Alphafold Versions Save

Version 2.1.0 adds the AlphaFold-Multimer model and fixes a number of issues reported in the last few months.

Change log:

• [new feature] AlphaFold-Multimer data pipeline, model and metrics have been added. Use model_preset=multimer to run with AlphaFold-Multimer.
• [change] AlphaFold-Multimer no longer pre-processes the features via TensorFlow but instead does it in the JAX module code.
• Added a note and a check that the directory with data is outside the AlphaFold repository for faster Docker builds (thanks @jamespeapen).
• Advertise Python 3.7, 3.8, 3.9, 3.10 in setup.py (thanks @anukaal).
• Added an FAQ explaining that the Colab on free tier can time out (thanks @mooingcat).
• Stop using hardcoded /tmp, instead use $TMPDIR (thanks @meson800, @EricDeveaud).
• Make run_docker fully configurable via flags: data_dir, docker_image_name, output_dir (thanks @akors, @chrisroat).
• Look for stereo_chemical_props.txt relative to the residue_constants module (thanks @rjgildea).
• Crop UniRef90 MSA to 10,000 sequences to prevent hitting the 2 GB proto field limit and use less memory (thanks @biohegedus and @chrisroat).
• Finding third party tool binaries is now more robust and gives you better errors if any are missing (thanks @FanchTheSystem).
• Refactor and a few fixes and usability improvements in the AlphaFold Colab.

Version 2.0.1 is mainly a bug fix release. We thank everyone who reported issues and proposed solutions.

Change log:

• [new feature] Added AlphaFold Colab notebook that enables convenient folding from your browser.
• [new feature] The reduced_dbs preset was added together with small BFD.
• Some of the genetic databases are now mirrored on GCP.
• Added a missing data/__init__.py and model/tf/__init__.py files.
• README fixes and additions.
• Switched to using cudnn base image based on Ubuntu 18.04.
• Switched to tensorflow-cpu since we don't need a GPU when running the data pipeline.
• Improved logging in the AlphaFold pipeline.
• Fixed a few typos and added and fixed a few comments.
• Added pLDDT in the B-factor column of the output PDBs.
• Skip obsolete PDB templates that don't have a replacement.
• Small test improvements.