Search

Background Identifying gene interactions is a topic of great importance in genomics, and approaches based on network models provide a powerful tool for studying these. Assuming a Gaussian graphical model, a gene association network may be estimated from multiomic data based on the non-zero entries of the inverse covariance matrix. Inferring such biological networks is challenging because of the high dimensionality of the problem, making traditional estimators unsuitable. The graphical lasso is constructed for the estimation of sparse inverse covariance matrices in such situations, using $$L_1$$ L 1 -penalization on the matrix entries. The weighted graphical lasso is an extension in which prior biological information from other sources is integrated into the model. There are however issues with this approach, as it naïvely forces the prior information into the network estimation, even if it is misleading or does not agree with the data at hand. Further, if an associated network based on other data is used as the prior, the method often fails to utilize the information effectively. Results We propose a novel graphical lasso approach, the tailored graphical lasso, that aims to handle prior information of unknown accuracy more effectively. We provide an R package implementing the method, . Applying the method to both simulated and real multiomic data sets, we find that it outperforms the unweighted and weighted graphical lasso in terms of all performance measures we consider. In fact, the graphical lasso and weighted graphical lasso can be considered special cases of the tailored graphical lasso, and a parameter determined by the data measures the usefulness of the prior information. We also find that among a larger set of methods, the tailored graphical is the most suitable for network inference from high-dimensional data with prior information of unknown accuracy. With our method, mRNA data are demonstrated to provide highly useful prior information for protein–protein interaction networks. Conclusions The method we introduce utilizes useful prior information more effectively without involving any risk of loss of accuracy should the prior information be misleading.

In many statistical regression and prediction problems, it is reasonable to assume monotone relationships between certain predictor variables and the outcome. Genomic effects on phenotypes are, for instance, often assumed to be monotone. However, in some settings, it may be reasonable to assume a partially linear model, where some of the covariates can be assumed to have a linear effect. One example is a prediction model using both high-dimensional gene expression data, and low-dimensional clinical data, or when combining continuous and categorical covariates. We study methods for fitting the partially linear monotone model, where some covariates are assumed to have a linear effect on the response, and some are assumed to have a monotone (potentially nonlinear) effect. Most existing methods in the literature for fitting such models are subject to the limitation that they have to be provided the monotonicity directions a priori for the different monotone effects. We here present methods for fitting partially linear monotone models which perform both automatic variable selection, and monotonicity direction discovery. The proposed methods perform comparably to, or better than, existing methods, in terms of estimation, prediction, and variable selection performance, in simulation experiments in both classical and high-dimensional data settings.

The generation and systematic collection of genome-wide data is ever-increasing. This vast amount of data has enabled researchers to study relations between a variety of genomic and epigenomic features, including genetic variation, gene regulation and phenotypic traits. Such relations are typically investigated by comparatively assessing genomic co-occurrence. Technically, this corresponds to assessing the similarity of pairs of genome-wide binary vectors. A variety of similarity measures have been proposed for this problem in other fields like ecology. However, while several of these measures have been employed for assessing genomic co-occurrence, their appropriateness for the genomic setting has never been investigated. We show that the choice of similarity measure may strongly influence results and propose two alternative modelling assumptions that can be used to guide this choice. On both simulated and real genomic data, the Jaccard index is strongly altered by dataset size and should be used with caution. The Forbes coefficient (fold change) and tetrachoric correlation are less influenced by dataset size, but one should be aware of increased variance for small datasets. All results on simulated and real data can be inspected and reproduced at https://hyperbrowser.uio.no/sim-measure.

