greenelab/snorkeling
Extracting biomedical relationships from literature with Snorkel 🏊
This project helps biomedical researchers and curators quickly extract specific relationships, like Disease-Gene associations or Compound-Gene interactions, from vast amounts of PubMed abstracts. It takes raw scientific literature as input and outputs structured information about these biological and pharmacological connections. This is for scientists or data curators who need to build comprehensive knowledge bases from published research.
No commits in the last 6 months.
Use this if you need to rapidly identify and extract specific biomedical relationships from scientific abstracts to populate or update a knowledge base, and manual curation is too slow.
Not ideal if you are looking for an off-the-shelf tool that extracts all types of relationships without any initial setup or if your primary data source is full-text articles rather than abstracts.
Stars
58
Forks
18
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 01, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/greenelab/snorkeling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
titipata/pubmed_parser
:clipboard: A Python Parser for PubMed Open-Access XML Subset and MEDLINE XML Dataset
nfflow/pubmedflow
Data Collection API for pubmed
purplepotion/sadrat
Smart Adverse Drug Reaction Assessment Tools.
databricks-industry-solutions/adverse-drug-events
To ensure ongoing drug safety, pharma companies need to monitor and report adverse drug events...
KarelDO/BioDEX
BioDEX: Large-Scale Biomedical Adverse Drug Event Extraction for Real-World Pharmacovigilance.