Skip to content

XYMOL: A Python package to understand and explain atom/bond contributions of small molecules in machine learning models.

License

Notifications You must be signed in to change notification settings

smu-tao-group/xymol

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

45 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

eXplain Your MOLecule (XYMOL)

Python github ci codecov

XYMOL: A Python package to understand and explain atom/bond contributions of small molecules in machine learning models.

Install

Using pip to install:

# for release (stable) version
pip install xymol

# for the latest version
pip install git+https://github.com/smu-tao-group/xymol.git

Usage

The easiest way to use XYMOL is to input your featurizer (function to featurize SMILES) and the trained ML model through create_map function.

from xymol import XYMOL

SMILES = "CCC" # replace with your SMILES
xymol = XYMOL(SMILES)
xymol.create_map(FEATURIZER, TRAINED_MODEL)

One example is displayed below. Green color means dropping this atom would lead to an increase in prediction, and vice versa.

License

Apache-2.0 license

About

XYMOL: A Python package to understand and explain atom/bond contributions of small molecules in machine learning models.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages