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.     

Predicting gastrointestinal infection morbidity based on environmental pollutants: Deep learning versus traditional models

Accurate morbidity prediction can contribute greatly to the efficiency of medical services. Gastrointestinal infectious diseases are largely influenced by environmental pollutants, but predicting their morbidity based on pollution indicators is quite difficult because of the complex relationship between the pollutants and the infections. This study presents a deep neural network (DNN) model for estimating the morbidity of gastrointestinal infections based on 129 types of pollutants contained in soil and water. The DNN uses a deep Boltzmann machine (DBM) to model the unknown probabilistic relationship between the pollutants, and employs a Gaussian mixture model (GMM) to output the estimated morbidity. We also propose an evolutionary algorithm for efficiently training the DNN. Experiment on a data set from four counties in central China shows that the proposed model can estimate the morbidity much more accurately than traditional neural network and linear regression models.     

A general framework of nonparametric feature selection in high-dimensional data

Nonparametric feature selection for high-dimensional data is an important and challenging problem in the fields of statistics and machine learning. Most of the existing methods for feature selection focus on parametric or additive models which may suffer from model misspecification. In this paper, we propose a new framework to perform nonparametric feature selection for both regression and classification problems. Under this framework, we learn prediction functions through empirical risk minimization over a reproducing kernel Hilbert space. The space is generated by a novel tensor product kernel, which depends on a set of parameters that determines the importance of the features. Computationally, we minimize the empirical risk with a penalty to estimate the prediction and kernel parameters simultaneously. The solution can be obtained by iteratively solving convex optimization problems. We study the theoretical property of the kernel feature space and prove the oracle selection property and Fisher consistency of our proposed method. Finally, we demonstrate the superior performance of our approach compared to existing methods via extensive simulation studies and applications to two real studies.     

基于TransformerMGI的microRNA靶向基因预测

生物小分子microRNA可以对基因表达进行正向或负向调控,研究microRNA与基因之间的关系对于机体稳态的维持和疾病治疗都有着重要意义。利用深度学习方法对microRNA和基因靶向关系进行预测,提出了TransformerMGI模型。在特征工程阶段,针对生物序列潜在信息难以准确地提取这一问题,TransformerMGI模型分别采用了基于图卷积神经网络的GP-GCN方法和DNA2Vec模型对microRNA和基因数据的潜在信息进行提取,得到了二者的表征嵌入矩阵,在模型方面,TransformerMGI模型引入了幂归一化来改进经典的深度学习模型。利用microRNA和基因数据经过特征提取后得到两个表征矩阵,这两个矩阵分别被放入TransformerMGI模型中,通过TransformerMGI模型内部的Attention机制对二者自身和相互的特征信息进行了聚合和关联运算,最终预测出microRNA调控基因的概率。采用ROC曲线下面积和准确召回率曲线作为模型性能评价指标,将TransformerMGI与其他现有模型进行了比较评估。实验结果表明,TransformerMGI模型的AUC和AUPRC评分均可达0.91以上,优于现有的其他模型。TransformerMGI模型能在不考虑生物学原理和基因组背景的前提下,仅依赖microRNA和基因的碱基序列信息,实现microRNA靶向基因的预测,从而为后续的microRNA靶向基因预测研究提供了可借鉴的深度学习方法。     

Development of a high-throughput SNP array for sea cucumber (Apostichopus japonicus) and its application in genomic selection with MCP regularized deep neural networks

High-throughput single nucleotide polymorphism (SNP) genotyping assays are powerful tools for genetic studies and genomic breeding applications for many species. Though large numbers of SNPs have been identified in sea cucumber (Apostichopus japonicus), but, as yet, no high-throughput genotyping platform is available for this species. In this study, we designed and developed a high-throughput 24 K SNP genotyping array named HaishenSNP24K for A. japonicus, based on the multi-objective-local optimization (MOLO) algorithm and HD-Marker genotyping method. The SNP array exhibited a relatively high genotyping call rate (> 96%), genotyping accuracy (>95%) and exhibited highly polymorphic in sea cucumber populations. In addition, we also assessed its application in genomic selection (GS). Deep neural networks (DNN) that can capture the complicated interactions of genes have been proposed as a promising tool in GS for SNP-based genomic prediction of complex traits in animal breeding. To overcome the problem of over-fitting when using the HaishenSNP24K array as high-dimensional DNN input, we developed minmax concave penalty (MCP) regularization for sparse deep neural networks (DNN-MCP) that finds an optimal sparse structure of a DNN by minimizing the square error subject to the non-convex penalty MCP on the parameters (weights and biases). Compared to two linear models, namely RR-GBLUP and Bayes B, and the nonlinear model DNN, DNN-MCP has greatly improved the genomic prediction ability for three quantitative traits (e.g., wet weight, dry weight and survival time) in the sea cucumber population. To the best of our knowledge, this is the first work to develop a high-throughput SNP array for A. japonicus and a new model DNN-MCP for genomic prediction of complex traits in GS. The present results provide evidence that supports the HaishenSNP24K array with DNN-MCP will be valuable for genetic studies and molecular breeding in A. japonicus.     

