def download_repeat_masker(repeat_masker_file=None):
if repeat_masker_file is None:
from basepair.config import get_data_dir
ddir = get_data_dir()
repeat_masker_file = Path(
f"{ddir}/raw/annotation/mm10/RepeatMasker/mm10.fa.out.gz")
repeat_masker_file.parent.mkdir(exist_ok=True, parents=True)
return RemoteFile(
'http://www.repeatmasker.org/genomes/mm10/RepeatMasker-rm405-db20140131/mm10.fa.out.gz',
md5='c046c8a8d1a1ce20eb865574d31d528b').get_file(repeat_masker_file)
("Essrb", "Oct4/m0_p16"),
])
# Use a fixed profile slice
PROFILE_SLICE = slice(65, 135)
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Run motif simulation')
parser.add_argument('exp', help='which experiment to run the simulation for')
parser.add_argument('--gpu', default=0, type=int, help='Which GPU to use')
args = parser.parse_args()
exp = args.exp
# imp_score = args.imp_score
ddir = get_data_dir()
# load the model
logger.info("Loading model")
if args.gpu is not None:
create_tf_session(args.gpu)
model_dir = models_dir / exp
bpnet = BPNetSeqModel.from_mdir(model_dir)
output_dir = model_dir / 'perturbation-analysis'
pairs = get_motif_pairs(motifs)
dfi = multiple_load_instances({task: model_dir / f'deeplift/{task}/out/profile/wn/instances.parq'
for task in bpnet.tasks},
motifs=motifs)