Domain-specific Background Research Articles

Integration of background knowledge for automatic detection of inconsistencies in gene ontology annotation.

Biological background knowledge plays an important role in the manual quality assurance (QA) of biological database records. One such QA task is the detection of inconsistencies in literature-based Gene Ontology Annotation (GOA). This manual verification ensures the accuracy of the GO annotations based on a comprehensive review of the literature used as evidence, Gene Ontology (GO) terms, and annotated genes in GOA records. While automatic approaches for the detection of semantic inconsistencies in GOA have been developed, they operate within predetermined contexts, lacking the ability to leverage broader evidence, especially relevant domain-specific background knowledge. This paper investigates various types of background knowledge that could improve the detection of prevalent inconsistencies in GOA. In addition, the paper proposes several approaches to integrate background knowledge into the automatic GOA inconsistency detection process. We have extended a previously developed GOA inconsistency dataset with several kinds of GOA-related background knowledge, including GeneRIF statements, biological concepts mentioned within evidence texts, GO hierarchy and existing GO annotations of the specific gene. We have proposed several effective approaches to integrate background knowledge as part of the automatic GOA inconsistency detection process. The proposed approaches can improve automatic detection of self-consistency and several of the most prevalent types of inconsistencies. https://github.com/jiyuc/de-inconsistency.

Cluster-based histopathology phenotype representation learning by self-supervised multi-class-token hierarchical ViT

Developing a clinical AI model necessitates a significant amount of highly curated and carefully annotated dataset by multiple medical experts, which results in increased development time and costs. Self-supervised learning (SSL) is a method that enables AI models to leverage unlabelled data to acquire domain-specific background knowledge that can enhance their performance on various downstream tasks. In this work, we introduce CypherViT, a cluster-based histo-pathology phenotype representation learning by self-supervised multi-class-token hierarchical Vision Transformer (ViT). CypherViT is a novel backbone that can be integrated into a SSL pipeline, accommodating both coarse and fine-grained feature learning for histopathological images via a hierarchical feature agglomerative attention module with multiple classification (cls) tokens in ViT. Our qualitative analysis showcases that our approach successfully learns semantically meaningful regions of interest that align with morphological phenotypes. To validate the model, we utilize the DINO self-supervised learning (SSL) framework to train CypherViT on a substantial dataset of unlabeled breast cancer histopathological images. This trained model proves to be a generalizable and robust feature extractor for colorectal cancer images. Notably, our model demonstrates promising performance in patch-level tissue phenotyping tasks across four public datasets. The results from our quantitative experiments highlight significant advantages over existing state-of-the-art SSL models and traditional transfer learning methods, such as those relying on ImageNet pre-training.

A functional diversity of argumentative styles

In dealing with the different ways in which argumentative styles manifest themselves in various communicative practices from several communicative domains, van Eemeren and Garssen start from a definition of argumentative style that is connected with the pragma-dialectical notion of strategic maneuvering. Depending on the argumentative moves that are made, the dialectical routes that are followed, and the strategic considerations that are brought to bear, they make a general distinction between detached and engaged argumentative styles. In this article, they report on recent research in which it is examined to what extent the argumentative styles that are prototypically used in different institutional macro-contexts from the political, the diplomatic, the juridical, the faciliatory, the academic and the medical domain belong to these two categories. In the analyses they discuss, the authors combine specialized and domain-specific background knowledge with pragma-dialectical insight into the properties of argumentative discourse that determine the argumentative style.

Health literacy, cancer literacy, comprehensions and knowledge among men attending a urology clinic

