The Poisson distribution model fits UMI-based single-cell RNA-sequencing data.

BACKGROUND: Modeling of single cell RNA-sequencing (scRNA-seq) data remains challenging due to a high percentage of zeros and data heterogeneity, so improved modeling has strong potential to benefit many downstream data analyses. The existing zero-inflated or over-dispersed models are based on aggregations at either the gene or the cell level. However, they typically lose accuracy due to a too crude aggregation at those two levels. RESULTS: We avoid the crude approximations entailed by such aggregation through proposing an independent Poisson distribution (IPD) particularly at each individual entry in the scRNA-seq data matrix. This approach naturally and intuitively models the large number of zeros as matrix entries with a very small Poisson parameter. The critical challenge of cell clustering is approached via a novel data representation as Departures from a simple homogeneous IPD (DIPD) to capture the per-gene-per-cell intrinsic heterogeneity generated by cell clusters. Our experiments using real data and crafted experiments show that using DIPD as a data representation for scRNA-seq data can uncover novel cell subtypes that are missed or can only be found by careful parameter tuning using conventional methods. CONCLUSIONS: This new method has multiple advantages, including (1) no need for prior feature selection or manual optimization of hyperparameters; (2) flexibility to combine with and improve upon other methods, such as Seurat. Another novel contribution is the use of crafted experiments as part of the validation of our newly developed DIPD-based clustering pipeline. This new clustering pipeline is implemented in the R (CRAN) package scpoisson.

The status of causality in biological databases: data resources and data retrieval possibilities to support logical modeling.

Causal molecular interactions represent key building blocks used in computational modeling, where they facilitate the assembly of regulatory networks. Logical regulatory networks can be used to predict biological and cellular behaviors by system perturbations and in silico simulations. Today, broad sets of causal interactions are available in a variety of biological knowledge resources. However, different visions, based on distinct biological interests, have led to the development of multiple ways to describe and annotate causal molecular interactions. It can therefore be challenging to efficiently explore various resources of causal interaction and maintain an overview of recorded contextual information that ensures valid use of the data. This review lists the different types of public resources with causal interactions, the different views on biological processes that they represent, the various data formats they use for data representation and storage, and the data exchange and conversion procedures that are available to extract and download these interactions. This may further raise awareness among the targeted audience, i.e. logical modelers and other scientists interested in molecular causal interactions, but also database managers and curators, about the abundance and variety of causal molecular interaction data, and the variety of tools and approaches to convert them into one interoperable resource.

A Note on Representational Understanding.

In this paper, we explore a new approach in which understanding is interpreted as a set representation. We prove that understanding/representation, finding the appropriate coordination of data, is equivalent to finding the minimum of the representational entropy. For the control of the search for the correct representation, we propose a loss function as a combination of the representational entropy, type one and type two errors. Computational complexity estimates are presented for the process of understanding and using the representation found.

Big Data Warehouse for Healthcare-Sensitive Data Applications.

Obesity is a major public health problem worldwide, and the prevalence of childhood obesity is of particular concern. Effective interventions for preventing and treating childhood obesity aim to change behaviour and exposure at the individual, community, and societal levels. However, monitoring and evaluating such changes is very challenging. The EU Horizon 2020 project "Big Data against Childhood Obesity (BigO)" aims at gathering large-scale data from a large number of children using different sensor technologies to create comprehensive obesity prevalence models for data-driven predictions about specific policies on a community. It further provides real-time monitoring of the population responses, supported by meaningful real-time data analysis and visualisations. Since BigO involves monitoring and storing of personal data related to the behaviours of a potentially vulnerable population, the data representation, security, and access control are crucial. In this paper, we briefly present the BigO system architecture and focus on the necessary components of the system that deals with data access control, storage, anonymisation, and the corresponding interfaces with the rest of the system. We propose a three-layered data warehouse architecture: The back-end layer consists of a database management system for data collection, de-identification, and anonymisation of the original datasets. The role-based permissions and secured views are implemented in the access control layer. Lastly, the controller layer regulates the data access protocols for any data access and data analysis. We further present the data representation methods and the storage models considering the privacy and security mechanisms. The data privacy and security plans are devised based on the types of collected personal, the types of users, data storage, data transmission, and data analysis. We discuss in detail the challenges of privacy protection in this large distributed data-driven application and implement novel privacy-aware data analysis protocols to ensure that the proposed models guarantee the privacy and security of datasets. Finally, we present the BigO system architecture and its implementation that integrates privacy-aware protocols.

Framework for Intelligent Swimming Analytics with Wearable Sensors for Stroke Classification.

Intelligent approaches in sports using IoT devices to gather data, attempting to optimize athlete's training and performance, are cutting edge research. Synergies between recent wearable hardware and wireless communication strategies, together with the advances in intelligent algorithms, which are able to perform online pattern recognition and classification with seamless results, are at the front line of high-performance sports coaching. In this work, an intelligent data analytics system for swimmer performance is proposed. The system includes (i) pre-processing of raw signals; (ii) feature representation of wearable sensors and biosensors; (iii) online recognition of the swimming style and turns; and (iv) post-analysis of the performance for coaching decision support, including stroke counting and average speed. The system is supported by wearable inertial (AHRS) and biosensors (heart rate and pulse oximetry) placed on a swimmer's body. Radio-frequency links are employed to communicate with the heart rate sensor and the station in the vicinity of the swimming pool, where analytics is carried out. Experiments were carried out in a real training setup, including 10 athletes aged 15 to 17 years. This scenario resulted in a set of circa 8000 samples. The experimental results show that the proposed system for intelligent swimming analytics with wearable sensors effectively yields immediate feedback to coaches and swimmers based on real-time data analysis. The best result was achieved with a Random Forest classifier with a macro-averaged F1 of 95.02%. The benefit of the proposed framework was demonstrated by effectively supporting coaches while monitoring the training of several swimmers.

EVOLUTIONARY DE RHAM-HODGE METHOD.

The de Rham-Hodge theory is a landmark of the 20th Century's mathematics and has had a great impact on mathematics, physics, computer science, and engineering. This work introduces an evolutionary de Rham-Hodge method to provide a unified paradigm for the multiscale geometric and topological analysis of evolving manifolds constructed from a filtration, which induces a family of evolutionary de Rham complexes. While the present method can be easily applied to close manifolds, the emphasis is given to more challenging compact manifolds with 2-manifold boundaries, which require appropriate analysis and treatment of boundary conditions on differential forms to maintain proper topological properties. Three sets of unique evolutionary Hodge Laplacians are proposed to generate three sets of topology-preserving singular spectra, for which the multiplicities of zero eigenvalues correspond to exactly the persistent Betti numbers of dimensions 0, 1 and 2. Additionally, three sets of non-zero eigenvalues further reveal both topological persistence and geometric progression during the manifold evolution. Extensive numerical experiments are carried out via the discrete exterior calculus to demonstrate the potential of the proposed paradigm for data representation and shape analysis of both point cloud data and density maps. To demonstrate the utility of the proposed method, the application is considered to the protein B-factor predictions of a few challenging cases for which existing biophysical models break down.

Optimizing Few-Shot Learning Based on Variational Autoencoders.

Despite the importance of few-shot learning, the lack of labeled training data in the real world makes it extremely challenging for existing machine learning methods because this limited dataset does not well represent the data variance. In this research, we suggest employing a generative approach using variational autoencoders (VAEs), which can be used specifically to optimize few-shot learning tasks by generating new samples with more intra-class variations on the Labeled Faces in the Wild (LFW) dataset. The purpose of our research is to increase the size of the training dataset using various methods to improve the accuracy and robustness of the few-shot face recognition. Specifically, we employ the VAE generator to increase the size of the training dataset, including the basic and the novel sets while utilizing transfer learning as the backend. Based on extensive experimental research, we analyze various data augmentation methods to observe how each method affects the accuracy of face recognition. The face generation method based on VAEs with perceptual loss can effectively improve the recognition accuracy rate to 96.47% using both the base and the novel sets.

Simultaneous display of multiple three-dimensional electrophysiological datasets (dot mapping).

