Automated Coding of Job Descriptions From a General Population Study: Overview of Existing Tools, Their Application and Comparison.

OBJECTIVES: Automatic job coding tools were developed to reduce the laborious task of manually assigning job codes based on free-text job descriptions in census and survey data sources, including large occupational health studies. The objective of this study is to provide a case study of comparative performance of job coding and JEM (Job-Exposure Matrix)-assigned exposures agreement using existing coding tools. METHODS: We compared three automatic job coding tools [AUTONOC, CASCOT (Computer-Assisted Structured Coding Tool), and LabourR], which were selected based on availability, coding of English free-text into coding systems closely related to the 1988 version of the International Standard Classification of Occupations (ISCO-88), and capability to perform batch coding. We used manually coded job histories from the AsiaLymph case-control study that were translated into English prior to auto-coding to assess their performance. We applied two general population JEMs to assess agreement at exposure level. Percent agreement and PABAK (Prevalence-Adjusted Bias-Adjusted Kappa) were used to compare the agreement of results from manual coders and automatic coding tools. RESULTS: The coding per cent agreement among the three tools ranged from 17.7 to 26.0% for exact matches at the most detailed 4-digit ISCO-88 level. The agreement was better at a more general level of job coding (e.g. 43.8-58.1% in 1-digit ISCO-88), and in exposure assignments (median values of PABAK coefficient ranging 0.69-0.78 across 12 JEM-assigned exposures). Based on our testing data, CASCOT was found to outperform others in terms of better agreement in both job coding (26% 4-digit agreement) and exposure assignment (median kappa 0.61). CONCLUSIONS: In this study, we observed that agreement on job coding was generally low for the three tools but noted a higher degree of agreement in assigned exposures. The results indicate the need for study-specific evaluations prior to their automatic use in general population studies, as well as improvements in the evaluated automatic coding tools.

Perspectives on automated composition of workflows in the life sciences.

Scientific data analyses often combine several computational tools in automated pipelines, or workflows. Thousands of such workflows have been used in the life sciences, though their composition has remained a cumbersome manual process due to a lack of standards for annotation, assembly, and implementation. Recent technological advances have returned the long-standing vision of automated workflow composition into focus. This article summarizes a recent Lorentz Center workshop dedicated to automated composition of workflows in the life sciences. We survey previous initiatives to automate the composition process, and discuss the current state of the art and future perspectives. We start by drawing the "big picture" of the scientific workflow development life cycle, before surveying and discussing current methods, technologies and practices for semantic domain modelling, automation in workflow development, and workflow assessment. Finally, we derive a roadmap of individual and community-based actions to work toward the vision of automated workflow development in the forthcoming years. A central outcome of the workshop is a general description of the workflow life cycle in six stages: 1) scientific question or hypothesis, 2) conceptual workflow, 3) abstract workflow, 4) concrete workflow, 5) production workflow, and 6) scientific results. The transitions between stages are facilitated by diverse tools and methods, usually incorporating domain knowledge in some form. Formal semantic domain modelling is hard and often a bottleneck for the application of semantic technologies. However, life science communities have made considerable progress here in recent years and are continuously improving, renewing interest in the application of semantic technologies for workflow exploration, composition and instantiation. Combined with systematic benchmarking with reference data and large-scale deployment of production-stage workflows, such technologies enable a more systematic process of workflow development than we know today. We believe that this can lead to more robust, reusable, and sustainable workflows in the future.

Occupation Coding of Job Titles: Iterative Development of an Automated Coding Algorithm for the Canadian National Occupation Classification (ACA-NOC).

BACKGROUND: In many research studies, the identification of social determinants is an important activity, in particular, information about occupations is frequently added to existing patient data. Such information is usually solicited during interviews with open-ended questions such as "What is your job?" and "What industry sector do you work in?" Before being able to use this information for further analysis, the responses need to be categorized using a coding system, such as the Canadian National Occupational Classification (NOC). Manual coding is the usual method, which is a time-consuming and error-prone activity, suitable for automation. OBJECTIVE: This study aims to facilitate automated coding by introducing a rigorous algorithm that will be able to identify the NOC (2016) codes using only job title and industry information as input. Using manually coded data sets, we sought to benchmark and iteratively improve the performance of the algorithm. METHODS: We developed the ACA-NOC algorithm based on the NOC (2016), which allowed users to match NOC codes with job and industry titles. We employed several different search strategies in the ACA-NOC algorithm to find the best match, including exact search, minor exact search, like search, near (same order) search, near (different order) search, any search, and weak match search. In addition, a filtering step based on the hierarchical structure of the NOC data was applied to the algorithm to select the best matching codes. RESULTS: The ACA-NOC was applied to over 500 manually coded job and industry titles. The accuracy rate at the four-digit NOC code level was 58.7% (332/566) and improved when broader job categories were considered (65.0% at the three-digit NOC code level, 72.3% at the two-digit NOC code level, and 81.6% at the one-digit NOC code level). CONCLUSIONS: The ACA-NOC is a rigorous algorithm for automatically coding the Canadian NOC system and has been evaluated using real-world data. It allows researchers to code moderate-sized data sets with occupation in a timely and cost-efficient manner such that further analytics are possible. Initial assessments indicate that it has state-of-the-art performance and is readily extensible upon further benchmarking on larger data sets.

Semantic Web of Things (SWoT) for Global Infectious Disease Control and Prevention.

This paper reports on the early-stage development of an analytics framework to support the semantic integration of dynamic surveillance data across multiple scales to inform decision making for malaria eradication. We propose using the Semantic Web of Things (SWoT), a combination of Internet of Things (IoT) and semantic web technologies, to support the evolution and integration of dynamic malaria data sources and improve interoperability between different datasets generated through relevant IoT assets (e.g. computers, sensors, persons, and other smart objects and devices).

Exploring Semantic Data Federation to Enable Malaria Surveillance Queries.

Malaria is an infectious disease affecting people across tropical countries. In order to devise efficient interventions, surveillance experts need to be able to answer increasingly complex queries integrating information coming from repositories distributed all over the globe. This, in turn, requires extraordinary coding abilities that cannot be expected from non-technical surveillance experts. In this paper, we present a deployment of Semantic Automated Discovery and Integration (SADI) Web services for the federation and querying of malaria data. More than 10 services were created to answer an example query requiring data coming from various sources. Our method assists surveillance experts in formulating their queries and gaining access to the answers they need.

Mouth-clicks used by blind expert human echolocators - signal description and model based signal synthesis.

Echolocation is the ability to use sound-echoes to infer spatial information about the environment. Some blind people have developed extraordinary proficiency in echolocation using mouth-clicks. The first step of human biosonar is the transmission (mouth click) and subsequent reception of the resultant sound through the ear. Existing head-related transfer function (HRTF) data bases provide descriptions of reception of the resultant sound. For the current report, we collected a large database of click emissions with three blind people expertly trained in echolocation, which allowed us to perform unprecedented analyses. Specifically, the current report provides the first ever description of the spatial distribution (i.e. beam pattern) of human expert echolocation transmissions, as well as spectro-temporal descriptions at a level of detail not available before. Our data show that transmission levels are fairly constant within a 60° cone emanating from the mouth, but levels drop gradually at further angles, more than for speech. In terms of spectro-temporal features, our data show that emissions are consistently very brief (~3ms duration) with peak frequencies 2-4kHz, but with energy also at 10kHz. This differs from previous reports of durations 3-15ms and peak frequencies 2-8kHz, which were based on less detailed measurements. Based on our measurements we propose to model transmissions as sum of monotones modulated by a decaying exponential, with angular attenuation by a modified cardioid. We provide model parameters for each echolocator. These results are a step towards developing computational models of human biosonar. For example, in bats, spatial and spectro-temporal features of emissions have been used to derive and test model based hypotheses about behaviour. The data we present here suggest similar research opportunities within the context of human echolocation. Relatedly, the data are a basis to develop synthetic models of human echolocation that could be virtual (i.e. simulated) or real (i.e. loudspeaker, microphones), and which will help understanding the link between physical principles and human behaviour.

A Novel Monopulse Technique for Adaptive Phased Array Radar.

The monopulse angle measuring technique is widely adopted in radar systems due to its simplicity and speed in accurately acquiring a target's angle. However, in a spatial adaptive array, beam distortion, due to adaptive beamforming, can result in serious deterioration of monopulse performance. In this paper, a novel constrained monopulse angle measuring algorithm is proposed for spatial adaptive arrays. This algorithm maintains the ability to suppress the unwanted signals without suffering from beam distortion. Compared with conventional adaptive monopulse methods, the proposed algorithm adopts a new form of constraint in forming the difference beam with the merit that it is more robust in most practical situations. At the same time, it also exhibits the simplicity of one-dimension monopulse, helping to make this algorithm even more appealing to use in adaptive planar arrays. The theoretical mean and variance of the proposed monopulse estimator is derived for theoretical analysis. Mathematical simulations are formulated to demonstrate the effectiveness and advantages of the proposed algorithm. Both theoretical analysis and simulation results show that the proposed algorithm can outperform the conventional adaptive monopulse methods in the presence of severe interference near the mainlobe.

From Cues to Nudge: A Knowledge-Based Framework for Surveillance of Healthcare-Associated Infections.

We propose an integrated semantic web framework consisting of formal ontologies, web services, a reasoner and a rule engine that together recommend appropriate level of patient-care based on the defined semantic rules and guidelines. The classification of healthcare-associated infections within the HAIKU (Hospital Acquired Infections - Knowledge in Use) framework enables hospitals to consistently follow the standards along with their routine clinical practice and diagnosis coding to improve quality of care and patient safety. The HAI ontology (HAIO) groups over thousands of codes into a consistent hierarchy of concepts, along with relationships and axioms to capture knowledge on hospital-associated infections and complications with focus on the big four types, surgical site infections (SSIs), catheter-associated urinary tract infection (CAUTI); hospital-acquired pneumonia, and blood stream infection. By employing statistical inferencing in our study we use a set of heuristics to define the rule axioms to improve the SSI case detection. We also demonstrate how the occurrence of an SSI is identified using semantic e-triggers. The e-triggers will be used to improve our risk assessment of post-operative surgical site infections (SSIs) for patients undergoing certain type of surgeries (e.g., coronary artery bypass graft surgery (CABG)).

Classifying chemical mode of action using gene networks and machine learning: a case study with the herbicide linuron.

The herbicide linuron (LIN) is an endocrine disruptor with an anti-androgenic mode of action. The objectives of this study were to (1) improve knowledge of androgen and anti-androgen signaling in the teleostean ovary and to (2) assess the ability of gene networks and machine learning to classify LIN as an anti-androgen using transcriptomic data. Ovarian explants from vitellogenic fathead minnows (FHMs) were exposed to three concentrations of either 5α-dihydrotestosterone (DHT), flutamide (FLUT), or LIN for 12h. Ovaries exposed to DHT showed a significant increase in 17ß-estradiol (E2) production while FLUT and LIN had no effect on E2. To improve understanding of androgen receptor signaling in the ovary, a reciprocal gene expression network was constructed for DHT and FLUT using pathway analysis and these data suggested that steroid metabolism, translation, and DNA replication are processes regulated through AR signaling in the ovary. Sub-network enrichment analysis revealed that FLUT and LIN shared more regulated gene networks in common compared to DHT. Using transcriptomic datasets from different fish species, machine learning algorithms classified LIN successfully with other anti-androgens. This study advances knowledge regarding molecular signaling cascades in the ovary that are responsive to androgens and anti-androgens and provides proof of concept that gene network analysis and machine learning can classify priority chemicals using experimental transcriptomic data collected from different fish species.

The SADI Personal Health Lens: A Web Browser-Based System for Identifying Personally Relevant Drug Interactions.