BackgroundIdentifying gene interactions is a topic of great importance in genomics, and approaches based on network models provide a powerful tool for studying these. Assuming a Gaussian graphical model, a gene association network may be estimated from multiomic data based on the non-zero entries of the inverse covariance matrix. Inferring such biological networks is challenging because of the high dimensionality of the problem, making traditional estimators unsuitable. The graphical lasso is constructed for the estimation of sparse inverse covariance matrices in Gaussian graphical models in such situations, using L1-penalization on the matrix entries. An extension of the graphical lasso is the weighted graphical lasso, in which prior biological information from other (data) sources is integrated into the model through the weights. There are however issues with this approach, as it naïvely forces the prior information into the network estimation, even if it is misleading or does not agree with the data at hand. Further, if an associated network based on other data is used as the prior, weighted graphical lasso often fails to utilize the information effectively.ResultsWe propose a novel graphical lasso approach, the tailored graphical lasso, that aims to handle prior information of unknown accuracy more effectively. We provide an R package implementing the method, tailoredGlasso. Applying the method to both simulated and real multiomic data sets, we find that it outperforms the unweighted and weighted graphical lasso in terms of all performance measures we consider. In fact, the graphical lasso and weighted graphical lasso can be considered special cases of the tailored graphical lasso, and a parameter determined by the data measures the usefulness of the prior information. With our method, mRNA data are demonstrated to provide highly useful prior information for protein-protein interaction networks.ConclusionsThe method we introduce utilizes useful prior information more effectively without involving any risk of loss of accuracy should the prior information be misleading.

Graph-based representations are considered to be the future for reference genomes, as they allow integrated representation of the steadily increasing data on individual variation. Currently available tools allow de novo assembly of graph-based reference genomes, alignment of new read sets to the graph representation as well as certain analyses like variant calling and haplotyping. We here present a first method for calling ChIP-Seq peaks on read data aligned to a graph-based reference genome. The method is a graph generalization of the peak caller MACS2, and is implemented in an open source tool, Graph Peak Caller. By using the existing tool vg to build a pan-genome of Arabidopsis thaliana, we validate our approach by showing that Graph Peak Caller with a pan-genome reference graph can trace variants within peaks that are not part of the linear reference genome, and find peaks that in general are more motif-enriched than those found by MACS2., Author summary The expression of genes is a tightly regulated process. A key regulatory mechanism is the modulation of transcription by a class of proteins called transcription factors that bind to DNA in the spatial proximity of regulated genes. Determining the binding locations of transcription factors for specific cell types and settings is thus a key step in understanding the dynamics of normal cells as well as disease states. Binding sites for a given transcription factor are typically obtained through an experimental technique called CHiP-seq, in which DNA binding locations are obtained by sequencing DNA fragments attached to the transcription factor and aligning these sequences to a reference genome. A computational technique known as peak calling is then used to separate signal from noise and predict where the protein binds. Current peak callers are based on linear reference genomes that do not contain known genetic variants from the population. They thus potentially miss cases where proteins bind to such alternative genome sequences. Recently, a new type of reference genomes based on graph representations have become popular, as they are able to also incorporate alternative genome sequences. We here present Graph Peak Caller, the first peak caller that is able to exploit such graph representations for the detection of transcription factor binding locations. Using a graph-based reference genome for Arabidopsis thaliana, we show that our peak caller can lead to better detection of transcription factor binding locations as compared to a similar existing peak caller that uses a linear reference genome representation.

We propose novel modifications to an anomaly detection methodology based on multivariate signal reconstruction followed by residuals analysis. The reconstructions are made using Auto Associative Kernel Regression (AAKR), where the query observations are compared to historical observations called memory vectors, representing normal operation. When the data set with historical observations grows large, the naive approach where all observations are used as memory vectors will lead to unacceptable large computational loads, hence a reduced set of memory vectors should be intelligently selected. The residuals between the observed and the reconstructed signals are analysed using standard Sequential Probability Ratio Tests (SPRT), where appropriate alarms are raised based on the sequential behaviour of the residuals. The modifications we introduce include: a novel cluster based method to select memory vectors to be considered by the AAKR, which gives an extensive reduction in computation time; a generalization of the distance measure, which makes it possible to distinguish between explanatory and response variables; and a regional credibility estimation used in the residuals analysis, to let the time used to identify if a sequence of query vectors represents an anomalous state or not, depend on the amount of data situated close to or surrounding the query vector. We demonstrate how the anomaly detection method and the proposed modifications can be successfully applied for anomaly detection on a set of imbalanced benchmark data sets, as well as on recent data from a marine diesel engine in operation.

