MOTIVATION: We introduce a statistical approach for pattern recognition in multivariate spatial transcriptomics data. RESULTS: Our algorithm constructs a projection of the data onto a low-dimensional feature space which is optimal in maximizing Moran's I, a measure of spatial dependency. This projection mitigates non-spatial variation and outperforms principal components analysis for pre-processing. Patterns of spatially variable genes are well represented in this feature space, and their projection can be shown to be a denoising operation. Our framework does not require any parameter tuning, and it furthermore gives rise to a calibrated, powerful test of spatial gene expression. AVAILABILITY AND IMPLEMENTATION: The algorithm is implemented in the open source software R and is available at https://github.com/IMSBCompBio/SpaCo.

Feature selection is crucial for the analysis of high-dimensional data, but benchmark studies for data with a survival outcome are rare. We compare 14 filter methods for feature selection based on 11 high-dimensional gene expression survival data sets. The aim is to provide guidance on the choice of filter methods for other researchers and practitioners. We analyze the accuracy of predictive models that employ the features selected by the filter methods. Also, we consider the run time, the number of selected features for fitting models with high predictive accuracy as well as the feature selection stability. We conclude that the simple variance filter outperforms all other considered filter methods. This filter selects the features with the largest variance and does not take into account the survival outcome. Also, we identify the correlation-adjusted regression scores filter as a more elaborate alternative that allows fitting models with similar predictive accuracy. Additionally, we investigate the filter methods based on feature rankings, finding groups of similar filters.

Over the last years, utilizing deep learning for the analysis of survival data has become attractive to many researchers. This has led to the advent of numerous network architectures for the prediction of possibly censored time-to-event variables. Unlike networks for cross-sectional data (used e.g., in classification), deep survival networks require the specification of a suitably defined loss function that incorporates typical characteristics of survival data such as censoring and time-dependent features. Here, we provide an in-depth analysis of the cross-entropy loss function, which is a popular loss function for training deep survival networks. For each time point t, the cross-entropy loss is defined in terms of a binary outcome with levels "event at or before t" and "event after t". Using both theoretical and empirical approaches, we show that this definition may result in a high prediction error and a heavy bias in the predicted survival probabilities. To overcome this problem, we analyze an alternative loss function that is derived from the negative log-likelihood function of a discrete time-to-event model. We show that replacing the cross-entropy loss by the negative log-likelihood loss results in much better calibrated prediction rules and also in an improved discriminatory power, as measured by the concordance index.

Abstract Random survival forests (RSF) are a powerful nonparametric method for building prediction models with a time-to-event outcome. RSF do not rely on the proportional hazards assumption and can be readily applied to both low- and higher-dimensional data. A remaining limitation of RSF, however, arises from the fact that the method is almost entirely focussed on continuously measured event times. This issue may become problematic in studies where time is measured on a discrete scale $$t = 1, 2, ...$$ t=1,2,... , referring to time intervals $$[0,a_1), [a_1,a_2), \ldots $$ [0,a1),[a1,a2),… . In this situation, the application of methods designed for continuous time-to-event data may lead to biased estimators and inaccurate predictions if discreteness is ignored. To address this issue, we develop a RSF algorithm that is specifically designed for the analysis of (possibly right-censored) discrete event times. The algorithm is based on an ensemble of discrete-time survival trees that operate on transformed versions of the original time-to-event data using tree methods for binary classification. As the outcome variable in these trees is typically highly imbalanced, our algorithm implements a node splitting strategy based on Hellinger’s distance, which is a skew-insensitive alternative to classical split criteria such as the Gini impurity. The new algorithm thus provides flexible nonparametric predictions of individual-specific discrete hazard and survival functions. Our numerical results suggest that node splitting by Hellinger’s distance improves predictive performance when compared to the Gini impurity. Furthermore, discrete-time RSF improve prediction accuracy when compared to RSF approaches treating discrete event times as continuous in situations where the number of time intervals is small.

