def test_is_poplar_gene_valid(self):
# Valid gene
result = BARUtils.is_poplar_gene_valid('Potri.019G123900.1')
self.assertTrue(result)
# Invalid gene
result = BARUtils.is_poplar_gene_valid('abc')
self.assertFalse(result)
def get(self, fixed_pdb='', moving_pdb=''):
"""This end point returns the superimposition of the moving PDB onto moving PDB in PDB format"""
fixed_pdb = escape(fixed_pdb)
moving_pdb = escape(moving_pdb)
arabidopsis_pdb_path = '/var/www/html/eplant_legacy/java/Phyre2-Models/Phyre2_'
poplar_pdb_path = '/var/www/html/eplant_poplar/pdb/'
phenix_pdb_link = 'https://bar.utoronto.ca/phenix-pdbs/'
phenix_pdb_path = '/var/www/html/phenix-pdbs/'
# Check if genes ids are valid
if BARUtils.is_arabidopsis_gene_valid(fixed_pdb):
fixed_pdb_path = arabidopsis_pdb_path + fixed_pdb.upper() + '.pdb'
elif BARUtils.is_poplar_gene_valid(fixed_pdb):
fixed_pdb_path = poplar_pdb_path + BARUtils.format_poplar(
fixed_pdb) + '.pdb'
else:
return BARUtils.error_exit('Invalid fixed pdb gene id'), 400
if BARUtils.is_arabidopsis_gene_valid(moving_pdb):
moving_pdb_path = arabidopsis_pdb_path + moving_pdb.upper(
) + '.pdb'
elif BARUtils.is_poplar_gene_valid(moving_pdb):
moving_pdb_path = poplar_pdb_path + BARUtils.format_poplar(
moving_pdb) + '.pdb'
else:
return BARUtils.error_exit('Invalid moving pdb gene id'), 400
# Check if model already exists
phenix_file_name = fixed_pdb.upper() + "-" + moving_pdb.upper(
) + "-phenix.pdb"
response = requests.get(phenix_pdb_link + phenix_file_name)
# If not, generate the model
if response.status_code != 200:
subprocess.run([
'phenix.superpose_pdbs',
'file_name=' + phenix_pdb_path + phenix_file_name,
fixed_pdb_path, moving_pdb_path
])
return redirect(phenix_pdb_link + phenix_file_name)
def get(self, gene_id=''):
""" Endpoint returns annotated SNP poplar data in order of (to match A th API format):
AA pos (zero-indexed), sample id, 'missense_variant','MODERATE', 'MISSENSE', codon/DNA base change,
AA change (DH), pro length, gene ID, 'protein_coding', 'CODING', transcript id, biotype
values with single quotes are fixed """
results_json = []
# Escape input
gene_id = escape(gene_id)
if BARUtils.is_poplar_gene_valid(gene_id) is False:
return BARUtils.error_exit('Invalid gene id'), 400
try:
rows = db.session.query(ProteinReference, SnpsToProtein, SnpsReference). \
select_from(ProteinReference). \
join(SnpsToProtein). \
join(SnpsReference). \
filter(ProteinReference.gene_identifier == gene_id).all()
# BAR A Th API format is chr, AA pos (zero-indexed), sample id, 'missense_variant',
# 'MODERATE', 'MISSENSE', codon/DNA base change, AA change (DH),
# pro length, gene ID, 'protein_coding', 'CODING', transcript id, biotype
for protein, snpsjoin, snpstbl in rows:
itm_lst = [
snpstbl.chromosome,
# snpstbl.chromosomal_loci,
snpsjoin.aa_pos - 1, # zero index-ed
snpstbl.sample_id,
'missense_variant',
'MODERATE',
'MISSENSE',
str(snpsjoin.transcript_pos) + snpsjoin.ref_DNA + '>' +
snpsjoin.alt_DNA,
snpsjoin.ref_aa + snpsjoin.alt_aa,
None,
re.sub(r".\d$", '', protein.gene_identifier),
'protein_coding',
'CODING',
protein.gene_identifier,
None,
]
results_json.append(itm_lst)
except OperationalError:
return BARUtils.error_exit('An internal error has occurred'), 500
# Return results if there are data
if len(results_json) > 0:
return BARUtils.success_exit(results_json)
else:
return BARUtils.error_exit(
'There are no data found for the given gene')
def get(self, species="", gene_id=""):
"""This end point provides gene isoforms given a gene ID.
Only genes/isoforms with pdb structures are returned"""
gene_isoforms = []
# Escape input
species = escape(species)
gene_id = escape(gene_id)
# Set the database and check if genes are valid
if species == "arabidopsis":
database = eplant2_isoforms()
if not BARUtils.is_arabidopsis_gene_valid(gene_id):
return BARUtils.error_exit("Invalid gene id"), 400
elif species == "poplar":
database = eplant_poplar_isoforms
if not BARUtils.is_poplar_gene_valid(gene_id):
return BARUtils.error_exit("Invalid gene id"), 400
# Format the gene first
gene_id = BARUtils.format_poplar(gene_id)
elif species == "tomato":
database = eplant_tomato_isoforms
if not BARUtils.is_tomato_gene_valid(gene_id, False):
return BARUtils.error_exit("Invalid gene id"), 400
else:
return BARUtils.error_exit("No data for the given species")
# Now get the data
try:
rows = database.query.filter_by(gene=gene_id).all()
except OperationalError:
return BARUtils.error_exit("An internal error has occurred"), 500
[gene_isoforms.append(row.isoform) for row in rows]
# Found isoforms
if len(gene_isoforms) > 0:
return BARUtils.success_exit(gene_isoforms)
else:
return BARUtils.error_exit(
"There are no data found for the given gene")
def get(self, species='', gene_id=''):
"""This end point provides gene isoforms given a gene ID.
Only genes/isoforms with pdb structures are returned"""
gene_isoforms = []
# Escape input
species = escape(species)
gene_id = escape(gene_id)
if species == 'arabidopsis':
if BARUtils.is_arabidopsis_gene_valid(gene_id):
try:
rows = isoforms.query.filter_by(gene=gene_id).all()
except OperationalError:
return BARUtils.error_exit(
'An internal error has occurred'), 500
[gene_isoforms.append(row.isoform) for row in rows]
# Found isoforms
if len(gene_isoforms) > 0:
return BARUtils.success_exit(gene_isoforms)
else:
return BARUtils.error_exit('Invalid gene id'), 400
elif species == 'poplar':
if BARUtils.is_poplar_gene_valid(gene_id):
# Path is the location of poplar pdb file
if os.environ.get('BAR'):
path = '/DATA/ePlants_Data/eplant_poplar/protein_structures/'
else:
path = os.getcwd(
) + '/data/gene_information/gene_isoforms/'
path += gene_id + '.pdb'
if os.path.exists(path) and os.path.isfile(path):
return BARUtils.success_exit(gene_id)
else:
return BARUtils.error_exit('Invalid gene id'), 400
else:
return BARUtils.error_exit('No data for the given species')
return BARUtils.error_exit(
'There are no data found for the given gene')
def post(self):
"""This end point returns gene isoforms data for a multiple genes for a species.
Only genes/isoforms with pdb structures are returned"""
json_data = request.get_json()
data = {}
# Validate json
try:
json_data = GeneIsoformsSchema().load(json_data)
except ValidationError as err:
return BARUtils.error_exit(err.messages), 400
genes = json_data['genes']
species = json_data['species']
# Set species and check gene ID format
if species == 'arabidopsis':
# Check if gene is valid
for gene in genes:
if not BARUtils.is_arabidopsis_gene_valid(gene):
return BARUtils.error_exit('Invalid gene id'), 400
# Query the database
database = isoforms()
try:
rows = database.query.filter(isoforms.gene.in_(genes)).all()
except OperationalError:
return BARUtils.error_exit(
'An internal error has occurred.'), 500
if len(rows) > 0:
for row in rows:
if row.gene in data:
data[row.gene].append(row.isoform)
else:
data[row.gene] = []
data[row.gene].append(row.isoform)
return BARUtils.success_exit(data)
else:
return BARUtils.error_exit(
'No data for the given species/genes'), 400
elif species == 'poplar':
for gene in genes:
# Check if gene is valid
if not BARUtils.is_poplar_gene_valid(gene):
return BARUtils.error_exit('Invalid gene id'), 400
# Path is the location of poplar pdb file
if os.environ.get('BAR'):
path = '/DATA/ePlants_Data/eplant_poplar/protein_structures/'
else:
path = os.getcwd() + '/data/gene_information/gene_isoforms/'
# Check if the genes exist.
for gene in genes:
gene_path = path + gene + '.pdb'
if os.path.exists(gene_path) and os.path.isfile(gene_path):
data[gene] = []
data[gene].append(gene)
# Return data if gene is found
if len(data) > 0:
return BARUtils.success_exit(data)
else:
return BARUtils.error_exit(
'No data for the given species/genes'), 400
else:
return BARUtils.error_exit('Invalid species'), 400
def post(self):
"""This end point returns gene isoforms data for a multiple genes for a species.
Only genes/isoforms with pdb structures are returned"""
json_data = request.get_json()
data = {}
# Validate json
try:
json_data = GeneIsoformsSchema().load(json_data)
except ValidationError as err:
return BARUtils.error_exit(err.messages), 400
genes = json_data["genes"]
species = json_data["species"]
# Set species and check gene ID format
if species == "arabidopsis":
database = eplant2_isoforms()
# Check if gene is valid
for gene in genes:
if not BARUtils.is_arabidopsis_gene_valid(gene):
return BARUtils.error_exit("Invalid gene id"), 400
# Query must be run individually for each species
try:
rows = database.query.filter(
eplant2_isoforms.gene.in_(genes)).all()
except OperationalError:
return BARUtils.error_exit(
"An internal error has occurred."), 500
elif species == "poplar":
database = eplant_poplar_isoforms()
for gene in genes:
# Check if gene is valid
if not BARUtils.is_poplar_gene_valid(gene):
return BARUtils.error_exit("Invalid gene id"), 400
try:
rows = database.query.filter(
eplant_poplar_isoforms.gene.in_(genes)).all()
except OperationalError:
return BARUtils.error_exit(
"An internal error has occurred."), 500
elif species == "tomato":
database = eplant_tomato_isoforms()
for gene in genes:
# Check if gene is valid
if not BARUtils.is_tomato_gene_valid(gene, False):
return BARUtils.error_exit("Invalid gene id"), 400
try:
rows = database.query.filter(
eplant_tomato_isoforms.gene.in_(genes)).all()
except OperationalError:
return BARUtils.error_exit(
"An internal error has occurred."), 500
else:
return BARUtils.error_exit("Invalid species"), 400
# If there any isoforms found, return data
if len(rows) > 0:
for row in rows:
if row.gene in data:
data[row.gene].append(row.isoform)
else:
data[row.gene] = []
data[row.gene].append(row.isoform)
return BARUtils.success_exit(data)
else:
return BARUtils.error_exit(
"No data for the given species/genes"), 400