In numerous problems where the aim is to estimate the effect of a predictor variable on a response, one can assume a monotone relationship. For example, dose-effect models in medicine are of this type. In a multiple regression setting, additive monotone regression models assume that each predictor has a monotone effect on the response. In this paper, we present an overview and comparison of very recent frequentist methods for fitting additive monotone regression models. Three of the methods we present can be used both in the high dimensional setting, where the number of parameters $p$ exceeds the number of observations $n$, and in the classical multiple setting where $1

BackgroundThe generation and systematic collection of genome-wide data is ever-increasing. This vast amount of data has enabled researchers to study relations between a variety of genomic and epigenomic features, including genetic variation, gene regulation, and phenotypic traits. Such relations are typically investigated by comparatively assessing genomic co-occurrence. Technically, this corresponds to assessing the similarity of pairs of genome-wide binary vectors. A variety of metrics have been proposed for this problem in other fields like ecology. However, while several of these metrics have been employed for assessing genomic co-occurrence, their appropriateness for the genomic setting has never been investigated.ResultsWe show that the choice of metric may strongly influence results and propose two alternative modelling assumptions that can be used to guide this choice. On both simulated and real genomic data, the Jaccard index is strongly affected by dataset size and should be used with caution. The Forbes coefficient (fold change) and tetrachoric correlation are less affected by dataset size, but one should be aware of increased variance for small datasets.AvailabilityAll results on simulated and real data can be inspected and reproduced athttps://hyperbrowser.uio.no/sim-measure

The continuous growth in maritime traffic and recent developments towards autonomous navigation have directed increasing attention to navigational safety in which new tools are required to identify real-time risk and complex navigation situations. These tools are of paramount importance to avoid potentially disastrous consequences of accidents and promote safe navigation at sea. In this study, an adaptive ship-safety-domain is proposed with spatial risk functions to identify both collision and grounding risk based on motion and maneuverability conditions for all vessels. The algorithm is designed and validated through extensive amounts of Automatic Identification System (AIS) data for decision support over a large area, while the integration of the algorithm with other navigational systems will increase effectiveness and ensure reliability. Since a successful evacuation of a potential vessel-to-vessel collision, or a vessel grounding situation, is highly dependent on the nearby maneuvering limitations and other possible accident situations, multi-vessel collision and grounding risk is considered in this work to identify real-time risk. The presented algorithm utilizes and exploits dynamic AIS information, vessel registry and high-resolution maps and it is robust to inaccuracies of position, course and speed over ground records. The computation-efficient algorithm allows for real-time situation risk identification at a large-scale monitored map up to country level and up to several years of operation with a very high accuracy.

Background Using high-dimensional penalized regression we studied genome-wide DNA-methylation in bone biopsies of 80 postmenopausal women in relation to their bone mineral density (BMD). The women showed BMD varying from severely osteoporotic to normal. Global gene expression data from the same individuals was available, and since DNA-methylation often affects gene expression, the overall aim of this paper was to include both of these omics data sets into an integrated analysis. Methods The classical penalized regression uses one penalty, but we incorporated individual penalties for each of the DNA-methylation sites. These individual penalties were guided by the strength of association between DNA-methylations and gene transcript levels. DNA-methylations that were highly associated to one or more transcripts got lower penalties and were therefore favored compared to DNA-methylations showing less association to expression. Because of the complex pathways and interactions among genes, we investigated both the association between DNA-methylations and their corresponding cis gene, as well as the association between DNA-methylations and trans-located genes. Two integrating penalized methods were used: first, an adaptive group-regularized ridge regression, and secondly, variable selection was performed through a modified version of the weighted lasso. Results When information from gene expressions was integrated, predictive performance was considerably improved, in terms of predictive mean square error, compared to classical penalized regression without data integration. We found a 14.7% improvement in the ridge regression case and a 17% improvement for the lasso case. Our version of the weighted lasso with data integration found a list of 22 interesting methylation sites. Several corresponded to genes that are known to be important in bone formation. Using BMD as response and these 22 methylation sites as covariates, least square regression analyses resulted in R2=0.726, comparable to an average R2=0.438 for 10000 randomly selected groups of DNA-methylations with group size 22. Conclusions Two recent types of penalized regression methods were adapted to integrate DNA-methylation and their association to gene expression in the analysis of bone mineral density. In both cases predictions clearly benefit from including the additional information on gene expressions.

