Talia B. Kimber

Missing features (in order of importance): - SELFIES as molecular string encoding - Check one-hot for selfies packages - Add k-fold cross-validation - Parser - Have a separate function for...

"Buried treasure" data set

2

## Data set We should include the data set which contains over 17k measurements of compounds on the CDK2 kinase. ## References: - The data set can be found in...

Document hierarchy of molecular representation classes

1

Have class-based documentation with hierarchy. In Sphinx docs. See example: https://open-forcefield-toolkit.readthedocs.io/en/0.10.0/topology.html Source: https://open-forcefield-toolkit.readthedocs.io/en/0.10.0/_sources/topology.md.txt

Update tests, ideally have 80% coverage. Note: have a check for estimate input for forward method in pytorch models, see https://github.com/openkinome/kinoml/pull/53

Dunbrack clusters

1

## Todos Add @jiayeguo's work on Dunbrack clusters.

running notebook with custom loss class for skorch.

1

## Description This PR focuses on how to use skorch (Pytorch + sklearn) package for training the machine learning models. Advantages: Cool features pre-implemented, e.g. - Built in cross-validation -...