Badapple: Bioassay data associative promiscuity pattern learning engine
Badapple 2.0 is released (May 2025)! Initially developed and published in 2016, Badapple has been fully rewritten, using RDKit, as Badapple2, with updates to the database and algorithmic enhancements. The lead developer for Badapple2 is Jack Ringer. A corresponding manuscript is in preparation.
Badapple is a method for rapidly identifying likely promiscuous compounds via associated scaffolds. Badapple generates a score associated with a pragmatic, empirical definition of promiscuity, with the overall goal to identify “false trails” and streamline workflows. Unlike methods reliant on expert curation of chemical substructure patterns, Badapple is fully evidence-driven, automated, self-improving via integration of additional data, and focused on scaffolds. Badapple is robust with respect to noise and errors, and skeptical of scanty evidence.

New Badapple 2.0 web app
Links:
- Badapple 2.0 WEB APP
- Badapple 2.0 API Docs
- GitHub repository: Badapple2
- GitHub repository: Badapple2-API (includes local installation instructions)
- GitHub repository: Badapple2-UI
- Paper (Yang, et al., 2016): Badapple: promiscuity patterns from noisy evidence, Jeremy J. Yang, Oleg Ursu, Christopher A. Lipinski, Larry A. Sklar, Tudor I. Oprea & Cristian G. Bologa, Journal of Cheminformatics, 8:29 (2016)