Skip to content

fastsolv python package, website, and paper code

License

Notifications You must be signed in to change notification settings

JacksonBurns/fastsolv

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

fastsolv Monorepo

This repository contains the code for the following three items:

  • fastsolv: the fastsolv python package which allows using the trained fastsolv model for solid solubility prediction (installable from PyPI via pip install fastsolv).
  • fastsolv_web: the fastsolv_web python package which serves a web-based version of the fastsolv predictor, one instance of which is hosted at fastsolv.mit.edu.
  • paper: the original development code and models used for training the fastsolv model, as described in 'Solid Solubility Prediction at the Limit of Aleatoric Uncertainty' by Attia, Burns, Doyle, and Green.

See the README.md file within each directory for additional details.