Health literacy (HL) is essential for men receiving urological treatment so that they can be involved in the shared decision making process. HL is supported by domain specific background knowledge which also informs cancer literacy and comprehension. Comprehension is in turn a determinant of HL. This study aimed to assess the level of HL among a group of men receiving urological treatment and to investigate if there were any correlations between the two different measures of HL, cancer literacy and comprehension, and prostate cancer knowledge. A survey was mailed to 200 men attending a urological clinic. The survey included: demographic questions, two validated tests of HL, (1) the Brief Health Literacy Score (BHLS) and (2) the Health Literacy Management Scale (HeLMS); a test of cancer comprehension; the Cancer Message Literacy Tests Reading (CMLT); and a prostate cancer knowledge test. Descriptive statistics were used to analyse the data. Surveys from 72 respondents, average age of 65 years, were included in the final analysis. Based on the BHLS, 22%of respondents had inadequate HL and 50% of respondents had inadequate HL in one or more of the HeLMS domains. Overall, the study participants had relatively high cancer literacy, comprehensions, and knowledge. However, for men with inadequate HL, based on the BHLS and the HeLMS, there were strong correlations with poor cancer literacy, comprehension, and knowledge. Our study highlights that many men receiving urological treatment with inadequate HL, require additional support to access health information which they can understand and act on to be part of the shared decision-making process.

Operational convective-scale data assimilation over Iran: A comparison between WRF and HARMONIE-AROME

The impact of applying three-dimensional variational data assimilation (3D-Var DA) on convective-scale forecasts is investigated by using two mesoscale models, the Weather Research and Forecasting model (WRF-ARW) and the Hirlam and Aladin Research Model On Non-hydrostatic-forecast Inside Europe (HARMONIE-AROME). One month (1 to 30 December 2013) of numerical experiments were conducted with these two models at 2.5 km horizontal resolution, in order to partly resolve convective phenomena, on the same domain over a mountainous area in Iran and neighboring areas. Furthermore, in order to estimate the domain specific background error statistics (BES) in convective scales, two months (1 November to 30 December 2017) of numerical experiments were carried out with both models by downscaling operational ECMWF forecasts. For setting the numerical experiments in an operational scenario, ECMWF operational forecast data were used as initial and lateral boundary conditions (ICs/LBCs). In order to examine the impact of data assimilation, the 3D-Var method in cycling mode was adopted and the forecasts were verified every 6 hours up to 36 hours for selected meteorological variables. In addition, 24 h accumulated precipitation forecasts were verified separately. Generally, the WRF and HARMONIE-AROME exhibit similar verification statistics for the selected forecast variables. The impact of DA on the numerical forecast shows some evidence of improvement in both models, and this effect decreases severely at longer lead times. Results from verifying the 24 h convective-scale precipitation forecasts from both models with and without DA suggest the superiority of the WRF model in forecasting more accurately the occurred precipitation over the simulation domain, even for the downscaling run.

Formal axioms in biomedical ontologies improve analysis and interpretation of associated data.

MotivationOver the past years, significant resources have been invested into formalizing biomedical ontologies. Formal axioms in ontologies have been developed and used to detect and ensure ontology consistency, find unsatisfiable classes, improve interoperability, guide ontology extension through the application of axiom-based design patterns and encode domain background knowledge. The domain knowledge of biomedical ontologies may have also the potential to provide background knowledge for machine learning and predictive modelling.ResultsWe use ontology-based machine learning methods to evaluate the contribution of formal axioms and ontology meta-data to the prediction of protein–protein interactions and gene–disease associations. We find that the background knowledge provided by the Gene Ontology and other ontologies significantly improves the performance of ontology-based prediction models through provision of domain-specific background knowledge. Furthermore, we find that the labels, synonyms and definitions in ontologies can also provide background knowledge that may be exploited for prediction. The axioms and meta-data of different ontologies contribute to improving data analysis in a context-specific manner. Our results have implications on the further development of formal knowledge bases and ontologies in the life sciences, in particular as machine learning methods are more frequently being applied. Our findings motivate the need for further development, and the systematic, application-driven evaluation and improvement, of formal axioms in ontologies.Availability and implementation https://github.com/bio-ontology-research-group/tsoe.Supplementary information Supplementary data are available at Bioinformatics online.

Deep learning of mutation-gene-drug relations from the literature

BackgroundMolecular biomarkers that can predict drug efficacy in cancer patients are crucial components for the advancement of precision medicine. However, identifying these molecular biomarkers remains a laborious and challenging task. Next-generation sequencing of patients and preclinical models have increasingly led to the identification of novel gene-mutation-drug relations, and these results have been reported and published in the scientific literature.ResultsHere, we present two new computational methods that utilize all the PubMed articles as domain specific background knowledge to assist in the extraction and curation of gene-mutation-drug relations from the literature. The first method uses the Biomedical Entity Search Tool (BEST) scoring results as some of the features to train the machine learning classifiers. The second method uses not only the BEST scoring results, but also word vectors in a deep convolutional neural network model that are constructed from and trained on numerous documents such as PubMed abstracts and Google News articles. Using the features obtained from both the BEST search engine scores and word vectors, we extract mutation-gene and mutation-drug relations from the literature using machine learning classifiers such as random forest and deep convolutional neural networks.Our methods achieved better results compared with the state-of-the-art methods. We used our proposed features in a simple machine learning model, and obtained F1-scores of 0.96 and 0.82 for mutation-gene and mutation-drug relation classification, respectively. We also developed a deep learning classification model using convolutional neural networks, BEST scores, and the word embeddings that are pre-trained on PubMed or Google News data. Using deep learning, the classification accuracy improved, and F1-scores of 0.96 and 0.86 were obtained for the mutation-gene and mutation-drug relations, respectively.ConclusionWe believe that our computational methods described in this research could be used as an important tool in identifying molecular biomarkers that predict drug responses in cancer patients. We also built a database of these mutation-gene-drug relations that were extracted from all the PubMed abstracts. We believe that our database can prove to be a valuable resource for precision medicine researchers.

The impact of different background errors in the assimilation of satellite radiances and in-situ observational data using WRFDA for three rainfall events over Iran

Satellite radiances and in-situ observations are assimilated through Weather Research and Forecasting Data Assimilation (WRFDA) system into Advanced Research WRF (ARW) model over Iran and its neighboring area. Domain specific background error based on x and y components of wind speed (UV) control variables is calculated for WRFDA system and some sensitivity experiments are carried out to compare the impact of global background error and the domain specific background errors, both on the precipitation and 2-m temperature forecasts over Iran. Three precipitation events that occurred over the country during January, September and October 2014 are simulated in three different experiments and the results for precipitation and 2-m temperature are verified against the verifying surface observations. Results show that using domain specific background error improves 2-m temperature and 24-h accumulated precipitation forecasts consistently, while global background error may even degrade the forecasts compared to the experiments without data assimilation. The improvement in 2-m temperature is more evident during the first forecast hours and decreases significantly as the forecast length increases.

Construction of Ontology for Software Requirements Elicitation

Background/Objective: Elicitation of requirements from informal descriptions remains a major challenge to be accomplished in software industry. Methods: An important task in order to accomplish this goal is to construct an ontology consisting of set of concepts i.e. entities, attributes and relations based on the application domain of interest. The ontology constructed here represents the domain knowledge and requirements are the specialized subset of it. As standard description formalism the ontology is encoded using OWL DL, supported by Pellet reasoned to check the consistency of the components of the ontology. The populated ontology can be queried for matching words using SPARQL. Findings: In software development projects, voluminous unstructured text documents from different stakeholders are to be analysed and to be converted into structured requirements. This process of elicitation will be time consuming if it is to be performed manually. Domain specific ontology helps in automating the process of requirements elicitation, this article intends to construct such domain specific background ontology. The findings are elaborated in Section 3. Improvements: This article portrays the construction and use of domain specific background ontology containing the concepts and their relationships in the Automated Teller Machine (ATM) operations domain to guide the process of automation of elicitation of requirements from informal descriptions or unstructured text, which otherwise would be time consuming if carried out manually.

Description-Driven Community Detection

Traditional approaches to community detection, as studied by physicists, sociologists, and more recently computer scientists, aim at simply partitioning the social network graph. However, with the advent of online social networking sites, richer data has become available: beyond the link information, each user in the network is annotated with additional information, for example, demographics, shopping behavior, or interests. In this context, it is therefore important to develop mining methods which can take advantage of all available information. In the case of community detection, this means finding good communities (a set of nodes cohesive in the social graph) which are associated with good descriptions in terms of user information (node attributes). Having good descriptions associated to our models make them understandable by domain experts and thus more useful in real-world applications. Another requirement dictated by real-world applications, is to develop methods that can use, when available, any domain-specific background knowledge. In the case of community detection the background knowledge could be a vague description of the communities sought in a specific application, or some prototypical nodes (e.g., good customers in the past), that represent what the analyst is looking for (a community of similar users). Towards this goal, in this article, we define and study the problem of finding a diverse set of cohesive communities with concise descriptions. We propose an effective algorithm that alternates between two phases: a hill-climbing phase producing (possibly overlapping) communities, and a description induction phase which uses techniques from supervised pattern set mining. Our framework has the nice feature of being able to build well-described cohesive communities starting from any given description or seed set of nodes, which makes it very flexible and easily applicable in real-world applications. Our experimental evaluation confirms that the proposed method discovers cohesive communities with concise descriptions in realistic and large online social networks such as D elicious , F lickr , and L ast FM.

Sequential Classification by Exploring Levels of Abstraction

In the paper we describe a sequential classification scheme that iteratively explores levels of abstraction in the description of examples. These levels of abstraction represent attribute values of increasing precision. Specifically, we assume attribute values constitute an ontology (i.e., attribute value ontology) reflecting a domain-specific background knowledge, where more general values subsumes more precise ones. While there are approaches that consider levels of abstraction during learning, the novelty of our proposal consists in exploring levels of abstraction when classifying new examples. The described scheme is essential when tests that increase precision of example description are associated with costs – such a situation is often encountered in medical diagnosis. Experimental evaluation of the proposed classification scheme combined with ontological Bayes classifier (i.e., a näıve Bayes classifier expanded to handle attribute value ontologies) demonstrates that the classification accuracy obtained at higher levels of abstraction (i.e., more general description of classified examples) converges very quickly to the classification accuracy for classified examples represented precisely. This finding indicates we should be able to reduce the number of tests and thus limit their cost without deterioration of the prediction accuracy.

Mining the pharmacogenomics literature--a survey of the state of the art.

This article surveys efforts on text mining of the pharmacogenomics literature, mainly from the period 2008 to 2011. Pharmacogenomics (or pharmacogenetics) is the field that studies how human genetic variation impacts drug response. Therefore, publications span the intersection of research in genotypes, phenotypes and pharmacology, a topic that has increasingly become a focus of active research in recent years. This survey covers efforts dealing with the automatic recognition of relevant named entities (e.g. genes, gene variants and proteins, diseases and other pathological phenomena, drugs and other chemicals relevant for medical treatment), as well as various forms of relations between them. A wide range of text genres is considered, such as scientific publications (abstracts, as well as full texts), patent texts and clinical narratives. We also discuss infrastructure and resources needed for advanced text analytics, e.g. document corpora annotated with corresponding semantic metadata (gold standards and training data), biomedical terminologies and ontologies providing domain-specific background knowledge at different levels of formality and specificity, software architectures for building complex and scalable text analytics pipelines and Web services grounded to them, as well as comprehensive ways to disseminate and interact with the typically huge amounts of semiformal knowledge structures extracted by text mining tools. Finally, we consider some of the novel applications that have already been developed in the field of pharmacogenomic text mining and point out perspectives for future research.

Ontology Mapping for Dynamic Multiagent Environment

Ontologies are essential for the realization of the Semantic Web, which in turn relies on the ability of systems to identify and exploit relationships that exist between and within ontologies. As ontologies can be used to represent different domains, there is a high need for efficient ontology matching techniques that can allow information to be easily shared between different heterogeneous systems. There are various systems were proposed recently for ontology mapping. Ontology mapping is a prerequisite for achieving heterogeneous data integration on the Semantic Web. The vision of the Semantic Web implies that a large number of ontologies present on the web need to be aligned before one can make use of them. At the same time, these ontologies can be used as domain-specific background knowledge by the ontology mapping systems to increase the mapping precision. However, these ontologies can differ in representation, quality, and size that pose different challenges to ontology mapping. In this paper, we analyzed the various challenges of recently introduced Multi-Agent Ontology Mapping Framework, DSSim and we have integrated an efficient feature called QoS-Web Services Composition with DSSsim. ie we have improved this framework with QoS based Service Compositions Mechanism. From our experimental results, it is established that this developed QoS based Web Services Compositions Mechanism for Multiagent Ontology Mapping Framework minimizing uncertain reasoning and improves matching time, which are encouraging results of our proposed work..

