Biomedical Text Mining and Ontologies

The paper assesses how model organism phenotypes contribute to identifying human disease genes and finds that only mouse phenotypes accurately predict human gene-disease associations.

The paper introduces the GA4GH Phenopacket schema to standardize the exchange of phenotypic data for precision medicine applications.

This paper introduces two deep learning models for metabolite named entity recognition and provides a corpus for metabolomics text-mining tasks.

The paper introduces the Xenopus Phenotype Ontology (XPO) to standardize phenotype data from Xenopus experiments and link them to human health and development.

The paper introduces the Neuron Phenotype Ontology (NPO) to standardize neuron naming and classification across neuroscientific studies, enabling interoperability and knowledge integration.

NLIMED converts natural language queries into SPARQL to discover model entities from biosimulation model repositories.

Auto-CORPus converts biomedical publication HTML and tables to standardized formats for text analytics.

LinkExplorer predicts, explains, and explores links in biomedical knowledge graphs using an explainable algorithm with a web interface for interactive analysis.

The paper introduces the BioThings SDK, a toolkit for building high-performance data APIs in biomedical research, enabling integration of annotations from multiple data sources.

HLA-SPREAD curates HLA associations from PubMed abstracts using NLP, providing structured data on diseases, ADRs, and populations across 112 countries and 32 ethnic groups.

The paper introduces STonKGs, a Transformer model trained on biomedical text and knowledge graphs, which outperforms single-modality models in classification tasks.

This paper develops a sequence labeling framework for drug-protein relation extraction, achieving higher performance than a text classification framework in the BioCreative VII challenge.

Gilda is a tool that normalizes biomedical entity names using machine-learned disambiguation models and provides a web service for this task.

DISEASES 2.0 updates a disease-gene association database by integrating text mining, curated data, and GWAS, increasing text-mined associations by 9-fold.

The paper develops automated methods to extract phenotypic features from literature to improve disease modeling for developmental disorders, showing increased accuracy over manual curation.

This paper explores sequence-to-sequence machine translation for concept recognition in biomedical text, achieving state-of-the-art results on the CRAFT Corpus with lower computational demands.

This study tracks the evolution of gene-disease associations over 30 years using text-mining to reveal shared mechanisms and drug targets across diseases.

TaxoNERD is a deep learning tool for recognizing taxonomic entities in ecological texts, outperforming existing methods on ecological corpora.

The paper introduces ABCkb, a database linking plants to human health by integrating curated data and mined relationships to generate nutritive hypotheses.

This paper introduces a method to automatically detect inconsistencies in gene ontology annotations using text mining models, achieving high precision on synthetic data.

ontoFAST is an R package that enables fast and interactive annotation of characters using biological ontologies, with features for querying and visualizing ontological hierarchies.

OnTheFly2.0 automates biomedical entity recognition and analysis from documents, revealing inflammatory and senescence pathways in severe COVID-19.

The paper uses word embeddings from PubMed to predict which protein kinases are relevant for treating specific cancers using machine learning.

The paper describes how the OBO Foundry formalized its principles into operational rules and implemented automated checks to evaluate ontology compliance, improving interoperability and quality.

The paper introduces FORUM, a Knowledge Graph that extracts and connects chemical-disease associations from databases and literature to support biological interpretation.

The paper constructs a planarian anatomy ontology to standardize nomenclature and enable cross-platform data integration and curation.

Ontoclick is a web browser extension that simplifies ontology term annotation in biomedical texts, making knowledge curation more accessible.

RENET2 extracts gene-disease associations from full-text articles with higher accuracy than existing tools, identifying 3.72M associations from 1.89M PMC articles.

MecCog provides a framework to structure and integrate genetic disease mechanisms from diverse sources, enabling the creation and sharing of mechanism schemas.