HeartBD2K's repositories
heartCases
A medical language processing system for case reports, particularly those involving cardiovascular disease.
aztec-text-analysis-tools
Libraries for text analysis (e.g., entry similarity evaluation, text summarization, etc.)
bd2kpubmed
BD2KPubMed is a tool to identify trends in the literature, quantifying the impact of particular proteins on current and future research.
Cubic-Spline-based-Temporal-Analysis-Workflow
Our workflow designed to capture the distinct temporal molecular signatures associated with the temporal profile of various types of disease pathogenesis.
BioComposer
A web application to assist scientists in publishing articles to Wikipedia
ProteoSeq-Django
ProteoSeq web service rebuilt with Django
RESTfulAPI
COPaKB database access functions for the RESTful API.
Aztec-Db-Expansion
To increase the Aztec database from 10,000 to >50,000 database entries while containing up-to-date metadata. This requires scraping text and/or downloading PDFs at scale (just once) and creating a web-crawler to update the metadata for the entries. The web-crawler should run on a weekly basis.
AztecRetrieval
Bioinformatics repository crawler and updater
bd2kccc-website-issues
Issue tracker for BD2KCCC website
COPaKB-DB-Updater
COPaKB database updater
CV.Signature.TCP
An open source R package to identify temporal molecular signatures from time-course omics data
Infrastructure
This is a documentation for new developers and developers starting on a new project to set things up
Metadata-Extraction-Service
Python scripts including Flask REST app for metadata extraction
Significant-Mapping
An R Shiny App for visualizing the geographic distribution of clinical case reports.
trainingsetbuilder
Build a training set for the Aztec tool classification.