with metagenomic samples from two or multiple treatment populations on the basis of count data. We developed a linear programming based support vector machine with and joint penalties for binary and multiclass classifications with metagenomic count data (metalinprog). We evaluated the performance of our method on several real and simulation datasets. The proposed method can simultaneously identify features and predict classes with the metagenomic count data.     

PSoL: a positive sample only learning algorithm for finding non-coding RNA genes

MOTIVATION: Small non-coding RNA (ncRNA) genes play important regulatory roles in a variety of cellular processes. However, detection of ncRNA genes is a great challenge to both experimental and computational approaches. In this study, we describe a new approach called positive sample only learning (PSoL) to predict ncRNA genes in the Escherichia coli genome. Although PSoL is a machine learning method for classification, it requires no negative training data, which, in general, is hard to define properly and affects the performance of machine learning dramatically. In addition, using the support vector machine (SVM) as the core learning algorithm, PSoL can integrate many different kinds of information to improve the accuracy of prediction. Besides the application of PSoL for predicting ncRNAs, PSoL is applicable to many other bioinformatics problems as well. RESULTS: The PSoL method is assessed by 5-fold cross-validation experiments which show that PSoL can achieve about 80% accuracy in recovery of known ncRNAs. We compared PSoL predictions with five previously published results. The PSoL method has the highest percentage of predictions overlapping with those from other methods.     

Ensemble Positive Unlabeled Learning for Disease Gene Identification

An increasing number of genes have been experimentally confirmed in recent years as causative genes to various human diseases. The newly available knowledge can be exploited by machine learning methods to discover additional unknown genes that are likely to be associated with diseases. In particular, positive unlabeled learning (PU learning) methods, which require only a positive training set P (confirmed disease genes) and an unlabeled set U (the unknown candidate genes) instead of a negative training set N, have been shown to be effective in uncovering new disease genes in the current scenario. Using only a single source of data for prediction can be susceptible to bias due to incompleteness and noise in the genomic data and a single machine learning predictor prone to bias caused by inherent limitations of individual methods. In this paper, we propose an effective PU learning framework that integrates multiple biological data sources and an ensemble of powerful machine learning classifiers for disease gene identification. Our proposed method integrates data from multiple biological sources for training PU learning classifiers. A novel ensemble-based PU learning method EPU is then used to integrate multiple PU learning classifiers to achieve accurate and robust disease gene predictions. Our evaluation experiments across six disease groups showed that EPU achieved significantly better results compared with various state-of-the-art prediction methods as well as ensemble learning classifiers. Through integrating multiple biological data sources for training and the outputs of an ensemble of PU learning classifiers for prediction, we are able to minimize the potential bias and errors in individual data sources and machine learning algorithms to achieve more accurate and robust disease gene predictions. In the future, our EPU method provides an effective framework to integrate the additional biological and computational resources for better disease gene predictions.     

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.     

Naïve Bayes for microRNA target predictions--machine learning for microRNA targets

MOTIVATION: Most computational methodologies for miRNA:mRNA target gene prediction use the seed segment of the miRNA and require cross-species sequence conservation in this region of the mRNA target. Methods that do not rely on conservation generate numbers of predictions, which are too large to validate. We describe a target prediction method (NBmiRTar) that does not require sequence conservation, using instead, machine learning by a na?ve Bayes classifier. It generates a model from sequence and miRNA:mRNA duplex information from validated targets and artificially generated negative examples. Both the 'seed' and 'out-seed' segments of the miRNA:mRNA duplex are used for target identification. RESULTS: The application of machine-learning techniques to the features we have used is a useful and general approach for microRNA target gene prediction. Our technique produces fewer false positive predictions and fewer target candidates to be tested. It exhibits higher sensitivity and specificity than algorithms that rely on conserved genomic regions to decrease false positive predictions.     

