Openfold

OpenFold as of the release of our manuscript. Many new features, including FP16 training + more stable training.

What's Changed
* use multiple models for inference by decarboxy in https://github.com/aqlaboratory/openfold/pull/117
* Update input processing by brianloyal in https://github.com/aqlaboratory/openfold/pull/116
* adding a caption to the image in the readme by decarboxy in https://github.com/aqlaboratory/openfold/pull/133
* Properly handling file outputs when multiple models are evaluated by decarboxy in https://github.com/aqlaboratory/openfold/pull/142
* Fix for issue in download_mgnify.sh by josemduarte in https://github.com/aqlaboratory/openfold/pull/166
* Fix tag-sequence mismatch when predicting for multiple fastas by sdvillal in https://github.com/aqlaboratory/openfold/pull/164
* Support openmm >= 7.6 by sdvillal in https://github.com/aqlaboratory/openfold/pull/163
* Fixing issue in download_uniref90.sh by josemduarte in https://github.com/aqlaboratory/openfold/pull/171
* Fix propagation of use_flash for offloaded inference by epenning in https://github.com/aqlaboratory/openfold/pull/178
* Update deepspeed version to 0.5.10 by NZ99 in https://github.com/aqlaboratory/openfold/pull/185
* Fixes errors when processing .pdb files by NZ99 in https://github.com/aqlaboratory/openfold/pull/188
* fix incorrect learning rate warm-up after restarting from ckpt by Zhang690683220 in https://github.com/aqlaboratory/openfold/pull/182
* Add opencontainers image-spec to `Dockerfile` by SauravMaheshkar in https://github.com/aqlaboratory/openfold/pull/128
* Write inference and relaxation timings to a file by brianloyal in https://github.com/aqlaboratory/openfold/pull/201
* Minor fixes in setup scripts by timodonnell in https://github.com/aqlaboratory/openfold/pull/202
* Minor optimizations & fixes to support ESMFold by nikitos9000 in https://github.com/aqlaboratory/openfold/pull/199
* Drop chains that are missing (structure) data in training by timodonnell in https://github.com/aqlaboratory/openfold/pull/210
* adding a script for threading a sequence onto a structure by decarboxy in https://github.com/aqlaboratory/openfold/pull/206
* Set pin_memory to True in default dataloader config. by NZ99 in https://github.com/aqlaboratory/openfold/pull/212
* Fix missing subtract_plddt argument in prep_output call by mhrmsn in https://github.com/aqlaboratory/openfold/pull/217
* fp16 fixes by beiwang2003 in https://github.com/aqlaboratory/openfold/pull/222
* Set clamped vs unclamped FAPE for each sample in batch independently by ar-nowaczynski in https://github.com/aqlaboratory/openfold/pull/223
* Fix probabilities type (`int` -> `float`) by atgctg in https://github.com/aqlaboratory/openfold/pull/225
* Small fix for prep_mmseqs_dbs. by jonathanking in https://github.com/aqlaboratory/openfold/pull/232

New Contributors
* brianloyal made their first contribution in https://github.com/aqlaboratory/openfold/pull/116
* josemduarte made their first contribution in https://github.com/aqlaboratory/openfold/pull/166
* sdvillal made their first contribution in https://github.com/aqlaboratory/openfold/pull/164
* epenning made their first contribution in https://github.com/aqlaboratory/openfold/pull/178
* NZ99 made their first contribution in https://github.com/aqlaboratory/openfold/pull/185
* Zhang690683220 made their first contribution in https://github.com/aqlaboratory/openfold/pull/182
* SauravMaheshkar made their first contribution in https://github.com/aqlaboratory/openfold/pull/128
* timodonnell made their first contribution in https://github.com/aqlaboratory/openfold/pull/202
* nikitos9000 made their first contribution in https://github.com/aqlaboratory/openfold/pull/199
* mhrmsn made their first contribution in https://github.com/aqlaboratory/openfold/pull/217
* beiwang2003 made their first contribution in https://github.com/aqlaboratory/openfold/pull/222
* ar-nowaczynski made their first contribution in https://github.com/aqlaboratory/openfold/pull/223
* atgctg made their first contribution in https://github.com/aqlaboratory/openfold/pull/225
* jonathanking made their first contribution in https://github.com/aqlaboratory/openfold/pull/232

**Full Changelog**: https://github.com/aqlaboratory/openfold/compare/v1.0.0...v1.0.1

OpenFold at the time of the release of our original model parameters and training database. Adds countless improvements over the previous beta release, including, but not limited to:

- Many bugfixes contribute to stabler, more correct, and more versatile training
- Options to run OpenFold using our original weights
- Custom attention kernels and alternative attention implementations that greatly reduce peak memory usage
- A vastly superior Colab notebook that runs inference many times faster than the original
- Efficient scripts for computation of alignments, including the option to run MMSeqs2's alignment pipeline
- Vastly improved logging during training & inference
- Careful optimizations for significantly improved speeds & memory usage during both inference and training
- Opportunistic optimizations that dynamically speed up inference on short (< ~1500 residues) chains
- Certain changes borrowed from updates made to the AlphaFold repo, including bugfixes, GPU relaxation, etc.
- "AlphaFold-Gap" support allows inference on complexes using OpenFold and AlphaFold weights
- WIP OpenFold-Multimer implementation on the `multimer` branch
- Improved testing for the data pipeline
- Partial CPU offloading extends the upper limit on inference sequence lengths
- Docker support
- Missing features from the original release, including learning rate schedulers, distillation set support, etc.

**Full Changelog**: https://github.com/aqlaboratory/openfold/compare/v0.1.0...v1.0.0

The initial release of OpenFold.

**Full Changelog**: https://github.com/aqlaboratory/openfold/commits/v0.1.0