_target_: onescience.datapipes.simplefold.train_datamodule.SimpleFoldTrainingDataModule

datasets:
  - _target_: onescience.datapipes.simplefold.train_datamodule.DatasetConfig
    data_name: rcsb_protein
    tokenized_dir: ./datasets/tokenized
    target_dir: ./datasets
    manifest_path: ./datasets/manifest.json
    cropper:
      _target_: onescience.datapipes.boltz_data_pipeline.crop.boltz.BoltzCropper
      min_neighborhood: 0
      max_neighborhood: 40
    filters:
      - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.resolution.ResolutionFilter
        resolution: 5.0
      - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.date.DateFilter
        date: "2027-05-01"
        ref: released

filters:
    - _target_: onescience.datapipes.boltz_data_pipeline.filter.dynamic.size.SizeFilter
      min_chains: 1
      max_chains: 300

tokenizer:
  _target_: onescience.datapipes.boltz_data_pipeline.tokenize.boltz_protein.BoltzTokenizer

featurizer:
  _target_: onescience.datapipes.boltz_data_pipeline.feature.featurizer.BoltzFeaturizer

symmetries: data/symmetry.pkl
max_tokens: 256
max_atoms: 2304
pad_to_max_tokens: False
pad_to_max_atoms: False
batch_size: 256
num_workers: 16
pin_memory: True
return_train_symmetries: False
min_dist: 2.0
max_dist: 22.0
num_bins: 64
atoms_per_window_queries: 32
rotation_augment_ref_pos: False
rotation_augment_coords: True