AIMS: Complex ablation procedures are supported by accurate representation of an increasing variety of electrophysiological and imaging data within electroanatomic mapping systems (EMS). This study aims to develop a novel method for representing multiple complementary datasets on a single cardiac chamber model. Validation of the system and its application to both atrial and ventricular arrhythmias is examined. METHODS AND RESULTS: Dot mapping was conceived to display multiple datasets by utilizing quantitative surface shading to represent one dataset and finely spaced dots to represent others. Dot positions are randomized within triangular (surface meshes) or tetrahedral (volumetric meshes) simplices making the approach directly transferrable to contemporary EMS. Test data representing uniform electrical activation (n = 10) and focal scarring (n = 10) were used to test dot mapping data perception accuracy. User experience of dot mapping with atrial and ventricular clinical data is evaluated. Dot mapping ensured constant screen dot density for regions of uniform dataset values, regardless of user manipulation of the cardiac chamber. Perception accuracy of dot mapping was equivalent to colour mapping for both propagation direction (1.5 ± 1.8 vs. 4.8 ± 5.3°, P = 0.24) and focal source localization (1.1 ± 0.7 vs. 1.4 ± 0.5 mm, P = 0.88). User acceptance testing revealed equivalent diagnostic accuracy and display fidelity when compared with colour mapping. CONCLUSION: Dot mapping provides the unique ability to display multiple datasets from multiple sources on a single cardiac chamber model. The visual combination of multiple datasets may facilitate interpretation of complex electrophysiological and imaging data.

Selecting relevant features from the electronic health record for clinical code prediction.

A multitude of information sources is present in the electronic health record (EHR), each of which can contain clues to automatically assign diagnosis and procedure codes. These sources however show information overlap and quality differences, which complicates the retrieval of these clues. Through feature selection, a denser representation with a consistent quality and less information overlap can be obtained. We introduce and compare coverage-based feature selection methods, based on confidence and information gain. These approaches were evaluated over a range of medical specialties, with seven different medical specialties for ICD-9-CM code prediction (six at the Antwerp University Hospital and one in the MIMIC-III dataset) and two different medical specialties for ICD-10-CM code prediction. Using confidence coverage to integrate all sources in an EHR shows a consistent improvement in F-measure (49.83% for diagnosis codes on average), both compared with the baseline (44.25% for diagnosis codes on average) and with using the best standalone source (44.41% for diagnosis codes on average). Confidence coverage creates a concise patient stay representation independent of a rigid framework such as UMLS, and contains easily interpretable features. Confidence coverage has several advantages to a baseline setup. In our baseline setup, feature selection was limited to a filter removing features with less than five total occurrences in the trainingset. Prediction results improved consistently when using multiple heterogeneous sources to predict clinical codes, while reducing the number of features and the processing time.

The biorepository portal toolkit: an honest brokered, modular service oriented software tool set for biospecimen-driven translational research.

BACKGROUND: High throughput molecular sequencing and increased biospecimen variety have introduced significant informatics challenges for research biorepository infrastructures. We applied a modular system integration approach to develop an operational biorepository management system. This method enables aggregation of the clinical, specimen and genomic data collected for biorepository resources. METHODS: We introduce an electronic Honest Broker (eHB) and Biorepository Portal (BRP) open source project that, in tandem, allow for data integration while protecting patient privacy. This modular approach allows data and specimens to be associated with a biorepository subject at any time point asynchronously. This lowers the bar to develop new research projects based on scientific merit without institutional review for a proposal. RESULTS: By facilitating the automated de-identification of specimen and associated clinical and genomic data we create a future proofed specimen set that can withstand new workflows and be connected to new associated information over time. Thus facilitating collaborative advanced genomic and tissue research. CONCLUSIONS: As of Janurary of 2016 there are 23 unique protocols/patient cohorts being managed in the Biorepository Portal (BRP). There are over 4000 unique subject records in the electronic honest broker (eHB), over 30,000 specimens accessioned and 8 institutions participating in various biobanking activities using this tool kit. We specifically set out to build rich annotation of biospecimens with longitudinal clinical data; BRP/REDCap integration for multi-institutional repositories; EMR integration; further annotated specimens with genomic data specific to a domain; build application hooks for experiments at the specimen level integrated with analytic software; while protecting privacy per the Office of Civil Rights (OCR) and HIPAA.

A review of machine learning-based methods for predicting drug-target interactions.

The prediction of drug-target interactions (DTI) is a crucial preliminary stage in drug discovery and development, given the substantial risk of failure and the prolonged validation period associated with in vitro and in vivo experiments. In the contemporary landscape, various machine learning-based methods have emerged as indispensable tools for DTI prediction. This paper begins by placing emphasis on the data representation employed by these methods, delineating five representations for drugs and four for proteins. The methods are then categorized into traditional machine learning-based approaches and deep learning-based ones, with a discussion of representative approaches in each category and the introduction of a novel taxonomy for deep neural network models in DTI prediction. Additionally, we present a synthesis of commonly used datasets and evaluation metrics to facilitate practical implementation. In conclusion, we address current challenges and outline potential future directions in this research field.

List2Net: Linking multiple lists of biological data in a network context.

Motivation: A common task in scientific research is the comparison of lists or sets of diverse biological entities such as biomolecules, ontologies, sequences and expression profiles. Such comparisons rely, one way or another, on calculating a measure of similarity either by means of vector correlation metrics, set operations such as union and intersection, or specific measures to capture, for example, sequence homology. Subsequently, depending on the data type, the results are often visualized using heatmaps, Venn, Euler, or Alluvial diagrams. While most of the abovementioned representations offer simplicity and interpretability, their effectiveness holds only for a limited number of lists and specific data types. Conversely, network representations provide a more versatile approach where data lists are viewed as interconnected nodes, with edges representing pairwise commonality, correlation, or any other similarity metric. Networks can represent an arbitrary number of lists of any data type, offering a holistic perspective and most importantly, enabling analytics for characterizing and discovering novel insights in terms of centralities, clusters and motifs that can exist in such networks. While several tools that implement the translation of lists to the various commonly used diagrams, such as Venn and Euler, have been developed, a similar tool that can parse, analyze the commonalities and generate networks from an arbitrary number of lists of the same or heterogenous content does not exist. Results: To address this gap, we introduce List2Net, a web-based tool that can rapidly process and represent lists in a network context, either in a single-layer or multi-layer mode, facilitating network analysis on multi-source/multi-layer data. Specifically, List2Net can seamlessly handle lists encompassing a wide variety of biological data types, such as named entities or ontologies (e.g., lists containing gene symbols), sequences (e.g., protein/peptide sequences), and numeric data types (e.g., omics-based expression or abundance profiles). Once the data is imported, the tool then (i) calculates the commonalities or correlations (edges) between the lists (nodes) of interest, (ii) generates and renders the network for visualization and analysis and (iii) provides a range of exporting options, including vector, raster format visualization but also the calculated edge lists and metrics in tabular format for further analysis in other tools. List2Net is a fast, lightweight, yet informative application that provides network-based holistic insights into the conditions represented by the lists of interest (e.g., disease-to-disease, gene-to-phenotype, drug-to-disease, etc.). As a case study, we demonstrate the utility of this tool applied on publicly available datasets related to Multiple Sclerosis (MS). Using the tool, we showcase the translation of various ontologies characterizing this specific condition on disease-to-disease subnetworks of neurodegenerative, autoimmune and infectious diseases generated from various levels of information such as genetic variation, genes, proteins, metabolites and phenotypic terms.

Data Representation Structure to Support Clinical Decision-Making in the Pediatric Intensive Care Unit: Interview Study and Preliminary Decision Support Interface Design.