Graph structured data can be found in an increasing amount of use-cases. While there exists a considerable number of solutions to store graphs in NoSQL databases, the combined storage of relationally stored data with huge graph structured data within the same relational database system is not well researched. We present a relational approach for storing and querying huge property graphs by combining NoSQL features, provided by nearly any state-of-the-art database system, and an adjacency table approach. Our approach is optimized for read-only queries but also performs well on update queries. Through an empirical evaluation we show that we achieve a 10 times higher throughput than previous works on a graph with up to 650 million edges. This way, we can use all the advantages of full-fledged relational database systems and seamlessly integrate classical relational data with graph-structured data in an efficient way.

MOTIVATION: Chromatin immunoprecipitation followed by deep sequencing (ChIP-Seq) is a widely used approach to study protein-DNA interactions. Often, the quantities of interest are the differential occupancies relative to controls, between genetic backgrounds, treatments, or combinations thereof. Current methods for differential occupancy of ChIP-Seq data rely however on binning or sliding window techniques, for which the choice of the window and bin sizes are subjective. RESULTS: Here, we present GenoGAM (Genome-wide Generalized Additive Model), which brings the well-established and flexible generalized additive models framework to genomic applications using a data parallelism strategy. We model ChIP-Seq read count frequencies as products of smooth functions along chromosomes. Smoothing parameters are objectively estimated from the data by cross-validation, eliminating ad hoc binning and windowing needed by current approaches. GenoGAM provides base-level and region-level significance testing for full factorial designs. Application to a ChIP-Seq dataset in yeast showed increased sensitivity over existing differential occupancy methods while controlling for type I error rate. By analyzing a set of DNA methylation data and illustrating an extension to a peak caller, we further demonstrate the potential of GenoGAM as a generic statistical modeling tool for genome-wide assays. AVAILABILITY AND IMPLEMENTATION: Software is available from Bioconductor: https://www.bioconductor.org/packages/release/bioc/html/GenoGAM.html . CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary information is available at Bioinformatics online.

UNLABELLED: Over the past years growing knowledge about biological processes and pathways revealed complex interaction networks involving many genes. In order to understand these networks, analysis of differential expression has continuously moved from single genes towards the study of gene sets. Various approaches for the assessment of gene sets have been developed in the context of gene set analysis (GSA). These approaches are bridging the gap between raw measurements and semantically meaningful terms.We present a novel approach for assessing uncertainty in the definition of gene sets. This is an essential step when new gene sets are constructed from domain knowledge or given gene sets are suspected to be affected by uncertainty. Quantification of uncertainty is implemented in the R-package GiANT. We also included widely used GSA methods, embedded in a generic framework that can readily be extended by custom methods. The package provides an easy to use front end and allows for fast parallelization. AVAILABILITY AND IMPLEMENTATION: The package GiANT is available on CRAN. CONTACTS: [email protected] or [email protected].

BACKGROUND: When constructing new biomarker or gene signature scores for time-to-event outcomes, the underlying aims are to develop a discrimination model that helps to predict whether patients have a poor or good prognosis and to identify the most influential variables for this task. In practice, this is often done fitting Cox models. Those are, however, not necessarily optimal with respect to the resulting discriminatory power and are based on restrictive assumptions. We present a combined approach to automatically select and fit sparse discrimination models for potentially high-dimensional survival data based on boosting a smooth version of the concordance index (C-index). Due to this objective function, the resulting prediction models are optimal with respect to their ability to discriminate between patients with longer and shorter survival times. The gradient boosting algorithm is combined with the stability selection approach to enhance and control its variable selection properties. RESULTS: The resulting algorithm fits prediction models based on the rankings of the survival times and automatically selects only the most stable predictors. The performance of the approach, which works best for small numbers of informative predictors, is demonstrated in a large scale simulation study: C-index boosting in combination with stability selection is able to identify a small subset of informative predictors from a much larger set of non-informative ones while controlling the per-family error rate. In an application to discover biomarkers for breast cancer patients based on gene expression data, stability selection yielded sparser models and the resulting discriminatory power was higher than with lasso penalized Cox regression models. CONCLUSION: The combination of stability selection and C-index boosting can be used to select small numbers of informative biomarkers and to derive new prediction rules that are optimal with respect to their discriminatory power. Stability selection controls the per-family error rate which makes the new approach also appealing from an inferential point of view, as it provides an alternative to classical hypothesis tests for single predictor effects. Due to the shrinkage and variable selection properties of statistical boosting algorithms, the latter tests are typically unfeasible for prediction models fitted by boosting.

BACKGROUND: The analysis of DNA methylation is a key component in the development of personalized treatment approaches. A common way to measure DNA methylation is the calculation of beta values, which are bounded variables of the form M/(M+U) that are generated by Illumina's 450k BeadChip array. The statistical analysis of beta values is considered to be challenging, as traditional methods for the analysis of bounded variables, such as M-value regression and beta regression, are based on regularity assumptions that are often too strong to adequately describe the distribution of beta values. RESULTS: We develop a statistical model for the analysis of beta values that is derived from a bivariate gamma distribution for the signal intensities M and U. By allowing for possible correlations between M and U, the proposed model explicitly takes into account the data-generating process underlying the calculation of beta values. Using simulated data and a real sample of DNA methylation data from the Heinz Nixdorf Recall cohort study, we demonstrate that the proposed model fits our data significantly better than beta regression and M-value regression. CONCLUSION: The proposed model contributes to an improved identification of associations between beta values and covariates such as clinical variables and lifestyle factors in epigenome-wide association studies. It is as easy to apply to a sample of beta values as beta regression and M-value regression.

Recent developments in molecular biology have led to the massive discovery of new marker candidates for the prediction of patient survival. To evaluate the predictive value of these markers, statistical tools for measuring the performance of survival models are needed. We consider estimators of discrimination measures, which are a popular approach to evaluate survival predictions in biomarker studies. Estimators of discrimination measures are usually based on regularity assumptions such as the proportional hazards assumption. Based on two sets of molecular data and a simulation study, we show that violations of the regularity assumptions may lead to over-optimistic estimates of prediction accuracy and may therefore result in biased conclusions regarding the clinical utility of new biomarkers. In particular, we demonstrate that biased medical decision making is possible even if statistical checks indicate that all regularity assumptions are satisfied.

BACKGROUND: With the help of epigenome-wide association studies (EWAS), increasing knowledge on the role of epigenetic mechanisms such as DNA methylation in disease processes is obtained. In addition, EWAS aid the understanding of behavioral and environmental effects on DNA methylation. In terms of statistical analysis, specific challenges arise from the characteristics of methylation data. First, methylation β-values represent proportions with skewed and heteroscedastic distributions. Thus, traditional modeling strategies assuming a normally distributed response might not be appropriate. Second, recent evidence suggests that not only mean differences but also variability in site-specific DNA methylation associates with diseases, including cancer. The purpose of this study was to compare different modeling strategies for methylation data in terms of model performance and performance of downstream hypothesis tests. Specifically, we used the generalized additive models for location, scale and shape (GAMLSS) framework to compare beta regression with Gaussian regression on raw, binary logit and arcsine square root transformed methylation data, with and without modeling a covariate effect on the scale parameter. RESULTS: Using simulated and real data from a large population-based study and an independent sample of cancer patients and healthy controls, we show that beta regression does not outperform competing strategies in terms of model performance. In addition, Gaussian models for location and scale showed an improved performance as compared to models for location only. The best performance was observed for the Gaussian model on binary logit transformed β-values, referred to as M-values. Our results further suggest that models for location and scale are specifically sensitive towards violations of the distribution assumption and towards outliers in the methylation data. Therefore, a resampling procedure is proposed as a mode of inference and shown to diminish type I error rate in practically relevant settings. We apply the proposed method in an EWAS of BMI and age and reveal strong associations of age with methylation variability that are validated in an independent sample. CONCLUSIONS: Models for location and scale are promising tools for EWAS that may help to understand the influence of environmental factors and disease-related phenotypes on methylation variability and its role during disease development.

