Rohith Krishna
bae631b9b4
force include yamls for inference
2025-12-03 02:35:36 -08:00
Rohith Krishna
86137ef3ed
fix: remove rootutils from inference.py
2025-12-03 02:17:30 -08:00
Rohith Krishna
eb4f8ab83e
Merge pull request #33 from RosettaCommons/fix/checkpoints
...
chore: ruff, fix checkpoint code
2025-12-03 01:50:44 -08:00
ncorley
1bf46afa21
chore: ruff, fix checkpoint code
2025-12-03 01:48:46 -08:00
Rohith Krishna
d14203b264
Merge pull request #31 from RosettaCommons/fix/rootutils
...
remove use of rootutils to allow for pypi
2025-12-03 01:17:01 -08:00
Rohith Krishna
7668d03d04
use .foundry as default for checkpoint dir
2025-12-03 01:15:23 -08:00
Rohith Krishna
c859ce4fc0
remove use of rootutils to allow for pypi
2025-12-03 01:12:14 -08:00
Rohith Krishna
5ae1567d3a
Merge pull request #30 from timkartar/patch-1
...
Make trajectory png slightly bigger
2025-12-03 00:53:02 -08:00
Raktim Mitra
fc9aea95a2
Merge branch 'RosettaCommons:production' into patch-1
2025-12-03 00:51:40 -08:00
Raktim Mitra
30231f1457
Update README.md
2025-12-03 00:50:53 -08:00
Rohith Krishna
31cedb1d0a
Merge pull request #29 from timkartar/patch-1
...
Update README.md fix trajectory.png link
2025-12-03 00:50:35 -08:00
Raktim Mitra
46eeaa45f0
Update README.md fix trajectory.png link
2025-12-03 00:47:49 -08:00
Rohith Krishna
e79dcb71ab
Merge pull request #28 from RosettaCommons/stage_for_production
...
Stage for production
2025-12-03 00:35:28 -08:00
AndrewKubaney
dfe5402a5d
add in weights docs and help string fix ( #727 )
...
* chore: add SolubleMPNN, additional warnings, wts.
* fix: fix --help string option.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
2025-12-03 00:34:46 -08:00
Rachel Clune
98b12108c7
Added details and fixed typos in NA binder design examples ( #721 )
...
* Fixed spelling and grammar mistakes in the md file for NA binder design examples. Created a .json file containing the code bits for users to easily run the examples.
* NA example clean up
Removed NA examples from foundry docs directory and moved necessary files to the RFD3 docs directory. Added example syntax for how to use `rfd3 design` instead of `python ...`
* Update na_binder_design.md small edits to the hbplus warning sentence
---------
Co-authored-by: Raktim Mitra <timkartar7879@gmail.com >
2025-12-03 00:34:46 -08:00
Nathaniel Corley
d72e49aa96
docs: dataset readme ( #726 )
...
* docs: dataset readme
* more docs for training
---------
Co-authored-by: Rohith Krishna <rohith@localhost>
2025-12-03 00:34:46 -08:00
Jasper Butcher
94bb987998
Refactor/checkpoint defaults ( #723 )
...
* Registry rework
* Update README 12
* Mc
* Add all option correction
2025-12-03 00:34:45 -08:00
Rohith Krishna
d07d003ae2
remove notebook outputs
2025-12-03 00:34:45 -08:00
Rohith Krishna
2cd401665b
initial progress on documentation cleanup ( #722 )
...
* initial progress on documentation cleanup
* formatting input.md
* docs: more documentation for ppi and sm binder design
* fix typo
---------
Co-authored-by: Rohith Krishna <rohith@localhost>
2025-12-03 00:34:45 -08:00
Nathaniel Corley
5ec34da7c1
chore: fix regression tests for rf3 ( #725 )
2025-12-03 00:34:45 -08:00
Rohith Krishna
adb11204c8
remove more instances of foundry ( #724 )
...
Co-authored-by: Rohith Krishna <rohith@localhost>
2025-12-03 00:34:45 -08:00
Raktim Mitra
3414c0e833
Refactor/sm binder cleanup ( #720 )
...