ESPD: a pattern detection model underlying gene expression profiles

MOTIVATION: DNA arrays permit rapid, large-scale screening for patterns of gene expression and simultaneously yield the expression levels of thousands of genes for samples. The number of samples is usually limited, and such datasets are very sparse in high-dimensional gene space. Furthermore, most of the genes collected may not necessarily be of interest and uncertainty about which genes are relevant makes it difficult to construct an informative gene space. Unsupervised empirical sample pattern discovery and informative genes identification of such sparse high-dimensional datasets present interesting but challenging problems. RESULTS: A new model called empirical sample pattern detection (ESPD) is proposed to delineate pattern quality with informative genes. By integrating statistical metrics, data mining and machine learning techniques, this model dynamically measures and manipulates the relationship between samples and genes while conducting an iterative detection of informative space and the empirical pattern. The performance of the proposed method with various array datasets is illustrated.     

Semi-supervised analysis of gene expression profiles for lineage-specific development in the Caenorhabditis elegans embryo

MOTIVATION: Gene expression profiling is a powerful approach to identify genes that may be involved in a specific biological process on a global scale. For example, gene expression profiling of mutant animals that lack or contain an excess of certain cell types is a common way to identify genes that are important for the development and maintenance of given cell types. However, it is difficult for traditional computational methods, including unsupervised and supervised learning methods, to detect relevant genes from a large collection of expression profiles with high sensitivity and specificity. Unsupervised methods group similar gene expressions together while ignoring important prior biological knowledge. Supervised methods utilize training data from prior biological knowledge to classify gene expression. However, for many biological problems, little prior knowledge is available, which limits the prediction performance of most supervised methods. RESULTS: We present a Bayesian semi-supervised learning method, called BGEN, that improves upon supervised and unsupervised methods by both capturing relevant expression profiles and using prior biological knowledge from literature and experimental validation. Unlike currently available semi-supervised learning methods, this new method trains a kernel classifier based on labeled and unlabeled gene expression examples. The semi-supervised trained classifier can then be used to efficiently classify the remaining genes in the dataset. Moreover, we model the confidence of microarray probes and probabilistically combine multiple probe predictions into gene predictions. We apply BGEN to identify genes involved in the development of a specific cell lineage in the C. elegans embryo, and to further identify the tissues in which these genes are enriched. Compared to K-means clustering and SVM classification, BGEN achieves higher sensitivity and specificity. We confirm certain predictions by biological experiments. AVAILABILITY: The results are available at http://www.csail.mit.edu/~alanqi/projects/BGEN.html.     

Simple decision rules for classifying human cancers from gene expression profiles

MOTIVATION: Various studies have shown that cancer tissue samples can be successfully detected and classified by their gene expression patterns using machine learning approaches. One of the challenges in applying these techniques for classifying gene expression data is to extract accurate, readily interpretable rules providing biological insight as to how classification is performed. Current methods generate classifiers that are accurate but difficult to interpret. This is the trade-off between credibility and comprehensibility of the classifiers. Here, we introduce a new classifier in order to address these problems. It is referred to as k-TSP (k-Top Scoring Pairs) and is based on the concept of 'relative expression reversals'. This method generates simple and accurate decision rules that only involve a small number of gene-to-gene expression comparisons, thereby facilitating follow-up studies. RESULTS: In this study, we have compared our approach to other machine learning techniques for class prediction in 19 binary and multi-class gene expression datasets involving human cancers. The k-TSP classifier performs as efficiently as Prediction Analysis of Microarray and support vector machine, and outperforms other learning methods (decision trees, k-nearest neighbour and na?ve Bayes). Our approach is easy to interpret as the classifier involves only a small number of informative genes. For these reasons, we consider the k-TSP method to be a useful tool for cancer classification from microarray gene expression data. AVAILABILITY: The software and datasets are available at http://www.ccbm.jhu.edu CONTACT: actan@jhu.edu.     

Prediction of subcellular protein localization based on functional domain composition

Assigning subcellular localization (SL) to proteins is one of the major tasks of functional proteomics. Despite the impressive technical advances of the past decades, it is still time-consuming and laborious to experimentally determine SL on a high throughput scale. Thus, computational predictions are the preferred method for large-scale assignment of protein SL, and if appropriate, followed up by experimental studies. In this report, using a machine learning approach, the Nearest Neighbor Algorithm (NNA), we developed a prediction system for protein SL in which we incorporated a protein functional domain profile. The overall accuracy achieved by this system is 93.96%. Furthermore, comparisons with other methods have been conducted to demonstrate the validity and efficiency of our prediction system. We also provide an implementation of our Subcellular Location Prediction System (SLPS), which is available at http://pcal.biosino.org.     

