Search

The ensemble method random forests has become a popular classification tool in bioinformatics and related fields. The out-of-bag error is an error estimation technique often used to evaluate the accuracy of a random forest and to select appropriate values for tuning parameters, such as the number of candidate predictors that are randomly drawn for a split, referred to as mtry. However, for binary classification problems with metric predictors it has been shown that the out-of-bag error can overestimate the true prediction error depending on the choices of random forests parameters. Based on simulated and real data this paper aims to identify settings for which this overestimation is likely. It is, moreover, questionable whether the out-of-bag error can be used in classification tasks for selecting tuning parameters like mtry, because the overestimation is seen to depend on the parameter mtry. The simulation-based and real-data based studies with metric predictor variables performed in this paper show that the overestimation is largest in balanced settings and in settings with few observations, a large number of predictor variables, small correlations between predictors and weak effects. There was hardly any impact of the overestimation on tuning parameter selection. However, although the prediction performance of random forests was not substantially affected when using the out-of-bag error for tuning parameter selection in the present studies, one cannot be sure that this applies to all future data. For settings with metric predictor variables it is therefore strongly recommended to use stratified subsampling with sampling fractions that are proportional to the class sizes for both tuning parameter selection and error estimation in random forests. This yielded less biased estimates of the true prediction error. In unbalanced settings, in which there is a strong interest in predicting observations from the smaller classes well, sampling the same number of observations from each class is a promising alternative. [ABSTRACT FROM AUTHOR]

The process of Nuclei detection in high-grade breast cancer images is quite challenging in the case of image processing techniques due to certain heterogeneous characteristics of cancer nuclei such as enlarged and irregularly shaped nuclei, highly coarse chromatin marginalized to the nuclei periphery and visible nucleoli. Recent reviews state that existing techniques show appreciable segmentation accuracy on breast histopathology images whose nuclei are dispersed and regular in texture and shape; however, typical cancer nuclei are often clustered and have irregular texture and shape properties. This paper proposes a novel segmentation algorithm for detecting individual nuclei from Hematoxylin and Eosin (H&E) stained breast histopathology images. This detection framework estimates a nuclei saliency map using tensor voting followed by boundary extraction of the nuclei on the saliency map using a Loopy Back Propagation (LBP) algorithm on a Markov Random Field (MRF). The method was tested on both whole-slide images and frames of breast cancer histopathology images. Experimental results demonstrate high segmentation performance with efficient precision, recall and dice-coefficient rates, upon testing high-grade breast cancer images containing several thousand nuclei. In addition to the optimal performance on the highly complex images presented in this paper, this method also gave appreciable results in comparison with two recently published methods—Wienert et al. (2012) and Veta et al. (2013), which were tested using their own datasets. [ABSTRACT FROM AUTHOR]

Breast cancer is an all too common disease in women, making how to effectively predict it an active research problem. A number of statistical and machine learning techniques have been employed to develop various breast cancer prediction models. Among them, support vector machines (SVM) have been shown to outperform many related techniques. To construct the SVM classifier, it is first necessary to decide the kernel function, and different kernel functions can result in different prediction performance. However, there have been very few studies focused on examining the prediction performances of SVM based on different kernel functions. Moreover, it is unknown whether SVM classifier ensembles which have been proposed to improve the performance of single classifiers can outperform single SVM classifiers in terms of breast cancer prediction. Therefore, the aim of this paper is to fully assess the prediction performance of SVM and SVM ensembles over small and large scale breast cancer datasets. The classification accuracy, ROC, F-measure, and computational times of training SVM and SVM ensembles are compared. The experimental results show that linear kernel based SVM ensembles based on the bagging method and RBF kernel based SVM ensembles with the boosting method can be the better choices for a small scale dataset, where feature selection should be performed in the data pre-processing stage. For a large scale dataset, RBF kernel based SVM ensembles based on boosting perform better than the other classifiers. [ABSTRACT FROM AUTHOR]

