CSNet: A new DeepNet framework for ischemic stroke lesion segmentation.

Comput Methods Programs Biomed. 2020 May 01;193:105524

Authors: Kumar A, Upadhyay N, Ghosal P, Chowdhury T, Das D, Mukherjee A, Nandi D

Abstract
BACKGROUND AND OBJECTIVES: Acute stroke lesion segmentation is of paramount importance as it can aid medical personnel to render a quicker diagnosis and administer consequent treatment. Automation of this task is technically exacting due to the variegated appearance of lesions and their dynamic development, medical discrepancies, unavailability of datasets, and the requirement of several MRI modalities for imaging. In this paper, we propose a composite deep learning model primarily based on the self-similar fractal networks and the U-Net model for performing acute stroke diagnosis tasks automatically to assist as well as expedite the decision-making process of medical practitioners.
METHODS: We put forth a new deep learning architecture, the Classifier-Segmenter network (CSNet), involving a hybrid training strategy with a self-similar (fractal) U-Net model, explicitly designed to perform the task of segmentation. In fractal networks, the underlying design strategy is based on the repetitive generation of self-similar fractals in place of residual connections. The U-Net model exploits both spatial as well as semantic information along with parameter sharing for a faster and efficient training process. In this new architecture, we exploit the benefits of both by combining them into one hybrid training scheme and developing the concept of a cascaded architecture, which further enhances the model's accuracy by removing redundant parts from the Segmenter's input. Lastly, a voting mechanism has been employed to further enhance the overall segmentation accuracy.
RESULTS: The performance of the proposed architecture has been scrutinized against the existing state-of-the-art deep learning architectures applied to various biomedical image processing tasks by submission on the publicly accessible web platform provided by the MICCAI Ischemic Stroke Lesion Segmentation (ISLES) challenge. The experimental results demonstrate the superiority of the proposed method when compared to similar submitted strategies, both qualitatively and quantitatively in terms of some of the well known evaluation metrics, such as Accuracy, Dice-Coefficient, Recall, and Precision.
CONCLUSIONS: We believe that our method may find use as a handy tool for doctors to identify the location and extent of irreversibly damaged brain tissue, which is said to be a critical part of the decision-making process in case of an acute stroke.

PMID: 32417618 [PubMed - as supplied by publisher]

Risk Response for Municipal Solid Waste Crisis Using Ontology-Based Reasoning.

Int J Environ Res Public Health. 2020 May 09;17(9):

Authors: Yang Q, Zuo C, Liu X, Yang Z, Zhou H

Abstract
Many cities in the world are besieged by municipal solid waste (MSW). MSW not only pollutes the ecological environment but can even induce a series of public safety crises. Risk response for MSW needs novel changes. This paper innovatively adopts the ideas and methods of semantic web ontology to build an ontology-based reasoning system for MSW risk response. Through the integration of crisis information and case resources in the field of MSW, combined with the reasoning ability of Semantic Web Rule Language (SWRL), a system of rule reasoning for risk transformation is constructed. Knowledge extraction and integration of MSW risk response can effectively excavate semantic correlation of crisis information along with key transformation points in the process of crisis evolution through rule reasoning. The results show that rule reasoning of transformation can effectively improve intelligent decision-making regarding MSW risk response.

PMID: 32397529 [PubMed - in process]

iPiDi-PUL: identifying Piwi-interacting RNA-disease associations based on positive unlabeled learning.

Brief Bioinform. 2020 May 11;:

Authors: Wei H, Xu Y, Liu B

Abstract
Accumulated researches have revealed that Piwi-interacting RNAs (piRNAs) are regulating the development of germ and stem cells, and they are closely associated with the progression of many diseases. As the number of the detected piRNAs is increasing rapidly, it is important to computationally identify new piRNA-disease associations with low cost and provide candidate piRNA targets for disease treatment. However, it is a challenging problem to learn effective association patterns from the positive piRNA-disease associations and the large amount of unknown piRNA-disease pairs. In this study, we proposed a computational predictor called iPiDi-PUL to identify the piRNA-disease associations. iPiDi-PUL extracted the features of piRNA-disease associations from three biological data sources, including piRNA sequence information, disease semantic terms and the available piRNA-disease association network. Principal component analysis (PCA) was then performed on these features to extract the key features. The training datasets were constructed based on known positive associations and the negative associations selected from the unknown pairs. Various random forest classifiers trained with these different training sets were merged to give the predictive results via an ensemble learning approach. Finally, the web server of iPiDi-PUL was established at http://bliulab.net/iPiDi-PUL to help the researchers to explore the associated diseases for newly discovered piRNAs.

PMID: 32393982 [PubMed - as supplied by publisher]

SIB Literature Services: RESTful customizable search engines in biomedical literature, enriched with automatically mapped biomedical concepts.

Nucleic Acids Res. 2020 May 07;:

Authors: Julien G, Déborah C, Pierre-André M, Luc M, Emilie P, Patrick R

Abstract
Thanks to recent efforts by the text mining community, biocurators have now access to plenty of good tools and Web interfaces for identifying and visualizing biomedical entities in literature. Yet, many of these systems start with a PubMed query, which is limited by strong Boolean constraints. Some semantic search engines exploit entities for Information Retrieval, and/or deliver relevance-based ranked results. Yet, they are not designed for supporting a specific curation workflow, and allow very limited control on the search process. The Swiss Institute of Bioinformatics Literature Services (SIBiLS) provide personalized Information Retrieval in the biological literature. Indeed, SIBiLS allow fully customizable search in semantically enriched contents, based on keywords and/or mapped biomedical entities from a growing set of standardized and legacy vocabularies. The services have been used and favourably evaluated to assist the curation of genes and gene products, by delivering customized literature triage engines to different curation teams. SIBiLS (https://candy.hesge.ch/SIBiLS) are freely accessible via REST APIs and are ready to empower any curation workflow, built on modern technologies scalable with big data: MongoDB and Elasticsearch. They cover MEDLINE and PubMed Central Open Access enriched by nearly 2 billion of mapped biomedical entities, and are daily updated.

PMID: 32379317 [PubMed - as supplied by publisher]

A multicentric IT platform for storage and sharing of imaging-based radiation dosimetric data.

Int J Comput Assist Radiol Surg. 2020 May 02;:

Authors: Spaltenstein J, van Dooren N, Pasquier G, Roduit N, Brenet M, Pasquier G, Gibaud B, Mildenberger P, Ratib O

Abstract
PURPOSE: The MEDIRAD project is about the effects of low radiation dose in the context of medical procedures. The goal of the work is to develop an informatics service that will provide the researchers of the MEDIRAD project with a platform to share acquired images, along with the associated dosimetric data pertaining to the radiation resulting from the procedure.
METHODS: The authors designed a system architecture to manage image data and dosimetric data in an integrated way. DICOM and non-DICOM data are stored in separated repositories, and the link between the two is provided through a semantic database, i.e., a database whose information schema in aligned with an ontology.
RESULTS: The system currently supports CT, PET, SPECT, and NM images as well as dose reports. Currently, two workflows for non-DICOM data generated from dosimetric calculations have been taken into account, one concerning Monte Carlo-based calculation of organ doses in Chest CT, and the other estimation of doses in nontarget organs in 131I targeted radionuclide therapy of the thyroid.
CONCLUSION: The system is currently deployed, thus providing access to image and related dosimetric data to all MEDIRAD users. The software was designed in such a way that it can be reused to support similar needs in other projects.

PMID: 32361856 [PubMed - as supplied by publisher]

Blended Face-to-Face and Web-Based Smoking Cessation Treatment: Qualitative Study of Patients' User Experience.