* remove dialect key, and exposed case
* change hbplus metric fail log to warning from error
---------
Co-authored-by: Raktim Mitra <raktim@digs.ipd.uw.edu >
2025-12-03 00:34:45 -08:00
Raktim Mitra
264bb79ee4
hbplus_instruction ( #719 )
...
Co-authored-by: Raktim Mitra <raktim@digs.ipd.uw.edu >
2025-12-03 00:34:45 -08:00
Rohith Krishna
faa2935417
remove ipd specific files
2025-12-02 20:56:06 -08:00
Rohith Krishna
bf8b44a83f
feat: enable installing checkpoints from command line
2025-12-02 20:29:09 -08:00
Rohith Krishna
db7cbf37d1
fix: fix path in paths for pdb parsing ( #715 )
...
* refactor: change modelhub to foundry
* fix: fix path in paths for pdb parsing
* Update run_inf_tutorial.sh
---------
Co-authored-by: Rohith Krishna <rohith@localhost>
Co-authored-by: Raktim Mitra <timkartar7879@gmail.com >
2025-12-02 17:55:02 -08:00
Jasper Butcher
62cbbe28e5
Finalizing READMEs ( #711 )
...
* Draft update to main
* Minor changes
* Add files
* ppi/sm/enzyme.md and input.md/reade.md cleanups
* fix run commands
* fix: typo in ppi md
* fix: Update header dna_binder_design.md
* description of dna_binder_design examples in .md
* fix: Update dna_binder_design.md fix typo
* fix: Update main README.md to add all citations
* fix: filename dna->na
* fix: filename dna->na
---------
Co-authored-by: Raktim Mitra <raktim@digs.ipd.uw.edu >
Co-authored-by: Raktim Mitra <timkartar7879@gmail.com >
2025-12-02 16:46:33 -08:00
Rachel Clune
76e61e0c2d
docs: update RFD3 README ( #714 )
...
* Added more explanation and fixed small issues in demo commands in RFD3 README
* fix github actions grepping ruff
---------
Co-authored-by: Rohith Krishna <rohith@localhost>
2025-12-02 16:42:04 -08:00
Nathaniel Corley
050390fd67
Feat/notebook and rf3 confidence refactor ( #713 )
...
* chore: ruff
* feat: rf3 confidence, notebook update
2025-12-02 16:26:38 -08:00
Rohith Krishna
a8bcaa0ffa
move parquet paths into default paths config: ( #712 )
...
Co-authored-by: Rohith Krishna <rohith@localhost>
2025-12-02 14:50:19 -08:00
jbutch
9a9d4c40d8
Remove old code for reference frame
2025-12-02 02:33:36 -08:00
jbutch
a9ced98137
Fixes to training
2025-12-02 02:33:08 -08:00
jbutch
d6d113f3d6
Minor config changes, fixes to training
2025-12-02 01:22:10 -08:00
jbutch
33cbd92b44
Less verbose logging
2025-12-02 00:16:43 -08:00
Raktim Mitra
152a0911f1
DRAFT: docs for release, soft code hbplus ( #699 )
...
* documentation for release draft start
* trajectory.png
* update readme to rf3-lab paths, annotate TODOs
* add input_pdbs, demo.json
* Update README.md example pngs
* tasks pngs
* Update README.md - restructure pngs and application links
* Update README.md mc
* Update README.md add ipynb kernel export instruction
* mpnn all.ipynb
* open and edit tutorial.zip
* Update run_inf_tutorial.sh
* remove outputs
* cleanup
* rename
* soft code hbplus executable
* rename modelforge to foundry (rfd3) README
* fix: enabled running rfd3, mpnn inline
* cleanup
* remove todos, one remaining
* clear outputs
---------
Co-authored-by: Raktim Mitra <raktim@digs>
Co-authored-by: Raktim Mitra <raktim@localhost>
Co-authored-by: Rohith Krishna <rohith@localhost>
Co-authored-by: Raktim Mitra <raktim@digs.ipd.uw.edu >
2025-12-01 18:23:02 -08:00
Nathaniel Corley
f3c01c2a2d
refactor: rf3 and rfd3 lab training ( #709 )
...