In this paper we propose a cluster based version of the anomaly detection methodology based on signal reconstruction, using Auto Associative Kernel Regression (AAKR), combined with residuals analysis, using Sequential Probability Ratio Test (SPRT). We demonstrate how the proposed cluster based methodology can be successfully applied for anomaly detection on a marine diesel engine in operation. Furthermore, we demonstrate the vast reduction in computation time compared to the original framework, and discuss other possible advantages and disadvantages of the proposed methodology.

Background: Recent large-scale undertakings such as ENCODE and Roadmap Epigenomics have generated experimental data mapped to the human reference genome (as genomic tracks) representing a variety of functional elements across a large number of cell types. Despite the high potential value of these publicly available data for a broad variety of investigations, little attention has been given to the analytical methodology necessary for their widespread utilisation. Findings: We here present a first principled treatment of the analysis of collections of genomic tracks. We have developed novel computational and statistical methodology to permit comparative and confirmatory analyses across multiple and disparate data sources. We delineate a set of generic questions that are useful across a broad range of investigations and discuss the implications of choosing different statistical measures and null models. Examples include contrasting analyses across different tissues or diseases. The methodology has been implemented in a comprehensive open-source software system, the GSuite HyperBrowser. To make the functionality accessible to biologists, and to facilitate reproducible analysis, we have also developed a web-based interface providing an expertly guided and customizable way of utilizing the methodology. With this system, many novel biological questions can flexibly be posed and rapidly answered. Conclusions: Through a combination of streamlined data acquisition, interoperable representation of dataset collections, and customizable statistical analysis with guided setup and interpretation, the GSuite HyperBrowser represents a first comprehensive solution for integrative analysis of track collections across the genome and epigenome. The software is available at: https://hyperbrowser.uio.no., This work was supported by the Research Council of Norway (under grant agreements 221580, 218241, and 231217/F20), by the Norwegian Cancer Society (under grant agreements 71220’PR-2006-0433 and 3485238-2013), and by the South-Eastern Norway Regional Health Authority (under grant agreement 2014041).

DNA methylation affects expression of associated genes and may contribute to the missing genetic effects from genome-wide association studies of osteoporosis. To improve insight into the mechanisms of postmenopausal osteoporosis, we combined transcript profiling with DNA methylation analyses in bone. RNA and DNA were isolated from 84 bone biopsies of postmenopausal donors varying markedly in bone mineral density (BMD). In all, 2529 CpGs in the top 100 genes most significantly associated with BMD were analyzed. The methylation levels at 63 CpGs differed significantly between healthy and osteoporotic women at 10% false discovery rate (FDR). Five of these CpGs at 5% FDR could explain 14% of BMD variation. To test whether blood DNA methylation reflect the situation in bone (as shown for other tissues), an independent cohort was selected and BMD association was demonstrated in blood for 13 of the 63 CpGs. Four transcripts representing inhibitors of bone metabolism—MEPE, SOST, WIF1, and DKK1—showed correlation to a high number of methylated CpGs, at 5% FDR. Our results link DNA methylation to the genetic influence modifying the skeleton, and the data suggest a complex interaction between CpG methylation and gene regulation. This is the first study in the hitherto largest number of postmenopausal women to demonstrate a strong association among bone CpG methylation, transcript levels, and BMD/fracture. This new insight may have implications for evaluation of osteoporosis stage and susceptibility. The final version of this research has been published in Epigenetics. © 2017 Taylor & Francis

Background It has been proposed that future reference genomes should be graph structures in order to better represent the sequence diversity present in a species. However, there is currently no standard method to represent genomic intervals, such as the positions of genes or transcription factor binding sites, on graph-based reference genomes. Results We formalize offset-based coordinate systems on graph-based reference genomes and introduce methods for representing intervals on these reference structures. We show the advantage of our methods by representing genes on a graph-based representation of the newest assembly of the human genome (GRCh38) and its alternative loci for regions that are highly variable. Conclusion More complex reference genomes, containing alternative loci, require methods to represent genomic data on these structures. Our proposed notation for genomic intervals makes it possible to fully utilize the alternative loci of the GRCh38 assembly and potential future graph-based reference genomes. We have made a Python package for representing such intervals on offset-based coordinate systems, available at https://github.com/uio-cels/offsetbasedgraph . An interactive web-tool using this Python package to visualize genes on a graph created from GRCh38 is available at https://github.com/uio-cels/genomicgraphcoords .

