0.5.2

• More tests
• Fix small bug when passing Irreps to e3nn (#55)
• Add missing package to conda env (#57)

0.5.1

Some additions to the package, which should be fully backwards-compatible with v0.5.0:

• Docs (including RTD)
• Wrapper and config for the ViSNet model from torch_geometric
• New pKi Readout class

0.5.0

This release modifies the way that mtenn.conversion_utils models are built so that all can be built by directly passing args for the underlying model. Additionally, we introduce mtenn.config, which implements Pydantic schema that can be used to reproducibly mtenn models.

0.4.0

This version implements a major change in the way the GroupedModel and Combination classes are written so that they now work natively in pytorch while also not gobbling all GPU memory. Additionally, all the different types of classes were split into their own files, which will break some API calls.

0.3.0

Update to the PIC50Readout class that will invalidate models trained in prior releases. NOTE THAT ANY MODELS TRAINED WITH PREVIOUS RELEASES WILL NEED TO BE RETRAINED.

Also add some Combination classes.

0.2.1

DGL 1.1 modified the way bias is assigned for the GATConv layers, which are used in the mtenn.GAT model. Update model construction to match this.

0.2.0

Merge pull request #22 from choderalab/add-gat-model

Add GAT model

0.1.0

rel 0.1.0

0.1.0-alpha

Improve packaging

-  Improve some packaging stuff
- Remove versioneer in favour of versiongit
- removed old setup.py
- setup conda environments
- Added install instructions.