

Multiupgrade v2.1.0.0 gracias code#
Removed unused code in amber_minimize.py.Fixed degraded performance when using num_recycle=0 with models trained with recycling due to incorrect skipping of layers (thanks Added split_rng=False (current default) to sharded_map to support new Haiku release.Added the ability to run with multiple seeds per model to match the AlphaFold-Multimer paper.Removed unused bias argument in GlobalAttention (thanks Removed prokaryotic MSA pairing algorithm as it didn’t improve accuracy on average.

Use DeviceRequest rather than runtime=nvidia to expose GPUs to the container (thanks Simplified mounting of files in Docker.Added new AlphaFold-Multimer models with greatly reduced numbers of clashes on average and slightly increased accuracy.

Read the updated AlphaFold-Multimer paper for more details.Ī number of other bug fixes and small improvements have been made. These new models have greatly reduced numbers of clashes on average and are slightly more accurate. Version v2.2.0 updates the AlphaFold-Multimer model parameters.
