def download_gencode_dir(output_dir):
"""Download all the required gencode files
"""
makedir_exist_ok(output_dir)
url_template = ("https://github.com/kipoi/models/blob/"
"7648d3fd57def50934835b52acadd26bcaaa275c/FactorNet/"
"template/dataloader_files/gencode_features/{}?raw=true")
# url_template = "https://github.com/uci-cbcl/FactorNet/blob/master/resources/{}?raw=true"
fnames = [('cpgisland.bed.gz', 'ac7dc007d7019c05adb7a331d1d6721d'),
('wgEncodeGencodeBasicV19.cds.merged.bed.gz',
'4ec9883932932efe87e4adc6c84ced1c'),
('wgEncodeGencodeBasicV19.intron.merged.bed.gz',
'd2db7e3255323d2b5b04e1c0c59ecd2d'),
('wgEncodeGencodeBasicV19.promoter.merged.bed.gz',
'48fe1ab3aa0e9f5d11f3e5dfedbd47b6'),
('wgEncodeGencodeBasicV19.utr5.merged.bed.gz',
'de87c14d4ff055226afeb01446aba6e6'),
('wgEncodeGencodeBasicV19.utr3.merged.bed.gz',
'8bbe08f5fba86306dfbef56d756856f1')]
for fname, md5 in fnames:
output_file = os.path.join(output_dir, fname)
rf = RemoteFile(url=url_template.format(fname), md5=md5)
if not os.path.exists(output_file) or not rf.validate(output_file):
rf.get_file(output_file)
def test_RemoteFile(tmpdir):
f = RemoteFile(
"https://i12g-gagneurweb.in.tum.de/public/docs/concise/index.html",
"a10361dc7f4582bb30eea089549bfc46")
p = tmpdir.mkdir("sub").join("output")
f.get_file(str(p))
assert f.validate(str(p)) is False
def __init__(self,
intervals_file,
fasta_file,
dnase_file,
cell_line=None,
RNAseq_PC_file=None,
mappability_file=None,
use_linecache=True):
# intervals
if use_linecache:
linecache.clearcache()
BT = BedToolLinecache
else:
BT = BedTool
self.bt = BT(intervals_file)
# Fasta
self.fasta_file = fasta_file
self.fasta_extractor = None # initialize later
# DNase
self.dnase_file = dnase_file
self.dnase_extractor = None
# mappability
if mappability_file is None:
# download the mappability file if not existing
common_dl_dir = os.path.join(this_dir, "../../template/downloaded/dataloader_files")
makedir_exist_ok(common_dl_dir)
rf = RemoteFile(url="http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeMapability/wgEncodeDukeMapabilityUniqueness35bp.bigWig",
md5="1d15ddafe2c8df51cf08495db96679e7")
mappability_file = os.path.join(common_dl_dir, "wgEncodeDukeMapabilityUniqueness35bp.bigWig")
if not os.path.exists(mappability_file) or not rf.validate(mappability_file):
# download the path
rf.get_file(mappability_file)
self.mappability_file = mappability_file
self.mappability_extractor = None
# Get the metadata features
if cell_line is None:
if RNAseq_PC_file is None:
raise ValueError("RNAseq_PC_file has to be specified when cell_line=None")
assert os.path.exists(RNAseq_PC_file)
else:
# Using the pre-defined cell-line
output_dir = os.path.join(this_dir, "../../template/downloaded/dataloader_files/RNAseq_features/")
makedir_exist_ok(output_dir)
RNAseq_PC_file = os.path.join(output_dir, cell_line, "meta.txt")
url_template = ('https://s3.eu-central-1.amazonaws.com/kipoi-models/dataloader_files/'
'FactorNet/dataloader_files/RNAseq_features/{}/meta.txt')
# rf = RemoteFile(url=url_template.format(cell_line))
if not os.path.exists(RNAseq_PC_file): # or not rf.validate(mappability_file):
# download the path
download_url(url_template.format(cell_line), os.path.join(output_dir, cell_line), "meta.txt")
# rf.get_file(RNAseq_PC_file)
self.meta_feat = pd.read_csv(RNAseq_PC_file,
sep="\t", header=None)[0].values
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)
def __init__(self,
