Biomedical Data Sources Research Articles

Prediction of potential drug-microbe associations based on matrix factorization and a three-layer heterogeneous network

Microbes in the human body are closely linked to many complex human diseases and are emerging as new drug targets. These microbes play a crucial role in drug development and disease treatment. Traditional methods of biological experiments are not only time-consuming but also costly. Using computational methods to predict microbe-drug associations can effectively complement biological experiments. In this experiment, we constructed heterogeneity networks for drugs, microbes, and diseases using multiple biomedical data sources. Then, we developed a model with matrix factorization and a three-layer heterogeneous network (MFTLHNMDA) to predict potential drug-microbe associations. The probability of microbe-drug association was obtained by a global network-based update algorithm. Finally, the performance of MFTLHNMDA was evaluated in the framework of leave-one-out cross-validation (LOOCV) and 5-fold cross-validation (5-fold CV). The results showed that our model performed better than six state-of-the-art methods that had AUC of 0.9396 and 0.9385 + /− 0.0000, respectively. This case study further confirms the effectiveness of MFTLHNMDA in identifying potential drug-microbe associations and new drug-microbe associations.

A Tissue-Specific and Toxicology-Focused Knowledge Graph

Molecular biology-focused knowledge graphs (KGs) are directed graphs that integrate information from heterogeneous sources of biological and biomedical data, such as ontologies and public databases. They provide a holistic view of biology, chemistry, and disease, allowing users to draw non-obvious connections between concepts through shared associations. While these massive graphs are constructed using carefully curated ontologies and annotations from public databases, much of the information relating the concepts is context specific. Two important variables that determine the applicability of a given ontology annotation are the species and (especially) the tissue type in which it takes place. Using a data-driven approach and the results from thousands of high-quality gene expression samples, we have constructed tissue-specific KGs (using liver, kidney, and heart as examples) that empirically validate the annotations provided by ontology curators. The resulting human-centered KGs are designed for toxicology applications but are generalizable to other areas of human biology, addressing the issue of tissue specificity that often limits the applicability of other large KGs. These knowledge graphs can serve as valuable tools for generating transparent explanations of experimental results in the form of mechanistic hypotheses that are highly relevant to the studied tissue. Because the data-driven relations are derived from a large collection of human in vitro data, these KGs are particularly well suited for in vitro toxicology applications.

A Novel System for AYUSH Healthcare Services using Classification and Regression

There are roughly 4000 AYUSH hospitals spread out across India under various councils and hospitals run by the Indian government. Today’s atmosphere makes it more challenging than ever to locate a suitable AYUSH facility for the treatment. The AYUSH Ministry provides India’s top option for healthcare delivery. The government is examining strategies to lower expenditures while enhancing patient care. We are proposing the ground-breaking idea of e-healthcare which involves various novel features like suggesting various tools to the patients those need to communicate with the healthcare professionals as per their convenience remotely. This research suggests an interactive system using Android in line with this trend. By integrating different bio-medical data sources that contain information pertinent to the hospital demographics, their inpatient procedure rates, Outpatient department, etc., we proposed a system that surveys on the various AYUSH hospitals to find. This system uses the Google Map API for tracking and highlighting the location to the nearby AYUSH hospitals with opening and closing timings. Additionally, the proposed system plays a crucial role in emergency scenarios by supporting the user in performing the necessary first aid techniques. Using this strategy, the entire system demonstrates that this research provides a superior method for making decisions than past studies.

Better together: Integrating biomedical informatics and healthcare IT operations to create a learning health system during the COVID-19 pandemic.

