v1.1.3

What's Changed

• fix issue with different sequences and order @gcorso
• Set any nans/infs in model scores to a small value @jsilter
• fix a typo by @deepsatflow in #222
• Add init files to all python modules by @burn-in-soul in #236
• Upated docker commands instructions in README.md by @juliocesar-io in #248
• Fixing bug leading to atom graph containing a lot of incorrect atoms by @bamattsson in #241

New Contributors

• @deepsatflow made their first contribution in #222
• @burn-in-soul made their first contribution in #236
• @juliocesar-io made their first contribution in #248
• @bamattsson made their first contribution in #241

Full Changelog: v1.1.2...v1.1.3

v1.1.2

What's Changed

Improve graph convolution performance to use significantly less memory for inference.

Various bugfixes:

• Ensure we calculate rotatable bonds on the version of the ligand with no hydrogens. Also fix spelling of rotable -> rotatable. Closes GH-220 (@Nobody-Zhang)

• Vectorize SO3 calculations. Closes PR GH-218 (@tornikeo)

• Pin pytorch-lightning version. Closes GH-193 (@mikael-h-christensen)

• Guard against divide by zero in torus.py. Closes GH-161 (@amorehead)

• Update e3nn version to 0.5.1. Closes GH-155 (@amorehead)

• Add more info on docker container to README.md

• Rename inference_args.yaml to default_inference_args.yaml in README.md by @amorehead in #188

New Contributors

• @amorehead made their first contribution in #188

Full Changelog: v1.1...v1.1.2

Version 1.1: DiffDock-L

What's Changed

We have released DiffDock-L, a new version of DiffDock that provides a significant improvement in performance and generalization capacity (see the description of the new version in our new paper). By default the repository now runs the new model, please use GitHub commit history to run the original DiffDock model. Further we now provide instructions for Docker and to set up your own local UI interface.

New Contributors

• @jsilter made their first contribution in #182

Full Changelog: v1.0...v1.1