Files
foundry/configs/datasets/train/pdb/af3_train_interface.yaml
Nathaniel Corley 5a492032d5 refactor: new modelhub (#109)
* Initial commit of chiral changes

Initial checkin of chiral feature code

Add chiral metric

* Update the way chiral features are incorporated into the model

Move initialization to new func

use default pytorch reset parameters

fix initialization for chirals

config

rename argument of confidence head

fix initialization for chirals

* refactor: src nest, rename rf2aa to modelhub

* refactor: initial commit without projects

* Initial commit of chiral changes

* Initial checkin of chiral feature code

* Add chiral metric

* Remove option for double residual connection.  Add kq_norm oiptions to base (20250125) config.

* Restoring flag

* config

* rename argument of confidence head

* Update the way chiral features are incorporated into the model

* config

* rename argument of confidence head

* Update the way chiral features are incorporated into the model

* Initial commit of chiral changes

Initial checkin of chiral feature code

Add chiral metric

* Update the way chiral features are incorporated into the model

Move initialization to new func

use default pytorch reset parameters

fix initialization for chirals

config

rename argument of confidence head

fix initialization for chirals

* refactor: new modelhub

---------

Co-authored-by: fdimaio <dimaio@uw.edu>
Co-authored-by: HaotianZhangAI4Science <haotianzhang@zju.edu.cn>
2025-04-08 13:33:17 -07:00

46 lines
1.5 KiB
YAML

defaults:
- base
dataset:
dataset_parser:
_target_: datahub.datasets.parsers.InterfacesDFParser
dataset:
name: interface
data: ${paths.data.pdb_data_dir}/interfaces_df_train.parquet
filters:
# filters common across all PDB datasets
- "deposition_date < '2021-09-30'"
- "resolution < 9.0"
- "num_polymer_pn_units <= 300"
- "cluster.notnull()"
# interface specific filters
- "~(pn_unit_1_non_polymer_res_names.notnull() and pn_unit_1_non_polymer_res_names.str.contains('${resolve_import:cifutils.constants,AF3_EXCLUDED_LIGANDS_REGEX}', regex=True))"
- "~(pn_unit_2_non_polymer_res_names.notnull() and pn_unit_2_non_polymer_res_names.str.contains('${resolve_import:cifutils.constants,AF3_EXCLUDED_LIGANDS_REGEX}', regex=True))"
- "is_inter_molecule"
columns_to_load:
# columns common across all PDB datasets
- example_id
- pdb_id
- assembly_id
- deposition_date
- resolution
- num_polymer_pn_units
- method
- cluster
- n_prot
- n_nuc
- n_ligand
- n_peptide
# interface specific columns
- pn_unit_1_iid
- pn_unit_2_iid
- pn_unit_1_non_polymer_res_names
- pn_unit_2_non_polymer_res_names
- is_inter_molecule
- all_pn_unit_iids_after_processing
- involves_loi
transform:
# interface-specific Transform pipeline parameters
crop_contiguous_probability: 0.0
crop_spatial_probability: 1.0