For studying cancer and genetic diseases, the issue of identifying high correlation genes from high-dimensional data is an important problem. It is a great challenge to select relevant biomarkers from gene expression data that contains some important correlation structures, and some of the genes can be divided into different groups with a common biological function, chromosomal location or regulation. In this paper, we propose a penalized accelerated failure time model CHR-DE using a non-convex regularization (local search) with differential evolution (global search) in a wrapper-embedded memetic framework. The complex harmonic regularization (CHR) can approximate to the combination and ℓq (1 ≤ q < 2) for selecting biomarkers in group. And differential evolution (DE) is utilized to globally optimize the CHR’s hyperparameters, which make CHR-DE achieve strong capability of selecting groups of genes in high-dimensional biological data. We also developed an efficient path seeking algorithm to optimize this penalized model. The proposed method is evaluated on synthetic and three gene expression datasets: breast cancer, hepatocellular carcinoma and colorectal cancer. The experimental results demonstrate that CHR-DE is a more effective tool for feature selection and learning prediction. [ABSTRACT FROM AUTHOR]

Several modern genomic technologies, such as DNA-Methylation arrays, measure spatially registered probes that number in the hundreds of thousands across multiple chromosomes. The measured probes are by themselves less interesting scientifically; instead scientists seek to discover biologically interpretable genomic regions comprised of contiguous groups of probes which may act as biomarkers of disease or serve as a dimension-reducing pre-processing step for downstream analyses. In this paper, we introduce an unsupervised feature learning technique which maps technological units (probes) to biological units (genomic regions) that are common across all subjects. We use ideas from fusion penalties and convex clustering to introduce a method for Spatial Convex Clustering, or SpaCC. Our method is specifically tailored to detecting multi-subject regions of methylation, but we also test our approach on the well-studied problem of detecting segments of copy number variation. We formulate our method as a convex optimization problem, develop a massively parallelizable algorithm to find its solution, and introduce automated approaches for handling missing values and determining tuning parameters. Through simulation studies based on real methylation and copy number variation data, we show that SpaCC exhibits significant performance gains relative to existing methods. Finally, we illustrate SpaCC’s advantages as a pre-processing technique that reduces large-scale genomics data into a smaller number of genomic regions through several cancer epigenetics case studies on subtype discovery, network estimation, and epigenetic-wide association. [ABSTRACT FROM AUTHOR]

Microarray technology is important to simultaneously express multiple genes over a number of time points. Multiple classifier models, such as sparse representation (SR)-based method, have been developed to classify microarray gene expression data. These methods allocate the gene data points to different clusters. In this paper, we propose a novel collaborative representation (CR)-based classification with regularized least square to classify gene data. First, the CR codes a testing sample as a sparse linear combination of all training samples and then classifies the testing sample by evaluating which class leads to the minimum representation error. This CR-based classification approach is remarkably less complex than traditional classification methods but leads to very competitive classification results. In addition, compressive sensing approach is adopted to project the high-dimensional gene expression dataset to a lower-dimensional space which nearly contains the whole information. This compression without loss is beneficial to reduce the computational load. Experiments to detect subtypes of diseases, such as leukemia and autism spectrum disorders, are performed by analyzing the gene expression. The results show that the proposed CR-based algorithm exhibits significantly higher stability and accuracy than the traditional classifiers, such as support vector machine algorithm. [ABSTRACT FROM AUTHOR]

Identification of disease-causing genes is a fundamental challenge for human health studies. The phenotypic similarity among diseases may reflect the interactions at the molecular level, and phenotype comparison can be used to predict disease candidate genes. Online Mendelian Inheritance in Man (OMIM) is a database of human genetic diseases and related genes that has become an authoritative source of disease phenotypes. However, disease phenotypes have been described by free text; thus, standardization of phenotypic descriptions is needed before diseases can be compared. Several disease phenotype networks have been established in OMIM using different standardization methods. Two of these networks are important for phenotypic similarity analysis: the first and most commonly used network (mimMiner) is standardized by medical subject heading, and the other network (resnikHPO) is the first to be standardized by human phenotype ontology. This paper comprehensively evaluates for the first time the accuracy of these two networks in gene prioritization based on protein–protein interactions using large-scale, leave-one-out cross-validation experiments. The results show that both networks can effectively prioritize disease-causing genes, and the approach that relates two diseases using a logistic function improves prioritization performance. Tanimoto, one of four methods for normalizing resnikHPO, generates a symmetric network and it performs similarly to mimMiner. Furthermore, an integration of these two networks outperforms either network alone in gene prioritization, indicating that these two disease networks are complementary. [ABSTRACT FROM AUTHOR]

The maximal information coefficient (MIC) captures dependences between paired variables, including both functional and non-functional relationships. In this paper, we develop a new method, ChiMIC, to calculate the MIC values. The ChiMIC algorithm uses the chi-square test to terminate grid optimization and then removes the restriction of maximal grid size limitation of original ApproxMaxMI algorithm. Computational experiments show that ChiMIC algorithm can maintain same MIC values for noiseless functional relationships, but gives much smaller MIC values for independent variables. For noise functional relationship, the ChiMIC algorithm can reach the optimal partition much faster. Furthermore, the MCN values based on MIC calculated by ChiMIC can capture the complexity of functional relationships in a better way, and the statistical powers of MIC calculated by ChiMIC are higher than those calculated by ApproxMaxMI. Moreover, the computational costs of ChiMIC are much less than those of ApproxMaxMI. We apply the MIC values tofeature selection and obtain better classification accuracy using features selected by the MIC values from ChiMIC. [ABSTRACT FROM AUTHOR]

miRNAs are small non-coding RNAs that regulate gene expression by binding to the 3′-UTR of genes. Many recent studies have reported that miRNAs play important biological roles by regulating specific mRNAs or genes. Many sequence-based target prediction algorithms have been developed to predict miRNA targets. However, these methods are not designed for condition-specific target predictions and produce many false positives; thus, expression-based target prediction algorithms have been developed for condition-specific target predictions. A typical strategy to utilize expression data is to leverage the negative control roles of miRNAs on genes. To control false positives, a stringent cutoff value is typically set, but in this case, these methods tend to reject many true target relationships, i.e., false negatives. To overcome these limitations, additional information should be utilized. The literature is probably the best resource that we can utilize. Recent literature mining systems compile millions of articles with experiments designed for specific biological questions, and the systems provide a function to search for specific information. To utilize the literature information, we used a literature mining system, BEST, that automatically extracts information from the literature in PubMed and that allows the user to perform searches of the literature with any English words. By integrating omics data analysis methods and BEST, we developed Context-MMIA, a miRNA-mRNA target prediction method that combines expression data analysis results and the literature information extracted based on the user-specified context. In the pathway enrichment analysis using genes included in the top 200 miRNA-targets, Context-MMIA outperformed the four existing target prediction methods that we tested. In another test on whether prediction methods can re-produce experimentally validated target relationships, Context-MMIA outperformed the four existing target prediction methods. In summary, Context-MMIA allows the user to specify a context of the experimental data to predict miRNA targets, and we believe that Context-MMIA is very useful for predicting condition-specific miRNA targets. [ABSTRACT FROM AUTHOR]

We apply the Google matrix algorithms for analysis of interactions and influence of 37 cancer types, 203 cancer drugs and 195 world countries using the network of 5 416 537 English Wikipedia articles with all their directed hyperlinks. The PageRank algorithm provides a ranking of cancers which has 60% and 70% overlaps with the top 10 deadliest cancers extracted from World Health Organization GLOBOCAN 2018 and Global Burden of Diseases Study 2017, respectively. The recently developed reduced Google matrix algorithm gives networks of interactions between cancers, drugs and countries taking into account all direct and indirect links between these selected 435 entities. These reduced networks allow to obtain sensitivity of countries to specific cancers and drugs. The strongest links between cancers and drugs are in good agreement with the approved medical prescriptions of specific drugs to specific cancers. We argue that this analysis of knowledge accumulated in Wikipedia provides useful complementary global information about interdependencies between cancers, drugs and world countries. [ABSTRACT FROM AUTHOR]

MiRNAs and proteins play important roles in different stages of breast tumor development and serve as biomarkers for the early diagnosis of breast cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to screen the most important miRNAs and proteins. Maximal information coefficient was applied to assess intralayer and interlayer connection. A multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. The degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer. [ABSTRACT FROM AUTHOR]

Since their inception, several tools have been developed for cluster analysis and heatmap construction. The application of such tools to the number and types of genome-wide data available from next generation sequencing (NGS) technologies requires the adaptation of statistical concepts, such as in defining a most variable gene set, and more intricate cluster analyses method to address multiple omic data types. Additionally, the growing number of publicly available datasets has created the desire to estimate the statistical significance of a gene signature derived from one dataset to similarly group samples based on another dataset. The currently available number of tools and their combined use for generating heatmaps, along with the several adaptations of statistical concepts for addressing the higher dimensionality of genome-wide NGS-derived data, has created a further challenge in the ability to replicate heatmap results. We introduce NOJAH (NOt Just Another Heatmap), an interactive tool that defines and implements a workflow for genome-wide cluster analysis and heatmap construction by creating and combining several tools into a single user interface. NOJAH includes several newly developed scripts for techniques that though frequently applied are not sufficiently documented to allow for replicability of results. These techniques include: defining a most variable gene set (a.k.a., ‘core genes’), estimating the statistical significance of a gene signature to separate samples into clusters, and performing a result merging integrated cluster analysis. With only a user uploaded dataset, NOJAH provides as output, among other things, the minimum documentation required for replicating heatmap results. Additionally, NOJAH contains five different existing R packages that are connected in the interface by their functionality as part of a defined workflow for genome-wide cluster analysis. The NOJAH application tool is available at with corresponding source code available at . [ABSTRACT FROM AUTHOR]

Different performance measures are used to assess the behaviour, and to carry out the comparison, of classifiers in Machine Learning. Many measures have been defined on the literature, and among them, a measure inspired by Shannon’s entropy named the Confusion Entropy (CEN). In this work we introduce a new measure, MCEN, by modifying CEN to avoid its unwanted behaviour in the binary case, that disables it as a suitable performance measure in classification. We compare MCEN with CEN and other performance measures, presenting analytical results in some particularly interesting cases, as well as some heuristic computational experimentation. [ABSTRACT FROM AUTHOR]

Introduction: Surveys indicate that patients, particularly those suffering from chronic conditions, strongly benefit from the information found in social networks and online forums. One challenge in accessing online health information is to differentiate between factual and more subjective information. In this work, we evaluate the feasibility of exploiting lexical, syntactic, semantic, network-based and emotional properties of texts to automatically classify patient-generated contents into three types: “experiences”, “facts” and “opinions”, using machine learning algorithms. In this context, our goal is to develop automatic methods that will make online health information more easily accessible and useful for patients, professionals and researchers. Material and methods: We work with a set of 3000 posts to online health forums in breast cancer, morbus crohn and different allergies. Each sentence in a post is manually labeled as “experience”, “fact” or “opinion”. Using this data, we train a support vector machine algorithm to perform classification. The results are evaluated in a 10-fold cross validation procedure. Results: Overall, we find that it is possible to predict the type of information contained in a forum post with a very high accuracy (over 80 percent) using simple text representations such as word embeddings and bags of words. We also analyze more complex features such as those based on the network properties, the polarity of words and the verbal tense of the sentences and show that, when combined with the previous ones, they can boost the results. [ABSTRACT FROM AUTHOR]

Introduction: Exploiting information in health-related social media services is of great interest for patients, researchers and medical companies. The challenge is, however, to provide easy, quick and relevant access to the vast amount of information that is available. One step towards facilitating information access to online health data is opinion mining. Even though the classification of patient opinions into positive and negative has been previously tackled, most works make use of machine learning methods and bags of words. Our first contribution is an extensive evaluation of different features, including lexical, syntactic, semantic, network-based, sentiment-based and word embeddings features to represent patient-authored texts for polarity classification. The second contribution of this work is the study of polar facts (i.e. objective information with polar connotations). Traditionally, the presence of polar facts has been neglected and research in polarity classification has been bounded to opinionated texts. We demonstrate the existence and importance of polar facts for the polarity classification of health information. Material and methods: We annotate a set of more than 3500 posts to online health forums of breast cancer, crohn and different allergies, respectively. Each sentence in a post is manually labeled as “experience”, “fact” or “opinion”, and as “positive”, “negative” and “neutral”. Using this data, we train different machine learning algorithms and compare traditional bags of words representations with word embeddings in combination with lexical, syntactic, semantic, network-based and emotional properties of texts to automatically classify patient-authored contents into positive, negative and neutral. Beside, we experiment with a combination of textual and semantic representations by generating concept embeddings using the UMLS Metathesaurus. Results: We reach two main results: first, we find that it is possible to predict polarity of patient-authored contents with a very high accuracy (≈ 70 percent) using word embeddings, and that this considerably outperforms more traditional representations like bags of words; and second, when dealing with medical information, negative and positive facts (i.e. objective information) are nearly as frequent as negative and positive opinions and experiences (i.e. subjective information), and their importance for polarity classification is crucial. [ABSTRACT FROM AUTHOR]