BACKGROUND: The Web provides widespread access to vast quantities of health-related information that can improve quality-of-life through better understanding of personal symptoms, medical conditions, and available treatments. Unfortunately, identifying a credible and personally relevant subset of information can be a time-consuming and challenging task for users without a medical background. OBJECTIVE: The objective of the Personal Health Lens system is to aid users when reading health-related webpages by providing warnings about personally relevant drug interactions. More broadly, we wish to present a prototype for a novel, generalizable approach to facilitating interactions between a patient, their practitioner(s), and the Web. METHODS: We utilized a distributed, Semantic Web-based architecture for recognizing personally dangerous drugs consisting of: (1) a private, local triple store of personal health information, (2) Semantic Web services, following the Semantic Automated Discovery and Integration (SADI) design pattern, for text mining and identifying substance interactions, (3) a bookmarklet to trigger analysis of a webpage and annotate it with personalized warnings, and (4) a semantic query that acts as an abstract template of the analytical workflow to be enacted by the system. RESULTS: A prototype implementation of the system is provided in the form of a Java standalone executable JAR file. The JAR file bundles all components of the system: the personal health database, locally-running versions of the SADI services, and a javascript bookmarklet that triggers analysis of a webpage. In addition, the demonstration includes a hypothetical personal health profile, allowing the system to be used immediately without configuration. Usage instructions are provided. CONCLUSIONS: The main strength of the Personal Health Lens system is its ability to organize medical information and to present it to the user in a personalized and contextually relevant manner. While this prototype was limited to a single knowledge domain (drug/drug interactions), the proposed architecture is generalizable, and could act as the foundation for much richer personalized-health-Web clients, while importantly providing a novel and personalizable mechanism for clinical experts to inject their expertise into the browsing experience of their patients in the form of customized semantic queries and ontologies.

HAIKU: A Semantic Framework for Surveillance of Healthcare-Associated Infections.

Healthcare-Associated Infections (HAI) impose a substantial health and financial burden. Surveillance for HAI is essential to develop and evaluate prevention and control efforts. The traditional approaches to HAI surveillance are often limited in scope and efficiency by the need to manually obtain and integrate data from disparate paper charts and information systems. The considerable effort required for discovery and integration of relevant data from multiple sources limits the current effectiveness of HAI surveillance. Knowledge-based systems can address this problem of contextualizing data to support integration and reasoning. In order to facilitate knowledge-based decision making in this area, availability of a reference vocabulary is crucial. The existing terminologies in this domain still suffer from inconsistencies and confusion in different medical/clinical practices, and there is a need for their further improvement and clarification. To develop a common understanding of the infection control domain and to achieve data interoperability in the area of hospital-acquired infections, we present the HAI Ontology (HAIO) to improve knowledge processing in pervasive healthcare environments, as part of the HAIKU (Hospital Acquired Infections - Knowledge in Use) system. The HAIKU framework assists physicians and infection control practitioners by providing recommendations regarding case detection, risk stratification and identification of diagnostic factors.

Deploying mutation impact text-mining software with the SADI Semantic Web Services framework.

BACKGROUND: Mutation impact extraction is an important task designed to harvest relevant annotations from scientific documents for reuse in multiple contexts. Our previous work on text mining for mutation impacts resulted in (i) the development of a GATE-based pipeline that mines texts for information about impacts of mutations on proteins, (ii) the population of this information into our OWL DL mutation impact ontology, and (iii) establishing an experimental semantic database for storing the results of text mining. RESULTS: This article explores the possibility of using the SADI framework as a medium for publishing our mutation impact software and data. SADI is a set of conventions for creating web services with semantic descriptions that facilitate automatic discovery and orchestration. We describe a case study exploring and demonstrating the utility of the SADI approach in our context. We describe several SADI services we created based on our text mining API and data, and demonstrate how they can be used in a number of biologically meaningful scenarios through a SPARQL interface (SHARE) to SADI services. In all cases we pay special attention to the integration of mutation impact services with external SADI services providing information about related biological entities, such as proteins, pathways, and drugs. CONCLUSION: We have identified that SADI provides an effective way of exposing our mutation impact data such that it can be leveraged by a variety of stakeholders in multiple use cases. The solutions we provide for our use cases can serve as examples to potential SADI adopters trying to solve similar integration problems.

Knowledge-based surveillance for preventing postoperative surgical site infection.

At least one out of every twenty people admitted to a Canadian hospital will acquire an infection. These hospital-acquired infections (HAIs) take a profound individual and system-wide toll, resulting in thousands of deaths and hundreds of millions of dollars in additional expenses each year. Surveillance for HAIs is essential to develop and evaluate prevention and control efforts. In nearly all healthcare institutions, however, surveillance for HAIs is a manual process, requiring highly trained infection control practitioners to consult multiple information systems and paper charts. The amount of effort required for discovery and integration of relevant data from multiple sources limits the current effectiveness of HAIs surveillance. In this research, we apply knowledge modeling and semantic technologies to facilitate the integration of disparate data and enable automatic reasoning with these integrated data to identify events of clinical interest. In this paper, we focus on Surgical Site Infections (SSIs), which account for a relatively large fraction of all hospital acquired infections.

OrganismTagger: detection, normalization and grounding of organism entities in biomedical documents.

MOTIVATION: Semantic tagging of organism mentions in full-text articles is an important part of literature mining and semantic enrichment solutions. Tagged organism mentions also play a pivotal role in disambiguating other entities in a text, such as proteins. A high-precision organism tagging system must be able to detect the numerous forms of organism mentions, including common names as well as the traditional taxonomic groups: genus, species and strains. In addition, such a system must resolve abbreviations and acronyms, assign the scientific name and if possible link the detected mention to the NCBI Taxonomy database for further semantic queries and literature navigation. RESULTS: We present the OrganismTagger, a hybrid rule-based/machine learning system to extract organism mentions from the literature. It includes tools for automatically generating lexical and ontological resources from a copy of the NCBI Taxonomy database, thereby facilitating system updates by end users. Its novel ontology-based resources can also be reused in other semantic mining and linked data tasks. Each detected organism mention is normalized to a canonical name through the resolution of acronyms and abbreviations and subsequently grounded with an NCBI Taxonomy database ID. In particular, our system combines a novel machine-learning approach with rule-based and lexical methods for detecting strain mentions in documents. On our manually annotated OT corpus, the OrganismTagger achieves a precision of 95%, a recall of 94% and a grounding accuracy of 97.5%. On the manually annotated corpus of Linnaeus-100, the results show a precision of 99%, recall of 97% and grounding accuracy of 97.4%. AVAILABILITY: The OrganismTagger, including supporting tools, resources, training data and manual annotations, as well as end user and developer documentation, is freely available under an open-source license at http://www.semanticsoftware.info/organism-tagger. CONTACT: witte@semanticsoftware.info.

Prototype semantic infrastructure for automated small molecule classification and annotation in lipidomics.

BACKGROUND: The development of high-throughput experimentation has led to astronomical growth in biologically relevant lipids and lipid derivatives identified, screened, and deposited in numerous online databases. Unfortunately, efforts to annotate, classify, and analyze these chemical entities have largely remained in the hands of human curators using manual or semi-automated protocols, leaving many novel entities unclassified. Since chemical function is often closely linked to structure, accurate structure-based classification and annotation of chemical entities is imperative to understanding their functionality. RESULTS: As part of an exploratory study, we have investigated the utility of semantic web technologies in automated chemical classification and annotation of lipids. Our prototype framework consists of two components: an ontology and a set of federated web services that operate upon it. The formal lipid ontology we use here extends a part of the LiPrO ontology and draws on the lipid hierarchy in the LIPID MAPS database, as well as literature-derived knowledge. The federated semantic web services that operate upon this ontology are deployed within the Semantic Annotation, Discovery, and Integration (SADI) framework. Structure-based lipid classification is enacted by two core services. Firstly, a structural annotation service detects and enumerates relevant functional groups for a specified chemical structure. A second service reasons over lipid ontology class descriptions using the attributes obtained from the annotation service and identifies the appropriate lipid classification. We extend the utility of these core services by combining them with additional SADI services that retrieve associations between lipids and proteins and identify publications related to specified lipid types. We analyze the performance of SADI-enabled eicosanoid classification relative to the LIPID MAPS classification and reflect on the contribution of our integrative methodology in the context of high-throughput lipidomics. CONCLUSIONS: Our prototype framework is capable of accurate automated classification of lipids and facile integration of lipid class information with additional data obtained with SADI web services. The potential of programming-free integration of external web services through the SADI framework offers an opportunity for development of powerful novel applications in lipidomics. We conclude that semantic web technologies can provide an accurate and versatile means of classification and annotation of lipids.

