“Annotation of Genes with Alteration-Centric function changes”. — A customized corpus for mining functions caused by mutations.
Literature-mined resources for regulatory events caused by genetic alterations. The extraction and curation of the event items is based on the in-house developed pipeline, GARE.
This database includes 16,681 thousand of regulatory events records encompassing 21K genes, 157K genetic alterations and 154K downstream bio-concepts, extracted from 4,354K pan-cancer literature.
A comprehensive database supporting the precise interpretation of the underlying pathological mechanisms of Alzheimer's disease. The web service provide convenient data queries, evidence displays, and result visualizations.
An ongoing project for rice annotation.
A project exploring large language models on Rice-Alterome data.
We are building ontologies for concept normalization.
The rice trait ontology (RTO) project is to define rice-specific ontology concepts for rice traits and phenotypes.
An online system for curation of Rice Trait Ontology concepts.
A project page describing interoperability of ontology curation systems.
A curation system for RTO with the assistance of the LLM.
We are integrating multi-omics data to support biological discovery and interpretation.
RiceMind project integrates multi-omics data and knowledge for rice research.
MaizeLitBase project is a shared task focusing on Zea mays L.
Various research strategies are used to extract, curate, and infer the knowledge bio-medicine. The main methods include BioNLP pipeline, Bayesian algorithms, and web-based data service.
An evidence-augmented data fusion is run to support the driver gene discovery via interpretable literature evidence and omics data. Case studies in AD, lung cancer and breast cancer.
A web service for querying the pathology networks with rich literature evidence in the Alzheimer's Disease context.
AD-LitMiner aims to present the most valuable AD literature statements and provides drug recommendations.