JMIR Form Res. 2020 Jan 27;:

Authors: Siemer L, Ben Allouch S, Pieterse ME, Brusse-Keizer M, Sanderman R, Postel MG

Abstract
BACKGROUND: Blended Web-based and face-to-face treatment is a promising electronic health service because it is expected that in a blended treatment the strengths of one mode of delivery will compensate for the weaknesses of the other.
OBJECTIVE: The aim of this study was to explore this expectation by examining the patients' user experience (UX) in a blended smoking cessation treatment (BSCT) in routine care.
METHODS: Patients' UX was collected by in-depth interviews (n=10) at an outpatient smoking cessation clinic in the Netherlands. Content analysis of the semantic domains was used to analyze the patients' UX. For the description of the UX, Hassenzahl's UX model was applied, examining the 4 of the 5 key elements of UX that form the UX from a user's perspective: (1) standards and expectations, (2) apparent character (pragmatic and hedonic attributes), (3) usage situation, and (4) consequences (appeal, emotions, and behavior).
RESULTS: BSCT appeared to be a mostly positively experienced service. Patients had a positive-pragmatic standard and neutral-open expectation toward BSCT at the treatment start. The pragmatic attributes of the F2F session were mostly perceived as positive, whereas the pragmatic attributes of the Web sessions were perceived as both positive and negative. For the hedonic attributes, there seems to be a difference between the F2F sessions and the Web sessions. Specifically, the hedonic attributes of the Web sessions were experienced as mostly negative, whereas those of the F2F sessions were mostly positive. For the usage situation, the physical and social contexts were experienced positively, whereas the task and technical contexts were experienced negatively. Nevertheless, the consequential appeal of BSCT was positive. However, the consequential emotions and behavior varied, ultimately resulting in diverse combinations of consequential appeal, emotions, and behavior (positive, negative, and mixed).
CONCLUSIONS: This study provided insight into the UX of a blended treatment, and the results support the expectation that in a blended treatment, one mode of delivery may compensate for the weaknesses of the other. However, in this certain setting, this is mainly achieved in only one way: F2F sessions compensated for the weaknesses of the Web sessions. As a practical conclusion, this may mean that the Web sessions, supported by the strength of the F2F sessions, offer an interesting approach for further improving the blended treatment. Our theoretical findings reflect the relevance of the aspects of hedonism, such as fun, joy, or happiness in the UX, which were not mentioned in relation to the Web sessions and were only scarcely mentioned in relation to the F2F sessions. Future research should further investigate the role of hedonistic aspects in a blended treatment, and if increased enjoyment of a blended treatment could increase treatment adherence and, ultimately, effectiveness.

PMID: 32343245 [PubMed - as supplied by publisher]

Epistemic vigilance online: Textual inaccuracy and children's selective trust in webpages.

Br J Dev Psychol. 2020 Apr 28;:

Authors: Einav S, Levey A, Patel P, Westwood A

Abstract
In this age of 'fake news', it is crucial that children are equipped with the skills to identify unreliable information online. Our study is the first to examine whether children are influenced by the presence of inaccuracies contained in webpages when deciding which sources to trust. Forty-eight 8- to 10-year-olds viewed three pairs of webpages, relating to the same topics, where one webpage per pair contained three obvious inaccuracies (factual, typographical, or exaggerations, according to condition). The paired webpages offered conflicting claims about two novel facts. We asked participants questions pertaining to the novel facts to assess whether they systematically selected answers from the accurate sources. Selective trust in the accurate webpage was found in the typos condition only. This study highlights the limitations of 8- to 10-year-olds in critically evaluating the accuracy of webpage content and indicates a potential focus for educational intervention. Statement of contribution What is already known on this subject? Children display early epistemic vigilance towards spoken testimony. They use speakers' past accuracy when deciding whom to trust regarding novel information. Little is known about children's selective trust towards web-based sources. What does this study add? This study is the first to examine whether textual inaccuracy affects children's trust in webpages. Typos but not semantic errors led to reduced trust in a webpage compared to an accurate source. Children aged 8-10 years show limited evaluation of the accuracy of online content.

