FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950416458> ?p ?o ?g. }

• W2950416458 abstract "Abstract Recent studies have proposed deep learning techniques, namely recurrent neural networks, to improve biomedical text mining tasks. However, these techniques rarely take advantage of existing domain-specific resources, such as ontologies. In Life and Health Sciences there is a vast and valuable set of such resources publicly available, which are continuously being updated. Biomedical ontologies are nowadays a mainstream approach to formalize existing knowledge about entities, such as genes, chemicals, phenotypes, and disorders. These resources contain supplementary information that may not be yet encoded in training data, particularly in domains with limited labeled data. We propose a new model, BO-LSTM, that takes advantage of domain-specific ontologies, by representing each entity as the sequence of its ancestors in the ontology. We implemented BO-LSTM as a recurrent neural network with long short-term memory units and using an open biomedical ontology, which in our case-study was Chemical Entities of Biological Interest (ChEBI). We assessed the performance of BO-LSTM on detecting and classifying drug-drug interactions in a publicly available corpus from an international challenge, composed of 792 drug descriptions and 233 scientific abstracts. By using the domain-specific ontology in addition to word embeddings and WordNet, BO-LSTM improved both the F1-score of the detection and classification of drug-drug interactions, particularly in a document set with a limited number of annotations. Our findings demonstrate that besides the high performance of current deep learning techniques, domain-specific ontologies can still be useful to mitigate the lack of labeled data. Author summary A high quantity of biomedical information is only available in documents such as scientific articles and patents. Due to the rate at which new documents are produced, we need automatic methods to extract useful information from them. Text mining is a subfield of information retrieval which aims at extracting relevant information from text. Scientific literature is a challenge to text mining because of the complexity and specificity of the topics approached. In recent years, deep learning has obtained promising results in various text mining tasks by exploring large datasets. On the other hand, ontologies provide a detailed and sound representation of a domain and have been developed to diverse biomedical domains. We propose a model that combines deep learning algorithms with biomedical ontologies to identify relations between concepts in text. We demonstrate the potential of this model to extract drug-drug interactions from abstracts and drug descriptions. This model can be applied to other biomedical domains using an annotated corpus of documents and an ontology related to that domain to train a new classifier." @default.
• W2950416458 created "2019-06-27" @default.
• W2950416458 creator A5014333753 @default.
• W2950416458 creator A5024583659 @default.
• W2950416458 creator A5064856680 @default.
• W2950416458 date "2018-06-01" @default.
• W2950416458 modified "2023-10-16" @default.
• W2950416458 title "BO-LSTM: Classifying relations via long short-term memory networks along biomedical ontologies" @default.
• W2950416458 cites W1971192989 @default.
• W2950416458 cites W1981082061 @default.
• W2950416458 cites W1987492677 @default.
• W2950416458 cites W2001417231 @default.
• W2950416458 cites W2017753937 @default.
• W2950416458 cites W2030408698 @default.
• W2950416458 cites W2043150741 @default.
• W2950416458 cites W2051390224 @default.
• W2950416458 cites W2053673723 @default.
• W2950416458 cites W2064675550 @default.
• W2950416458 cites W2067704478 @default.
• W2950416458 cites W2096951189 @default.
• W2950416458 cites W2103017472 @default.
• W2950416458 cites W2104324457 @default.
• W2950416458 cites W2113142309 @default.
• W2950416458 cites W2114063639 @default.
• W2950416458 cites W2124555364 @default.
• W2950416458 cites W2135192531 @default.
• W2950416458 cites W2140611297 @default.
• W2950416458 cites W2149369282 @default.
• W2950416458 cites W2170189740 @default.
• W2950416458 cites W2250539671 @default.
• W2950416458 cites W2485374661 @default.
• W2950416458 cites W2774333084 @default.
• W2950416458 cites W2964078317 @default.
• W2950416458 cites W2964167098 @default.
• W2950416458 cites W2964217331 @default.
• W2950416458 cites W2964318298 @default.
• W2950416458 cites W3012733872 @default.
• W2950416458 cites W4244809183 @default.
• W2950416458 doi "https://doi.org/10.1101/336719" @default.
• W2950416458 hasPublicationYear "2018" @default.
• W2950416458 type Work @default.
• W2950416458 sameAs 2950416458 @default.
• W2950416458 citedByCount "1" @default.
• W2950416458 countsByYear W29504164582022 @default.
• W2950416458 crossrefType "posted-content" @default.
• W2950416458 hasAuthorship W2950416458A5014333753 @default.
• W2950416458 hasAuthorship W2950416458A5024583659 @default.
• W2950416458 hasAuthorship W2950416458A5064856680 @default.
• W2950416458 hasBestOaLocation W29504164581 @default.
• W2950416458 hasConcept C108583219 @default.
• W2950416458 hasConcept C111472728 @default.
• W2950416458 hasConcept C119857082 @default.
• W2950416458 hasConcept C121332964 @default.
• W2950416458 hasConcept C134306372 @default.
• W2950416458 hasConcept C137982476 @default.
• W2950416458 hasConcept C138885662 @default.
• W2950416458 hasConcept C154945302 @default.
• W2950416458 hasConcept C157659113 @default.
• W2950416458 hasConcept C177264268 @default.
• W2950416458 hasConcept C199360897 @default.
• W2950416458 hasConcept C204321447 @default.
• W2950416458 hasConcept C207685749 @default.
• W2950416458 hasConcept C22550185 @default.
• W2950416458 hasConcept C23123220 @default.
• W2950416458 hasConcept C25810664 @default.
• W2950416458 hasConcept C33923547 @default.
• W2950416458 hasConcept C36503486 @default.
• W2950416458 hasConcept C41008148 @default.
• W2950416458 hasConcept C50971890 @default.
• W2950416458 hasConcept C61797465 @default.
• W2950416458 hasConcept C62520636 @default.
• W2950416458 hasConceptScore W2950416458C108583219 @default.
• W2950416458 hasConceptScore W2950416458C111472728 @default.
• W2950416458 hasConceptScore W2950416458C119857082 @default.
• W2950416458 hasConceptScore W2950416458C121332964 @default.
• W2950416458 hasConceptScore W2950416458C134306372 @default.
• W2950416458 hasConceptScore W2950416458C137982476 @default.
• W2950416458 hasConceptScore W2950416458C138885662 @default.
• W2950416458 hasConceptScore W2950416458C154945302 @default.
• W2950416458 hasConceptScore W2950416458C157659113 @default.
• W2950416458 hasConceptScore W2950416458C177264268 @default.
• W2950416458 hasConceptScore W2950416458C199360897 @default.
• W2950416458 hasConceptScore W2950416458C204321447 @default.
• W2950416458 hasConceptScore W2950416458C207685749 @default.
• W2950416458 hasConceptScore W2950416458C22550185 @default.
• W2950416458 hasConceptScore W2950416458C23123220 @default.
• W2950416458 hasConceptScore W2950416458C25810664 @default.
• W2950416458 hasConceptScore W2950416458C33923547 @default.
• W2950416458 hasConceptScore W2950416458C36503486 @default.
• W2950416458 hasConceptScore W2950416458C41008148 @default.
• W2950416458 hasConceptScore W2950416458C50971890 @default.
• W2950416458 hasConceptScore W2950416458C61797465 @default.
• W2950416458 hasConceptScore W2950416458C62520636 @default.
• W2950416458 hasLocation W29504164581 @default.
• W2950416458 hasLocation W29504164582 @default.
• W2950416458 hasLocation W29504164583 @default.
• W2950416458 hasOpenAccess W2950416458 @default.
• W2950416458 hasPrimaryLocation W29504164581 @default.
• W2950416458 hasRelatedWork W1572517894 @default.
• W2950416458 hasRelatedWork W2011365423 @default.

• next