Regularized ROC method for disease classification and biomarker selection with microarray data

MOTIVATION: An important application of microarrays is to discover genomic biomarkers, among tens of thousands of genes assayed, for disease classification. Thus there is a need for developing statistical methods that can efficiently use such high-throughput genomic data, select biomarkers with discriminant power and construct classification rules. The ROC (receiver operator characteristic) technique has been widely used in disease classification with low-dimensional biomarkers because (1) it does not assume a parametric form of the class probability as required for example in the logistic regression method; (2) it accommodates case-control designs and (3) it allows treating false positives and false negatives differently. However, due to computational difficulties, the ROC-based classification has not been used with microarray data. Moreover, the standard ROC technique does not incorporate built-in biomarker selection. RESULTS: We propose a novel method for biomarker selection and classification using the ROC technique for microarray data. The proposed method uses a sigmoid approximation to the area under the ROC curve as the objective function for classification and the threshold gradient descent regularization method for estimation and biomarker selection. Tuning parameter selection based on the V-fold cross validation and predictive performance evaluation are also investigated. The proposed approach is demonstrated with a simulation study, the Colon data and the Estrogen data. The proposed approach yields parsimonious models with excellent classification performance.     

Integrating node embeddings and biological annotations for genes to predict disease-gene associations

Background

Predicting disease causative genes (or simply, disease genes) has played critical roles in understanding the genetic basis of human diseases and further providing disease treatment guidelines. While various computational methods have been proposed for disease gene prediction, with the recent increasing availability of biological information for genes, it is highly motivated to leverage these valuable data sources and extract useful information for accurately predicting disease genes.

Results

We present an integrative framework called N2VKO to predict disease genes. Firstly, we learn the node embeddings from protein-protein interaction (PPI) network for genes by adapting the well-known representation learning method node2vec. Secondly, we combine the learned node embeddings with various biological annotations as rich feature representation for genes, and subsequently build binary classification models for disease gene prediction. Finally, as the data for disease gene prediction is usually imbalanced (i.e. the number of the causative genes for a specific disease is much less than that of its non-causative genes), we further address this serious data imbalance issue by applying oversampling techniques for imbalance data correction to improve the prediction performance. Comprehensive experiments demonstrate that our proposed N2VKO significantly outperforms four state-of-the-art methods for disease gene prediction across seven diseases.

Conclusions

In this study, we show that node embeddings learned from PPI networks work well for disease gene prediction, while integrating node embeddings with other biological annotations further improves the performance of classification models. Moreover, oversampling techniques for imbalance correction further enhances the prediction performance. In addition, the literature search of predicted disease genes also shows the effectiveness of our proposed N2VKO framework for disease gene prediction.

     

Gene selection for classification of cancers using probabilistic model building genetic algorithm

Recently, DNA microarray-based gene expression profiles have been used to correlate the clinical behavior of cancers with the differential gene expression levels in cancerous and normal tissues. To this end, after selection of some predictive genes based on signal-to-noise (S2N) ratio, unsupervised learning like clustering and supervised learning like k-nearest neighbor (k NN) classifier are widely used. Instead of S2N ratio, adaptive searches like Probabilistic Model Building Genetic Algorithm (PMBGA) can be applied for selection of a smaller size gene subset that would classify patient samples more accurately. In this paper, we propose a new PMBGA-based method for identification of informative genes from microarray data. By applying our proposed method to classification of three microarray data sets of binary and multi-type tumors, we demonstrate that the gene subsets selected with our technique yield better classification accuracy.     

A Copula Based Approach for Design of Multivariate Random Forests for Drug Sensitivity Prediction

Modeling sensitivity to drugs based on genetic characterizations is a significant challenge in the area of systems medicine. Ensemble based approaches such as Random Forests have been shown to perform well in both individual sensitivity prediction studies and team science based prediction challenges. However, Random Forests generate a deterministic predictive model for each drug based on the genetic characterization of the cell lines and ignores the relationship between different drug sensitivities during model generation. This application motivates the need for generation of multivariate ensemble learning techniques that can increase prediction accuracy and improve variable importance ranking by incorporating the relationships between different output responses. In this article, we propose a novel cost criterion that captures the dissimilarity in the output response structure between the training data and node samples as the difference in the two empirical copulas. We illustrate that copulas are suitable for capturing the multivariate structure of output responses independent of the marginal distributions and the copula based multivariate random forest framework can provide higher accuracy prediction and improved variable selection. The proposed framework has been validated on genomics of drug sensitivity for cancer and cancer cell line encyclopedia database.     