* Add current_epoch arg to validation_batch_end, minor corrections to rfd3 validation
* fix: callbacks, readmes
* chore: rf3 checkpoints, quiet mode
* fix: fabric trainer model imports
* chore: commit .env
---------
Co-authored-by: jbutch <jbutch@uw.edu >
2025-12-01 18:14:07 -08:00
Jasper Butcher
a5532404f5
Refactor/rf3 rfd3 training ( #705 )
...
* Initial pass at file structure for MPNN merge.
* Copy and refactor for clarity pos encoding.
* PositionWiseFeedForward copied.
* Message passing layers, refactored.
* Token and atom encodings for MPNN.
* Naming consistency.
* Graph featurization for ProteinMPNN.
As well as membrane and pssm versions of MPNN.
* Finished LigandMPNN graph features.
* Code cleanup.
* MPNN classes rough draft.
* Additional comments.
* Move structure noise/sc atomize flag to kwargs.
* Finish encoding for protein and ligand MPNN.
* Saved some features for bookkeeping.
* Masks and decoding order. Decoder in progress.
* Added decoding; many bug fixes.
* feat: MPNN pipeline (#268 )
* feat: MPNN pipeline, pipeline tests
* feat: backbone occupancy threshold
* chore: MR comments
* chore: fix tests
* Directory cleanup.
* Rework kwargs, change masking.
* Bug fix: permutation of causality masks.
* Chore: push probability utils.
* Chore: variable name typo.
* Feat: Symmetry handling during decoding.
* Bug fix: repeat symmetry input along batch.
* Bug fix: if/else for symmetry_weight.
* Bug fix: node_features -> num_node_features.
* Bug fix: various typos/misnamings.
* Bug fix: np.minimum -> min for python ints.
* Chore: spacing.
* Chore: rename forward output.
* Chore: documentation.
* Feat: loss.
* Feat: weight init static method.
* Chore: int->bool for masks.
* Chore: ensure decode_last_mask is bool.
* Bug: fix modelhub imports.
* Chore: refactor ligand subgraph featurization.
* Chore: missing imports.
* Chore: rename loss.
* Chore: rename model file.
* Chore: bug fixes and documentation.
* Bug fix: symmetry and autograd.
* Chore: documentation.
* Bug: save "pre noise" coords even when no noise.
* Bug: Fix dtypes.
* Chore: Model tests.
* Chore: input names.
* Chore: update comment.
* Chore: change input to model.
* Chore: rename feats.
* Chore: rename feats downstream.
* Chore: S_pred->S_sampled rename for clarity.
* Chore: linter
* Feat: protein-ligand interface calculation. (#410 )
* Feat: protein-ligand interface calculation.
* Chore: use datahub validation check.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
* Chore: move token encoding.
* Chore: split transforms from pipeline.
* Feat: protein interface mask and batching.
* Chore: move protein-interface calc.
* Chore: empty commits for sampler/trainer.
* Chore: rename protein-ligand to polymer-ligand
* Feat: turn interface calcs into transform.
* Feat: transform for polymer interface mask.
* Bug: rename feats->input_features in tests.
* Bug: rename S_pred->S_sampled in tests.
* Bug: fix tests to match new model input format.
* Bug: fixed issues with polymer-ligand tests.
* Feat: collator.
* Chore: remove empty sampler.
* Chore: test refactor.
* Chore: update collate default.
* Chore: remove dist calc from interface for speed.
* Feat: auxillary settings in pipeline.
* Bug: fix mask_for_loss repeating.
* Feat: metrics and test updates.
* Chore: cleanup old files.
* Feat: padded token bucket sampler. (#432 )
* Feat: padded token bucket sampler.
* Chore: defaults.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
* Bug: ligand subgraph shapes.
* Feat: trainer.
* Bug: call .item() on metrics.
* Bug: move idx to proper device.
* Chore: remove compute train metrics (unused).
* Feat: checkpointing.
* Feat: minimal return option in pipeline (for mem).
* Chore: refactor sampler.
* Chore: move empty atom_array assert.
* Feat: rough training code.
* Feat: set_epoch and torch generator.
* Bug: sampler name.
* Feat: token budget aware collation.
* Chore: cleanup prints.
* Chore: code style.
* Feat: more robust pipeline (from Nate).