PMID: 32342990 [PubMed - as supplied by publisher]

Semantic Networks and Mechanisms of Exposure Therapy: Implications for the Treatment of Panic Disorder.

Am J Psychiatry. 2020 03 01;177(3):197-199

Authors: Cisler JM

PMID: 32114776 [PubMed - indexed for MEDLINE]

Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-Based Health Recommender System.

JMIR Med Inform. 2020 Apr 23;8(4):e17642

Authors: Wang Z, Huang H, Cui L, Chen J, An J, Duan H, Ge H, Deng N

Abstract
BACKGROUND: Health education emerged as an important intervention for improving the awareness and self-management abilities of chronic disease patients. The development of information technologies has changed the form of patient educational materials from traditional paper materials to electronic materials. To date, the amount of patient educational materials on the internet is tremendous, with variable quality, which makes it hard to identify the most valuable materials by individuals lacking medical backgrounds.
OBJECTIVE: The aim of this study was to develop a health recommender system to provide appropriate educational materials for chronic disease patients in China and evaluate the effect of this system.
METHODS: A knowledge-based recommender system was implemented using ontology and several natural language processing (NLP) techniques. The development process was divided into 3 stages. In stage 1, an ontology was constructed to describe patient characteristics contained in the data. In stage 2, an algorithm was designed and implemented to generate recommendations based on the ontology. Patient data and educational materials were mapped to the ontology and converted into vectors of the same length, and then recommendations were generated according to similarity between these vectors. In stage 3, the ontology and algorithm were incorporated into an mHealth system for practical use. Keyword extraction algorithms and pretrained word embeddings were used to preprocess educational materials. Three strategies were proposed to improve the performance of keyword extraction. System evaluation was based on a manually assembled test collection for 50 patients and 100 educational documents. Recommendation performance was assessed using the macro precision of top-ranked documents and the overall mean average precision (MAP).
RESULTS: The constructed ontology contained 40 classes, 31 object properties, 67 data properties, and 32 individuals. A total of 80 SWRL rules were defined to implement the semantic logic of mapping patient original data to the ontology vector space. The recommender system was implemented as a separate Web service connected with patients' smartphones. According to the evaluation results, our system can achieve a macro precision up to 0.970 for the top 1 recommendation and an overall MAP score up to 0.628.
CONCLUSIONS: This study demonstrated that a knowledge-based health recommender system has the potential to accurately recommend educational materials to chronic disease patients. Traditional NLP techniques combined with improvement strategies for specific language and domain proved to be effective for improving system performance. One direction for future work is to explore the effect of such systems from the perspective of patients in a practical setting.

PMID: 32324148 [PubMed - as supplied by publisher]

BioHackathon 2015: Semantics of data for life sciences and reproducible research.

F1000Res. 2020;9:136

Authors: Vos RA, Katayama T, Mishima H, Kawano S, Kawashima S, Kim JD, Moriya Y, Tokimatsu T, Yamaguchi A, Yamamoto Y, Wu H, Amstutz P, Antezana E, Aoki NP, Arakawa K, Bolleman JT, Bolton E, Bonnal RJP, Bono H, Burger K, Chiba H, Cohen KB, Deutsch EW, Fernández-Breis JT, Fu G, Fujisawa T, Fukushima A, García A, Goto N, Groza T, Hercus C, Hoehndorf R, Itaya K, Juty N, Kawashima T, Kim JH, Kinjo AR, Kotera M, Kozaki K, Kumagai S, Kushida T, Lütteke T, Matsubara M, Miyamoto J, Mohsen A, Mori H, Naito Y, Nakazato T, Nguyen-Xuan J, Nishida K, Nishida N, Nishide H, Ogishima S, Ohta T, Okuda S, Paten B, Perret JL, Prathipati P, Prins P, Queralt-Rosinach N, Shinmachi D, Suzuki S, Tabata T, Takatsuki T, Taylor K, Thompson M, Uchiyama I, Vieira B, Wei CH, Wilkinson M, Yamada I, Yamanaka R, Yoshitake K, Yoshizawa AC, Dumontier M, Kosaki K, Takagi T

Abstract
We report on the activities of the 2015 edition of the BioHackathon, an annual event that brings together researchers and developers from around the world to develop tools and technologies that promote the reusability of biological data. We discuss issues surrounding the representation, publication, integration, mining and reuse of biological data and metadata across a wide range of biomedical data types of relevance for the life sciences, including chemistry, genotypes and phenotypes, orthology and phylogeny, proteomics, genomics, glycomics, and metabolomics. We describe our progress to address ongoing challenges to the reusability and reproducibility of research results, and identify outstanding issues that continue to impede the progress of bioinformatics research. We share our perspective on the state of the art, continued challenges, and goals for future research and development for the life sciences Semantic Web.

PMID: 32308977 [PubMed - in process]

Design, development and validation of a system for automatic help to medical text understanding.

Int J Med Inform. 2020 Mar 04;138:104109

Authors: Alfano M, Lenzitti B, Lo Bosco G, Muriana C, Piazza T, Vizzini G

Abstract
OBJECTIVE: The paper presents a web-based application, SIMPLE, that facilitates medical text comprehension by identifying the health-related terms of a medical text and providing the corresponding consumer terms and explanations.
BACKGROUND: The comprehension of a medical text is often a difficult task for laypeople because it requires semantic abilities that can differ from a person to another, depending on his/her health-literacy level. Some systems have been developed for facilitating the comprehension of medical texts through text simplification, either syntactical or lexical. The ones dealing with lexical simplification usually replace the original text and do not provide additional information. We have developed a system that provides the consumer terms alongside the original medical terms and also adds consumer explanations. Moreover, differently from other solutions, our system works with multiple languages.
METHODS: We have developed the SIMPLE application that is able to automatically: 1) identify medical terms in a medical text by using medical vocabularies; 2) translate the medical terms into consumer terms through medical-consumer thesauri; 3) provide term explanations by using health-consumer dictionaries. SIMPLE can be used as a standalone web application or can it be embedded into common health platforms for real time identification and explanation of medical terms. At present, it works with English and Italian texts but it can be easily extended to other languages. We have run subjective tests with both medical experts and non-experts as well as objective tests to verify the effectiveness of SIMPLE and its simplicity of use.
RESULTS: Non-experts found SIMPLE easy to use and responsive. The big majority of respondents confirmed they were helped by SIMPLE in understanding medical texts and declared their willingness to continue using SIMPLE and to recommend it to other people. The subjective tests, conducted with medical experts on a set of Italian radiology reports, showed an agreement between SIMPLE and the experts, on the highlighted medical terms, that ranges between 74.05 % and 81.16 % as well as an agreement of around 60 % on the consumer term translation. The objective tests showed that the consumer terms, provided by SIMPLE, are, on average, eighteen times more familiar than the relative medical terms so proving, once more, the effectiveness of SIMPLE in simplifying the medical terms.
CONCLUSIONS: The performed tests demonstrate the effectiveness of SIMPLE, its simplicity of use and the willingness of people in continuing with its use. SIMPLE provides, with a good agreement level, the same information that medical experts would provide. Finally, the consumer terms are 'objectively' more familiar than the related technical terms and as a consequence, much easier to understand.

PMID: 32305022 [PubMed - as supplied by publisher]

Engaging with big data: Occupational therapy needs to recognise the potential of using linked data to support evidence-based practice.

Aust Occup Ther J. 2019 02;66(1):3-4

Authors: Cordier R, Ferrante A

PMID: 30714629 [PubMed - indexed for MEDLINE]

Optimizing Sensor Ontology Alignment through Compact co-Firefly Algorithm.

Sensors (Basel). 2020 Apr 06;20(7):

Authors: Xue X, Chen J

Abstract
Semantic Sensor Web (SSW) links the semantic web technique with the sensor network, which utilizes sensor ontology to describe sensor information. Annotating sensor data with different sensor ontologies can be of help to implement different sensor systems' inter-operability, which requires that the sensor ontologies themselves are inter-operable. Therefore, it is necessary to match the sensor ontologies by establishing the meaningful links between semantically related sensor information. Since the Swarm Intelligent Algorithm (SIA) represents a good methodology for addressing the ontology matching problem, we investigate a popular SIA, that is, the Firefly Algorithm (FA), to optimize the ontology alignment. To save the memory consumption and better trade off the algorithm's exploitation and exploration, in this work, we propose a general-purpose ontology matching technique based on Compact co-Firefly Algorithm (CcFA), which combines the compact encoding mechanism with the co-Evolutionary mechanism. Our proposal utilizes the Gray code to encode the solutions, two compact operators to respectively implement the exploiting strategy and exploring strategy, and two Probability Vectors (PVs) to represent the swarms that respectively focuses on the exploitation and exploration. Through the communications between two swarms in each generation, CcFA is able to efficiently improve the searching efficiency when addressing the sensor ontology matching problem. The experiment utilizes the Conference track and three pairs of real sensor ontologies to test our proposal's performance. The statistical results show that CcFA based ontology matching technique can effectively match the sensor ontologies and other general ontologies in the domain of organizing conferences.

PMID: 32268547 [PubMed - in process]

The Innovative and Sustainable Use of Dental Panoramic Radiographs for the Detection of Osteoporosis.

Int J Environ Res Public Health. 2020 Apr 03;17(7):

Authors: Yeung AWK, Mozos I

Abstract
This bibliometric study evaluated the scientific impact of papers dealing with osteoporosis detected by dental panoramic radiographs by performing citation analysis and cited reference analysis. Retrospective data was extracted from the Web of Science Core Collection database and imported into VOSviewer, CRExplorer, and CitNetExplorer for analyzing semantic contents, cited references, and temporal citation network. The 280 relevant papers identified were cited 4874 times, having an h-index of 38 and 17.4 citations per paper. The top five major contributing countries were Japan (n = 54, 19.3%), USA (n = 43, 15.4%), Brazil (n = 38, 13.6%), Turkey (n = 38, 13.6%), and the UK (n = 32, 11.4%). Citation per paper correlated with publication count among the authors and institutions. Mandibular cortical width was the most frequently used and most cited measurement index. References published during the 1970s and 1980s have built the foundation for the development of research that investigates the potential associations between osteoporosis and radiographic measurements on panoramic radiographs. Osteoporosis detection by dental panoramic radiographs is a perennially investigated research topic with global contributions. Panoramic radiographs are considered early detection and screening tools for osteoporosis by worldwide research.

PMID: 32260243 [PubMed - in process]

Dynamically loading IFC models on a web browser based on spatial semantic partitioning.

Vis Comput Ind Biomed Art. 2019 Jun 03;2(1):4

Authors: Lu HL, Wu JX, Liu YS, Wang WQ

Abstract
Industry foundation classes (IFC) is an open and neutral data format specification for building information modeling (BIM) that plays a crucial role in facilitating interoperability. With increases in web-based BIM applications, there is an urgent need for fast loading large IFC models on a web browser. However, the task of fully loading large IFC models typically consumes a large amount of memory of a web browser or even crashes the browser, and this significantly limits further BIM applications. In order to address the issue, a method is proposed for dynamically loading IFC models based on spatial semantic partitioning (SSP). First, the spatial semantic structure of an input IFC model is partitioned via the extraction of story information and establishing a component space index table on the server. Subsequently, based on user interaction, only the model data that a user is interested in is transmitted, loaded, and displayed on the client. The presented method is implemented via Web Graphics Library, and this enables large IFC models to be fast loaded on the web browser without requiring any plug-ins. When compared with conventional methods that load all IFC model data for display purposes, the proposed method significantly reduces memory consumption in a web browser, thereby allowing the loading of large IFC models. When compared with the existing method of spatial partitioning for 3D data, the proposed SSP entirely uses semantic information in the IFC file itself, and thereby provides a better interactive experience for users.

PMID: 32240404 [PubMed - as supplied by publisher]

Big Trouble in Big Datasets: The Problem with Causality.

Eur J Vasc Endovasc Surg. 2020 03;59(3):446

Authors: Twine CP

PMID: 31740283 [PubMed - indexed for MEDLINE]

A propositional AI system for supporting epilepsy diagnosis based on the 2017 epilepsy classification: Illustrated by Dravet syndrome.

Epilepsy Behav. 2020 Mar 27;106:107021

Authors: Chiang KL, Huang CY, Hsieh LP, Chang KP

Abstract
PURPOSE: The 2017 epilepsy and seizure diagnosis framework emphasizes epilepsy syndromes and the etiology-based approach. We developed a propositional artificial intelligence (AI) system based on the above concepts to support physicians in the diagnosis of epilepsy.
METHODS: We analyzed and built ontology knowledge for the classification of seizure patterns, epilepsy, epilepsy syndrome, and etiologies. Protégé ontology tool was applied in this study. In order to enable the system to be close to the inferential thinking of clinical experts, we classified and constructed knowledge of other epilepsy-related knowledge, including comorbidities, epilepsy imitators, epilepsy descriptors, characteristic electroencephalography (EEG) findings, treatments, etc. We used the Ontology Web Language with Description Logic (OWL-DL) and Semantic Web Rule Language (SWRL) to design rules for expressing the relationship between these ontologies.
RESULTS: Dravet syndrome was taken as an illustration for epilepsy syndromes implementation. We designed an interface for the physician to enter the various characteristics of the patients. Clinical data of an 18-year-old boy with epilepsy was applied to the AI system. Through SWRL and reasoning engine Drool's execution, we successfully demonstrate the process of differential diagnosis.
CONCLUSION: We developed a propositional AI system by using the OWL-DL/SWRL approach to deal with the complexity of current epilepsy diagnosis. The experience of this system, centered on the clinical epilepsy syndromes, paves a path to construct an AI system for further complicated epilepsy diagnosis.

PMID: 32224446 [PubMed - as supplied by publisher]

Drug vector representation: a tool for drug similarity analysis.

Mol Genet Genomics. 2020 Mar 28;:

Authors: Lin L, Wan L, He H, Liu W

Abstract
DrugMatrix is a valuable toxicogenomic dataset, which provides in vivo transcriptome data corresponding to hundreds of chemical drugs. However, the relationships between drugs and how those drugs affect the biological process are still unknown. The high dimensionality of the microarray data hinders its application. The aims of this study are to (1) represent the transcriptome data by lower-dimensional vectors, (2) compare drug similarity, (3) represent drug combinations by adding vectors and (4) infer drug mechanism of action (MoA) and genotoxicity features. We borrowed the latent semantic analysis (LSA) technique from natural language processing to represent treatments (drugs with multiple concentrations and time points) by dense vectors, each dimension of which is an orthogonal biological feature. The gProfiler enrichment tool was used for the 100-dimensional vector feature annotation. The similarity between treatments vectors was calculated by the cosine function. Adding vectors may represent drug combinations, treatment times or treatment doses that are not presented in the original data. Drug-drug interaction pairs had a higher similarity than random drug pairs in the hepatocyte data. The vector features helped to reveal the MoA. Differential feature expression was also implicated for genotoxic and non-genotoxic carcinogens. An easy-to-use Web tool was developed by Shiny Web application framework for the exploration of treatment similarities and drug combinations (https://bioinformatics.fafu.edu.cn/drugmatrix/). We represented treatments by vectors and provided a tool that is useful for hypothesis generation in toxicogenomic, such as drug similarity, drug repurposing, combination therapy and MoA.

