Dataset Information

LAITOR--Literature Assistant for Identification of Terms co-Occurrences and Relationships.

ABSTRACT: BACKGROUND: Biological knowledge is represented in scientific literature that often describes the function of genes/proteins (bioentities) in terms of their interactions (biointeractions). Such bioentities are often related to biological concepts of interest that are specific of a determined research field. Therefore, the study of the current literature about a selected topic deposited in public databases, facilitates the generation of novel hypotheses associating a set of bioentities to a common context. RESULTS: We created a text mining system (LAITOR: Literature Assistant for Identification of Terms co-Occurrences and Relationships) that analyses co-occurrences of bioentities, biointeractions, and other biological terms in MEDLINE abstracts. The method accounts for the position of the co-occurring terms within sentences or abstracts. The system detected abstracts mentioning protein-protein interactions in a standard test (BioCreative II IAS test data) with a precision of 0.82-0.89 and a recall of 0.48-0.70. We illustrate the application of LAITOR to the detection of plant response genes in a dataset of 1000 abstracts relevant to the topic. CONCLUSIONS: Text mining tools combining the extraction of interacting bioentities and biological concepts with network displays can be helpful in developing reasonable hypotheses in different scientific backgrounds.

SUBMITTER: Barbosa-Silva A

PROVIDER: S-EPMC3098111 | biostudies-literature | 2010

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

LAITOR--Literature Assistant for Identification of Terms co-Occurrences and Relationships.

Barbosa-Silva Adriano A Soldatos Theodoros G TG Magalhães Ivan L F IL Pavlopoulos Georgios A GA Fontaine Jean-Fred JF Andrade-Navarro Miguel A MA Schneider Reinhard R Ortega J Miguel JM

BMC bioinformatics 20100201

<h4>Background</h4>Biological knowledge is represented in scientific literature that often describes the function of genes/proteins (bioentities) in terms of their interactions (biointeractions). Such bioentities are often related to biological concepts of interest that are specific of a determined research field. Therefore, the study of the current literature about a selected topic deposited in public databases, facilitates the generation of novel hypotheses associating a set of bioentities to ...[more]

PMID: 20122157

Similar Datasets

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

LAITOR--Literature Assistant for Identification of Terms co-Occurrences and Relationships.

Publications

LAITOR--Literature Assistant for Identification of Terms co-Occurrences and Relationships.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets