Knowledge Representation and Management: a Linked Data Perspective

Barros, M.; Couto, Francisco M.

doi:10.15265/iy-2016-022

Cited by 18 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It would also be interesting to apply phenotypic similarity to identify potential misannotations that are not semantically related to the entities found in the text [ 21 ]. Since electronic health records contain HPO terms, an exciting challenge would be to assess the performance of IHP in a multilingual corpus [ 22 ] and how it could help us to represent their knowledge using linked data technologies [ 23 ].…”

Section: Discussionmentioning

confidence: 99%

Identifying Human Phenotype Terms by Combining Machine Learning and Validation Rules

Lobo

Lamurias

Couto

2017

BioMed Research International

View full text Add to dashboard Cite

Named-Entity Recognition is commonly used to identify biological entities such as proteins, genes, and chemical compounds found in scientific articles. The Human Phenotype Ontology (HPO) is an ontology that provides a standardized vocabulary for phenotypic abnormalities found in human diseases. This article presents the Identifying Human Phenotypes (IHP) system, tuned to recognize HPO entities in unstructured text. IHP uses Stanford CoreNLP for text processing and applies Conditional Random Fields trained with a rich feature set, which includes linguistic, orthographic, morphologic, lexical, and context features created for the machine learning-based classifier. However, the main novelty of IHP is its validation step based on a set of carefully crafted manual rules, such as the negative connotation analysis, that combined with a dictionary can filter incorrectly identified entities, find missed entities, and combine adjacent entities. The performance of IHP was evaluated using the recently published HPO Gold Standardized Corpora (GSC), where the system Bio-LarK CR obtained the best -measure of 0.56. IHP achieved an -measure of 0.65 on the GSC. Due to inconsistencies found in the GSC, an extended version of the GSC was created, adding 881 entities and modifying 4 entities. IHP achieved an -measure of 0.863 on the new GSC.

show abstract

Section: Discussionmentioning

confidence: 99%

Identifying Human Phenotype Terms by Combining Machine Learning and Validation Rules

Lobo

Lamurias

Couto

2017

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Several knowledge-bases of biomedicine based on these technologies have been developed (e.g. [ 3 , 6 , 31 , 48 ]), and their uses extend beyond deductive retrieval alone.…”

Section: Knowledge-based Inferencementioning

confidence: 99%

Knowledge-based biomedical Data Science

Hunter

2017

View full text Add to dashboard Cite

Computational manipulation of knowledge is an important, and often under-appreciated, aspect of biomedical Data Science. The first Data Science initiative from the US National Institutes of Health was entitled “Big Data to Knowledge (BD2K).” The main emphasis of the more than $200M allocated to that program has been on “Big Data;” the “Knowledge” component has largely been the implicit assumption that the work will lead to new biomedical knowledge. However, there is long-standing and highly productive work in computational knowledge representation and reasoning, and computational processing of knowledge has a role in the world of Data Science. Knowledge-based biomedical Data Science involves the design and implementation of computer systems that act as if they knew about biomedicine. There are many ways in which a computational approach might act as if it knew something: for example, it might be able to answer a natural language question about a biomedical topic, or pass an exam; it might be able to use existing biomedical knowledge to rank or evaluate hypotheses; it might explain or interpret data in light of prior knowledge, either in a Bayesian or other sort of framework. These are all examples of automated reasoning that act on computational representations of knowledge. After a brief survey of existing approaches to knowledge-based data science, this position paper argues that such research is ripe for expansion, and expanded application.

show abstract

“…By making use of open linked data -a previously validated method 68 of publishing structured data so that it can be interlinked and become more useful through semantic queries -, it is possible to cross validate, counter-examine, and derive additional knowledge (to name a few practical applications) from our own findings deduced from this work. In this manner, it is possible to provide continuity to our studies not only in temporal terms but also in knowledgegathering and, consequently, wisdom acquirement.…”

Section: Future Workmentioning

confidence: 99%

Anthropometric Data Analytics: A Portuguese Case Study

Barata

Carvalho

Couto

2017

11th International Conference on Practical Applications of Computational Biology &Amp; Bioinformatics

View full text Add to dashboard Cite

"Sometimes science is more art than science, Morty.A lot of people don't get that." AgradecimentosTodo o organismo pode ser interpretado como um somatório de instantes. Ao longo do tempo, em cada instante, há troca de informação entre o indivíduo e o ambiente. De modo a proporcionar a continuidade do ser, a memória será uma das características de maior relevância que advém da experienciação da vida. O processo de aprendizagem será a retenção, interpretação, e utilização de informação passada. A capacidade de formular hipóteses face novos problemas, utilizando conhecimento adquirido através de eventos passados, tem para mim uma conotação fascinante. Fascinante é, também, o facto destas propriedades algorítmicas da mente humana em pouco ou nada me servirem para o exercício de elaboração de tese uma de mestrado. Quaisquer noções empíricas previamente adquiridas servem apenas para providenciar algum tipo de aconchego contra a perceção tardia da realidade. É nesse momento de maximização da variável incompetência que a contribuição intelectual de outros tem maior validade e aplicação prática. Por esse fator, é necessário mencionar as entidades sem as quais nenhum deste trabalho seria possível.Independentemente de ordem, a todos agradeço igualmente. Considero que a omissão de um qualquer interveniente tenha a mesma consequência: a ausência do produto final que é o presente trabalho. Ao Professor Doutor Francisco Couto, agradeço pela sua paciência aparentemente infinita enquanto meu orientador, pela sua disponibilidade constante, associado ao seu sentido crítico e construtivo. Agradeço em particular à Dr.ª Sância Ramos, diretora do serviço de Anatomia Patológica do Centro Hospitalar de Lisboa Ocidental, e à Dr.ª Lucília Carvalho, minha co-orientadora e assistente com grau de consultor do mesmo serviço e responsável pelo setor de Fetopatologia associado ao mesmo centro hospitalar, por me facultarem o seu tempo e amabilidade durante todo este longo e árduo percurso académico. Relativamente à minha família, tenho em elevada estima o facto de me terem sempre apoiado incondicionalmente; por me terem aturado e às minhas lamúrias, por partilharem comigo as suas experiências, opiniões, conselhos, e considerações. Aos meus amigos, por não só partilharem os seus ombros carinhosos como por me ajudarem a desanuviar nos momentos de maior ansiedade, agradeço imensamente.vi Resumo Durante o período neonatal, para produzir corretamente um diagnóstico patológico e permitir assim uma reposta adequada, é imperativo realizar uma rigorosa estimação acerca da idade gestacional do feto. Esta previsão é aplicada como ferramenta essencial para o aconselhamento parental de modo a providenciar um plano de cuidados perinatais apropriado. Durante uma autópsia fetal, a idade gestacional é uma variável a ter em consideração, particularmente utilizada aquando de situações de terminação de gravidez medicamente assistida e/ou infanticídios. No nosso caso, foram colecionadas observações representativas da população Portuguesa da região Centro-Sul de Port...

show abstract

Knowledge Representation and Management: a Linked Data Perspective

Cited by 18 publications

References 39 publications

Identifying Human Phenotype Terms by Combining Machine Learning and Validation Rules

Identifying Human Phenotype Terms by Combining Machine Learning and Validation Rules

Knowledge-based biomedical Data Science

Anthropometric Data Analytics: A Portuguese Case Study

Contact Info

Product

Resources

About