PMID: 32222838 [PubMed - as supplied by publisher]

MLCD: A Unified Software Package for Cancer Diagnosis.

JCO Clin Cancer Inform. 2020 Mar;4:290-298

Authors: Wu W, Li B, Mercan E, Mehta S, Bartlett J, Weaver DL, Elmore JG, Shapiro LG

Abstract
PURPOSE: Machine Learning Package for Cancer Diagnosis (MLCD) is the result of a National Institutes of Health/National Cancer Institute (NIH/NCI)-sponsored project for developing a unified software package from state-of-the-art breast cancer biopsy diagnosis and machine learning algorithms that can improve the quality of both clinical practice and ongoing research.
METHODS: Whole-slide images of 240 well-characterized breast biopsy cases, initially assembled under R01 CA140560, were used for developing the algorithms and training the machine learning models. This software package is based on the methodology developed and published under our recent NIH/NCI-sponsored research grant (R01 CA172343) for finding regions of interest (ROIs) in whole-slide breast biopsy images, for segmenting ROIs into histopathologic tissue types and for using this segmentation in classifiers that can suggest final diagnoses.
RESULT: The package provides an ROI detector for whole-slide images and modules for semantic segmentation into tissue classes and diagnostic classification into 4 classes (benign, atypia, ductal carcinoma in situ, invasive cancer) of the ROIs. It is available through the GitHub repository under the Massachusetts Institute of Technology license and will later be distributed with the Pathology Image Informatics Platform system. A Web page provides instructions for use.
CONCLUSION: Our tools have the potential to provide help to other cancer researchers and, ultimately, to practicing physicians and will motivate future research in this field. This article describes the methodology behind the software development and gives sample outputs to guide those interested in using this package.

PMID: 32216637 [PubMed - as supplied by publisher]

Enabling semantic queries across federated bioinformatics databases.

Database (Oxford). 2019 01 01;2019:

Authors: Sima AC, Mendes de Farias T, Zbinden E, Anisimova M, Gil M, Stockinger H, Stockinger K, Robinson-Rechavi M, Dessimoz C

Abstract
MOTIVATION: Data integration promises to be one of the main catalysts in enabling new insights to be drawn from the wealth of biological data available publicly. However, the heterogeneity of the different data sources, both at the syntactic and the semantic level, still poses significant challenges for achieving interoperability among biological databases.
RESULTS: We introduce an ontology-based federated approach for data integration. We applied this approach to three heterogeneous data stores that span different areas of biological knowledge: (i) Bgee, a gene expression relational database; (ii) Orthologous Matrix (OMA), a Hierarchical Data Format 5 orthology DS; and (iii) UniProtKB, a Resource Description Framework (RDF) store containing protein sequence and functional information. To enable federated queries across these sources, we first defined a new semantic model for gene expression called GenEx. We then show how the relational data in Bgee can be expressed as a virtual RDF graph, instantiating GenEx, through dedicated relational-to-RDF mappings. By applying these mappings, Bgee data are now accessible through a public SPARQL endpoint. Similarly, the materialized RDF data of OMA, expressed in terms of the Orthology ontology, is made available in a public SPARQL endpoint. We identified and formally described intersection points (i.e. virtual links) among the three data sources. These allow performing joint queries across the data stores. Finally, we lay the groundwork to enable nontechnical users to benefit from the integrated data, by providing a natural language template-based search interface.

PMID: 31697362 [PubMed - indexed for MEDLINE]