def test_is_arabidopsis_gene_valid(self):
# Valid gene
result = BARUtils.is_arabidopsis_gene_valid('At1g01010')
self.assertTrue(result)
result = BARUtils.is_arabidopsis_gene_valid('At1g01010.1')
self.assertTrue(result)
# Invalid gene
result = BARUtils.is_arabidopsis_gene_valid('abc')
self.assertFalse(result)
result = BARUtils.is_arabidopsis_gene_valid('At1g01010.11')
self.assertFalse(result)
def test_is_arabidopsis_gene_valid(self):
# Valid gene
result = BARUtils.is_arabidopsis_gene_valid("At1g01010")
self.assertTrue(result)
result = BARUtils.is_arabidopsis_gene_valid("At1g01010.1")
self.assertTrue(result)
# Invalid gene
result = BARUtils.is_arabidopsis_gene_valid("abc")
self.assertFalse(result)
result = BARUtils.is_arabidopsis_gene_valid("At1g01010.11")
self.assertFalse(result)
def get(self, gene_id=""):
"""This end point retrieves publications from ThaleMine given an AGI ID"""
gene_id = escape(gene_id)
# Is data valid
if not BARUtils.is_arabidopsis_gene_valid(gene_id):
return BARUtils.error_exit("Invalid gene id"), 400
query = (
'<query name="" model="genomic" view="Gene.publications.firstAuthor Gene.publications.issue '
"Gene.publications.journal Gene.publications.pages Gene.publications.pubMedId Gene.publications.title "
'Gene.publications.volume Gene.publications.year" longDescription="" '
'sortOrder="Gene.publications.firstAuthor asc"><constraint path="Gene.primaryIdentifier" op="=" value="{'
'}"/></query> ')
query = query.format(gene_id)
# Now query the web service
payload = {"format": "json", "query": query}
resp = requests.post(
"https://bar.utoronto.ca/thalemine/service/query/results",
data=payload,
headers=request_headers,
)
return resp.json()
def get(self, species='', gene_id=''):
"""This end point provides gene alias given a gene ID."""
aliases = []
# Escape input
species = escape(species)
gene_id = escape(gene_id)
if species == 'arabidopsis':
if BARUtils.is_arabidopsis_gene_valid(gene_id):
try:
rows = AgiAlias.query.filter_by(agi=gene_id).all()
except OperationalError:
return BARUtils.error_exit(
'An internal error has occurred'), 500
[aliases.append(row.alias) for row in rows]
else:
return BARUtils.error_exit('Invalid gene id'), 400
else:
return BARUtils.error_exit('No data for the given species')
# Return results if there are data
if len(aliases) > 0:
return BARUtils.success_exit(aliases)
else:
return BARUtils.error_exit(
'There are no data found for the given gene')
def get(self, table_id, sample, gene):
"""Returns the value for a given gene and sample. If no sample is given returns all values for that gene"""
if not BARUtils.is_arabidopsis_gene_valid(gene):
return BARUtils.success_exit("Invalid gene ID"), 400
else:
key = request.headers.get("X-Api-Key")
if SummarizationGeneExpressionUtils.decrement_uses(key):
con = db.get_engine(bind="summarization")
tbl = SummarizationGeneExpressionUtils.get_table_object(
table_id)
if sample == "":
values = {}
try:
rows = con.execute(
tbl.select(tbl.c.Value).where(tbl.c.Gene == gene))
except SQLAlchemyError:
return BARUtils.error_exit(
"Internal server error"), 500
for row in rows:
values.update({str(row.Sample): float(row.Value)})
else:
values = []
try:
rows = con.execute(
tbl.select(tbl.c.Value).where(
tbl.c.Sample == sample).where(
tbl.c.Gene == gene))
except SQLAlchemyError:
return BARUtils.error_exit(
"Internal server error"), 500
[values.append(row.Value) for row in rows]
return BARUtils.success_exit(values)
else:
return BARUtils.error_exit("Invalid API key")
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, 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 get(self, gene_id=''):
"""This end point retrieves Gene RIFs from ThaleMine given an AGI ID"""
gene_id = escape(gene_id)
# Is data valid
if not BARUtils.is_arabidopsis_gene_valid(gene_id):
return BARUtils.error_exit('Invalid gene id'), 400
query = '<query name="" model="genomic" view="Gene.geneRifs.annotation Gene.geneRifs.timeStamp ' \
'Gene.geneRifs.publication.pubMedId" longDescription="" sortOrder="Gene.geneRifs.annotation ' \
'asc"><constraint path="Gene.primaryIdentifier" op="=" value="{}"/></query>'
query = query.format(gene_id)
# Now query the web service
payload = {'format': 'json', 'query': query}
resp = requests.post(
'https://bar.utoronto.ca/thalemine/service/query/results',
data=payload,
headers=request_headers)
return resp.json()
def get(self, gene_id='', top_n=''):
"""This end point is a proxy for ATTED-II api version 4.
This is used by ThaleMine.
This end point is currently not cached.
"""
gene_id = escape(gene_id)
top_n = escape(top_n)
# Is data valid
if not BARUtils.is_arabidopsis_gene_valid(gene_id):
return BARUtils.error_exit('Invalid gene id'), 400
if not BARUtils.is_integer(top_n):
return BARUtils.error_exit('Invalid count'), 400
# Now query the web service
payload = {'gene': gene_id, 'topN': top_n}
resp = requests.get('https://atted.jp/cgi-bin/api4.cgi',
params=payload,
headers=request_headers)
# I think the remote API always returns status 200, so skip status checking
return resp.json()
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 get_data(species, database, gene_id, sample_ids=None):
"""This function is used to query the database for gene expression
:param species: name of species
:param database: name of BAR database
:param gene_id: gene id in the data_probeset column
:param sample_ids: sample ids in the data_bot_id column
:return: dict gene expression data
"""
if sample_ids is None:
sample_ids = []
data = {}
# Set species and check gene ID format
if species == 'arabidopsis':
if not BARUtils.is_arabidopsis_gene_valid(gene_id):
return {
'success': False,
'error': 'Invalid gene id',
'error_code': 400
}
else:
return {
'success': False,
'error': 'Invalid species',
'error_code': 400
}
# Set model
if database == 'single_cell':
database = SingleCell()
# Example: cluster0_WT1.ExprMean
sample_regex = re.compile(r"^\D+\d+_WT\d+.ExprMean$", re.I)
else:
return {
'success': False,
'error': 'Invalid database',
'error_code': 400
}
# Now query the database
if len(sample_ids) == 0 or sample_ids is None:
try:
rows = database.query.filter_by(data_probeset_id=gene_id).all()
except OperationalError:
return {
'success': False,
'error': 'An internal error has occurred',
'error_code': 500
}
if len(rows) > 0:
for row in rows:
data[row.data_bot_id] = row.data_signal
else:
# Validate all samples
for sample_id in sample_ids:
if not sample_regex.search(sample_id):
return {
'success': False,
'error': 'Invalid sample id',
'error_code': 400
}
try:
# This optimizes query of MySQL in operator.
rows = database.query.filter(
SingleCell.data_probeset_id == gene_id,
SingleCell.data_bot_id.in_(sample_ids)).all()
except OperationalError:
return {
'success': False,
'error': 'An internal error has occurred',
'error_code': 500
}
if len(rows) > 0:
for row in rows:
data[row.data_bot_id] = row.data_signal
return {'success': True, 'data': data}
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