Network-based Phenome-Genome Association Prediction by Bi-Random Walk

MotivationThe availability of ontologies and systematic documentations of phenotypes and their genetic associations has enabled large-scale network-based global analyses of the association between the complete collection of phenotypes (phenome) and genes. To provide a fundamental understanding of how the network information is relevant to phenotype-gene associations, we analyze the circular bigraphs (CBGs) in OMIM human disease phenotype-gene association network and MGI mouse phentoype-gene association network, and introduce a bi-random walk (BiRW) algorithm to capture the CBG patterns in the networks for unveiling human and mouse phenome-genome association. BiRW performs separate random walk simultaneously on gene interaction network and phenotype similarity network to explore gene paths and phenotype paths in CBGs of different sizes to summarize their associations as predictions.ResultsThe analysis of both OMIM and MGI associations revealed that majority of the phenotype-gene associations are covered by CBG patterns of small path lengths, and there is a clear correlation between the CBG coverage and the predictability of the phenotype-gene associations. In the experiments on recovering known associations in cross-validations on human disease phenotypes and mouse phenotypes, BiRW effectively improved prediction performance over the compared methods. The constructed global human disease phenome-genome association map also revealed interesting new predictions and phenotype-gene modules by disease classes.     

Use of extreme patient samples for outcome prediction from gene expression data

MOTIVATION: Patient outcome prediction using microarray technologies is an important application in bioinformatics. Based on patients' genotypic microarray data, predictions are made to estimate patients' survival time and their risk of tumor metastasis or recurrence. So, accurate prediction can potentially help to provide better treatment for patients. RESULTS: We present a new computational method for patient outcome prediction. In the training phase of this method, we make use of two types of extreme patient samples: short-term survivors who got an unfavorable outcome within a short period and long-term survivors who were maintaining a favorable outcome after a long follow-up time. These extreme training samples yield a clear platform for us to identify relevant genes whose expression is closely related to the outcome. The selected extreme samples and the relevant genes are then integrated by a support vector machine to build a prediction model, by which each validation sample is assigned a risk score that falls into one of the special pre-defined risk groups. We apply this method to several public datasets. In most cases, patients in high and low risk groups stratified by our method have clearly distinguishable outcome status as seen in their Kaplan-Meier curves. We also show that the idea of selecting only extreme patient samples for training is effective for improving the prediction accuracy when different gene selection methods are used.     

No Longer Confidential: Estimating the Confidence of Individual Regression Predictions

Quantitative predictions in computational life sciences are often based on regression models. The advent of machine learning has led to highly accurate regression models that have gained widespread acceptance. While there are statistical methods available to estimate the global performance of regression models on a test or training dataset, it is often not clear how well this performance transfers to other datasets or how reliable an individual prediction is–a fact that often reduces a user’s trust into a computational method. In analogy to the concept of an experimental error, we sketch how estimators for individual prediction errors can be used to provide confidence intervals for individual predictions. Two novel statistical methods, named CONFINE and CONFIVE, can estimate the reliability of an individual prediction based on the local properties of nearby training data. The methods can be applied equally to linear and non-linear regression methods with very little computational overhead. We compare our confidence estimators with other existing confidence and applicability domain estimators on two biologically relevant problems (MHC–peptide binding prediction and quantitative structure-activity relationship (QSAR)). Our results suggest that the proposed confidence estimators perform comparable to or better than previously proposed estimation methods. Given a sufficient amount of training data, the estimators exhibit error estimates of high quality. In addition, we observed that the quality of estimated confidence intervals is predictable. We discuss how confidence estimation is influenced by noise, the number of features, and the dataset size. Estimating the confidence in individual prediction in terms of error intervals represents an important step from plain, non-informative predictions towards transparent and interpretable predictions that will help to improve the acceptance of computational methods in the biological community.     

