def make_anat_part(anat_id, anatomy_name):
# anatomical part
anatomical_part = DatsObj("AnatomicalPart", [("name", anatomy_name)])
if anat_id is not None:
anatomy_identifier = OrderedDict([("identifier",
"UBERON:" + str(anat_id)),
("identifierSource", "UBERON")])
anatomy_alt_ids = [
OrderedDict([
("identifier",
"http://purl.obolibrary.org/obo/UBERON_" + str(anat_id)),
("identifierSource", "UBERON")
])
]
anatomical_part.set("identifier", anatomy_identifier)
anatomical_part.set("alternateIdentifiers", anatomy_alt_ids)
return anatomical_part
def get_files_dats_datasets(cache, dats_samples_d, p_samples, gh_samples,
protected_cram_files, no_circular_links):
file_datasets = []
rnaseq_datatype = DatsObj("DataType", [
("information", util.get_annotation("transcription profiling", cache)),
("method", util.get_annotation("RNA-seq assay", cache)),
("platform", util.get_annotation("Illumina", cache))
])
def get_rnaseq_datatype():
dkey = ".".join(["DataType", "RNA-seq"])
return cache.get_obj_or_ref(dkey, lambda: rnaseq_datatype)
wgs_datatype = DatsObj(
"DataType",
[("information", util.get_annotation("DNA sequencing", cache)),
("method", util.get_annotation("whole genome sequencing assay",
cache)),
("platform", util.get_annotation("Illumina", cache))])
def get_wgs_datatype():
dkey = ".".join(["DataType", "WGS"])
return cache.get_obj_or_ref(dkey, lambda: wgs_datatype)
broad_key = ":".join(["Organization", "Broad Institute"])
broad = cache.get_obj_or_ref(
broad_key,
lambda: DatsObj("Organization", [("name", "Broad Institute")]))
creators = [broad]
def make_data_standard(format):
return DatsObj("DataStandard",
[("name", format),
("type", util.get_value_annotation("format", cache)),
("description", format + " file format")])
cram_ds_key = ":".join(["DataStandard", "CRAM"])
cram_ds = cache.get_obj_or_ref(cram_ds_key,
lambda: make_data_standard("CRAM"))
crai_ds_key = ":".join(["DataStandard", "CRAI"])
crai_ds = cache.get_obj_or_ref(crai_ds_key,
lambda: make_data_standard("CRAI"))
for sample_id in protected_cram_files:
file = protected_cram_files[sample_id]
material_type = None
ds_types = None
# determine file type
if re.search(r'wgs\/', file['cram_file_aws']['raw_value']):
material_type = 'DNA'
ds_types = get_wgs_datatype()
gcp_suffix = '_gcp'
elif re.search(r'rnaseq\/', file['cram_file_aws']['raw_value']):
material_type = 'RNA'
ds_types = get_rnaseq_datatype()
gcp_suffix = ''
else:
logging.fatal(
"unable to determine material/sequence type from cram_file_aws="
+ file['cram_file_aws']['raw_value'])
sys.exit(1)
# RNA-Seq keys = sample_id cram_file cram_file_md5 cram_file_size cram_index cram_file_aws cram_index_aws
# WGS keys = same as above + firecloud_id
cram_file = file['cram_file' + gcp_suffix]['raw_value']
cram_file_md5 = file['cram_file_md5']['raw_value']
# TODO - review the following encoding decisions:
# - storing .crai URI as relatedIdentifier of the DatasetDistribution for the .cram file
# - storing MD5 checksum of the .cram file as an extraProperty of the DatasetDistribution
# - storing firecloud_id as a relatedIdentifier of the Dataset (not the DatasetDistribution)
# Google Cloud Platform / Google Storage copy
gs_access = DatsObj(
"Access",
[("landingPage", file['cram_file' + gcp_suffix]['raw_value'])])
gs_distro = DatsObj(
"DatasetDistribution",
[
("access", gs_access),
("identifier",
DatsObj("Identifier",
[("identifier",
file['cram_file' + gcp_suffix]['raw_value'])])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier",
[("identifier",
file['cram_index' + gcp_suffix]['raw_value']),
("relationType", "cram_index")])