Development and Validation of a Gene-Based Model for Outcome Prediction in Germ Cell Tumors Using a Combined Genomic and Expression Profiling Approach

Germ Cell Tumors (GCT) have a high cure rate, but we currently lack the ability to accurately identify the small subset of patients who will die from their disease. We used a combined genomic and expression profiling approach to identify genomic regions and underlying genes that are predictive of outcome in GCT patients. We performed array-based comparative genomic hybridization (CGH) on 53 non-seminomatous GCTs (NSGCTs) treated with cisplatin based chemotherapy and defined altered genomic regions using Circular Binary Segmentation. We identified 14 regions associated with two year disease-free survival (2yDFS) and 16 regions associated with five year disease-specific survival (5yDSS). From corresponding expression data, we identified 101 probe sets that showed significant changes in expression. We built several models based on these differentially expressed genes, then tested them in an independent validation set of 54 NSGCTs. These predictive models correctly classified outcome in 64–79.6% of patients in the validation set, depending on the endpoint utilized. Survival analysis demonstrated a significant separation of patients with good versus poor predicted outcome when using a combined gene set model. Multivariate analysis using clinical risk classification with the combined gene model indicated that they were independent prognostic markers. This novel set of predictive genes from altered genomic regions is almost entirely independent of our previously identified set of predictive genes for patients with NSGCTs. These genes may aid in the identification of the small subset of patients who are at high risk of poor outcome.     

Using rule-based machine learning for candidate disease gene prioritization and sample classification of cancer gene expression data

Microarray data analysis has been shown to provide an effective tool for studying cancer and genetic diseases. Although classical machine learning techniques have successfully been applied to find informative genes and to predict class labels for new samples, common restrictions of microarray analysis such as small sample sizes, a large attribute space and high noise levels still limit its scientific and clinical applications. Increasing the interpretability of prediction models while retaining a high accuracy would help to exploit the information content in microarray data more effectively. For this purpose, we evaluate our rule-based evolutionary machine learning systems, BioHEL and GAssist, on three public microarray cancer datasets, obtaining simple rule-based models for sample classification. A comparison with other benchmark microarray sample classifiers based on three diverse feature selection algorithms suggests that these evolutionary learning techniques can compete with state-of-the-art methods like support vector machines. The obtained models reach accuracies above 90% in two-level external cross-validation, with the added value of facilitating interpretation by using only combinations of simple if-then-else rules. As a further benefit, a literature mining analysis reveals that prioritizations of informative genes extracted from BioHEL's classification rule sets can outperform gene rankings obtained from a conventional ensemble feature selection in terms of the pointwise mutual information between relevant disease terms and the standardized names of top-ranked genes.     

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.     

Gene selection via the BAHSIC family of algorithms

MOTIVATION: Identifying significant genes among thousands of sequences on a microarray is a central challenge for cancer research in bioinformatics. The ultimate goal is to detect the genes that are involved in disease outbreak and progression. A multitude of methods have been proposed for this task of feature selection, yet the selected gene lists differ greatly between different methods. To accomplish biologically meaningful gene selection from microarray data, we have to understand the theoretical connections and the differences between these methods. In this article, we define a kernel-based framework for feature selection based on the Hilbert-Schmidt independence criterion and backward elimination, called BAHSIC. We show that several well-known feature selectors are instances of BAHSIC, thereby clarifying their relationship. Furthermore, by choosing a different kernel, BAHSIC allows us to easily define novel feature selection algorithms. As a further advantage, feature selection via BAHSIC works directly on multiclass problems. RESULTS: In a broad experimental evaluation, the members of the BAHSIC family reach high levels of accuracy and robustness when compared to other feature selection techniques. Experiments show that features selected with a linear kernel provide the best classification performance in general, but if strong non-linearities are present in the data then non-linear kernels can be more suitable. AVAILABILITY: Accompanying homepage is http://www.dbs.ifi.lmu.de/~borgward/BAHSIC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.     