In this work, a computer-aided tool for detection was developed to segment breast masses from clinical ultrasound (US) scans. The underlying Multi U-net algorithm is based on convolutional neural networks. Under the Mayo Clinic Institutional Review Board protocol, a prospective study of the automatic segmentation of suspicious breast masses was performed. The cohort consisted of 258 female patients who were clinically identified with suspicious breast masses and underwent clinical US scan and breast biopsy. The computer-aided detection tool effectively segmented the breast masses, achieving a mean Dice coefficient of 0.82, a true positive fraction (TPF) of 0.84, and a false positive fraction (FPF) of 0.01. By avoiding positioning of an initial seed, the algorithm is able to segment images in real time (13–55 ms per image), and can have potential clinical applications. The algorithm is at par with a conventional seeded algorithm, which had a mean Dice coefficient of 0.84 and performs significantly better (P< 0.0001) than the original U-net algorithm. [ABSTRACT FROM AUTHOR]

Wavelet Neural Networks are a combination of neural networks and wavelets and have been mostly used in the area of time-series prediction and control. Recently, Evolutionary Wavelet Neural Networks have been employed to develop cancer prediction models. The present study proposes to use ensembles of Evolutionary Wavelet Neural Networks. The search for a high quality ensemble is directed by a fitness function that incorporates the accuracy of the classifiers both independently and as part of the ensemble itself. The ensemble approach is tested on three publicly available biomedical benchmark datasets, one on Breast Cancer and two on Parkinson’s disease, using a 10-fold cross-validation strategy. Our experimental results show that, for the first dataset, the performance was similar to previous studies reported in literature. On the second dataset, the Evolutionary Wavelet Neural Network ensembles performed better than all previous methods. The third dataset is relatively new and this study is the first to report benchmark results. [ABSTRACT FROM AUTHOR]

We introduce a novel method called Prophetic Granger Causality (PGC) for inferring gene regulatory networks (GRNs) from protein-level time series data. The method uses an L1-penalized regression adaptation of Granger Causality to model protein levels as a function of time, stimuli, and other perturbations. When combined with a data-independent network prior, the framework outperformed all other methods submitted to the HPN-DREAM 8 breast cancer network inference challenge. Our investigations reveal that PGC provides complementary information to other approaches, raising the performance of ensemble learners, while on its own achieves moderate performance. Thus, PGC serves as a valuable new tool in the bioinformatics toolkit for analyzing temporal datasets. We investigate the general and cell-specific interactions predicted by our method and find several novel interactions, demonstrating the utility of the approach in charting new tumor wiring. [ABSTRACT FROM AUTHOR]

Integrative analyses of high-throughput ‘omic data, such as DNA methylation, DNA copy number alteration, mRNA and protein expression levels, have created unprecedented opportunities to understand the molecular basis of human disease. In particular, integrative analyses have been the cornerstone in the study of cancer to determine molecular subtypes within a given cancer. As malignant tumors with similar morphological characteristics have been shown to exhibit entirely different molecular profiles, there has been significant interest in using multiple ‘omic data for the identification of novel molecular subtypes of disease, which could impact treatment decisions. Therefore, we have developed intNMF, an integrative approach for disease subtype classification based on non-negative matrix factorization. The proposed approach carries out integrative clustering of multiple high dimensional molecular data in a single comprehensive analysis utilizing the information across multiple biological levels assessed on the same individual. As intNMF does not assume any distributional form for the data, it has obvious advantages over other model based clustering methods which require specific distributional assumptions. Application of intNMF is illustrated using both simulated and real data from The Cancer Genome Atlas (TCGA). [ABSTRACT FROM AUTHOR]