]),
("size", int(file['cram_file_size']['raw_value'])),
# TODO - add unit for bytes, include IRI?
# ("unit", util.get_value_annotation("bytes", cache))
("conformsTo", [
cache.get_obj_or_ref(cram_ds_key,
lambda: make_data_standard("CRAM"))
])
])
# AWS / S3 copy
s3_access = DatsObj(
"Access", [("landingPage", file['cram_file_aws']['raw_value'])])
s3_distro = DatsObj(
"DatasetDistribution",
[
("access", s3_access),
("identifier",
DatsObj("Identifier", [
("identifier", file['cram_file_aws']['raw_value'])
])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier", [
("identifier", file['cram_index_aws']['raw_value']),
("relationType", "cram_index")
])
]),
("size", int(file['cram_file_size']['raw_value'])),
# TODO - add unit for bytes, include IRI?
# ("unit", util.get_value_annotation("bytes", cache))
("conformsTo", [
cache.get_obj_or_ref(cram_ds_key,
lambda: make_data_standard("CRAM"))
])
])
m = re.match(r'^.*\/([^\/]+)$', cram_file)
if m is None:
logging.fatal("unable to parse filename from CRAM file URI " +
cram_file)
sys.exit(1)
filename = m.group(1)
# TODO - replace this with DATS-specific MD5 checksum encoding (TBD)
md5_dimension = DatsObj(
"Dimension", [("name", util.get_value_annotation("MD5", cache)),
("values", [file['cram_file_md5']['raw_value']])])
ds = DatsObj("Dataset", [
("distributions", [gs_distro, s3_distro]),
("dimensions", [md5_dimension]),
("title", filename),
("types", [ds_types]),
("creators", creators),
])
# add firecloud_id for WGS
if 'firecloud_id' in file:
f_id = DatsObj("RelatedIdentifier",
[("identifier", file['firecloud_id']['raw_value']),
("identifierSource", "FireCloud")])
ds.set("relatedIdentifiers", [f_id])
# input RNA/DNA extract that was sequenced
if sample_id not in dats_samples_d:
logging.fatal("no sample exists for " + sample_id +
" found in file " +
file['cram_file_aws']['raw_value'])
sys.exit(1)
dats_sample = dats_samples_d[sample_id]
dats_samp_key = ":".join(["Material", dats_sample.get("name")])
dats_samp = cache.get_obj_or_ref(dats_samp_key, lambda: dats_sample)
da = DatsObj(
"DataAcquisition",
[("name", filename), ("input", [dats_samp])
# ("uses", []) # software used
])
if not no_circular_links:
# circular link back to enclosing Dataset as the output
da.set("output", [ds.getIdRef()])
ds.set("producedBy", da)
file_datasets.append(ds)
return file_datasets
def get_files_dats_datasets(cache, dats_samples_d, sample_manifest, file_guids,
no_circular_links):
file_datasets_l = []
wgs_datatype = DatsObj(
"DataType",
[("information", util.get_annotation("DNA sequencing", cache)),
("method", util.get_annotation("whole genome sequencing assay",
cache)),
("platform", util.get_annotation("Illumina", cache))])
def get_wgs_datatype():
dkey = ".".join(["DataType", "WGS"])
return cache.get_obj_or_ref(dkey, lambda: wgs_datatype)
snp_datatype = DatsObj(
"DataType", [("information", util.get_annotation("SNP", cache)),
("method", util.get_annotation("SNP analysis", cache))])
cnv_datatype = DatsObj(
"DataType", [("information", util.get_annotation("CNV", cache)),
("method", util.get_annotation("CNV analysis", cache))])
def get_snp_datatype():
dkey = ".".join(["DataType", "SNP"])
return cache.get_obj_or_ref(dkey, lambda: snp_datatype)
def get_cnv_datatype():
dkey = ".".join(["DataType", "CNV"])
return cache.get_obj_or_ref(dkey, lambda: cnv_datatype)
nhlbi_key = ":".join(["Organization", "NHLBI"])
nhlbi = cache.get_obj_or_ref(nhlbi_key, lambda: NIH_NHLBI)
creators = [nhlbi]
def make_data_standard(format):
return DatsObj("DataStandard",
[("name", format),
("type", util.get_value_annotation("format", cache)),