Toward better understanding of protein secondary structure: extracting prediction rules

Although numerous computational techniques have been applied to predict protein secondary structure (PSS), only limited studies have dealt with discovery of logic rules underlying the prediction itself. Such rules offer interesting links between the prediction model and the underlying biology. In addition, they enhance interpretability of PSS prediction by providing a degree of transparency to the predicting model usually regarded as a black box. In this paper, we explore the generation and use of C4.5 decision trees to extract relevant rules from PSS predictions modeled with two-stage support vector machines (TS-SVM). The proposed rules were derived on the RS126 data set of 126 nonhomologous globular proteins and on the PSIPRED data set of 1,923 protein sequences. Our approach has produced sets of comprehensible, and often interpretable, rules underlying the PSS predictions. Moreover, many of the rules seem to be strongly supported by biological evidence. Further, our approach resulted in good prediction accuracy, few and usually compact rules, and rules that are generally of higher confidence levels than those generated by other rule extraction techniques.     

A simulation study of the genetic regulatory hierarchy for butterfly eyespot focus determination

The color patterns on the wings of butterflies have been an important model system in evolutionary developmental biology. Two types of models have been used to study these patterns. The first type of model employs computational techniques and generalized mechanisms of pattern formation to make predictions about how color patterns will vary as parameters of the model are changed. These generalized mechanisms include diffusion gradient, reaction-diffusion, lateral inhibition, and threshold responses. The second type of model uses known genetic interactions from Drosophila melanogaster and patterns of candidate gene expression in one of several butterfly species (most often Junonia (Precis) coenia or Bicyclus anynana) to propose specific genetic regulatory hierarchies that appear to be involved in color pattern formation. This study combines these two approaches using computational techniques to test proposed genetic regulatory hierarchies for the determination of butterfly eyespot foci (also known as border ocelli foci). Two computer programs, STELLA 8.1 and Delphi 2.0, were used to simulate the determination of eyespot foci. Both programs revealed weaknesses in a genetic model previously proposed for eyespot focus determination. On the basis of these simulations, we propose two revised models for eyespot focus determination and identify components of the genetic regulatory hierarchy that are particularly sensitive to changes in model parameter values. These components may play a key role in the evolution of butterfly eyespots. Simulations like these may be useful tools for the study of other evolutionary developmental model systems and reveal similar sensitive components of the relevant genetic regulatory hierarchies.     

Graph embedding ensemble methods based on the heterogeneous network for lncRNA-miRNA interaction prediction

Background

Researchers discover LncRNA–miRNA regulatory paradigms modulate gene expression patterns and drive major cellular processes. Identification of lncRNA-miRNA interactions (LMIs) is critical to reveal the mechanism of biological processes and complicated diseases. Because conventional wet experiments are time-consuming, labor-intensive and costly, a few computational methods have been proposed to expedite the identification of lncRNA-miRNA interactions. However, little attention has been paid to fully exploit the structural and topological information of the lncRNA-miRNA interaction network.

Results

In this paper, we propose novel lncRNA-miRNA prediction methods by using graph embedding and ensemble learning. First, we calculate lncRNA-lncRNA sequence similarity and miRNA-miRNA sequence similarity, and then we combine them with the known lncRNA-miRNA interactions to construct a heterogeneous network. Second, we adopt several graph embedding methods to learn embedded representations of lncRNAs and miRNAs from the heterogeneous network, and construct the ensemble models using two ensemble strategies. For the former, we consider individual graph embedding based models as base predictors and integrate their predictions, and develop a method, named GEEL-PI. For the latter, we construct a deep attention neural network (DANN) to integrate various graph embeddings, and present an ensemble method, named GEEL-FI. The experimental results demonstrate both GEEL-PI and GEEL-FI outperform other state-of-the-art methods. The effectiveness of two ensemble strategies is validated by further experiments. Moreover, the case studies show that GEEL-PI and GEEL-FI can find novel lncRNA-miRNA associations.

Conclusion

The study reveals that graph embedding and ensemble learning based method is efficient for integrating heterogeneous information derived from lncRNA-miRNA interaction network and can achieve better performance on LMI prediction task. In conclusion, GEEL-PI and GEEL-FI are promising for lncRNA-miRNA interaction prediction.