Logistic regression for disease classification using microarray data: model selection in a large p and small n case

MOTIVATION: Logistic regression is a standard method for building prediction models for a binary outcome and has been extended for disease classification with microarray data by many authors. A feature (gene) selection step, however, must be added to penalized logistic modeling due to a large number of genes and a small number of subjects. Model selection for this two-step approach requires new statistical tools because prediction error estimation ignoring the feature selection step can be severely downward biased. Generic methods such as cross-validation and non-parametric bootstrap can be very ineffective due to the big variability in the prediction error estimate. RESULTS: We propose a parametric bootstrap model for more accurate estimation of the prediction error that is tailored to the microarray data by borrowing from the extensive research in identifying differentially expressed genes, especially the local false discovery rate. The proposed method provides guidance on the two critical issues in model selection: the number of genes to include in the model and the optimal shrinkage for the penalized logistic regression. We show that selecting more than 20 genes usually helps little in further reducing the prediction error. Application to Golub's leukemia data and our own cervical cancer data leads to highly accurate prediction models. AVAILABILITY: R library GeneLogit at http://geocities.com/jg_liao     

A unifying framework for evaluating the predictive power of genetic variants based on the level of heritability explained

An increasing number of genetic variants have been identified for many complex diseases. However, it is controversial whether risk prediction based on genomic profiles will be useful clinically. Appropriate statistical measures to evaluate the performance of genetic risk prediction models are required. Previous studies have mainly focused on the use of the area under the receiver operating characteristic (ROC) curve, or AUC, to judge the predictive value of genetic tests. However, AUC has its limitations and should be complemented by other measures. In this study, we develop a novel unifying statistical framework that connects a large variety of predictive indices together. We showed that, given the overall disease probability and the level of variance in total liability (or heritability) explained by the genetic variants, we can estimate analytically a large variety of prediction metrics, for example the AUC, the mean risk difference between cases and non-cases, the net reclassification improvement (ability to reclassify people into high- and low-risk categories), the proportion of cases explained by a specific percentile of population at the highest risk, the variance of predicted risks, and the risk at any percentile. We also demonstrate how to construct graphs to visualize the performance of risk models, such as the ROC curve, the density of risks, and the predictiveness curve (disease risk plotted against risk percentile). The results from simulations match very well with our theoretical estimates. Finally we apply the methodology to nine complex diseases, evaluating the predictive power of genetic tests based on known susceptibility variants for each trait.     

Kernel-imbedded Gaussian processes for disease classification using microarray gene expression data

Background  

Designing appropriate machine learning methods for identifying genes that have a significant discriminating power for disease outcomes has become more and more important for our understanding of diseases at genomic level. Although many machine learning methods have been developed and applied to the area of microarray gene expression data analysis, the majority of them are based on linear models, which however are not necessarily appropriate for the underlying connection between the target disease and its associated explanatory genes. Linear model based methods usually also bring in false positive significant features more easily. Furthermore, linear model based algorithms often involve calculating the inverse of a matrix that is possibly singular when the number of potentially important genes is relatively large. This leads to problems of numerical instability. To overcome these limitations, a few non-linear methods have recently been introduced to the area. Many of the existing non-linear methods have a couple of critical problems, the model selection problem and the model parameter tuning problem, that remain unsolved or even untouched. In general, a unified framework that allows model parameters of both linear and non-linear models to be easily tuned is always preferred in real-world applications. Kernel-induced learning methods form a class of approaches that show promising potentials to achieve this goal.     

Sparse Zero-Sum Games as Stable Functional Feature Selection

In large-scale systems biology applications, features are structured in hidden functional categories whose predictive power is identical. Feature selection, therefore, can lead not only to a problem with a reduced dimensionality, but also reveal some knowledge on functional classes of variables. In this contribution, we propose a framework based on a sparse zero-sum game which performs a stable functional feature selection. In particular, the approach is based on feature subsets ranking by a thresholding stochastic bandit. We provide a theoretical analysis of the introduced algorithm. We illustrate by experiments on both synthetic and real complex data that the proposed method is competitive from the predictive and stability viewpoints.     

Gene selection for tumor classification using a novel bio-inspired multi-objective approach

Identifying the informative genes has always been a major step in microarray data analysis. The complexity of various cancer datasets makes this issue still challenging. In this paper, a novel Bio-inspired Multi-objective algorithm is proposed for gene selection in microarray data classification specifically in the binary domain of feature selection. The presented method extends the traditional Bat Algorithm with refined formulations, effective multi-objective operators, and novel local search strategies employing social learning concepts in designing random walks. A hybrid model using the Fisher criterion is then applied to three widely-used microarray cancer datasets to explore significant biomarkers which reveal the effectiveness of the proposed method for genomic analysis. Experimental results unveil new combinations of informative biomarkers have association with other studies.