In an automotive pre-crash application, it is vital to quickly and accurately estimate the position and velocity of objects in the frontal area of the vehicle. To improve such estimations, several radar sensors are fused to detect objects. Due to their different performance characteristics, their measurements can arrive at the pre-crash processing unit out-of-sequence. This work presents several techniques to integrate measurements into a tracking algorithm that arrive with such an out-of-sequence measurement (OOSM) scenario. A comprehensive complexity analysis of the algorithms is also presented. Most importantly, the algorithms are run on a test vehicle during real crash scenarios. The algorithms' performance is evaluated against reference data from a highly accurate laser scanner. It is shown that using advanced OOSM algorithms in pre-crash systems significantly increases performance and reduces computational cost compared to previous approaches.

BACKGROUND: When boosting algorithms are used for building survival models from high-dimensional data, it is common to fit a Cox proportional hazards model or to use least squares techniques for fitting semiparametric accelerated failure time models. There are cases, however, where fitting a fully parametric accelerated failure time model is a good alternative to these methods, especially when the proportional hazards assumption is not justified. Boosting algorithms for the estimation of parametric accelerated failure time models have not been developed so far, since these models require the estimation of a model-specific scale parameter which traditional boosting algorithms are not able to deal with. RESULTS: We introduce a new boosting algorithm for censored time-to-event data which is suitable for fitting parametric accelerated failure time models. Estimation of the predictor function is carried out simultaneously with the estimation of the scale parameter, so that the negative log likelihood of the survival distribution can be used as a loss function for the boosting algorithm. The estimation of the scale parameter does not affect the favorable properties of boosting with respect to variable selection. CONCLUSION: The analysis of a high-dimensional set of microarray data demonstrates that the new algorithm is able to outperform boosting with the Cox partial likelihood when the proportional hazards assumption is questionable. In low-dimensional settings, i.e., when classical likelihood estimation of a parametric accelerated failure time model is possible, simulations show that the new boosting algorithm closely approximates the estimates obtained from the maximum likelihood method.

The business of content providers is being threatened by technology advances in hardware, software and IP-networks such as the Internet or peer-to-peer file sharing systems. The result is an increasing amount of illegal copies available on-line as well as off-line.With the emergence of Digital Rights Management Systems (DRMS), the media and entertainment industry seems to have found the appropriate tool to simultaneously fight piracy and to monetize their assets. Although these systems are very powerful and include multiple protection technologies, it is currently unknown to what extent such systems are used by content providers.This paper provides empirical results, analyses and conclusions related to Digital Rights Management Systems and the protection of digital content in the music, film, and print industries. It outlines the similarities and the differences of usages among the above mentioned industries. The paper concludes that each industry uses different protection technologies and that password and encryption are the most frequently used. The majority of the respondents are satisfied with their current protection but want to enforce it in the future due to fear of increasing piracy. The requirements for DRMS are perceived differently from industry to industry as is the average amount of investment. Furthermore, approximately half of the respondents from the music industry do not believe in the ability of DRMS to reduce piracy, whereas respondents from the film and print industry believe that DRMS will be able to do so.

In this paper, we consider real-time speech traffic, real-time circuit-switched data (CSD) and nonreal-time packet-switched data (PSD) in the UMTS terrestrial radio access network (UTRAN). The focus is on the single low-bandwidth link that interconnects the radio network controller (RNC) and the base station (node B). We show that all traffic on this link has real-time requirements. But we take advantage of the radio link control (RLC) layer protocol and formulate suitable quality of service (QoS) criteria that lead to two different transport service classes (TSC): A stringent TSC for speech traffic and CSD, and a tolerant TSC for PSD. The RNC transmits packets from both TSCs via a single low-bandwidth link to the node B. Since transmission capacity on this interface is a serious cost factor in the UTRAN, the link utilization should be optimized while respecting the QoS requirements of both TSCs. We propose a modified version (MEDF) of the earliest deadline first (EOF) algorithm for that task. In contrast to EDF, the MEDF is easy to implement in hardware and in contrast to algorithms like weighted fair queueing (WFQ), the knowledge of the traffic mix is not needed for a suitable parameter setting in the MEDF scheduler. The simulation results show its superiority over first-in-first-out (FIFO), static priority (SP), and weighted round robin (WRR) scheduling. The analysis of the waiting time distribution explains why MEDF performs better than the other scheduling strategies.