Search

Cardiovascular disease (CVD) is the most important cause of morbidity and mortality worldwide. Early detection, prevention or even prediction is of pivotal importance to reduce the burden of cardiovascular disease and its associated costs. Low cost, consumer-grade smartwatches have the potential to revolutionize cardiovascular medicine by enabling continuous monitoring of heart rate and activity. When combined with machine learning(ML), the resulting large amounts of time series data hold the potential of detection, or exclusion of CVD. However, analyzing such large datasets is challenging due to the sparse presence of informative segments. Efficient selection of these segments is essential for developing predictive models for clinical deployment. The objective of this paper was to investigate the potential of an acceleration-deceleration curvebased ML model as a novel clinical indicator for the detection of cardiovascular diseases. We used data from the ME-TIME study; 42 participants from which 21 have a cardiovascular disease and 21 are health controls. Data from each subject was normalized to decrease inter-subject variability. A neural network model aggregated predictions per week. We showed that per-subject normalization by the peak value of curves during inactivity, aggregation of model predictions over a week, and using a contrastive loss, resulted in a predictive model with 99 % ± 3 % specificity and 40 % ± 49 % sensitivity on the development set, and 100 % specificity with 67 % ± 47 % sensitivity on the test set. Acceleration-deceleration curves are effective patterns for ruling out the presence of cardiovascular disease, but caution must be taken to properly pre-process the curves and carefully choosing a model that reduces the variability in the extracted curves.

BackgroundNon-Invasive Prenatal Testing is often performed by utilizing read coverage-based profiles obtained from shallow whole genome sequencing to detect fetal copy number variations. Such screening typically operates on a discretized binned representation of the genome, where (ab)normality of bins of a set size is judged relative to a reference panel of healthy samples. In practice such approaches are too costly given that for each tested sample they require the resequencing of the reference panel to avoid technical bias. Within-sample testing methods utilize the observation that bins on one chromosome can be judged relative to the behavior of similarly behaving bins on other chromosomes, allowing the bins of a sample to be compared among themselves, avoiding technical bias.ResultsWe present a comprehensive performance analysis of the within-sample testing method Wisecondor and its variants, using both experimental and simulated data. We introduced alterations to Wisecondor to explicitly address and exploit paired-end sequencing data. Wisecondor was found to yield the most stable results across different bin size scales while producing more robust calls by assigning higher Z-scores at all fetal fraction ranges.ConclusionsOur findings show that the most recent available version of Wisecondor performs best.

A digital twin (DT), originally defined as a virtual representation of a physical asset, system, or process, is a new concept in health care. A DT in health care is not a single technology but a domain-adapted multimodal modeling approach incorporating the acquisition, management, analysis, prediction, and interpretation of data, aiming to improve medical decision-making. However, there are many challenges and barriers that must be overcome before a DT can be used in health care. In this viewpoint paper, we build on the current literature, address these challenges, and describe a dynamic DT in health care for optimizing individual patient health care journeys, specifically for women at risk for cardiovascular complications in the preconception and pregnancy periods and across the life course. We describe how we can commit multiple domains to developing this DT. With our cross-domain definition of the DT, we aim to define future goals, trade-offs, and methods that will guide the development of the dynamic DT and implementation strategies in health care.

Background Coeliac disease (CD) is a highly prevalent (∼1%) disease that allegedly remains undiagnosed in over 80% of the cases because of atypical symptoms or silent disease. Currently, it is unknown how GPs deal with (suspected) CD. Objectives This study aimed to better understand the diagnostic approach and the clinical reasoning process of GPs concerning CD and concurrently address diagnostic pitfalls. Methods A questionnaire with case vignettes to assess the knowledge, diagnostic reasoning pattern and practice for CD by GPs was developed. It was sent through academic GP research networks (encompassing over 1500 GPs) in two large cities and to smaller practices in rural areas. The questionnaire was composed of seven background questions, 13 questions related to four case vignettes and six additional CD-related questions Results Responses were received from 106 GPs. Knowledge on risk factors for CD and appropriate testing of at-risk populations was limited. Twenty-two percent would diagnose CD in adults exclusively based on serology, without histopathological confirmation. In total, 99% would refer a newly diagnosed patient to a dietitian to initiate a gluten-free diet (GFD). In the absence of symptoms, only 33% would initiate a GFD. Conclusion The results of this study have given us insight into the diagnostic process of GPs encountering patient with gluten-related complaints. Multiple serology test is available and used, while a positive serology test is not always followed up by a gastroduodenal biopsy to confirm the diagnosis. Most GPs would refer a symptomatic CD patient to a dietician for a GFD.

Abstract The practical use of graph-based reference genomes depends on the ability to align reads to them. Performing substring queries to paths through these graphs lies at the core of this task. The combination of increasing pattern length and encoded variations inevitably leads to a combinatorial explosion of the search space. Instead of heuristic filtering or pruning steps to reduce the complexity, we propose CHOP, a method that constrains the search space by exploiting haplotype information, bounding the search space to the number of haplotypes so that a combinatorial explosion is prevented. We show that CHOP can be applied to large and complex datasets, by applying it on a graph-based representation of the human genome encoding all 80 million variants reported by the 1000 Genomes Project.

Abstract Background In animal breeding, identification of causative genetic variants is of major importance and high economical value. Usually, the number of candidate variants exceeds the number of variants that can be validated. One way of prioritizing probable candidates is by evaluating their potential to have a deleterious effect, e.g. by predicting their consequence. Due to experimental difficulties to evaluate variants that do not cause an amino-acid substitution, other prioritization methods are needed. For human genomes, the prediction of deleterious genomic variants has taken a step forward with the introduction of the combined annotation dependent depletion (CADD) method. In theory, this approach can be applied to any species. Here, we present pCADD (p for pig), a model to score single nucleotide variants (SNVs) in pig genomes. Results To evaluate whether pCADD captures sites with biological meaning, we used transcripts from miRNAs and introns, sequences from genes that are specific for a particular tissue, and the different sites of codons, to test how well pCADD scores differentiate between functional and non-functional elements. Furthermore, we conducted an assessment of examples of non-coding and coding SNVs, which are causal for changes in phenotypes. Our results show that pCADD scores discriminate between functional and non-functional sequences and prioritize functional SNVs, and that pCADD is able to score the different positions in a codon relative to their redundancy. Taken together, these results indicate that based on pCADD scores, regions with biological relevance can be identified and distinguished according to their rate of adaptation. Conclusions We present the ability of pCADD to prioritize SNVs in the pig genome with respect to their putative deleteriousness, in accordance to the biological significance of the region in which they are located. We created scores for all possible SNVs, coding and non-coding, for all autosomes and the X chromosome of the pig reference sequence Sscrofa11.1, proposing a toolbox to prioritize variants and evaluate sequences to highlight new sites of interest to explain biological functions that are relevant to animal breeding.

Abstract The recent boom in microfluidics and combinatorial indexing strategies, combined with low sequencing costs, has empowered single-cell sequencing technology. Thousands—or even millions—of cells analyzed in a single experiment amount to a data revolution in single-cell biology and pose unique data science problems. Here, we outline eleven challenges that will be central to bringing this emerging field of single-cell data science forward. For each challenge, we highlight motivating research questions, review prior work, and formulate open problems. This compendium is for established researchers, newcomers, and students alike, highlighting interesting and rewarding problems for the coming years.

BackgroundWearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention. ObjectiveThis study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology. MethodsWe searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as “wearables,” “machine learning,” and “cardiovascular disease.” Methodologies were categorized and analyzed according to machine learning–based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready). ResultsAfter the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL

Computationally annotating proteins with a molecular function is a difficult problem that is made even harder due to the limited amount of available labeled protein training data. Unsupervised protein embeddings partly circumvent this limitation by learning a universal protein representation from many unlabeled sequences. Such embeddings incorporate contextual information of amino acids, thereby modeling the underlying principles of protein sequences insensitive to the context of species. We used an existing pre-trained protein embedding method and subjected its molecular function prediction performance to detailed characterization, first to advance the understanding of protein language models, and second to determine areas of improvement. Then, we applied the model in a transfer learning task by training a function predictor based on the embeddings of annotated protein sequences of one training species and making predictions on the proteins of several test species with varying evolutionary distance. We show that this approach successfully generalizes knowledge about protein function from one eukaryotic species to various other species, outperforming both an alignment-based and a supervised-learning-based baseline. This implies that such a method could be effective for molecular function prediction in inadequately annotated species from understudied taxonomic kingdoms.

The availability of genomes for many species has advanced our understanding of the non-protein-coding fraction of the genome. Comparative genomics has proven itself to be an invaluable approach for the systematic, genome-wide identification of conserved non-protein-coding elements (CNEs). However, for many non-mammalian model species, including chicken, our capability to interpret the functional importance of variants overlapping CNEs has been limited by current genomic annotations, which rely on a single information type (e.g. conservation). We here studied CNEs in chicken using a combination of population genomics and comparative genomics. To investigate the functional importance of variants found in CNEs we develop a ch(icken) Combined Annotation-Dependent Depletion (chCADD) model, a variant effect prediction tool first introduced for humans and later on for mouse and pig. We show that 73 Mb of the chicken genome has been conserved across more than 280 million years of vertebrate evolution. The vast majority of the conserved elements are in non-protein-coding regions, which display SNP densities and allele frequency distributions characteristic of genomic regions constrained by purifying selection. By annotating SNPs with the chCADD score we are able to pinpoint specific subregions of the CNEs to be of higher functional importance, as supported by SNPs found in these subregions are associated with known disease genes in humans, mice, and rats. Taken together, our findings indicate that CNEs harbor variants of functional significance that should be object of further investigation along with protein-coding mutations. We therefore anticipate chCADD to be of great use to the scientific community and breeding companies in future functional studies in chicken.

Physical interaction between two proteins is strong evidence that the proteins are involved in the same biological process, making Protein-Protein Interaction (PPI) networks a valuable data resource for predicting the cellular functions of proteins. However, PPI networks are largely incomplete for non-model species. Here, we tested to what extent these incomplete networks are still useful for genome-wide function prediction. We used two network-based classifiers to predict Biological Process Gene Ontology terms from protein interaction data in four species: Saccharomyces cerevisiae, Escherichia coli, Arabidopsis thaliana and Solanum lycopersicum (tomato). The classifiers had reasonable performance in the well-studied yeast, but performed poorly in the other species. We showed that this poor performance can be considerably improved by adding edges predicted from various data sources, such as text mining, and that associations from the STRING database are more useful than interactions predicted by a neural network from sequence-based features.

Several studies have analyzed gene expression profiles in the substantia nigra to better understand the pathological mechanisms causing Parkinson’s disease (PD). However, the concordance between the identified gene signatures in these individual studies was generally low. This might have been caused by a change in cell type composition as loss of dopaminergic neurons in the substantia nigra pars compacta is a hallmark of PD. Through an extensive meta-analysis of nine previously published microarray studies, we demonstrated that a big proportion of the detected differentially expressed genes was indeed caused by cyto-architectural alterations due to the heterogeneity in the neurodegenerative stage and/or technical artefacts. After correcting for cell composition, we identified a common signature that deregulated the previously unreported ammonium transport, as well as known biological processes such as bioenergetic pathways, response to proteotoxic stress, and immune response. By integrating with protein interaction data, we shortlisted a set of key genes, such as LRRK2, PINK1, PRKN, and FBXO7, known to be related to PD, others with compelling evidence for their role in neurodegeneration, such as GSK3β, WWOX, and VPC, and novel potential players in the PD pathogenesis. Together, these data show the importance of accounting for cyto-architecture in these analyses and highlight the contribution of multiple cell types and novel processes to PD pathology, providing potential new targets for drug development.

Abstract Background Predicting the deleteriousness of observed genomic variants has taken a step forward with the introduction of the Combined Annotation Dependent Depletion (CADD) approach, which trains a classifier on the wealth of available human genomic information. This raises the question whether it can be done with less data for non-human species. Here, we investigate the prerequisites to construct a CADD-based model for a non-human species. Results Performance of the mouse model is competitive with that of the human CADD model and better than established methods like PhastCons conservation scores and SIFT. Like in the human case, performance varies for different genomic regions and is best for coding regions. We also show the benefits of generating a species-specific model over lifting variants to a different species or applying a generic model. With fewer genomic annotations, performance on the test set as well as on the three validation sets is still good. Conclusions It is feasible to construct species-specific CADD models even when annotations such as epigenetic markers are not available. The minimal requirement for these models is the availability of a set of genomes of closely related species that can be used to infer an ancestor genome and substitution rates for the data generation.

In prenatal diagnostics, NIPT screening utilizing read coverage-based profiles obtained from shallow WGS data is routinely used to detect fetal CNVs. From this same data, fragment size distributions of fetal and maternal DNA fragments can be derived, which are known to be different, and often used to infer fetal fractions. We argue that the fragment size has the potential to aid in the detection of CNVs. By integrating, in parallel, fragment size and read coverage in a within-sample normalization approach, it is possible to construct a reference set encompassing both data types. This reference then allows the detection of CNVs within queried samples, utilizing both data sources. We present a new methodology, WisecondorFF, which improves sensitivity, while maintaining specificity, relative to existing approaches. WisecondorFF increases robustness of detected CNVs, and can reliably detect even at lower fetal fractions (

The three dimensional conformation of the genome in the cell nucleus influences important biological processes such as gene expression regulation. Recent studies have shown a strong correlation between chromatin interactions and gene co-expression. However, predicting gene co-expression from frequent long-range chromatin interactions remains challenging. We address this by characterizing the topology of the cortical chromatin interaction network using scale-aware topological measures. We demonstrate that based on these characterizations it is possible to accurately predict spatial co-expression between genes in the mouse cortex. Consistent with previous findings, we find that the chromatin interaction profile of a gene-pair is a good predictor of their spatial co-expression. However, the accuracy of the prediction can be substantially improved when chromatin interactions are described using scale-aware topological measures of the multi-resolution chromatin interaction network. We conclude that, for co-expression prediction, it is necessary to take into account different levels of chromatin interactions ranging from direct interaction between genes (i.e. small-scale) to chromatin compartment interactions (i.e. large-scale).

Human aging is associated with loss of function and regenerative capacity. Human bone marrow derived mesenchymal stromal cells (hMSCs) are involved in tissue regeneration, evidenced by their capacity to differentiate into several lineages and therefore are considered the golden standard for cell-based regeneration therapy. Tissue maintenance and regeneration is dependent on stem cells and declines with age and aging is thought to influence therapeutic efficacy, therefore, more insight in the process of aging of hMSCs is of high interest. We, therefore, hypothesized that hMSCs might reflect signs of aging. In order to find markers for donor age, early passage hMSCs were isolated from bone marrow of 61 donors, with ages varying from 17-84, and clinical parameters, in vitro characteristics and microarray analysis were assessed. Although clinical parameters and in vitro performance did not yield reliable markers for aging since large donor variations were present, genome-wide microarray analysis resulted in a considerable list of genes correlating with human age. By comparing the transcriptional profile of aging in human with the one from rat, we discovered follistatin as a common marker for aging in both species. The gene signature presented here could be a useful tool for drug testing to rejuvenate hMSCs or for the selection of more potent, hMSCs for cell-based therapy.

Tumorigenesis is a multi-step process in which normal cells transform into malignant tumors following the accumulation of genetic mutations that enable them to evade the growth control checkpoints that would normally suppress their growth or result in apoptosis. It is therefore important to identify those combinations of mutations that collaborate in cancer development and progression. DNA copy number alterations (CNAs) are one of the ways in which cancer genes are deregulated in tumor cells. We hypothesized that synergistic interactions between cancer genes might be identified by looking for regions of co-occurring gain and/or loss. To this end we developed a scoring framework to separate truly co-occurring aberrations from passenger mutations and dominant single signals present in the data. The resulting regions of high co-occurrence can be investigated for between-region functional interactions. Analysis of high-resolution DNA copy number data from a panel of 95 hematological tumor cell lines correctly identified co-occurring recombinations at the T-cell receptor and immunoglobulin loci in T- and B-cell malignancies, respectively, showing that we can recover truly co-occurring genomic alterations. In addition, our analysis revealed networks of co-occurring genomic losses and gains that are enriched for cancer genes. These networks are also highly enriched for functional relationships between genes. We further examine sub-networks of these networks, core networks, which contain many known cancer genes. The core network for co-occurring DNA losses we find seems to be independent of the canonical cancer genes within the network. Our findings suggest that large-scale, low-intensity copy number alterations may be an important feature of cancer development or maintenance by affecting gene dosage of a large interconnected network of functionally related genes.

Retroviral insertional mutagenesis screens, which identify genes involved in tumor development in mice, have yielded a substantial number of retroviral integration sites, and this number is expected to grow substantially due to the introduction of high-throughput screening techniques. The data of various retroviral insertional mutagenesis screens are compiled in the publicly available Retroviral Tagged Cancer Gene Database (RTCGD). Integrally analyzing these screens for the presence of common insertion sites (CISs, i.e., regions in the genome that have been hit by viral insertions in multiple independent tumors significantly more than expected by chance) requires an approach that corrects for the increased probability of finding false CISs as the amount of available data increases. Moreover, significance estimates of CISs should be established taking into account both the noise, arising from the random nature of the insertion process, as well as the bias, stemming from preferential insertion sites present in the genome and the data retrieval methodology. We introduce a framework, the kernel convolution (KC) framework, to find CISs in a noisy and biased environment using a predefined significance level while controlling the family-wise error (FWE) (the probability of detecting false CISs). Where previous methods use one, two, or three predetermined fixed scales, our method is capable of operating at any biologically relevant scale. This creates the possibility to analyze the CISs in a scale space by varying the width of the CISs, providing new insights in the behavior of CISs across multiple scales. Our method also features the possibility of including models for background bias. Using simulated data, we evaluate the KC framework using three kernel functions, the Gaussian, triangular, and rectangular kernel function. We applied the Gaussian KC to the data from the combined set of screens in the RTCGD and found that 53% of the CISs do not reach the significance threshold in this combined setting. Still, with the FWE under control, application of our method resulted in the discovery of eight novel CISs, which each have a probability less than 5% of being false detections.

Abstract  We introduce personalization on Tribler, a peer-to-peer (P2P) television system. Personalization allows users to browse programs much more efficiently according to their taste. It also enables to build social networks that can improve the performance of current P2P systems considerably, by increasing content availability, trust and the realization of proper incentives to exchange content. This paper presents a novel scheme, called BuddyCast, that builds such a social network for a user by exchanging user interest profiles using exploitation and exploration principles. Additionally, we show how the interest of a user in TV programs can be predicted from the zapping behavior by the introduced user-item relevance models, thereby avoiding the explicit rating of TV programs. Further, we present how the social network of a user can be used to realize a truly distributed recommendation of TV programs. Finally, we demonstrate a novel user interface for the personalized peer-to-peer television system that encompasses a personalized tag-based navigation to browse the available distributed content. The user interface also visualizes the social network of a user, thereby increasing community feeling which increases trust amongst users and within available content and creates incentives of to exchange content within the community. [ABSTRACT FROM AUTHOR]

Motivation: Cancers are caused by an accumulation of multiple independent mutations that collectively deregulate cellular pathways, e.g. such as those regulating cell division and cell-death. The publicly available Retroviral Tagged Cancer Gene Database (RTCGD) contains the data of many insertional mutagenesis screens, in which the virally induced mutations result in tumor formation in mice. The insertion loci therefore indicate the location of putative cancer genes. Additionally, the presence of multiple independent insertions within one tumor hints towards a cooperation between the insertionally mutated genes. In this study we focus on the detection of statistically significant co-mutations. Results: We propose a two-dimensional Gaussian Kernel Convolution method (2DGKC), a computational technique that identifies the cooperating mutations in insertional mutagenesis data. We define the Common Co-occurrence of Insertions (CCI), signifying the co-mutations that are statistically significant across all different screens in the RTCGD. Significance estimates are made on multiple scales, and the results visualized in a scale space, thereby providing valuable extra information on the putative cooperation. The multidimensional analysis of the insertion data results in the discovery of 86 statistically significant co-mutations, indicating the presence of cooperating oncogenes that play a role in tumor development. Since oncogenes may cooperate with several members of a parallel pathway, we combined the co-occurrence data with gene family information to find significant cooperations between oncogenes and families of genes. We show, for instance, the interchangeable cooperation of Myc insertions with insertions in the Pim family. Availability: A list of the resulting CCIs is available at: http://ict.ewi.tudelft.nl/~jeroen/CCI/CCI_list.txt Contact: m.j.t.reinders@tudelft.nl [ABSTRACT FROM AUTHOR]