GitHub Repository

76,907 phytochemical records enriched with PubMed, ClinicalTrials.gov, ChEMBL bioactivity & USPTO patents. Production-ready JSON + Parquet. Free 400-row sample. Full dataset: ethno-api.com

6 starsJupyter Notebook

I enriched 24K phytochemicals with trials, bioactivity, and patent data

Name: I enriched 24K phytochemicals with trials, bioactivity, and patent data
Availability: InStock
Author: wirthal1990

by wirthal1990·Mar 17, 2026·2 points·1 comment

Visit Project View on HN

AI Analysis

●MidNiche GemSolve My Problem

Pre-joined USDA phytochemical records with clinical trials and patents, saving biotech ETL time.

Strengths

•Joins four distinct biomedical APIs into a single consistent schema without rate limit headaches.
•Parquet format ensures efficient querying for large-scale bioinformatics pipelines and local analysis.
•Includes DOI and HuggingFace hosting, adding academic credibility and easy sample access.

Weaknesses

•Full dataset behind a paywall limits community verification and open-source collaboration potential.
•Competes with free APIs like PubChem and ChEMBL if you build your own ETL pipeline.