def process_formdata(self, input_data):
if input_data:
self.data = input_data[0]
else:
self.data = None
self.processed_data = None
return
self.error_items = [] # Cells to highlight as having errors
try:
data = json.loads(input_data[0])
except ValueError as e:
raise ValidationError(e.msg)
# Read in data
headers = data.pop(0)
df = pd.DataFrame(data, columns=headers) \
.replace('', np.nan) \
.dropna(how='all') \
.dropna(how='all', axis=1)
if 'STRAIN' in df.columns:
self.strain_list = list(df.STRAIN)
# Resolve isotypes and insert as second column
try:
df = df.assign(ISOTYPE=[query_strains(x, resolve_isotype=True) for x in df.STRAIN])
isotype_col = df.pop("ISOTYPE")
df.insert(1, "ISOTYPE", isotype_col)
logger.info(df)
except AttributeError:
# If the user fails to pass data it will be flagged
pass
self.processed_data = df
def isotype_page(isotype_name, release=config['DATASET_RELEASE']):
"""
Isotype page
"""
isotype = query_strains(isotype_name=isotype_name)
if not isotype:
abort(404)
# Fetch isotype images
photos = list_release_files(f"photos/isolation/{isotype_name}")
photo_set = {}
for row in photos:
if 'thumb' not in row:
strains = basename(row).replace(".jpg", "").split("_")[1:]
photo_set[row.replace(".jpg", ".thumb.jpg")] = strains
# High impact variants
logger.info(release)
VARS = {
"title": f"Isotype {isotype_name}",
"isotype": isotype,
"isotype_name": isotype_name,
"isotype_ref_strain": [x for x in isotype if x.isotype_ref_strain][0],
"strain_json_output": dump_json(isotype),
"photo_set": photo_set
}
return render_template('strain/isotype.html', **VARS)
def data(selected_release=DATASET_RELEASE):
"""
Default data page - lists
available releases.
"""
title = "Releases"
strain_listing = query_strains(release=selected_release)
# Fetch variant data
url = "https://storage.googleapis.com/elegansvariation.org/releases/{selected_release}/multiqc_bcftools_stats.json".format(
selected_release=selected_release)
vcf_summary = requests.get(url).json()
release_summary = strain_m.release_summary(selected_release)
try:
phylo_url = list_release_files(
f"releases/{DATASET_RELEASE}/popgen/trees/genome.pdf")[0]
except IndexError:
pass
VARS = {
'title': title,
'strain_listing': strain_listing,
'vcf_summary': vcf_summary,
'phylo_url': phylo_url,
'RELEASES': RELEASES,
'release_summary': release_summary,
'selected_release': selected_release,
'wormbase_genome_version': dict(RELEASES)[selected_release]
}
return render_template('data.html', **VARS)
def download_script_strain_v2():
v2 = True
strain_listing = query_strains(release=config["DATASET_RELEASE"])
download_page = render_template('download_script.sh', **locals())
response = make_response(download_page)
response.headers["Content-Type"] = "text/plain"
return response
def generate():
first = True
if first:
first = False
header = [x.name for x in list(strain_m.__mapper__.columns)]
yield ('\t'.join(header) + "\n").encode('utf-8')
for row in query_strains():
row = [getattr(row, column.name) for column in col_list]
yield ('\t'.join(map(str, row)) + "\n").encode('utf-8')
def generate():
col_list = list(Strain.__mapper__.columns)
col_order = [
1, 0, 3, 4, 5, 7, 8, 9, 10, 28, 11, 12, 13, 14, 15, 16, 17, 18, 19,
20, 21, 22, 23, 24, 25, 26, 27, 2, 6
]
col_list[:] = [col_list[i] for i in col_order]
header = [x.name for x in col_list]
yield '\t'.join(header) + "\n"
for row in query_strains(issues=False):
row = [getattr(row, column.name) for column in col_list]
yield '\t'.join(map(str, row)) + "\n"
def data(selected_release=config["DATASET_RELEASE"]):
"""
Default data page - lists
available releases.
"""
# Pre-2020 releases used BAMs grouped by isotype.
if int(selected_release) < 20200101:
return data_v01(selected_release)
# Post-2020 releases keep strain-level bams separate.
title = "Releases"
sub_page = selected_release
strain_listing = query_strains(release=selected_release)
strain_listing_issues = query_strains(release=selected_release,
issues=True)
release_summary = Strain.release_summary(selected_release)
RELEASES = config["RELEASES"]
DATASET_RELEASE, WORMBASE_VERSION = list(
filter(lambda x: x[0] == selected_release, RELEASES))[0]
REPORTS = ["alignment"]
return render_template('data_v2.html', **locals())
def strain_catalog():
# [ ] REVERT; TEMPORARY BAN ON NEW ORDERS
flash(Markup(
"<strong>Due to COVID-19, we are unable to accept new orders until further notice.</strong>"
),
category="danger")
VARS = {
"title": "Strain Catalog",
"warning": request.args.get('warning'),
"strain_listing": query_strains()
}
return render_template('strain/strain_catalog.html', **VARS)
def data_v01(selected_release):
# Legacy releases (Pre 20200101)
title = "Releases"
subtitle = selected_release
strain_listing = query_strains(release=selected_release)
# Fetch variant data
url = "https://storage.googleapis.com/elegansvariation.org/releases/{selected_release}/multiqc_bcftools_stats.json".format(
selected_release=selected_release)
try:
vcf_summary = requests.get(url).json()
except JSONDecodeError:
vcf_summary = None
release_summary = Strain.release_summary(selected_release)
try:
phylo_url = list_release_files(
f"releases/{config['DATASET_RELEASE']}/popgen/trees/genome.pdf")[0]
except IndexError:
phylo_url = None
RELEASES = config["RELEASES"]
wormbase_genome_version = dict(config["RELEASES"])[selected_release]
return render_template('data.html', **locals())
def isotype_page(isotype_name):
"""
Isotype page
"""
isotype = query_strains(isotype_name=isotype_name)
if not isotype:
abort(404)
# Fetch isotype images
photos = list_release_files(f"photos/isolation/{isotype_name}")
photo_set = {}
for row in photos:
if 'thumb' not in row:
strains = basename(row).replace(".jpg", "").split("_")[1:]
photo_set[row.replace(".jpg", ".thumb.jpg")] = strains
# High impact variants
soft_variant = requests.get(
f"https://storage.googleapis.com/elegansvariation.org/releases/{DATASET_RELEASE}/variation/sample_summary/soft.isotype_summary.json"
).json()
hard_variant = requests.get(
f"https://storage.googleapis.com/elegansvariation.org/releases/{DATASET_RELEASE}/variation/sample_summary/hard.isotype_summary.json"
).json()
soft_variant = [x for x in soft_variant if x['isotype'] == isotype_name][0]
hard_variant = [x for x in hard_variant if x['isotype'] == isotype_name][0]
VARS = {
"title": isotype_name,
"isotype": isotype,
"isotype_name": isotype_name,
"reference_strain": [x for x in isotype if x.reference_strain][0],
"strain_json_output": dump_json(isotype),
"photo_set": photo_set,
"soft_variant": soft_variant,
"hard_variant": hard_variant
}
return render_template('strain/strain.html', **VARS)