Multiagent Ontology Mapping Framework for the Semantic Web

Ontology mapping is a prerequisite for achieving heterogeneous data integration on the Semantic Web. The vision of the Semantic Web implies that a large number of ontologies present on the web need to be aligned before one can make use of them, for example, a question answering on the Semantic Web. At the same time, these ontologies can be used as domain-specific background knowledge by the ontology mapping systems to increase the mapping precision. However, these ontologies can differ in representation, quality, and size that pose different challenges to ontology mapping. In this paper, we analyze these challenges and introduce a multiagent ontology mapping framework that has been designed to operate effectively in the Semantic Web environment.

An ontological approach to focusing attention and enhancing machine perception on the Web

Today, many sensor networks and their applications employ a brute force approach to collecting and analyzing sensor data. Such an approach often wastes valuable energy and computational resources by unnecessarily tasking sensors and generating observations of minimal use. People, on the other hand, have evolved sophisticated mechanisms to efficiently perceive their environment. One such mechanism includes the use of background knowledge to determine what aspects of the environment to focus our attention. In this paper, we develop an ontology of perception, IntellegO, that may be used to more efficiently convert observations into perceptions. IntellegO is derived from cognitive theory, encoded in set-theory, and provides a formal semantics of machine perception. We then present an implementation that iteratively and efficiently processes low level, heterogeneous sensor data into knowledge through use of the perception ontology and domain specific background knowledge. Finally, we evaluate IntellegO by collecting and analyzing observations of weather conditions on the Web, and show significant resource savings in the generation and storage of perceptual knowledge.

Impact of Doppler weather radar data on numerical forecast of Indian monsoon depressions

This work is a first assessment of utilizing Doppler Weather Radar (DWR) radial velocity and reflectivity in a mesoscale model for prediction of Bay of Bengal monsoon depressions (MDs). The Weather Research Forecasting (WRF) modelling system—Advanced Research version (ARW) is customized and evaluated for the Indian monsoon region by generating domain-specific Background Error (BE) statistics and experiments involving two assimilation strategies (cold start and cycling). The monthly averaged 24 h forecast errors for wind, temperature and moisture profiles were analysed. From the statistical skill scores, it is concluded that the cycling mode assimilation enhanced the performance of the WRF three-dimensional variational data assimilation (3DVAR) system over the Indian region using conventional and non-conventional observations. DWR data from a coastal site were assimilated for simulation of two different summer MDs over India using the WRF-3DVAR analysis system. Three numerical experiments (control without any Global Telecommunication System (GTS) data, with GTS, and GTS as well as DWR) were performed for simulating these extreme weather events to study the impact of DWR data. The results show that even though MDs are large synoptic systems, assimilation of DWR data has a positive impact on the prediction of the location, propagation and development of rain bands associated with the MDs. All aspects of the MD simulations such as mean-sea-level pressure, winds, vertical structure and the track are significantly improved due to the DWR assimilation. Study results provide a positive proof of concept that the assimilation of the Indian DWR data within WRF can help improve the simulation of intense convective systems influencing the large-scale monsoonal flow. Copyright © 2010 Royal Meteorological Society

An empirical study of the use of relevance information in inductive logic programming

Inductive Logic Programming (ILP) systems construct models for data using domain-specific background information. When using these systems, it is typically assumed that sufficient human expertise is at hand to rule out irrelevant background information. Such irrelevant information can, and typically does, hinder an ILP system's search for good models. Here, we provide evidence that if expertise is available that can provide a partial-ordering on sets of background predicates in terms of relevance to the analysis task, then this can be used to good effect by an ILP system. In particular, using data from biochemical domains, we investigate an incremental strategy of including sets of predicates in decreasing order of relevance. Results obtained suggest that: (a) the incremental approach identifies, in substantially less time, a model that is comparable in predictive accuracy to that obtained with all background information in place; and (b) the incremental approach using the relevance ordering performs better than one that does not (that is, one that adds sets of predicates randomly). For a practitioner concerned with use of ILP, the implication of these findings are two-fold: (1) when not all background information can be used at once (either due to limitations of the ILP system, or the nature of the domain) expert assessment of the relevance of background predicates can assist substantially in the construction of good models; and (2) good first-cut results can be obtained quickly by a simple exclusion of information known to be less relevant.

