- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Data Quality and Management
- Electronic Health Records Systems
- Service-Oriented Architecture and Web Services
- Genetic Associations and Epidemiology
- Single-cell and spatial transcriptomics
- Environmental Monitoring and Data Management
- Advanced Database Systems and Queries
- Advanced Graph Neural Networks
- Business Process Modeling and Analysis
- AI-based Problem Solving and Planning
- Cancer Genomics and Diagnostics
- Library Science and Information Systems
- Modeling and Simulation Systems
- Web Data Mining and Analysis
- Data Management and Algorithms
- Privacy-Preserving Technologies in Data
- Computational Drug Discovery Methods
- Graph Theory and Algorithms
- Scientific Computing and Data Management
- Genetic and phenotypic traits in livestock
- linguistics and terminology studies
AstraZeneca (United Kingdom)
2021
Ollscoil na Gaillimhe – University of Galway
2008-2020
Fraunhofer Institute for Applied Information Technology
2020
National University of Ireland
2013-2014
University of Cyprus
2013
Chinese University of Hong Kong
2013
Applied Multilayers (United Kingdom)
2013
University of Kaiserslautern
2013
Enterprise Ireland
2011
Data retrieval systems are facing a paradigm shift due to the proliferation of specialized data storage engines (SQL, NoSQL, Column Stores, MapReduce, Stream, and Graph) supported by varied models (CSV, JSON, RDB, RDF, XML).One immediate consequence this results into bottleneck over web; which means, web applications unable retrieve with intensity at being generated from different facilities.Especially in genomics healthcare verticals, growing petascale exascale, biomedical stakeholders...
Determining the association between tumor sample and gene is demanding because it requires a high cost for conducting genetic experiments. Thus, discovered further clinical verification validation. This entire mechanism time-consuming expensive. Due to this issue, predicting samples genes remain challenge in biomedicine.Here we present, computational model based on heat diffusion algorithm which can predict genes. We proposed 2-layered graph. In first layer, constructed graph of where these...
Several query federation engines have been proposed for accessing public Linked Open Data sources. However, in many domains, resources are sensitive and access to these is tightly controlled by stakeholders; consequently, privacy a major concern when federating queries over such datasets. In the Healthcare Life Sciences (HCLS) domain real-world datasets contain statistical information: strict ownership granted individuals working hospitals, research labs, clinical trial organisers, etc....
Next Generation Sequencing (NGS) is playing a key role in therapeutic decision making for the cancer prognosis and treatment. The NGS technologies are producing massive amount of sequencing datasets. Often, these datasets published from isolated different facilities. Consequently, process sharing aggregating multisite thwarted by issues such as need to discover relevant data sources, built scalable repositories, automation linkage, volume data, efficient querying mechanism, information rich...
The integration of Electronic Patient Record (EPR) systems is at the centre many new regional and national initiatives to integrate clinical processes across department, region, levels. Web Service technologies offer significant solutions provide an interoperable communication infrastructure but are unable support precise definitions for healthcare messages, functionality, standards, required making meaningful integration. lack interoperability within standards adds complexity initiatives....
Electronic Health Records (EHRs) contain an increasing wealth of medical information, which has the potential to significantly advance research and health policies formulation, providing society with additional benefits within a global perspective. However, European healthcare information space is fragmented due lack legal technical standards, cost effective platforms, sustainable business models. Providing interoperability infrastructure for EHRs on agenda many regional, international...
A mishap in anti-cancer drug distribution is critical breast cancer patients due to poor prediction model identify the treatment regime ER+ve and ER-ve (Estrogen Receptor (ER)) patients. The traditional method for depends on change expression across normal-disease pair. However, it certainly misses multidimensional aspect underlying cause of relapse, such as various mutations, dosage side effects, methylation, etc. In this paper, we have developed a multi-layer neural network classify...
A significant portion of the LOD cloud consists Life Sciences data sets, which together contain billions clinical facts that interlink to form a "Web Clinical Data". However, tools for new publishers find relevant datasets could potentially be linked are missing, particularly in specialist domain-specific settings. Based on set keywords extracted from local dataset, this paper proposes methods automatically identify public SPARQL endpoints list candidates.
The study of genetic variants (GVs) can help find correlating population groups and to identify cohorts that are predisposed common diseases explain differences in disease susceptibility how patients react drugs. Machine learning techniques increasingly being applied interacting GVs understand their complex phenotypic traits. Since the performance a algorithm not only depends on size nature data but also quality underlying representation, deep neural networks (DNNs) learn non-linear mappings...
Despite the significant health impacts of adverse events associated with drug-drug interactions, no standard models exist for managing and sharing evidence describing potential interactions between medications. Minimal information have been used in other communities to establish community consensus around simple capable communicating useful information. This paper reports on a new minimal model interactions. A task force Semantic Web Health Care Life Sciences Community Group World-Wide...
This paper proposes a Bayesian association rule mining algorithm (BAR) which combines the Apriori with networks. Two interesting-ness measures of rules: confidence (BC) and lift (BL) measure conditional dependence independence relationships between items are defined based on joint probabilities represented by networks rules. BAR outputs best rules according to BC BL. is evaluated for its performance using two anonymized clinical phenotype datasets from UCI Repository: Thyroid disease...
The dynamicity of sensor data sources and publishing real-time over a generalised infrastructure like the Web pose new set integration challenges. Semantic Sensor Networks demand excessive expressivity for efficient formal analysis data. This article specifically addresses problem adapting model specific or context-specific properties in automatic generation multidimensional cubes. idea is to generate cubes on-the-fly from syntactic sustain decision making, event processing publish this as...
The database, semantic web, and linked data communities have proposed solutions that federate queries over multiple sources using a single model. Nowadays, the retrieval requirements originating from versatile broad domains like healthcare life sciences (HCLS) are changing this conventional trend - of federating query model primarily due to simultaneous use different models (CSV, JSON, RDB, RDF, XML, etc.) in real-life scenario. It's now impractical assume variety (graph, key-value, stream,...
A key property of linked data, i.e., the web-based representation and publication data as interconnected labeled graphs, is that it enables querying navigating through datasets distributed across network. SPARQL1.1, current standard query language for RDF-based defines a construct-called paths (PP)-to navigate between entities graph. This potentially very useful in number use cases, e.g., biomedical domain, where large are available graphs. However, PP SPARQL 1.1. possible only on single...
A set of well-integrated clinical terminologies is at the core delivering an efficient trial system. The design and outcomes a can be improved significantly through unambiguous consistent used in participating institute. However, due to lack generalised legal technical standards, heterogeneity exists between prominent as well within systems several levels, e.g., data, schema, medical codes. This article specifically addresses problem integrating local or proprietary with globally defined...
Biosimulation models have been recently introduced to understand the exact causative factors that give rise impairment in human organs. Finite Element Method (FEM) provides a mathematical framework simulate dynamic biological systems, with applications ranging from ear, cardiovascular, neurovascular research. Due lack of well-integrated data infrastructure, steps involved execution and comparative evaluation large (FE) simulations are time consuming performed isolated environments. In this...
The LOD cloud comprises of billions facts covering hundreds datasets. In accordance with the Linked Data principles, these datasets are connected by a variety typed links, forming an interlinked "Web Data". growing diversity Web makes it more and challenging for publishers to find relevant that could be linked to, particularly in specialist domain-specific settings. This paper thus proposes baseline method automatically identify list public SPARQL endpoints whose content is deemed local...