* Feat: batch sampler logic (from Nate).
* Feat: train updates.
* Feat: checks for invalid examples.
* Bug: fix for empty non_atomized_array.
* Feat: shell scripts for training.
* Feat: first pass old weight loading.
* Chore: updates to training hyperparams.
* Chore: partial restructure under src.
* Chore: changes for amp and comment.
* Chore: move MPNN into models.
* Chore: add mpnn to shebang.
* Chore: initial readme.
* Chore: fix imports for atomworks and model.
* Chore: conftest added.
* Chore: move training shell scripts.
* Chore: add __init__.py.
* Chore: restructure mpnn dir.
* Bug: fix atomworks imports.
* Bug: continued import fixing.
* Chore: update autocast dtype functions.
* Bug: fix issues with tests.
* Chore: add model route in data pipeline.
* Chore: fix comment about ligandmpnn legacy bug.
* Chore: rename add auxillary settings.
* chore: organize transforms.
* feat: pipeline handles atomarray annotation.
* chore: split mpnn and rf3 exec.
* chore: rename old -> legacy.
* chore: rename old->legacy in code.
* chore: update intro README.
* chore: update shebang.
* chore: update training scripts.
* chore: move launch training scripts.
* chore: fix path for train file.
* chore: add addn params protein vs ligand.
* fix: make train.py/inference.py executable.
* fix: python->srun.
* chore: update notes.
* feat: add back metrics_logging to modelhub.
TODO: deduplicate rf3/rfd3 for callback
StoreValidationMetricsInDFCallback.
* chore: fix atomworks imports.
* chore: add .env call.
* fix: actually fix env setup.
* chore: rename featurization of user setting.
* fix: move featurize user settings to end.
* fix: import.
* chore: import order.
* fix: train date cutoff, ckpt loading.
* fix: update atomworks to fix residue starts.
* chore: rearrange utils.
* chore: create io utils file.
* chore: file rename.
* feat: DRAFT of inference engine/utils/script.
* small inference input loading fixes
* fix: collater and repeat_sample_num handling.
* feat: significant upgrade of cli/inference input.
* fix: addtional checks for user inputs.
* chore: update high level inference script.
* chore: minor changes; prepping for refactor.
* chore: comment and small fix legacy wts.
* chore: reorder constants in legacy wts.
* chore: warnings to README.
* chore: more notes on readme.
* chore: readme updates.
* feat: inference working.
* chore: note on README.
* fix: readme syntax issue.
* chore: readme format.
* chore: tests for inference.
* chore: formatting.
* Remove old configs, add dump validation structures callback, fix tests
* Fix training and add exec file
* Make format mpnn & with unsafe fixes
* Fix training and add exec file
* Bugfix to losses
* Alright we rollin boys
* Update regression tests
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
Co-authored-by: Nathaniel Corley <ncorley@uw.edu >
Co-authored-by: AndrewKubaney <48457494+AndrewKubaney@users.noreply.github.com >
Co-authored-by: Andrew Kubaney <akubaney@digs>
Co-authored-by: Raktim Mitra <raktim@localhost>
2025-11-30 00:35:07 -08:00
jbutch
d603dee7c4
Make format mpnn & with unsafe fixes
2025-11-29 23:39:25 -08:00
AndrewKubaney
87264c2cb3
feat: add mpnn to refactor/rf3-lab ( #704 )
...
* Initial pass at file structure for MPNN merge.
* Copy and refactor for clarity pos encoding.
* PositionWiseFeedForward copied.
* Message passing layers, refactored.
* Token and atom encodings for MPNN.
* Naming consistency.
* Graph featurization for ProteinMPNN.
As well as membrane and pssm versions of MPNN.
* Finished LigandMPNN graph features.
* Code cleanup.
* MPNN classes rough draft.
* Additional comments.
* Move structure noise/sc atomize flag to kwargs.
* Finish encoding for protein and ligand MPNN.
* Saved some features for bookkeeping.
* Masks and decoding order. Decoder in progress.
* Added decoding; many bug fixes.
* feat: MPNN pipeline (#268 )
* feat: MPNN pipeline, pipeline tests
* feat: backbone occupancy threshold
* chore: MR comments
* chore: fix tests
* Directory cleanup.
* Rework kwargs, change masking.
* Bug fix: permutation of causality masks.
* Chore: push probability utils.
* Chore: variable name typo.
* Feat: Symmetry handling during decoding.
* Bug fix: repeat symmetry input along batch.
* Bug fix: if/else for symmetry_weight.
* Bug fix: node_features -> num_node_features.
* Bug fix: various typos/misnamings.
* Bug fix: np.minimum -> min for python ints.
* Chore: spacing.
* Chore: rename forward output.
* Chore: documentation.
* Feat: loss.
* Feat: weight init static method.
* Chore: int->bool for masks.
* Chore: ensure decode_last_mask is bool.
* Bug: fix modelhub imports.
* Chore: refactor ligand subgraph featurization.
* Chore: missing imports.
* Chore: rename loss.
* Chore: rename model file.
* Chore: bug fixes and documentation.
* Bug fix: symmetry and autograd.
* Chore: documentation.
* Bug: save "pre noise" coords even when no noise.
* Bug: Fix dtypes.
* Chore: Model tests.
* Chore: input names.
* Chore: update comment.
* Chore: change input to model.
* Chore: rename feats.
* Chore: rename feats downstream.
* Chore: S_pred->S_sampled rename for clarity.
* Chore: linter
* Feat: protein-ligand interface calculation. (#410 )
* Feat: protein-ligand interface calculation.
* Chore: use datahub validation check.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
* Chore: move token encoding.
* Chore: split transforms from pipeline.
* Feat: protein interface mask and batching.
* Chore: move protein-interface calc.
* Chore: empty commits for sampler/trainer.
* Chore: rename protein-ligand to polymer-ligand
* Feat: turn interface calcs into transform.
* Feat: transform for polymer interface mask.
* Bug: rename feats->input_features in tests.
* Bug: rename S_pred->S_sampled in tests.
* Bug: fix tests to match new model input format.
* Bug: fixed issues with polymer-ligand tests.
* Feat: collator.
* Chore: remove empty sampler.
* Chore: test refactor.
* Chore: update collate default.
* Chore: remove dist calc from interface for speed.
* Feat: auxillary settings in pipeline.
* Bug: fix mask_for_loss repeating.
* Feat: metrics and test updates.
* Chore: cleanup old files.
* Feat: padded token bucket sampler. (#432 )
* Feat: padded token bucket sampler.
* Chore: defaults.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
* Bug: ligand subgraph shapes.
* Feat: trainer.
* Bug: call .item() on metrics.
* Bug: move idx to proper device.
* Chore: remove compute train metrics (unused).
* Feat: checkpointing.
* Feat: minimal return option in pipeline (for mem).
* Chore: refactor sampler.
* Chore: move empty atom_array assert.
* Feat: rough training code.
* Feat: set_epoch and torch generator.
* Bug: sampler name.
* Feat: token budget aware collation.
* Chore: cleanup prints.
* Chore: code style.
* Feat: more robust pipeline (from Nate).
* Feat: batch sampler logic (from Nate).
* Feat: train updates.
* Feat: checks for invalid examples.
* Bug: fix for empty non_atomized_array.
* Feat: shell scripts for training.
* Feat: first pass old weight loading.
* Chore: updates to training hyperparams.
* Chore: partial restructure under src.
* Chore: changes for amp and comment.
* Chore: move MPNN into models.
* Chore: add mpnn to shebang.
* Chore: initial readme.
* Chore: fix imports for atomworks and model.
* Chore: conftest added.
* Chore: move training shell scripts.
* Chore: add __init__.py.
* Chore: restructure mpnn dir.
* Bug: fix atomworks imports.
* Bug: continued import fixing.
* Chore: update autocast dtype functions.
* Bug: fix issues with tests.
* Chore: add model route in data pipeline.
* Chore: fix comment about ligandmpnn legacy bug.
* Chore: rename add auxillary settings.
* chore: organize transforms.
* feat: pipeline handles atomarray annotation.
* chore: split mpnn and rf3 exec.
* chore: rename old -> legacy.
* chore: rename old->legacy in code.
* chore: update intro README.
* chore: update shebang.
* chore: update training scripts.
* chore: move launch training scripts.
* chore: fix path for train file.
* chore: add addn params protein vs ligand.
* fix: make train.py/inference.py executable.
* fix: python->srun.
* chore: update notes.
* feat: add back metrics_logging to modelhub.
TODO: deduplicate rf3/rfd3 for callback
StoreValidationMetricsInDFCallback.
* chore: fix atomworks imports.
* chore: add .env call.
* fix: actually fix env setup.
* chore: rename featurization of user setting.
* fix: move featurize user settings to end.
* fix: import.
* chore: import order.
* fix: train date cutoff, ckpt loading.
* fix: update atomworks to fix residue starts.
* chore: rearrange utils.
* chore: create io utils file.
* chore: file rename.
* feat: DRAFT of inference engine/utils/script.
* small inference input loading fixes
* fix: collater and repeat_sample_num handling.
* feat: significant upgrade of cli/inference input.
* fix: addtional checks for user inputs.
* chore: update high level inference script.
* chore: minor changes; prepping for refactor.
* chore: comment and small fix legacy wts.
* chore: reorder constants in legacy wts.
* chore: warnings to README.
* chore: more notes on readme.
* chore: readme updates.
* feat: inference working.
* chore: note on README.
* fix: readme syntax issue.
* chore: readme format.
* chore: tests for inference.
* chore: formatting.
---------
Co-authored-by: Andrew Kubaney <akubaney@localhost>
Co-authored-by: Nathaniel Corley <ncorley@uw.edu >
Co-authored-by: Andrew Kubaney <akubaney@digs>
Co-authored-by: Raktim Mitra <raktim@localhost>
2025-11-29 22:34:05 -08:00
Jasper Butcher
fcd37487fc
Add traning ( #694 )
...
* Add enzyme example, refactor io
* udpate
* Delete old configs, add training code for rfd3
* minor changes
2025-11-26 00:57:45 -08:00
Jasper Butcher
7c1a77ff0c
Add enzyme example, refactor io ( #688 )
...
* Add enzyme example, refactor io
* udpate
2025-11-25 16:45:25 -08:00
jbutch
e419028257
Update example
2025-11-23 22:54:06 -08:00
jbutch
1251f0fcf1
Add non-hydra interface for instantiating model
2025-11-23 22:38:39 -08:00
jbutch
22407d510c
Update regression tests and defaults
2025-11-23 20:21:01 -08:00
jbutch
12115d052b
Update RFD3 regression tests
2025-11-23 19:31:45 -08:00
jbutch
e520df0a97
Update to aa_design/main latest (post loop fix)
2025-11-23 19:30:17 -08:00
Jasper Butcher
3dba499b6d
refactor source files for open sourcing ( #648 )
...
* mc
* Add base class for inference engine
* refactor inference engine
* Move constants and components out of rfd3 folder
* Fixes to engine
* Update with working checkpoint
* revert layer utils
* Fix more imports
* Move alignment, conditiontransitionblock
* Update sampler name
* mc
* More import fixes
* make format
* Minor fixes
* mc
* Fix rf3 inference engine
* Fix inference sampler
* Fix modules
* Running inference
* Make format
* add pre-commit hook
* fix: RF3 inference (#670 )
fix: make rf3 tests in new format
* Minor cleanup
---------
Co-authored-by: Nathaniel Corley <ncorley@uw.edu >
2025-11-20 16:29:47 -08:00
Nathaniel Corley
aa4cb6875f
fix: paths and ipd readme ( #656 )
...
fix: update paths; add IPD readme
2025-11-13 17:46:04 -08:00
Jasper Butcher
5e7b739ed3
Add initial RFD3 Files and passing tests
...
* Add initial files
* add files
* Move projects.aa_design -> rfd3
* Make format
* Delete test files
* Add configs
* Mc
* Fixed tests
* remove test files
2025-11-11 10:07:43 -08:00
Rafael Brent
36f668b5ae
fix: clean up logging ( #587 )
...
* fix: don't log all-nan metrics
* fix: typo in logging
* chore: ruff
---------
Co-authored-by: Rafi Brent <rafi.brent@gmail.com >
2025-11-10 14:23:07 -08:00
