Dataset Information

Inferring new relations between medical entities using literature curated term co-occurrences.

ABSTRACT: Objectives:Identifying new relations between medical entities, such as drugs, diseases, and side effects, is typically a resource-intensive task, involving experimentation and clinical trials. The increased availability of related data and curated knowledge enables a computational approach to this task, notably by training models to predict likely relations. Such models rely on meaningful representations of the medical entities being studied. We propose a generic features vector representation that leverages co-occurrences of medical terms, linked with PubMed citations. Materials and Methods:We demonstrate the usefulness of the proposed representation by inferring two types of relations: a drug causes a side effect and a drug treats an indication. To predict these relations and assess their effectiveness, we applied 2 modeling approaches: multi-task modeling using neural networks and single-task modeling based on gradient boosting machines and logistic regression. Results:These trained models, which predict either side effects or indications, obtained significantly better results than baseline models that use a single direct co-occurrence feature. The results demonstrate the advantage of a comprehensive representation. Discussion:Selecting the appropriate representation has an immense impact on the predictive performance of machine learning models. Our proposed representation is powerful, as it spans multiple medical domains and can be used to predict a wide range of relation types. Conclusion:The discovery of new relations between various medical entities can be translated into meaningful insights, for example, related to drug development or disease understanding. Our representation of medical entities can be used to train models that predict such relations, thus accelerating healthcare-related discoveries.

SUBMITTER: Spiro A

PROVIDER: S-EPMC6951958 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background Entity relation extraction technology can be used to extract entities and relations from medical literature, and automatically establish professional mapping knowledge domains. The classical text classification model, convolutional neural networks for sentence classification (TEXTCNN), has been shown to have good classification performance, but also has a long-distance dependency problem, which is a common problem of convolutional neural networks (CNNs). Recurrent neural networks (RNN) address the long-distance dependency problem but cannot capture text features at a specific scale in the text. Methods To solve these problems, this study sought to establish a model with a multi-scale convolutional recurrent neural network for Sentence Classification (TEXTCRNN) to address the deficiencies in the 2 neural network structures. In entity relation extraction, the entity pair is generally composed of a subject and an object, but as the subject in the entity pair of medical literature is always omitted, it is difficult to use this coding method to obtain general entity position information. Thus, we proposed a new coding method to obtain entity position information to re-establish the relationship between subject and object and complete the entity relation extraction. Results By comparing the benchmark neural network model and 2 typical multi-scale TEXTCRNN models, the TEXTCRNN [bidirectional long- and short-term memory (BiLSTM)] and TEXTCRNN [double-layer stacking gated recurrent unit (GRU)], the results showed that the multi-scale CRNN model had the best F1 value performance, and the TEXTCRNN (double-layer stacking GRU) was more capable of entity relation classification when the same entity word did not belong to the same entity relation. Conclusions The experimental results of the entity relation extraction from Pharmacopoeia of the People’s Republic of China—Guidelines for Clinical Drug Use—Volume of Chemical Drugs and Biological Products showed that entity relation extraction could effectively proceed using the new labeling method. Additionally, compared to typical neural network models, including the TEXTCNN, GRU, and BiLSTM, the multi-scale convolutional recurrent neural network structure had advantages across several evaluation indicators.

Project description:Analysing the relationships between biomolecules and the genetic diseases is a highly active area of research, where the aim is to identify the genes and their products that cause a particular disease due to functional changes originated from mutations. Biological ontologies are frequently employed in these studies, which provides researchers with extensive opportunities for knowledge discovery through computational data analysis. In this study, a novel approach is proposed for the identification of relationships between biomedical entities by automatically mapping phenotypic abnormality defining HPO terms with biomolecular function defining GO terms, where each association indicates the occurrence of the abnormality due to the loss of the biomolecular function expressed by the corresponding GO term. The proposed HPO2GO mappings were extracted by calculating the frequency of the co-annotations of the terms on the same genes/proteins, using already existing curated HPO and GO annotation sets. This was followed by the filtering of the unreliable mappings that could be observed due to chance, by statistical resampling of the co-occurrence similarity distributions. Furthermore, the biological relevance of the finalized mappings were discussed over selected cases, using the literature. The resulting HPO2GO mappings can be employed in different settings to predict and to analyse novel gene/protein-ontology term-disease relations. As an application of the proposed approach, HPO term-protein associations (i.e., HPO2protein) were predicted. In order to test the predictive performance of the method on a quantitative basis, and to compare it with the state-of-the-art, CAFA2 challenge HPO prediction target protein set was employed. The results of the benchmark indicated the potential of the proposed approach, as HPO2GO performance was among the best (Fmax = 0.35). The automated cross ontology mapping approach developed in this work may be extended to other ontologies as well, to identify unexplored relation patterns at the systemic level. The datasets, results and the source code of HPO2GO are available for download at: https://github.com/cansyl/HPO2GO.

Project description:BackgroundVenezuela has suffered a severe academic and research management crisis and funding opportunities for marine research and data management have been practically absent. This has worsened over the past five years and, as a result, libraries and other institutional spaces have been repeatedly vandalised, with hundreds of records, specimens and historical data stolen, destroyed or burned. To avoid the loss of irreplaceable data on Venezuelan biodiversity, an initiative was promoted, aimed at digitising information to create a rich dataset of biodiversity records, with emphasis on marine protected areas for the country, as well as to fill gaps in the distribution and status of marine biodiversity in Venezuela. Nighteen (19) institutions in the country focusing on marine science have consistently produced a wealth of information about Venezuela's marine biodiversity in the form of specimen collections, unpublished sampled data and research theses through the work of hundreds of researchers and students. An inventory of available data sources at these national institutions was conducted under the National Biodiversity Data Mobilization Grant and the Biodiversity Information for Development Program, together with the Global Biodiversity Information Facility (GBIF) support. All recovered and processed datasets were published in the Ocean Biodiversity Information System (OBIS) and the Global Biodiversity Information Facility (GBIF) repositories.New informationThis occurrences data collection represents a major contribution to the marine biodiversity inventory in Venezuela. It is based on numerous published papers, reports, books and checklists provided by experts, covering a broad taxonomic collection from which we obtained species occurrences (present and absent), organised into 59 datasets containing 40,881 records. This represents a 28.49% contribution to the records of the Venezuelan marine biodiversity reported to the OBIS (143,513 records in the OBIS until November 2022). The extracted data showed 3,041 marine species, with representatives of each of the six kingdoms: Animalia, Chromista, Bacteria, Plantae, Fungi and Protozoa. The datasets provide information on occurrence since 1822, extending the temporal coverage of the species occurrence inventory for Venezuela, which was established in 1879 before this project. The number of records for Venezuela increased by 41.3% compared with the data available before the project. Most of the occurrences (63.47%) were registered in Marine Protected Areas. Data collection included records of non-native species, descriptions of new species and species listed under different IUCN categories.

Dataset Information

Inferring new relations between medical entities using literature curated term co-occurrences.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets