v2.0.0

Major Changes

• SoloSeq inference: Single Sequence Inference using ESM-1b embeddings with template features is now supported. Check out SoloSeq in the README for more information.
• Multimer : Inference in multimer mode using the AlphaFold-Multimer weights is now supported. Check out Multimer in the README for more instructions, or try out multimer inference in the Colab notebook.
• Addition of a custom DeepSpeed DS4Sci_EvoformerAttention kernel for 13X reduced peak device memory requirement, leading to 15% faster training and 4x speedup during inference. Test it out using the use_deepspeed_evo_attention option in openfold/config.py. More information in the README.

All Changes

• add long_sequence_inference option to command line by @decarboxy in #253
• Fix for CPU only install by @p-durandin in #252
• Obsolete parsing and File not found fix by @l-bick in #264
• Load pretrained jax weights by @l-bick in #263
• Fix --cpus_per_task argument in README by @awaelchli in #278
• Add a .gitignore file by @awaelchli in #279
• Add missing warmup_num_steps parameters to DeepSpeed config generation script. by @jonathanking in #290
• Fix notebook: Colab now has python 3.8, fix imports, mitigate UTF-8 glitch by @vaclavhanzl in #285
• New option to output in ModelCIF format instead of PDB format by @josemduarte in #287
• Fix comparison for max_seqlen when downloading CAMEO. by @jonathanking in #292
• Resolving torch cuda availability for cpu-only installation by @zrqiao in #275
• Improve TriangularMultiplicativeUpdate stability in fp16 mode by @nikitos9000 in #295
• Advance python version to 3.9 to build docker in Ubuntu Lunar Lobster by @vaclavhanzl in #309
• add comment about the interpretation of ambiguous atoms by @luwei0917 in #314
• Fix Colab again after ModelCIF merge and python version change in Colab by @vaclavhanzl in #308
• Fix Colab: Install all conda packages together by @vaclavhanzl in #320
• Multimer by @dingquanyu in #331
• Added multi-chain permutation steps, multimer datamodule, and training code for multimer by @dingquanyu in #336
• Fix multimer boolean tensor error by @dingquanyu in #337
• Update multi-chain permutation by @dingquanyu in #343
• Update validation by @dingquanyu in #346
• Fixes cuda/float wrapper error in unit tests by @jnwei in #350
• Fixed inference script in multimer mode by @dingquanyu in #348
• Update multi-chain permutation and training codes by @dingquanyu in #353
• fixed the creation of best_align when permutation is turned off by @dingquanyu in #355
• Single-sequence model by @sachinkadyan7 in #354
• move the kabsch rotation step to gpu by @dingquanyu in #359
• Installation updates by @jnwei in #360
• [DNM] Update Docker config by @mattwthompson in #361
• Bump actions/checkout from 2 to 4 by @dependabot in #366
• Bump actions/setup-python from 2 to 4 by @dependabot in #365
• Fixes imports to colab notebook. by @jnwei in #372
• Adds Soloseq parameter download script. by @jnwei in #373
• Fix for MSA block deletion by @christinaflo in #374
• Adds query_multiple to jackhammer.py by @jnwei in #375
• Deepspeed evoformer attention by @christinaflo in #378
• Speed up data loading process by @dingquanyu in #376
• Update data pipeline by @dingquanyu in #385
• Bump actions/setup-python from 4 to 5 by @dependabot in #380
• Readme changes by @jnwei in #389
• suporting newer numpy by @YoelShoshan in #307
• Change test_compare_model in deepspeed test to use mean instead of max by @jnwei in #396
• Fix Miniforge3 download link in Dockerfile by @controny in #402
• Adding multimer support to OpenFold notebook by @jnwei in #401
• Type fixes and README changes for multimer branch by @jnwei in #404
• Full multimer merge by @christinaflo in #405

New Contributors

• @p-durandin made their first contribution in #252
• @l-bick made their first contribution in #264
• @awaelchli made their first contribution in #278
• @vaclavhanzl made their first contribution in #285
• @zrqiao made their first contribution in #275
• @luwei0917 made their first contribution in #314
• @dingquanyu made their first contribution in #331
• @jnwei made their first contribution in #350
• @mattwthompson made their first contribution in #361
• @dependabot made their first contribution in #366
• @christinaflo made their first contribution in #374
• @YoelShoshan made their first contribution in #307
• @controny made their first contribution in #402

Full Changelog: v1.0.1...v2.0.0