("description", format + " file format")])
cram_ds_key = ":".join(["DataStandard", "CRAM"])
cram_dstan = cache.get_obj_or_ref(cram_ds_key,
lambda: make_data_standard("CRAM"))
vcf_ds_key = ":".join(["DataStandard", "VCF"])
vcf_dstan = cache.get_obj_or_ref(vcf_ds_key,
lambda: make_data_standard("VCF"))
n_samples = len(dats_samples_d)
n_samples_found = 0
for sample_id in dats_samples_d:
dats_sample = dats_samples_d[sample_id]
# look up corresponding file paths in manifest file
if sample_id not in sample_manifest:
logging.debug("sample not found in manifest - " + sample_id)
continue
n_samples_found += 1
ms = sample_manifest[sample_id]
material_type = 'DNA'
wgs_type = get_wgs_datatype()
snp_type = get_snp_datatype()
cnv_type = get_cnv_datatype()
# ------------------------------------------------
# WGS sequence - CRAM and CRAI files
# ------------------------------------------------
def get_filename(gs_uri):
m = re.match(r'^.*\/([^\/]+)$', gs_uri)
if m is None:
logging.fatal("unable to parse filename from " + gs_uri)
sys.exit(1)
filename = m.group(1)
return filename
gs_cram = ms['gs_cram']['mapped_value']
gs_crai = ms['gs_crai']['mapped_value']
# GUID lookup
cram_file = get_filename(gs_cram)
crai_file = get_filename(gs_crai)
cram_doi = file_guids[cram_file]['Sodium_GUID']['raw_value']
cram_size = file_guids[cram_file]['File size']['raw_value']
cram_md5 = file_guids[cram_file]['md5sum']['raw_value']
crai_doi = file_guids[crai_file]['Sodium_GUID']['raw_value']
crai_md5 = file_guids[crai_file]['md5sum']['raw_value']
# handle file size values with "e" in them
def filesize_to_int(size):
if re.match(r'.*e.*', size):
size = int(float(size))
else:
size = int(size)
# Google Cloud Platform / Google Storage copy
gs_cram_access = DatsObj("Access", [("accessURL", gs_cram)])
gs_cram_distro = DatsObj(
"DatasetDistribution",
[
("access", gs_cram_access),
("identifier", DatsObj("Identifier",
[("identifier", cram_doi)])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier",
[("identifier", crai_doi),
("relationType", "cram_index")])
]),
("size", filesize_to_int(cram_size)),
# TODO - add file size units
("conformsTo", [cram_dstan])
])
# AWS / S3 copy
s3_cram = ms['s3_cram']['mapped_value']
s3_crai = ms['s3_crai']['mapped_value']
s3_cram_access = DatsObj("Access", [("accessURL", s3_cram)])
s3_cram_distro = DatsObj(
"DatasetDistribution",
[
("access", s3_cram_access),
("identifier", DatsObj("Identifier",
[("identifier", cram_doi)])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier",
[("identifier", crai_doi),
("relationType", "cram_index")])
]),
("size", filesize_to_int(cram_size)),
# TODO - add file size units
("conformsTo", [cram_dstan])
])
m = re.match(r'^.*\/([^\/]+)$', gs_cram)
if m is None:
logging.fatal("unable to parse filename from CRAM file URI " +
gs_cram)
sys.exit(1)
filename = m.group(1)
# TODO - replace this with DATS-specific MD5 checksum encoding (TBD)
md5_dimension = DatsObj(
"Dimension", [("name", util.get_value_annotation("MD5", cache)),
("values", [cram_md5])])
cram_dataset = DatsObj("Dataset", [
("distributions", [gs_cram_distro, s3_cram_distro]),
("dimensions", [md5_dimension]),
("title", filename),
("types", [wgs_type]),
("creators", creators),
])
cram_da = DatsObj(
"DataAcquisition",
[("name", filename), ("input", [dats_sample.getIdRef()])
# ("uses", []) # software used
])
cram_dataset.set("producedBy", cram_da)
# circular link back to enclosing Dataset as the output
if not no_circular_links:
cram_da.set("output", [cram_dataset.getIdRef()])
file_datasets_l.append(cram_dataset)
# ------------------------------------------------
# Variant calls - VCF and CSI files
# ------------------------------------------------
gs_vcf = ms['gs_vcf']['mapped_value']
gs_csi = ms['gs_csi']['mapped_value']
if gs_vcf is None:
logging.warn("no VCF file found for " + sample_id)
continue
# GUID lookup
vcf_file = get_filename(gs_vcf)
csi_file = get_filename(gs_csi)
vcf_doi = file_guids[vcf_file]['Sodium_GUID']['raw_value']
vcf_size = file_guids[vcf_file]['File size']['raw_value']
vcf_md5 = file_guids[vcf_file]['md5sum']['raw_value']
csi_doi = file_guids[csi_file]['Sodium_GUID']['raw_value']
csi_md5 = file_guids[csi_file]['md5sum']['raw_value']
# Google Cloud Platform / Google Storage copy
gs_vcf_access = DatsObj("Access", [("accessURL", gs_vcf)])
gs_vcf_distro = DatsObj(
"DatasetDistribution",
[
("access", gs_vcf_access),
("identifier", DatsObj("Identifier",
[("identifier", vcf_doi)])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier",
[("identifier", csi_doi),
("relationType", "vcf_index")])
]),
("size", filesize_to_int(vcf_size)),
# TODO - add file size units
("conformsTo", [vcf_dstan])
])
# AWS / S3 copy
s3_vcf = ms['s3_vcf']['mapped_value']
s3_csi = ms['s3_csi']['mapped_value']
s3_vcf_access = DatsObj("Access", [("accessURL", s3_vcf)])
s3_vcf_distro = DatsObj(
"DatasetDistribution",
[
("access", s3_vcf_access),
("identifier", DatsObj("Identifier",
[("identifier", vcf_doi)])),
("relatedIdentifiers", [
DatsObj("RelatedIdentifier",
[("identifier", csi_doi),
("relationType", "vcf_index")])
]),
("size", filesize_to_int(vcf_size)),
# TODO - add file size units
("conformsTo", [vcf_dstan])
])
m = re.match(r'^.*\/([^\/]+)$', gs_vcf)
if m is None:
logging.fatal("unable to parse filename from VCF file URI " +
gs_vcf)
sys.exit(1)
filename = m.group(1)
# TODO - replace this with DATS-specific MD5 checksum encoding (TBD)
md5_dimension = DatsObj(
"Dimension", [("name", util.get_value_annotation("MD5", cache)),
("values", [vcf_md5])])
vcf_dataset = DatsObj("Dataset", [
("distributions", [gs_vcf_distro, s3_vcf_distro]),
("dimensions", [md5_dimension]),
("title", filename),
("types", [snp_type, cnv_type]),
("creators", creators),
])
vcf_da = DatsObj(
"DataAcquisition",
[("name", filename), ("input", [dats_sample.getIdRef()])
# ("uses", []) # software used
])
vcf_dataset.set("producedBy", vcf_da)
# circular link back to enclosing Dataset as the output
if not no_circular_links:
vcf_da.set("output", [vcf_dataset.getIdRef()])
file_datasets_l.append(vcf_dataset)
logging.info("found " + str(n_samples_found) + " / " + str(n_samples) +
" sample(s) in TOPMed file manifest")
return file_datasets_l
imi_project = DatsObj("Dataset", [
("identifier",
DatsObj("Identifier", [("identifier", "IMI-Cat#" + str(i))])),
("title", df["Project Acronym"][i]),
("description",
df["ShortDescription"][i] + ". SUMMARY: " + df["Summary"][i]),
("distributions", []), ("creators", [d_orgs, d_person]),
("keywords", d_kwds), ("dates", [start_date, end_date]),
("types", []), ("producedBy", []), ("storedIn", ""),
("isAbout", [d_kwds]), ("version", ""), ("isAbout", []),
("extraProperties", [dataset_extra_props])
])
imi_projects.append(imi_project)
imi_project_catalogue.set("hasPart", imi_projects)
DATSEncoder().encode(imi_project_catalogue)
# imi_data_jstr = json.dumps(cls=DATSEncoder)
# print(imi_project_catalogue.toJSON())
# imi_data_jstr = json.dumps(imi_project_catalogue.__dict__)
# print("FULL CATALOGUE:", imi_data_jstr)
script_dir = os.path.dirname(__file__)
print("DIR", script_dir)
filename = 'IMI_datacatalogue_as_DATS.json'
with open(join(output_dir, filename), 'w', encoding='utf-8') as f:
json.dump(imi_project_catalogue.toJSON(), f)