BACKGROUND: Clinical decision-making is a complex cognitive process that relies on the interpretation of a large variety of data from different sources and involves the use of knowledge bases and scientific recommendations. The representation of clinical data plays a key role in the speed and efficiency of its interpretation. In addition, the increasing use of clinical decision support systems (CDSSs) provides assistance to clinicians in their practice, allowing them to improve patient outcomes. In the pediatric intensive care unit (PICU), clinicians must process high volumes of data and deal with ever-growing workloads. As they use multiple systems daily to assess patients' status and to adjust the health care plan, including electronic health records (EHR), clinical systems (eg, laboratory, imaging and pharmacy), and connected devices (eg, bedside monitors, mechanical ventilators, intravenous pumps, and syringes), clinicians rely mostly on their judgment and ability to trace relevant data for decision-making. In these circumstances, the lack of optimal data structure and adapted visual representation hinder clinician's cognitive processes and clinical decision-making skills. OBJECTIVE: In this study, we designed a prototype to optimize the representation of clinical data collected from existing sources (eg, EHR, clinical systems, and devices) via a structure that supports the integration of a home-developed CDSS in the PICU. This study was based on analyzing end user needs and their clinical workflow. METHODS: First, we observed clinical activities in a PICU to secure a better understanding of the workflow in terms of staff tasks and their use of EHR on a typical work shift. Second, we conducted interviews with 11 clinicians from different staff categories (eg, intensivists, fellows, nurses, and nurse practitioners) to compile their needs for decision support. Third, we structured the data to design a prototype that illustrates the proposed representation. We used a brain injury care scenario to validate the relevance of integrated data and the utility of main functionalities in a clinical context. Fourth, we held design meetings with 5 clinicians to present, revise, and adapt the prototype to meet their needs. RESULTS: We created a structure with 3 levels of abstraction-unit level, patient level, and system level-to optimize clinical data representation and display for efficient patient assessment and to provide a flexible platform to host the internally developed CDSS. Subsequently, we designed a preliminary prototype based on this structure. CONCLUSIONS: The data representation structure allows prioritizing patients via criticality indicators, assessing their conditions using a personalized dashboard, and monitoring their courses based on the evolution of clinical values. Further research is required to define and model the concepts of criticality, problem recognition, and evolution. Furthermore, feasibility tests will be conducted to ensure user satisfaction.

Efficacy of information extraction from bar, line, circular, bubble and radar graphs.

With the emergence of enormous amounts of data, numerous ways to visualize such data have been used. Bar, circular, line, radar and bubble graphs that are ubiquitous were investigated for their effectiveness. Fourteen participants performed four types of evaluations: between categories (cities), within categories (transport modes within a city), all categories, and a direct reading within a category from a graph. The representations were presented in random order and participants were asked to respond to sixteen questions to the best of their ability after visually scanning the related graph. There were two trials on two separate days for each participant. Eye movements were recorded using an eye tracker. Bar and line graphs show superiority over circular and radial graphs in effectiveness, efficiency, and perceived ease of use primarily due to eye saccades. The radar graph had the worst performance. "Vibration-type" fill pattern could be improved by adding colors and symbolic fills. Design guidelines are proposed for the effective representation of data so that the presentation and communication of information are effective.

From text to interaction: The digital advance directive method for advance directives.

Advance directives allow people to specify individual treatment preferences in case of decision-making incapacity involving decisions of utmost importance. There are many tools that provide information on the topic, digital forms for structured data input, or platforms that support data storage and availability. Yet, there is no tool supporting the innermost process of an advance directive: decision making itself. To address this issue, we developed a visual-interactive, semi-quantitative method for generating digital advance directives (DiADs) that harnesses the potential of digitalization in healthcare. In this article, we describe the DiAD method and its app lined with the exemplary narrative of user Mr S. linking the theory to an exemplary use case. The DiAD method is intended to lower barriers and increase comfort in creating an advance directive by shifting the focus from heavily text-based processes to visual representation and interaction, that is, from text to reflection.

Graph-ETMB: A graph neural network-based model for tumour mutation burden estimation.

As a critical indicator of how easily the human immune system recognizes tumour cells, tumour mutational burden (TMB) is widely used to identify the potential effectiveness of immune checkpoint inhibitor therapy. However, the difficulties associated with the whole exome sequencing (WES) process, such as high tissue sampling requirements, high costs, and long turnaround times, have hindered the widespread clinical use of WES. Furthermore, the mutation landscape varies across cancer types, and the distribution of TMBs varies across cancer subtypes. Therefore, there is an urgent clinical need to develop a small cancer-specific panel to estimate TMB accurately, predict immunotherapy response cost-effectively and assist physicians in precise decision-making. This paper uses a graph neural network framework (Graph-ETMB) to address the cancer specificity problem in TMB. The correlation and tractability between mutated genes are described through message-passing and aggregation algorithms between graph networks. Then the graph neural network is trained in the lung adenocarcinoma data through a semi-supervised approach, resulting in a mutation panel containing 20 genes with a length of only 0.16 Mb. The number of genes to be detected is smaller than most commercial panels currently in clinical use. In addition, the efficacy of the designed panel in predicting immunotherapy response was further determined in an independent validation dataset, exploring the association between TMB and immunotherapy efficacy.

Variable body and tissue weight reporting in preclinical cachexia literature may alter study outcomes and interpretation.

Cancer cachexia is a multifactorial syndrome of body weight loss, muscle wasting and progressive functional decline, affecting many advanced cancer patients and leading to worsened clinical outcomes. Despite inherent limitations of many preclinical cachexia models, including large tumor burden, rapid tumor growth and young age of animals, these animal models are widely used and imperative for the study of cachexia mechanisms and experimental therapeutics. However, there are currently no guidelines for the reporting and representation of data in preclinical cachexia literature. We examined the current state of data reporting in publications using the colon-26 adenocarcinoma (C26) model of cachexia and compared statistical differences in reporting mechanisms using animals from our laboratory. We show that data reporting and representation in C26 preclinical cachexia literature are diverse, making comparison of study outcomes difficult. Further, different expression of body and tissue weights in our animals led to differential statistical significance, which could significantly alter data interpretation. This study highlights a need for consistent data reporting in preclinical cancer cachexia literature to effectively compare outcomes between studies and increase translatability to the human condition.

A Multi-perspective Model for Protein-Ligand-Binding Affinity Prediction.

Gathering information from multi-perspective graphs is an essential issue for many applications especially for protein-ligand-binding affinity prediction. Most of traditional approaches obtained such information individually with low interpretability. In this paper, we harness the rich information from multi-perspective graphs with a general model, which abstractly represents protein-ligand complexes with better interpretability while achieving excellent predictive performance. In addition, we specially analyze the protein-ligand-binding affinity problem, taking into account the heterogeneity of proteins and ligands. Experimental evaluations demonstrate the effectiveness of our data representation strategy on public datasets by fusing information from different perspectives. All codes are available in the https://github.com/Jthy-af/HaPPy .

Achieving deep clustering through the use of variational autoencoders and similarity-based loss.

Clustering is an important and challenging research topic in many fields. Although various clustering algorithms have been developed in the past, traditional shallow clustering algorithms cannot mine the underlying structural information of the data. Recent advances have shown that deep clustering can achieve excellent performance on clustering tasks. In this work, a novel variational autoencoder-based deep clustering algorithm is proposed. It treats the Gaussian mixture model as the prior latent space and uses an additional classifier to distinguish different clusters in the latent space accurately. A similarity-based loss function is proposed consisting specifically of the cross-entropy of the predicted transition probabilities of clusters and the Wasserstein distance of the predicted posterior distributions. The new loss encourages the model to learn meaningful cluster-oriented representations to facilitate clustering tasks. The experimental results show that our method consistently achieves competitive results on various data sets.

Informatics Ecosystems to Advance the Biology of Glycans.

Glycomics researchers have identified the need for integrated database systems for collecting glycomics information in a consistent format. The goal is to create a resource for knowledge discovery and dissemination to wider research communities. This has the potential and has exhibited initial success, to extend the research community to include biologists, clinicians, chemists, and computer scientists. This chapter discusses the technology and approach needed to create integrated data resources and informatics ecosystems to empower the broader community to leverage extant glycomics data. The focus is on glycosaminoglycan (GAGs) and proteoglycan research, but the approach can be generalized. The methods described span the development of glycomics standards from CarbBank to Glyco Connection Tables. Integrated data sets provide a foundation for novel methods of analysis such as machine learning and deep learning for knowledge discovery. The implications of predictive analysis are examined in relation to disease biomarker to expand the target audience of GAG and proteoglycan research.