intervals_file,
fasta_file,
dnase_file,
mappability_file=None,
use_linecache=True):
# intervals
if use_linecache:
linecache.clearcache()
BT = BedToolLinecache
else:
BT = BedTool
self.bt = BT(intervals_file)
# Fasta
self.fasta_file = fasta_file
self.fasta_extractor = None # initialize later
# DNase
self.dnase_file = dnase_file
self.dnase_extractor = None
# mappability
if mappability_file is None:
# download the mappability file if not existing
common_dl_dir = os.path.join(
this_dir, "../../template/downloaded/dataloader_files")
makedir_exist_ok(common_dl_dir)
rf = RemoteFile(
url=
"http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeMapability/wgEncodeDukeMapabilityUniqueness35bp.bigWig",
md5="1d15ddafe2c8df51cf08495db96679e7")
mappability_file = os.path.join(
common_dl_dir, "wgEncodeDukeMapabilityUniqueness35bp.bigWig")
if not os.path.exists(mappability_file) or not rf.validate(
mappability_file):
# download the path
rf.get_file(mappability_file)
self.mappability_file = mappability_file
self.mappability_extractor = None
def test_recursive_dict_parse():
a = {"a": 1, "b": 2}
assert a == recursive_dict_parse(a, "url", RemoteFile.from_config)
a = {"a": 1, "b": 2, "c": {"e": 3}}
assert a == recursive_dict_parse(a, "url", RemoteFile.from_config)
a = {"a": 1, "b": 2, "c": [{"url": "a", "md5": "b"}]}
out = recursive_dict_parse(a, "url", RemoteFile.from_config)
assert a != out
assert out['a'] == a['a']
assert out['b'] == a['b']
assert out['c'] == [RemoteFile(url=a['c'][0]['url'], md5=a['c'][0]['md5'])]
def __init__(self,
intervals_file,
fasta_file,
dnase_file,
cell_line=None,
RNAseq_PC_file=None,
mappability_file=None,
GENCODE_dir=None,
use_linecache=True):
# intervals
if use_linecache:
linecache.clearcache()
BT = BedToolLinecache
else:
BT = BedTool
self.bt = BT(intervals_file)
# Fasta
self.fasta_file = fasta_file
self.fasta_extractor = None # initialize later
# DNase
self.dnase_file = dnase_file
self.dnase_extractor = None
# mappability
if mappability_file is None:
# download the mappability file if not existing
common_dl_dir = os.path.join(
this_dir, "../../template/downloaded/dataloader_files")
makedir_exist_ok(common_dl_dir)
rf = RemoteFile(
url=
"http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeMapability/wgEncodeDukeMapabilityUniqueness35bp.bigWig",
md5="1d15ddafe2c8df51cf08495db96679e7")
mappability_file = os.path.join(
common_dl_dir, "wgEncodeDukeMapabilityUniqueness35bp.bigWig")
if not os.path.exists(mappability_file) or not rf.validate(
mappability_file):
# download the path
rf.get_file(mappability_file)
self.mappability_file = mappability_file
self.mappability_extractor = None
# Gencode features
if GENCODE_dir is None:
gp = os.path.join(
this_dir,
"../../template/downloaded/dataloader_files/gencode_features/")
else:
gp = GENCODE_dir
download_gencode_dir(gp) # download files
self.gencode_beds = [
("cpg", BedTool(gp + '/cpgisland.bed.gz')),
("cds",
BedTool(gp + '/wgEncodeGencodeBasicV19.cds.merged.bed.gz')),
("intron",
BedTool(gp + '/wgEncodeGencodeBasicV19.intron.merged.bed.gz')),
("promoter",
BedTool(gp + '/wgEncodeGencodeBasicV19.promoter.merged.bed.gz')),
("utr5",
BedTool(gp + '/wgEncodeGencodeBasicV19.utr5.merged.bed.gz')),
("utr3",
BedTool(gp + '/wgEncodeGencodeBasicV19.utr3.merged.bed.gz')),
]
# Overlap beds - could be done incrementally
print("Overlapping all the bed-files")
# The BT() and .fn are there in order to leverage BedToolLinecache
self.overlap_beds = [(b, BT(self.bt.intersect(v, wa=True, c=True).fn))
for b, v in self.gencode_beds]
print("Assesing the file")
assert len(self.overlap_beds[1][1]) == len(self.bt)
# Get the metadata features
if cell_line is None:
if RNAseq_PC_file is None:
raise ValueError(
"RNAseq_PC_file has to be specified when cell_line=None")
assert os.path.exists(RNAseq_PC_file)
else:
# Using the pre-defined cell-line
output_dir = os.path.join(
this_dir,
"../../template/downloaded/dataloader_files/RNAseq_features/")
makedir_exist_ok(output_dir)
RNAseq_PC_file = os.path.join(output_dir, cell_line, "meta.txt")
url_template = (
'https://s3.eu-central-1.amazonaws.com/kipoi-models/dataloader_files/'
'FactorNet/dataloader_files/RNAseq_features/{}/meta.txt')
# rf = RemoteFile(url=url_template.format(cell_line))
if not os.path.exists(
RNAseq_PC_file): # or not rf.validate(mappability_file):
# download the path
download_url(url_template.format(cell_line),
os.path.join(output_dir, cell_line), "meta.txt")
# rf.get_file(RNAseq_PC_file)
self.meta_feat = pd.read_csv(RNAseq_PC_file, sep="\t",
header=None)[0].values
def __init__(self,
intervals_file,
fasta_file,
dnase_file,
cell_line=None,
mappability_file=None,
GENCODE_dir=None,
use_linecache=True):
# intervals
if use_linecache:
linecache.clearcache()
BT = BedToolLinecache
else:
BT = BedTool
self.bt = BT(intervals_file)
# Fasta
self.fasta_file = fasta_file
self.fasta_extractor = None # initialize later
# DNase
self.dnase_file = dnase_file
self.dnase_extractor = None
# mappability
if mappability_file is None:
# download the mappability file if not existing
common_dl_dir = os.path.join(
this_dir, "../../template/downloaded/dataloader_files")
makedir_exist_ok(common_dl_dir)
rf = RemoteFile(
url=
"http://hgdownload.cse.ucsc.edu/goldenPath/hg19/encodeDCC/wgEncodeMapability/wgEncodeDukeMapabilityUniqueness35bp.bigWig",
md5="1d15ddafe2c8df51cf08495db96679e7")
mappability_file = os.path.join(
common_dl_dir, "wgEncodeDukeMapabilityUniqueness35bp.bigWig")
if not os.path.exists(mappability_file) or not rf.validate(
mappability_file):
# download the path
rf.get_file(mappability_file)
self.mappability_file = mappability_file
self.mappability_extractor = None
# Gencode features
if GENCODE_dir is None:
gp = os.path.join(
this_dir,
"../../template/downloaded/dataloader_files/gencode_features/")
else:
gp = GENCODE_dir
download_gencode_dir(gp) # download files
self.gencode_beds = [
("cpg", BedTool(gp + '/cpgisland.bed.gz')),
("cds",
BedTool(gp + '/wgEncodeGencodeBasicV19.cds.merged.bed.gz')),
("intron",
BedTool(gp + '/wgEncodeGencodeBasicV19.intron.merged.bed.gz')),
("promoter",
BedTool(gp + '/wgEncodeGencodeBasicV19.promoter.merged.bed.gz')),
("utr5",
BedTool(gp + '/wgEncodeGencodeBasicV19.utr5.merged.bed.gz')),
("utr3",
BedTool(gp + '/wgEncodeGencodeBasicV19.utr3.merged.bed.gz')),
]
# Overlap beds - could be done incrementally
print("Overlapping all the bed-files")
# The BT() and .fn are there in order to leverage BedToolLinecache
self.overlap_beds = [(b, BT(self.bt.intersect(v, wa=True, c=True).fn))
for b, v in self.gencode_beds]
print("Assesing the file")
assert len(self.overlap_beds[1][1]) == len(self.bt)
def wget_repeat_masker(output_file):
from kipoi.specs import RemoteFile
RemoteFile(
"http://www.repeatmasker.org/genomes/mm10/RepeatMasker-rm405-db20140131/mm10.fa.out.gz",
"c046c8a8d1a1ce20eb865574d31d528b").get_file(output_file)
