Biomedical Text Mining and Ontologies

dgiLIT: A Method for Prioritization and AI Curation of Drug-Gene Interactions

The paper introduces dgiLIT, an AI-driven method to prioritize and curate drug-gene interactions from biomedical literature for inclusion in DGIdb, achieving high validation rates.

textToKnowledgeGraph: Generation of Molecular Interaction Knowledge Graphs Using Large Language Models for Exploration in Cytoscape

The paper introduces textToKnowledgeGraph, a tool using large language models to extract molecular interactions into BEL format for analysis in Cytoscape.

SEA CDM: Study-Experiment-Assay Common Data Model and Databases for Cross-Domain Data Integration and Analysis

The paper introduces a common data model and databases for integrating heterogeneous biomedical data, enabling cross-domain analysis and revealing sex-specific immune response insights.

A general strategy for generating expert-guided, simplified views of ontologies

The paper presents tools to validate and simplify ontology term hierarchies for better usability in biomedical research.

Curation at Scale with EPITOME: Extraction Pipeline for Immunological Texts and Open-Source Multimodal Enquiry

EPITOME is a multimodal pipeline that combines OCR, text matching, and VLMs to automate and enhance epitope data curation from scientific papers.

DISGENET: Accelerating Data-Driven Discovery in Disease Genomics and Therapeutic Development

DISGENET integrates genotype-phenotype data to support precision medicine and drug development through comprehensive, up-to-date associations and tools.

GeneReL: A Large Language Model-Powered Platform for Gene Regulatory Relationship Extraction with Community Curation

GeneReL extracts and curates gene regulatory relationships from literature using LLMs and community validation, providing a database of 13,710 interactions in Arabidopsis thaliana.

KG-Microbe - Building Modular and Scalable Knowledge Graphs for Microbiome and Microbial Sciences

KG-Microbe constructs modular knowledge graphs to integrate microbial data, enabling analysis of complex interactions in health and environment.

Application of large language models to the annotation of cell lines and mouse strains in genomics data

This paper evaluates using GPT-4o to annotate mouse strains and cell lines in genomics data, achieving 77% and 59% accuracy, and identifies manual curation errors.

GOFlowLLM - Curating miRNA literature with Large Language Models and flowcharts

GOFlowLLM automates miRNA literature curation using LLMs and flowcharts, achieving high accuracy and efficiency in annotating gene silencing data.

Federated Knowledge Retrieval Elevates Large Language Model Performance on Biomedical Benchmarks

This paper introduces BTE-RAG, a retrieval-augmented generation framework that improves LLM performance on biomedical benchmarks by integrating mechanistic evidence from federated knowledge sources.

An Evidence-Grounded Research Assistant for Functional Genomics and Drug Target Assessment

Alvessa improves accuracy in functional genomics and drug target assessment by integrating evidence-based reasoning and verification.

Defining and Evaluating Cell-Cell Relation Extraction from Biomedical Literature under Realistic Annotation Constraints

This paper defines a cell-cell relation extraction task, constructs annotated corpora, and evaluates models under realistic constraints, finding performance remains around 70% accuracy.

Specifind: A Natural Language Processing Tool for Automating Species Occurrence (Re-)Discovery from Scientific Literature

Specifind automates the extraction of species occurrence data from scientific literature by identifying species names, geographic references, and their relationships.

Application of Large Language Models for Annotating Genes into Reactome Pathways

This paper applies large language models to assist in gene annotation into Reactome pathways, showing promising results in supporting curation workflows.

SKiM-GPT: Combining Biomedical Literature-Based Discovery with Large Language Model Hypothesis Evaluation

SKiM-GPT evaluates biomedical hypotheses by combining literature-based discovery with large language models to assess hypothesis validity using retrieved PubMed abstracts.

GENET: AI-Powered Interactive Visualization Workflows to Explore Biomedical Entity Networks

GENET streamlines hypothesis generation for gene-disease associations by integrating AI-driven network analysis, literature mining, clustering, and visualization.

React-to-Me: A Conversational Interface for Interactive Exploration of the Reactome Pathway Knowledgebase.

React-to-Me, a retrieval-augmented chatbot grounding GPT-4o-mini in curated Reactome pathways with hyperlinked citations, earned higher blinded expert ratings than ungrounded GPT-4o-mini (odds ratio 2.01).

Comparative Assessment of Large Language Models for Microbial Phenotype Annotation

This study evaluates LLMs for microbial phenotype annotation, finding varied performance across models and traits, with confidence scores correlating with accuracy.

Domain-wide Mapping of Peer-reviewed Literature for Genetic Developmental Disorders using Machine Learning and Gene2Phenotype

The paper develops an automated pipeline to map genetic developmental disorder literature to Gene2Phenotype using NLP models, achieving high accuracy and scalability for biocuration.

A Multi-Agent Approach to Generating Context-Rich Gene Sets

This paper introduces a multi-agent system using large language models to enhance gene set databases by incorporating biological context from PubMed abstracts.

Performance of Information Theory Derived Semantic Similarity Algorithms for Differential Diagnosis and Clustering

The paper compares semantic similarity algorithms for differential diagnosis and clustering using HPO, finding Phenomizer performs best for ranking and non-normalized algorithms for clustering.

A hidden network of gene relationships unifies behavioral and molecular research

The paper develops a model to predict gene relevance in behavioral research using a large language model, revealing shared gene signatures between molecular and behavioral studies.

CellOntologyMapper: Consensus mapping of cell type annotation

CellOntologyMapper standardizes cell type annotations by mapping user-defined names to standardized ontological terms, improving data integration and analysis across diverse single-cell datasets.

SOORENA: Self-lOOp containing or autoREgulatory Nodes in biological network Analysis

SOORENA identifies autoregulatory mechanisms in biological networks by analyzing PubMed abstracts, finding 97,657 protein-specific records and generating a curated database.

OmixLitMiner 2: Guided Literature Mining Tools for Automated Categorization of Marker Candidates in Omics Studies

OmixLitMiner 2 automates literature mining to categorize marker candidates by their literature coverage, improving efficiency in omics data interpretation.

Linking protein residues in literature and structure

The paper introduces a tool that links protein residue mentions in text to their corresponding positions in protein structures, enabling integrated exploration with experimental evidence.

Integrating natural language processing and genome analysis enables accurate bacterial phenotype prediction

This study combines NLP and genome analysis to predict bacterial phenotypes by integrating literature and genomic data, revealing gene-phenotype correlations and hub species in microbial communities.

Automating Candidate Gene Prioritization with Large Language Models: From Naive Scoring to Literature-Grounded Validation

This paper develops a framework using large language models for gene prioritization, validated against literature, identifying 30 high-confidence therapeutic candidates for sepsis.

AI-based mining of biomedical literature: Applications for drug repurposing for the treatment of dementia

This paper introduces AGATHA, an AI tool for drug repurposing in dementia by analyzing biomedical literature and identifying gene-disease associations using statistical methods.