mirror of
https://github.com/KosinskiLab/AlphaPulldown.git
synced 2026-06-04 14:14:24 +08:00
4d802be7d6
* symmetrical refactoring to support both af2 and af3 data pipelines * Clean tests * Keep GPU tests in place * Reverted accidentally deleted templates * Add AlphaFold3 feature creation pipeline and per-chain input generation - Implement `create_pipeline_af3` to construct the AlphaFold3 data pipeline with correct database and binary paths. - Add `create_af3_individual_features` to generate AlphaFold3 input features for each chain in a FASTA, handling protein, RNA, and DNA sequences. - Integrate new AF3 logic into the main entry point, dispatching to AF2 or AF3 as appropriate. - Ensure output directory creation and error handling for missing dependencies or invalid sequences. * Convert template dates to datetime for af3 * First check for nucleotides, then for amino-acids * Skip existing features json if --skip_existing=true * Check if DNA before RNA * Bump 2.1.0 * Git ignore build/ dir
42 lines
1.1 KiB
Python
42 lines
1.1 KiB
Python
#!/usr/bin/env python
|
|
from absl import flags, app, logging
|
|
import json
|
|
from alphapulldown.utils.modelling_setup import parse_fold, create_custom_info
|
|
from alphapulldown.utils.create_combinations import process_files
|
|
import io
|
|
|
|
logging.set_verbosity(logging.INFO)
|
|
|
|
flags.DEFINE_list(
|
|
'input_list', None,
|
|
'Path to input file list.')
|
|
flags.DEFINE_list(
|
|
'features_directory', None,
|
|
'Path to computed monomer features.')
|
|
flags.DEFINE_string(
|
|
'protein_delimiter', '+',
|
|
'Delimiter for proteins.')
|
|
flags.DEFINE_string(
|
|
'output_prefix', None,
|
|
'Prefix for output JSON files.')
|
|
|
|
FLAGS = flags.FLAGS
|
|
|
|
def main(argv):
|
|
buffer = io.StringIO()
|
|
_ = process_files(
|
|
input_files=FLAGS.input_list,
|
|
output_path=buffer,
|
|
exclude_permutations = True
|
|
)
|
|
buffer.seek(0)
|
|
all_folds = buffer.readlines()
|
|
all_folds = [x.strip() for x in all_folds]
|
|
parsed = parse_fold(all_folds, FLAGS.features_directory, FLAGS.protein_delimiter)
|
|
data = create_custom_info(parsed)
|
|
|
|
with open(FLAGS.output_prefix + "data.json", 'w') as out_f:
|
|
json.dump(data, out_f, indent=1)
|
|
|
|
app.run(main)
|