Including the urban heat island in spatial heat health risk assessment strategies: a case study for Birmingham, UK.

BACKGROUND: Heatwaves present a significant health risk and the hazard is likely to escalate with the increased future temperatures presently predicted by climate change models. The impact of heatwaves is often felt strongest in towns and cities where populations are concentrated and where the climate is often unintentionally modified to produce an urban heat island effect; where urban areas can be significantly warmer than surrounding rural areas. The purpose of this interdisciplinary study is to integrate remotely sensed urban heat island data alongside commercial social segmentation data via a spatial risk assessment methodology in order to highlight potential heat health risk areas and build the foundations for a climate change risk assessment. This paper uses the city of Birmingham, UK as a case study area. RESULTS: When looking at vulnerable sections of the population, the analysis identifies a concentration of "very high" risk areas within the city centre, and a number of pockets of "high risk" areas scattered throughout the conurbation. Further analysis looks at household level data which yields a complicated picture with a considerable range of vulnerabilities at a neighbourhood scale. CONCLUSIONS: The results illustrate that a concentration of "very high" risk people live within the urban heat island, and this should be taken into account by urban planners and city centre environmental managers when considering climate change adaptation strategies or heatwave alert schemes. The methodology has been designed to be transparent and to make use of powerful and readily available datasets so that it can be easily replicated in other urban areas.

Toward a knowledge infrastructure for traits-based ecological risk assessment.

The trait approach has already indicated significant potential as a tool in understanding natural variation among species in sensitivity to contaminants in the process of ecological risk assessment. However, to realize its full potential, a defined nomenclature for traits is urgently required, and significant effort is required to populate databases of species-trait relationships. Recently, there have been significant advances in the area of information management and discovery in the area of the semantic web. Combined with continuing progress in biological trait knowledge, these suggest that the time is right for a reevaluation of how trait information from divergent research traditions is collated and made available for end users in the field of environmental management. Although there has already been a great deal of work on traits, the information is scattered throughout databases, literature, and undiscovered sources. Further progress will require better leverage of this existing data and research to fill in the gaps. We review and discuss a number of technical and social challenges to bringing together existing information and moving toward a new, collaborative approach. Finally, we outline a path toward enhanced knowledge discovery within the traits domain space, showing that, by linking knowledge management infrastructure, semantic metadata (trait ontologies), and Web 2.0 and 3.0 technologies, we can begin to construct a dedicated platform for TERA science.

Algorithms and semantic infrastructure for mutation impact extraction and grounding.

BACKGROUND: Mutation impact extraction is a hitherto unaccomplished task in state of the art mutation extraction systems. Protein mutations and their impacts on protein properties are hidden in scientific literature, making them poorly accessible for protein engineers and inaccessible for phenotype-prediction systems that currently depend on manually curated genomic variation databases. RESULTS: We present the first rule-based approach for the extraction of mutation impacts on protein properties, categorizing their directionality as positive, negative or neutral. Furthermore protein and mutation mentions are grounded to their respective UniProtKB IDs and selected protein properties, namely protein functions to concepts found in the Gene Ontology. The extracted entities are populated to an OWL-DL Mutation Impact ontology facilitating complex querying for mutation impacts using SPARQL. We illustrate retrieval of proteins and mutant sequences for a given direction of impact on specific protein properties. Moreover we provide programmatic access to the data through semantic web services using the SADI (Semantic Automated Discovery and Integration) framework. CONCLUSION: We address the problem of access to legacy mutation data in unstructured form through the creation of novel mutation impact extraction methods which are evaluated on a corpus of full-text articles on haloalkane dehalogenases, tagged by domain experts. Our approaches show state of the art levels of precision and recall for Mutation Grounding and respectable level of precision but lower recall for the task of Mutant-Impact relation extraction. The system is deployed using text mining and semantic web technologies with the goal of publishing to a broad spectrum of consumers.