Extracting Context-Sensitive Models in Inductive Logic Programming

Given domain-specific background knowledge and data in the form of examples, an Inductive Logic Programming (ILP) system extracts models in the data-analytic sense. We view the model-selection step facing an ILP system as a decision problem, the solution of which requires knowledge of the context in which the model is to be deployed. In this paper, “context” will be defined by the current specification of the prior class distribution and the client's preferences concerning errors of classification. Within this restricted setting, we consider the use of an ILP system in situations where: (a) contexts can change regularly. This can arise for example, from changes to class distributions or misclassification costss and (b) the data are from observational studies. That is, they may not have been collected with any particular context in mind. Some repercussions of these are: (a) any one model may not be the optimal choice for all contextss and (b) not all the background information provided may be relevant for all contexts. Using results from the analysis of Receiver Operating Characteristic curves, we investigate a technique that can equip an ILP system to reject those models that cannot possibly be optimal in any context. We present empirical results from using the technique to analyse two datasets concerned with the toxicity of chemicals (in particular, their mutagenic and carcinogenic properties). Clients can, and typically do, approach such datasets with quite different requirements. For example, a synthetic chemist would require models with a low rate of commission errors which could be used to direct efficiently the synthesis of new compounds. A toxicologist on the other hand, would prefer models with a low rate of omission errors. This would enable a more complete identification of toxic chemicals at a calculated cost of misidentification of non-toxic cases as toxic. The approach adopted here attempts to obtain a solution that contains models that are optimal for each such user according to the cost function that he or she wishes to apply. In doing so, it also provides one solution to the problem of how the relevance of background predicates is to be assessed in ILP.

Web search behavior of Internet experts and newbies

Searching for relevant information on the World Wide Web is often a laborious and frustrating task for casual and experienced users. To help improve searching on the Web based on a better understanding of user characteristics, we investigate what types of knowledge are relevant for Web-based information seeking, and which knowledge structures and strategies are involved. Two experimental studies are presented, which address these questions from different angles and with different methodologies. In the first experiment, 12 established Internet experts are first interviewed about search strategies and then perform a series of realistic search tasks on the World Wide Web. From this study a model of information seeking on the World Wide Web is derived and then tested in a second study. In the second experiment two types of potentially relevant types of knowledge are compared directly. Effects of Web experience and domain-specific background knowledge are investigated with a series of search tasks in an economics-related domain (introduction of the Euro currency). We find differential and combined effects of both Web experience and domain knowledge: while successful search performance requires the combination of the two types of expertise, specific strategies directly related to Web experience or domain knowledge can be identified.

Extracting information from an animation during complex visual learning

The construction of a high quality mental model from a complex visual display relies the capacity of learners to extract appropriate information from that display. Beginning students of meteorology complied written records of generalisations extracted from animated weather map sequences in order to prepare themselves for a subsequent prediction task. Analysis of these records revealed that much of the information extracted was perceptually salient rather than thematically relevant. This perceptual dominance effect was found for both visuospatial and temporal aspects of the display. The statements produced were deficient with regard to the causal explanations that would be necessary to build a satisfactory mental model of the depicted situation. These deficiencies involved both the proportion of causal material recorded and the attribution of causality on an everyday rather than a domain-appropriate basis. The limitations of the information extracted were interpreted as evidence of subjects’ use of selective attention to control cognitive load in a complex, demanding processing situation and the effects of their lack of domain-specific background knowledge. Contrary to prevailing orthodoxies, the results raise the possibility that in some circumstances, animations may not be instructionally superior to static depictions because the processing demands involved can have negative effects on learning.