Scientists have unprecedented access to a wide variety of high-quality datasets. These datasets, which are often independently curated, commonly use unstructured spreadsheets to store their data. Standardized annotations are essential to perform synthesis studies across investigators, but are often not used in practice. Therefore, accurately combining records in spreadsheets from differing studies requires tedious and error-prone human curation. These efforts result in a significant time and cost barrier to synthesis research. We propose an information retrieval inspired algorithm, Synthesize, that merges unstructured data automatically based on both column labels and values. Application of the Synthesize algorithm to cancer and ecological datasets had high accuracy (on the order of 85–100%). We further implement Synthesize in an open source web application, Synthesizer (). The software accepts input as spreadsheets in comma separated value (CSV) format, visualizes the merged data, and outputs the results as a new spreadsheet. Synthesizer includes an easy to use graphical user interface, which enables the user to finish combining data and obtain perfect accuracy. Future work will allow detection of units to automatically merge continuous data and application of the algorithm to other data formats, including databases. [ABSTRACT FROM AUTHOR]

Digital imaging of H&E stained slides has enabled the application of image processing to support pathology workflows. Potential applications include computer-aided diagnostics, advanced quantification tools, and innovative visualization platforms. However, the intrinsic variability of biological tissue and the vast differences in tissue preparation protocols often lead to significant image variability that can hamper the effectiveness of these computational tools. We developed an alternative representation for H&E images that operates within a space that is more amenable to many of these image processing tools. The algorithm to derive this representation operates by exploiting the correlation between color and the spatial properties of the biological structures present in most H&E images. In this way, images are transformed into a structure-centric space in which images are segregated into tissue structure channels. We demonstrate that this framework can be extended to achieve color normalization, effectively reducing inter-slide variability. [ABSTRACT FROM AUTHOR]

Four of the most common limitations of the many available clustering methods are: i) the lack of a proper strategy to deal with outliers; ii) the need for a good a priori estimate of the number of clusters to obtain reasonable results; iii) the lack of a method able to detect when partitioning of a specific data set is not appropriate; and iv) the dependence of the result on the initialization. Here we propose Cross-clustering (CC), a partial clustering algorithm that overcomes these four limitations by combining the principles of two well established hierarchical clustering algorithms: Ward’s minimum variance and Complete-linkage. We validated CC by comparing it with a number of existing clustering methods, including Ward’s and Complete-linkage. We show on both simulated and real datasets, that CC performs better than the other methods in terms of: the identification of the correct number of clusters, the identification of outliers, and the determination of real cluster memberships. We used CC to cluster samples in order to identify disease subtypes, and on gene profiles, in order to determine groups of genes with the same behavior. Results obtained on a non-biological dataset show that the method is general enough to be successfully used in such diverse applications. The algorithm has been implemented in the statistical language R and is freely available from the CRAN contributed packages repository. [ABSTRACT FROM AUTHOR]

DNA methylation is an important epigenetic event that effects gene expression during development and various diseases such as cancer. Understanding the mechanism of action of DNA methylation is important for downstream analysis. In the Illumina Infinium HumanMethylation 450K array, there are tens of probes associated with each gene. Given methylation intensities of all these probes, it is necessary to compute which of these probes are most representative of the gene centric methylation level. In this study, we developed a feature selection algorithm based on sequential forward selection that utilized different classification methods to compute gene centric DNA methylation using probe level DNA methylation data. We compared our algorithm to other feature selection algorithms such as support vector machines with recursive feature elimination, genetic algorithms and ReliefF. We evaluated all methods based on the predictive power of selected probes on their mRNA expression levels and found that a K-Nearest Neighbors classification using the sequential forward selection algorithm performed better than other algorithms based on all metrics. We also observed that transcriptional activities of certain genes were more sensitive to DNA methylation changes than transcriptional activities of other genes. Our algorithm was able to predict the expression of those genes with high accuracy using only DNA methylation data. Our results also showed that those DNA methylation-sensitive genes were enriched in Gene Ontology terms related to the regulation of various biological processes. [ABSTRACT FROM AUTHOR]