Watson and Holmes propose ways of investigating robustness of statistical decisions by examining certain neighbourhoods around a posterior distribution. This may partly amount to ad hoc modelling of extra uncertainty. Instead of creating neighbourhoods around the posterior a posteriori, we argue that it might be more fruitful to model a layer of extra uncertainty first, in the model building process, and then allow the data to determine how big the resulting neighbourhoods ought to be. We develop and briefly illustrate a general strategy along such lines.

Genome-wide, cell-type-specific profiles are being systematically generated for numerous genomic and epigenomic features. There is, however, no universally applicable analytical methodology for such data. We present GSuite HyperBrowser, the first comprehensive solution for integrative analysis of dataset collections across the genome and epigenome. The GSuite HyperBrowser is an open-source system for streamlined acquisition and customizable statistical analysis of large collections of genome-wide datasets. The system is based on new computational and statistical methodologies that permit comparative and confirmatory analyses across multiple disparate data sources. Expert guidance and reproducibility are facilitated via a Galaxy-based web-interface. The software is available athttps://hyperbrowser.uio.no/gsuite

In this paper we present an application of sensorbased anomaly detection in maritime transport. The study is based on real sensor data streamed from a ship to shore, where the data is analysed through a big data analytics platform. The novelty of this work originates in the use of data from sensors covering different aspects of the ship operation, exemplified here by propulsion power, speed over ground and ship motion in four different degrees of freedom. The developed method employs Auto Associative Kernel Regression (AAKR) for signal reconstruction, and the Sequential Probability Ratio Test (SPRT) technique for anomaly detection, where different hypothesis tests looking both at mean and variance deviations have been tested. In order to compare different settings, formal state of the art performance metrics have been used. We demonstrate that the AAKR model produces good reconstructions when the observations are similar to observations represented in the training data, and for some examples of simulated anomalies, the method reveals the abnormal behaviour. As long as the parameters are tuned carefully, alarms are triggered appropriately by the SPRT.

We address the issue of variable preselection in high-dimensional penalized regression, such as the lasso, a commonly used approach to variable selection and prediction in genomics. Preselection—to start with a manageable set of covariates—is becoming increasingly necessary for enabling advanced analysis tasks to be carried out on data sets of huge size created by high throughput technologies. Preselection of features to be included in multivariate analyses based on simple univariate ranking is a natural strategy that has often been implemented despite its potential bias. We demonstrate this bias and propose a way to correct it. Starting with a sequential implementation of the lasso with increasing lists of predictors, we exploit a property of the set of corresponding cross-validation curves, a pattern that we call “freezing”. The ranking of the predictors to be included sequentially is based on simple measures of associations with the outcome, which can be pre-computed in an efficient way for ultra high dimensional data sets externally to the penalized regression implementation. We demonstrate by simulation that our sequential approach leads in a vast majority of cases to a safe and efficient way of focusing the lasso analysis on a smaller and manageable number of predictors. In situations where the lasso performs well, we need typically less than 20 % of the variables to recover the same solution as if using the full set of variables. We illustrate the applicability of our strategy in the context of a genome-wide association study and on microarray genomic data where we need just 2. 5 % and 13 % of the variables respectively. Finally we include an example where 260 million gene-gene interactions are ranked and we are able to recover the lasso solution using only 1 % of these. Freezing offers great potential for extending the applicability of penalized regressions to current and upcoming ultra high dimensional problems in bioinformatics. Its applicability is not limited to the standard lasso but is a generic property of many penalized approaches.

The symposium covered a broad spectrum of themes on High-Dimensional Statistics. We present here a short overview of some of the topics discussed at the symposium: high-dimensional inference in regression, high-dimensional causal inference, Bayesian variable selection for high-dimensional analysis, and integration of multiple high-dimensional data, but this categorization is not exhaustive. The contributions by some of the participants, appearing as chapters in the book, include both in-depth reviews and development of new statistical methodology, applications and theory.