Biomedical Text Mining and Ontologies

Phen2Disease: A Phenotype-driven Semantic Similarity-based Integrated Model for Disease and Gene Prioritization

Phen2Disease prioritizes diseases and genes using phenotype similarity scores calculated from HPO terms, outperforming existing methods in cohorts with fewer HPO terms.

Unifying the Identification of Biomedical Entities with the Bioregistry

The paper introduces the Bioregistry, an open metaregistry that integrates and expands existing biomedical entity registries to improve interoperability and data reuse.

A curated collection of human vaccination response signatures

The paper curates a collection of >600 immune signatures from human vaccination studies and provides a data model and web dashboard for querying these signatures.

PEMT: A patent enrichment tool for drug discovery

PEMT extracts patent information linked to chemical structures and gene names from public databases to support drug discovery and research.

Assembling a corpus of phosphoproteomic annotations using ProtMapper to normalize site information from databases and text mining

The paper develops ProtMapper to normalize phosphosite positions from databases and text mining, creating a comprehensive corpus of regulatory annotations.

We are not ready yet: limitations of transfer learning for Disease Named Entity Recognition

The paper evaluates transfer learning's limitations in disease named entity recognition, showing poor generalization to new data like COVID-19 preprints.

Expanding a Database-derived Biomedical Knowledge Graph via Multi-relation Extraction from Biomedical Abstracts

The paper improves knowledge graph expansion by reusing label functions for multiple edge types in biomedical abstracts.

RTX-KG2: a system for building a semantically standardized knowledge graph for translational biomedicine

RTX-KG2 integrates 70 biomedical knowledge sources into a standards-compliant knowledge graph with a Biolink schema, providing downloadable and queryable versions via API.

Literature-based predictions of treatments for genetic disease pathology

This paper introduces PARMESAN, a tool that predicts drug-gene relationships using PubMed data, showing high accuracy for top-scoring predictions.

Bridging The Evolving Semantics: A Data Driven Approach to Knowledge Discovery In Biomedicine

The paper develops a data-driven approach to answer non-factoid biomedical questions by integrating authoritative and social media sources to support hypothesis generation and discovery.

Predicting cross-tissue hormone-gene relations usingbalanced word embeddings

The paper predicts hormone-gene associations across tissues using balanced word embeddings and a new dataset, identifying both known and novel genes involved in inter-tissue signaling.

OncoPubMiner: A platform for oncology publication mining

OncoPubMiner is a platform that mines oncology publications to create structured knowledge bases, enabling efficient and accurate gathering of precision oncology insights from scientific articles.

Discovering Monogenic Patients with a Confirmed Molecular Diagnosis in Millions of Clinical Notes with MonoMiner

MonoMiner identifies monogenic disease patients with confirmed molecular diagnoses from clinical notes, achieving high precision and recall in a large hospital system.

The VGNC: Expanding Standardized Vertebrate Gene Nomenclature

The paper describes the VGNC project, which standardizes gene nomenclature across vertebrate species, and reports its current status and availability.

dialogi: Utilising NLP with chemical and disease similarities to drive the identification of Drug-Induced Liver Injury literature

The paper presents an automated pipeline using NLP and chemical/disease embeddings to classify DILI-related literature, achieving high F1-scores in distinguishing DILI-positive from negative papers.

Analysis of Inbred Mouse strains' High-Impact Genotype-phenotype Hypotheses (AIMHIGH) reveals novel disease-causing candidate genes

AIMHIGH identifies novel disease-causing genes by analyzing inbred mouse strain data and machine learning-driven literature-based discovery.

Learning phenotypic patterns in genetic disease by symptom interaction modeling

This paper develops a symptom interaction model to address heterogeneous phenotype reporting in genetic disease, improving gene prioritization by 42%.

OUGene 2.0: An updated disease-associated over- and under-expressed gene database by mining full-text articles

OUGene 2.0 is an updated database of disease-associated over- and under-expressed genes, mined from full-text articles, containing 197,236 associations.

Gene symbol recognition with GeneOCR

GeneOCR is a web-based tool that recognizes, extracts, and checks gene symbols from figures, achieving over 80% accuracy in simulations.

How much do model organism phenotypes contribute to the computational identification of human disease genes?

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.

Validating the representation of distance between infarctdiseases using Word2Vec word embedding

The paper evaluates Word2Vec embeddings for infarction-related diseases, finding that cosine distance best aligns with ICD-10 codes while Euclidean distance reflects word frequency.

A machine learning based method for the identification of functionally important genes

The paper develops a machine learning method to identify gene-physiological response associations using literature data from bacterial and plant species.

The GA4GH Phenopacket schema: A computable representation of clinical data for precision medicine

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

OntoContext, a new python package for gene contextualization based on the annotation of biomedical texts

OntoContext is a Python package that annotates biomedical texts with gene, RNA, and protein names in specific contexts using ontologies, outperforming NCBO Annotator in evaluations.

Extending the Boundaries of Cancer Therapeutic Complexity with Literature Data Mining

This paper develops a text data mining tool to enable high complexity combination cancer treatment planning, showing it improves speed and quality of plan creation.

BioAct: Biomedical Knowledge Base Construction using Active Learning

This paper introduces BioAct, an active learning method for creating curated datasets to enable biomedical knowledge base construction, and releases an annotated dataset on antimicrobial resistance.

MetaboListem and TABoLiSTM: Two Deep Learning Algorithms for Metabolite Named Entity Recognition

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

Ontology-Aware Biomedical Relation Extraction

The paper introduces a multi-channel deep neural network for biomedical relation extraction that outperforms existing methods by leveraging textual and graph features.

The Xenopus Phenotype Ontology: bridging model organism phenotype data to human health and development.

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

The Neuron Phenotype Ontology: A FAIR Approach to Proposing and Classifying Neuronal Types

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