The growing availability of multi‐scale biomedical data sources that can be used to enable research and improve healthcare delivery has brought about what can be described as a healthcare “data age.” This new era is defined by the explosive growth in bio‐molecular, clinical, and population‐level data that can be readily accessed by researchers, clinicians, and decision‐makers, and utilized for systems‐level approaches to hypothesis generation and testing as well as operational decision‐making. However, taking full advantage of these unprecedented opportunities presents an opportunity to revisit the alignment between traditionally academic biomedical informatics (BMI) and operational healthcare information technology (HIT) personnel and activities in academic health systems. While the history of the academic field of BMI includes active engagement in the delivery of operational HIT platforms, in many contemporary settings these efforts have grown distinct. Recent experiences during the COVID‐19 pandemic have demonstrated greater coordination of BMI and HIT activities that have allowed organizations to respond to pandemic‐related changes more effectively, with demonstrable and positive impact as a result. In this position paper, we discuss the challenges and opportunities associated with driving alignment between BMI and HIT, as viewed from the perspective of a learning healthcare system. In doing so, we hope to illustrate the benefits of coordination between BMI and HIT in terms of the quality, safety, and outcomes of care provided to patients and populations, demonstrating that these two groups can be “better together.”

Elevated blood pressure, antihypertensive medications and bone health in the population: revisiting old hypotheses and exploring future research directions

Blood pressure and bone metabolism appear to share commonalities in their physiologic regulation. Specific antihypertensive drug classes may also influence bone mineral density. However, current evidence from existing observational studies and randomised trials is insufficient to establish causal associations for blood pressure and use of blood pressure–lowering drugs with bone health outcomes, particularly with the risks of osteoporosis and fractures. The availability and access to relevant large-scale biomedical data sources as well as developments in study designs and analytical approaches provide opportunities to examine the nature of the association between blood pressure and bone health more reliably and in greater detail than has ever been possible. It is unlikely that a single source of data or study design can provide a definitive answer. However, with appropriate considerations of the strengths and limitations of the different data sources and analytical techniques, we should be able to advance our understanding of the role of raised blood pressure and its drug treatment on the risks of low bone mineral density and fractures. As elevated blood pressure is highly prevalent and blood pressure–lowering drugs are widely prescribed, even small effects of these exposures on bone health outcomes could be important at a population level.

Heterogeneous graph attention networks for drug virus association prediction.

Coronavirus Disease-19 (COVID-19) has lead global epidemics with high morbidity and mortality. However, there are currently no proven effective drugs targeting COVID-19. Identifying drug-virus associations can not only provide insights into the understanding of drug-virus interaction mechanism, but also guide and facilitate the screening of compound candidates for antiviral drug discovery. Since conventional experiment methods are time-consuming, laborious and expensive, computational methods to identify potential drug candidates for viruses (e.g., COVID-19) provide an alternative strategy. In this work, we propose a novel framework of Heterogeneous Graph Attention Networks for Drug-Virus Association predictions, named HGATDVA. First, we fully incorporate multiple sources of biomedical data, e.g., drug chemical information, virus genome sequences and viral protein sequences, to construct abundant features for drugs and viruses. Second, we construct two drug-virus heterogeneous graphs. For each graph, we design a self-enhanced graph attention network (SGAT) to explicitly model the dependency between a node and its local neighbors and derive the graph-specific representations for nodes. Third, we further develop a neural network architecture with tri-aggregator to aggregate the graph-specific representations to generate the final node representations. Extensive experiments were conducted on two datasets, i.e., DrugVirus and MDAD, and the results demonstrated that our model outperformed 7 state-of-the-art methods. Case study on SARS-CoV-2 validated the effectiveness of our model in identifying potential drugs for viruses.

Multi-Layer Picture of Neurodegenerative Diseases: Lessons from the Use of Big Data through Artificial Intelligence.

In the big data era, artificial intelligence techniques have been applied to tackle traditional issues in the study of neurodegenerative diseases. Despite the progress made in understanding the complex (epi)genetics signatures underlying neurodegenerative disorders, performing early diagnosis and developing drug repurposing strategies remain serious challenges for such conditions. In this context, the integration of multi-omics, neuroimaging, and electronic health records data can be exploited using deep learning methods to provide the most accurate representation of patients possible. Deep learning allows researchers to find multi-modal biomarkers to develop more effective and personalized treatments, early diagnosis tools, as well as useful information for drug discovering and repurposing in neurodegenerative pathologies. In this review, we will describe how relevant studies have been able to demonstrate the potential of deep learning to enhance the knowledge of neurodegenerative disorders such as Alzheimer’s and Parkinson’s diseases through the integration of all sources of biomedical data.

Elevated Blood Pressure, Antihypertensive Medications and Bone Health in the Population: Revisiting Old Hypotheses and Exploring Future Research Directions

Blood pressure and bone metabolism appear to share commonalities in their physiologic regulation. Specific antihypertensive drug classes may also influence bone mineral density. However, current evidence from existing observational studies and randomized trials is insufficient to definitely suggest likely causal associations between blood pressure levels and use of blood-pressure lowering drugs on bone health outcomes, particularly on the risks of osteoporosis and fractures. Nevertheless, the availability and access to relevant large-scale biomedical data sources as well as developments in study designs and analytical approaches are providing opportunities to examine the nature of the association between blood pressure and bone health more reliably and in greater detail than has ever been possible. It is unlikely that a single source of data or study design can provide a definitive answer. However, with appropriate considerations of the strengths and limitations of the different data sources and analytical approaches, we should be able to advance our understanding of the role of raised blood pressure and its drug treatment on bone health outcomes. As elevated blood pressure and use of blood pressure-lowering drugs are highly prevalent, even small effects of these exposures on bone health outcomes could be important at a population level.

Optimizing sampling rate of wrist-worn optical sensors for physiologic monitoring.

Personalized medicine has exposed wearable sensors as new sources of biomedical data which are expected to accrue annual data storage costs of approximately $7.2 trillion by 2020 (>2000 exabytes). To improve the usability of wearable devices in healthcare, it is necessary to determine the minimum amount of data needed for accurate health assessment. Here, we present a generalizable optimization framework for determining the minimum necessary sampling rate for wearable sensors and apply our method to determine optimal optical blood volume pulse sampling rate. We implement t-tests, Bland-Altman analysis, and regression-based visualizations to identify optimal sampling rates of wrist-worn optical sensors. We determine the optimal sampling rate of wrist-worn optical sensors for heart rate and heart rate variability monitoring to be 21-64 Hz, depending on the metric. Determining the optimal sampling rate allows us to compress biomedical data and reduce storage needs and financial costs. We have used optical heart rate sensors as a case study for the connection between data volumes and resource requirements to develop methodology for determining the optimal sampling rate for clinical relevance that minimizes resource utilization. This methodology is extensible to other wearable sensors.

Predicting human microbe-disease associations via graph attention networks with inductive matrix completion.

human microbes play a critical role in an extensive range of complex human diseases and become a new target in precision medicine. In silico methods of identifying microbe-disease associations not only can provide a deep insight into understanding the pathogenic mechanism of complex human diseases but also assist pharmacologists to screen candidate targets for drug development. However, the majority of existing approaches are based on linear models or label propagation, which suffers from limitations in capturing nonlinear associations between microbes and diseases. Besides, it is still a great challenge for most previous methods to make predictions for new diseases (or new microbes) with few or without any observed associations. in this work, we construct features for microbes and diseases by fully exploiting multiply sources of biomedical data, and then propose a novel deep learning framework of graph attention networks with inductive matrix completion for human microbe-disease association prediction, named GATMDA. To our knowledge, this is the first attempt to leverage graph attention networks for this important task. In particular, we develop an optimized graph attention network with talking-heads to learn representations for nodes (i.e. microbes and diseases). To focus on more important neighbours and filter out noises, we further design a bi-interaction aggregator to enforce representation aggregation of similar neighbours. In addition, we combine inductive matrix completion to reconstruct microbe-disease associations to capture the complicated associations between diseases and microbes. Comprehensive experiments on two data sets (i.e. HMDAD and Disbiome) demonstrated that our proposed model consistently outperformed baseline methods. Case studies on two diseases, i.e. asthma and inflammatory bowel disease, further confirmed the effectiveness of our proposed model of GATMDA. python codes and data set are available at: https://github.com/yahuilong/GATMDA. luojiawei@hnu.edu.cn.

Association Mining to Identify Microbe Drug Interactions Based on Heterogeneous Network Embedding Representation.

Accurately identifying microbe-drug associations plays a critical role in drug development and precision medicine. Considering that the conventional wet-lab method is time-consuming, labor-intensive and expensive, computational approach is an alternative choice. The increasing availability of numerous biological data provides a great opportunity to systematically understand complex interaction mechanisms between microbes and drugs. However, few computational methods have been developed for microbe drug prediction. In this work, we leverage multiple sources of biomedical data to construct a heterogeneous network for microbes and drugs, including drug-drug interactions, microbe-microbe interactions and microbe-drug associations. And then we propose a novel Heterogeneous Network Embedding Representation framework for Microbe-Drug Association prediction, named (HNERMDA), by combining metapath2vec with bipartite network recommendation. In this framework, we introduce metapath2vec, a heterogeneous network representation learning method, to learn low-dimensional embedding representations for microbes and drugs. Following that, we further design a bias bipartite network projection recommendation algorithm to improve prediction accuracy. Comprehensive experiments on two datasets, named MDAD and aBiofilm, demonstrated that our model consistently outperformed five baseline methods in three types of cross-validations. Case study on two popular drugs (i.e., Ciprofloxacin and Pefloxacin) further validated the effectiveness of our HNERMDA model in inferring potential target microbes for drugs.

Identifying Herbal Adverse Events From Spontaneous Reporting Systems Using Taxonomic Name Resolution Approach.

The efficacy and safety of herbal supplements suffer from challenges due to non-uniform representation of ingredient terms within biomedical and observational health data sources. The nature of how supplement data are reported within Spontaneous Reporting Systems (SRS) can limit analyses of supplement-associated adverse events due to the use of incorrect nomenclature or failing to identify herbs. This study aimed to extract, standardize, and summarize supplement-relevant reports from two SRSs: (1) Food and Drug Administration Adverse Event Reporting System (FAERS) and (2) Canada Vigilance Adverse Reaction (CVAR) database. A thesaurus of plant names was developed and integrated with a mapping and normalization approach that accommodated misspellings and variants. The reports gathered from FAERS between the years 2004 and 2016 show 185,915 herbal and 7,235,330 non-herbal accounting for 2.51%. The data from CVAR found 36,940 reports of herbal and 503,580 non-herbal reports between the years 1965 and 2017 for a total of 6.83%. Although not all cases were actual adverse events due to numerous variables and incomplete reporting, it is interesting to note that the herbs most frequently reported and significantly associated with adverse events were as follows: Avena sativa (Oats), Cannabis sativa (marijuana), Digitalis purpurea (foxglove), Humulus lupulus (hops), Hypericum perforatum (St John’s Wort), Paullinia cupana (guarana), Phleum pretense (timothy-grass), Silybum marianum (milk thistle), Taraxacum officinale (Dandelion), and Valeriana officinalis (valerian). Using a scalable approach for mapping and resolution of herb names allowed data-driven exploration of potential adverse events from sources that have remained isolated in this specific area of research. The results from this study highlight several herb-associated safety issues providing motivation for subsequent in-depth analyses, including those that focus on the scope and severity of potential safety issues with supplement use.

An omics perspective on drug target discovery platforms.

The drug discovery process starts with identification of a disease-modifying target. This critical step traditionally begins with manual investigation of scientific literature and biomedical databases to gather evidence linking molecular target to disease, and to evaluate the efficacy, safety and commercial potential of the target. The high-throughput and affordability of current omics technologies, allowing quantitative measurements of many putative targets (e.g. DNA, RNA, protein, metabolite), has exponentially increased the volume of scientific data available for this arduous task. Therefore, computational platforms identifying and ranking disease-relevant targets from existing biomedical data sources, including omics databases, are needed. To date, more than 30 drug target discovery (DTD) platforms exist. They provide information-rich databases and graphical user interfaces to help scientists identify putative targets and pre-evaluate their therapeutic efficacy and potential side effects. Here we survey and compare a set of popular DTD platforms that utilize multiple data sources and omics-driven knowledge bases (either directly or indirectly) for identifying drug targets. We also provide a description of omics technologies and related data repositories which are important for DTD tasks.

Integrative factorization of bidimensionally linked matrices.

Advances in molecular "omics" technologies have motivated new methodologies for the integration of multiple sources of high-content biomedical data. However, most statistical methods for integrating multiple data matrices only consider data shared vertically (one cohort on multiple platforms) or horizontally (different cohorts on a single platform). This is limiting for data that take the form of bidimensionally linked matrices (eg, multiple cohorts measured on multiple platforms), which are increasingly common in large-scale biomedical studies. In this paper, we propose bidimensional integrative factorization (BIDIFAC) for integrative dimension reduction and signal approximation of bidimensionally linked data matrices. Our method factorizes data into (a) globally shared, (b) row-shared, (c) column-shared, and (d) single-matrix structural components, facilitating the investigation of shared and unique patterns of variability. For estimation, we use a penalized objective function that extends the nuclear norm penalization for a single matrix. As an alternative to the complicated rank selection problem, we use results from the random matrix theory to choose tuning parameters. We apply our method to integrate two genomics platforms (messenger RNA and microRNA expression) across two sample cohorts (tumor samples and normal tissue samples) using the breast cancer data from the Cancer Genome Atlas. We provide R code for fitting BIDIFAC, imputing missing values, and generating simulated data.

Inference on chains of disease progression based on disease networks.

MotivationDisease progression originates from the concept that an individual disease may go through different changes as it evolves, and such changes can cause new diseases. It is important to find a progression between diseases since knowing the prior-posterior relationship beforehand can prevent further complications or evolutions to other diseases. Furthermore, the series of progressions can be represented in the form of a chain, which enables us to readily infer successive influences from one disease to another after many passages through other diseases.MethodsIn this paper, we propose a systematic approach for finding a disease progression chain from a source disease to a target one via exploring a disease network. The network is constructed based on various sets of biomedical data. To find the most influential progression chains, the k-shortest path search algorithm is employed. The most representative algorithms such as A*, Dijkstra, and Yen’s are incorporated into the proposed method.ResultsA disease network consisting of 3,302 diseases was constructed based on four sources of biomedical data: disease-protein relations, biological pathways, clinical history, and biomedical literature information. The last three sets of data contain prior-posterior information, and they endow directionality on the edges of the network. The results were interesting and informative: for example, when colitis and respiratory insufficiency were set as a source disease and a target one, respectively, five progression chains were found within several seconds (when k = 5). Each chain was provided with a progression score, which indicates the strength of plausibility relative to others. Similarly, the proposed method can be expanded to any pair of source-target diseases in the network. This can be utilized as a preliminary tool for inferring complications or progressions between diseases.

Towards a content agnostic computable knowledge repository for data quality assessment

Background and objectiveIn recent years, several data quality conceptual frameworks have been proposed across the Data Quality and Information Quality domains towards assessment of quality of data. These frameworks are diverse, varying from simple lists of concepts to complex ontological and taxonomical representations of data quality concepts. The goal of this study is to design, develop and implement a platform agnostic computable data quality knowledge repository for data quality assessments. MethodsWe identified computable data quality concepts by performing a comprehensive literature review of articles indexed in three major bibliographic data sources. From this corpus, we extracted data quality concepts, their definitions, applicable measures, their computability and identified conceptual relationships. We used these relationships to design and develop a data quality meta-model and implemented it in a quality knowledge repository. ResultsWe identified three primitives for programmatically performing data quality assessments: data quality concept, its definition, its measure or rule for data quality assessment, and their associations. We modeled a computable data quality meta-data repository and extended this framework to adapt, store, retrieve and automate assessment of other existing data quality assessment models. ConclusionWe identified research gaps in data quality literature towards automating data quality assessments methods. In this process, we designed, developed and implemented a computable data quality knowledge repository for assessing quality and characterizing data in health data repositories. We leverage this knowledge repository in a service-oriented architecture to perform scalable and reproducible framework for data quality assessments in disparate biomedical data sources.

Network Medicine in the Age of Biomedical Big Data.

Network medicine is an emerging area of research dealing with molecular and genetic interactions, network biomarkers of disease, and therapeutic target discovery. Large-scale biomedical data generation offers a unique opportunity to assess the effect and impact of cellular heterogeneity and environmental perturbations on the observed phenotype. Marrying the two, network medicine with biomedical data provides a framework to build meaningful models and extract impactful results at a network level. In this review, we survey existing network types and biomedical data sources. More importantly, we delve into ways in which the network medicine approach, aided by phenotype-specific biomedical data, can be gainfully applied. We provide three paradigms, mainly dealing with three major biological network archetypes: protein-protein interaction, expression-based, and gene regulatory networks. For each of these paradigms, we discuss a broad overview of philosophies under which various network methods work. We also provide a few examples in each paradigm as a test case of its successful application. Finally, we delineate several opportunities and challenges in the field of network medicine. We hope this review provides a lexicon for researchers from biological sciences and network theory to come on the same page to work on research areas that require interdisciplinary expertise. Taken together, the understanding gained from combining biomedical data with networks can be useful for characterizing disease etiologies and identifying therapeutic targets, which, in turn, will lead to better preventive medicine with translational impact on personalized healthcare.

The Transverse Ultrasonogram of Thyroid Papillary Carcinoma Has a Better Prediction Accuracy Than the Longitudinal One

Thyroid produces multiple essential hormones for vital life processes. Thyroid cancer has no symptoms and may be detected by ultrasound imaging incidentally for other medical conditions. An accurate computational detection model may help the precise diagnose of thyroid papillary cancer (TPC). A standard protocol captures at least the transverse and longitudinal ultrasonograms of the thyroid. This study investigated the detection problem of thyroid cancer using the ultrasound images. Our data suggested that the original local binary pattern (LBP) features extracted from the ultrasonograms were very sparse and the compressed LBP features outperformed the original version. And the best model (Acc = 0.9829) was achieved by the fivefold cross validation of the classifier support vector machine (SVM). Other sources of biomedical data may be integrated to further improve the TPC detection model in future studies.

Data Analysis Strategies in Medical Imaging.

Radiographic imaging continues to be one of the most effective and clinically useful tools within oncology. Sophistication of artificial intelligence has allowed for detailed quantification of radiographic characteristics of tissues using predefined engineered algorithms or deep learning methods. Precedents in radiology as well as a wealth of research studies hint at the clinical relevance of these characteristics. However, critical challenges are associated with the analysis of medical imaging data. Although some of these challenges are specific to the imaging field, many others like reproducibility and batch effects are generic and have already been addressed in other quantitative fields such as genomics. Here, we identify these pitfalls and provide recommendations for analysis strategies of medical imaging data, including data normalization, development of robust models, and rigorous statistical analyses. Adhering to these recommendations will not only improve analysis quality but also enhance precision medicine by allowing better integration of imaging data with other biomedical data sources. Clin Cancer Res; 24(15); 3492-9. ©2018 AACR.

Predicting Adverse Drug Effects from Literature- and Database-Mined Assertions.

Given that adverse drug effects (ADEs) have led to post-market patient harm and subsequent drug withdrawal, failure of candidate agents in the drug development process, and other negative outcomes, it is essential to attempt to forecast ADEs and other relevant drug-target-effect relationships as early as possible. Current pharmacologic data sources, providing multiple complementary perspectives on the drug-target-effect paradigm, can be integrated to facilitate the inference of relationships between these entities. This study aims to identify both existing and unknown relationships between chemicals (C), protein targets (T), and ADEs (E) based on evidence in the literature. Cheminformatics and data mining approaches were employed to integrate and analyze publicly available clinical pharmacology data and literature assertions interrelating drugs, targets, and ADEs. Based on these assertions, a C-T-E relationship knowledge base was developed. Known pairwise relationships between chemicals, targets, and ADEs were collected from several pharmacological and biomedical data sources. These relationships were curated and integrated according to Swanson's paradigm to form C-T-E triangles. Missing C-E edges were then inferred as C-E relationships. Unreported associations between drugs, targets, and ADEs were inferred, and inferences were prioritized as testable hypotheses. Several C-E inferences, including testosterone → myocardial infarction, were identified using inferences based on the literature sources published prior to confirmatory case reports. Timestamping approaches confirmed the predictive ability of this inference strategy on a larger scale. The presented workflow, based on free-access databases and an association-based inference scheme, provided novel C-E relationships that have been validated post hoc in case reports. With refinement of prioritization schemes for the generated C-E inferences, this workflow may provide an effective computational method for the early detection of potential drug candidate ADEs that can be followed by targeted experimental investigations.