Skip to content

Releases: choderalab/mtenn

0.6.2

23 Aug 09:19
0e06eda
Compare
Choose a tag to compare

What's Changed

Full Changelog: 0.6.0...0.6.2

0.6.1

05 Aug 23:32
0e06eda
Compare
Choose a tag to compare

What's Changed

Full Changelog: 0.6.0...0.6.1

0.6.0

01 Aug 15:26
c18b034
Compare
Choose a tag to compare
  • Main (breaking) change of this release is the change of the Combination classes to return the per-pose predictions as well as the final combined prediction. This was done in order to connect these per-pose predictions back into the computation graph, so that they can be included in a loss function
  • Fleshed out docs and comments a bit more

0.5.2

28 Mar 13:45
5eb43e1
Compare
Choose a tag to compare
  • More tests
  • Fix small bug when passing Irreps to e3nn (#55)
  • Add missing package to conda env (#57)

0.5.1

16 Feb 15:20
6fcec40
Compare
Choose a tag to compare

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

08 Jan 16:38
3cae786
Compare
Choose a tag to compare

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

01 Nov 18:59
6f6d8e8
Compare
Choose a tag to compare

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

17 Aug 15:12
aafd56b
Compare
Choose a tag to compare

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

15 May 19:18
07ea82b
Compare
Choose a tag to compare

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

21 Apr 13:34
42893ce
Compare
Choose a tag to compare
Merge pull request #22 from choderalab/add-gat-model

Add GAT model