def setUp(self):
self.ticket1 = ticket.ImportTicket()
self.src1 = source.Source()
self.src1.id = "L5_SRC_1"
self.src2 = source.Source()
self.src2.id = "L5_SRC_2"
self.src3 = source.Source()
self.src3.id = "L5_SRC_3"
self.cds1 = cds.Cds()
self.cds1.id = "L5_CDS_1"
self.cds2 = cds.Cds()
self.cds2.id = "L5_CDS_2"
self.cds3 = cds.Cds()
self.cds3.id = "L5_CDS_3"
self.trna1 = trna.Trna()
self.trna1.id = "L5_TRNA_1"
self.trna2 = trna.Trna()
self.trna2.id = "L5_TRNA_2"
self.trna3 = trna.Trna()
self.trna3.id = "L5_TRNA_3"
self.tmrna1 = tmrna.Tmrna()
self.tmrna1.id = "L5_TMRNA_1"
self.tmrna2 = tmrna.Tmrna()
self.tmrna2.id = "L5_TMRNA_2"
self.tmrna3 = tmrna.Tmrna()
self.tmrna3.id = "L5_TMRNA_3"
self.genome1 = genome.Genome()
self.genome1.type = "flat_file"
self.genome1.cds_features = [self.cds1, self.cds2]
self.genome1.source_features = [self.src1, self.src2]
self.genome1.trna_features = [self.trna1, self.trna2]
self.genome1.tmrna_features = [self.tmrna1, self.tmrna2]
self.genome2 = genome.Genome()
self.genome2.type = "mysql"
self.genome_pair1 = genomepair.GenomePair()
self.genome_pair2 = genomepair.GenomePair()
self.bndl = bundle.Bundle()
self.bndl.ticket = self.ticket1
self.bndl.genome_dict[self.genome1.type] = self.genome1
self.bndl.genome_dict[self.genome2.type] = self.genome2
self.bndl.genome_pair_dict["genome_pair1"] = self.genome_pair1
self.bndl.genome_pair_dict["genome_pair2"] = self.genome_pair2
self.eval_correct1 = evaluation.Evaluation(status="correct")
self.eval_correct2 = evaluation.Evaluation(status="correct")
self.eval_error1 = evaluation.Evaluation(status="error")
self.eval_error2 = evaluation.Evaluation(status="error")
def test_create_genome_statements_3(self):
"""Verify list of INSERT statements is created correctly for:
'add' ticket, and two CDS features."""
cds1 = cds.Cds()
cds1.genome_id = "L5"
cds1.start = 10
cds1.stop = 100
cds1.parts = 1
cds1.length = 1000
cds1.name = "1"
cds1.type = "CDS"
cds1.translation = "AGGPT"
cds1.orientation = "F"
cds1.description = "description"
cds1.locus_tag = "SEA_L5_001"
cds2 = cds.Cds()
cds2.genome_id = "L5"
cds2.start = 100
cds2.stop = 1000
cds2.parts = 1
cds2.length = 10000
cds2.name = "2"
cds2.type = "CDS"
cds2.translation = "AKKQE"
cds2.orientation = "R"
cds2.description = "description"
cds2.locus_tag = "SEA_L5_002"
self.genome1.id = "L5"
self.genome1.name = "L5_Draft"
self.genome1.host_genus = "Mycobacterium"
self.genome1.annotation_status = "final"
self.genome1.accession = "ABC123"
self.genome1.seq = "ATCG"
self.genome1.length = 4
self.genome1.gc = 0.5001
self.genome1.date = '1/1/2000'
self.genome1.retrieve_record = "1"
self.genome1.annotation_author = "1"
self.genome1.cluster = "A"
self.genome1.subcluster = "A2"
self.genome1.cds_features = [cds1, cds2]
statements = mysqldb.create_genome_statements(self.genome1,
tkt_type="add")
self.assertEqual(len(statements), 3)
def test_create_gene_table_insert_2(self):
"""Verify gene table INSERT statement is created correctly when
locus_tag is empty."""
# Note: even though this function returns a string and doesn't
# actually utilize a MySQL database, this test ensures
# that the returned statement will function properly in MySQL.
cds1 = cds.Cds()
cds1.id = "SEA_TRIXIE_123"
cds1.genome_id = "Trixie"
cds1.start = 5
cds1.stop = 10
cds1.parts = 1
cds1.translation_length = 20
cds1.name = "Int"
cds1.type = "CDS"
cds1.translation = Seq("ACKLG", IUPAC.protein)
cds1.orientation = "F"
cds1.description = "integrase"
cds1.locus_tag = ""
statement = mysqldb.create_gene_table_insert(cds1)
test_db_utils.execute(statement)
result = test_db_utils.get_data(self.gene_query)
results = result[0]
exp = ("""INSERT INTO gene """
"""(GeneID, PhageID, Start, Stop, Length, Name, """
"""Translation, Orientation, Notes, LocusTag, Parts) """
"""VALUES """
"""("SEA_TRIXIE_123", "Trixie", 5, 10, 20, "Int", """
""""ACKLG", "F", "integrase", NULL, 1);""")
with self.subTest():
self.assertEqual(statement, exp)
with self.subTest():
self.assertEqual(results["GeneID"], "SEA_TRIXIE_123")
with self.subTest():
self.assertEqual(results["LocusTag"], None)
def test_create_gene_table_insert_1(self):
"""Verify gene table INSERT statement is created correctly when
locus_tag is not empty and description contains a "'"."""
# Note: even though this function returns a string and doesn't
# actually utilize a MySQL database, this test ensures
# that the returned statement will function properly in MySQL.
cds1 = cds.Cds()
cds1.id = "SEA_TRIXIE_123"
cds1.genome_id = "Trixie"
cds1.start = 5
cds1.stop = 10
cds1.parts = 1
cds1.translation_length = 20
cds1.length = 200
cds1.name = "Int"
cds1.type = "CDS"
cds1.translation = Seq("ACKLG", IUPAC.protein)
cds1.orientation = "F"
cds1.description = "5' nucleotide phosphatase"
cds1.locus_tag = "TAG1"
statement = mysqldb.create_gene_table_insert(cds1)
test_db_utils.execute(statement)
result = test_db_utils.get_data(GENE_QUERY2)
results = result[0]
exp = ("""INSERT INTO gene """
"""(GeneID, PhageID, Start, Stop, Length, Name, """
"""Translation, Orientation, Notes, LocusTag, Parts) """
"""VALUES """
"""("SEA_TRIXIE_123", "Trixie", 5, 10, 200, "Int", """
""""ACKLG", "F", "5' nucleotide phosphatase", "TAG1", 1);""")
with self.subTest():
self.assertEqual(statement, exp)
with self.subTest():
self.assertEqual(results["GeneID"], "SEA_TRIXIE_123")
with self.subTest():
self.assertEqual(results["PhageID"], "Trixie")
with self.subTest():
self.assertEqual(results["Start"], 5)
with self.subTest():
self.assertEqual(results["Stop"], 10)
with self.subTest():
self.assertEqual(results["Parts"], 1)
with self.subTest():
self.assertEqual(results["Length"], 200)
with self.subTest():
self.assertEqual(results["Name"], "Int")
with self.subTest():
self.assertEqual(results["Translation"].decode("utf-8"), "ACKLG")
with self.subTest():
self.assertEqual(results["Orientation"], "F")
with self.subTest():
self.assertEqual(results["Notes"].decode("utf-8"),
"5' nucleotide phosphatase")
with self.subTest():
self.assertEqual(results["LocusTag"], "TAG1")
def setUp(self):
"""
Creates objects for unit testing of the export_db pipeline
"""
#Creates test phage name list
phage_name_list = []
phage_name_list.append("TestPhage_1")
phage_name_list.append("TestPhage_2")
phage_name_list.append("TestPhage_3")
self.names = phage_name_list
#Creates test Genome objects
test_phage1 = genome.Genome()
test_phage1.name = self.names[0]
test_phage2 = genome.Genome()
test_phage2.name = self.names[1]
test_phage3 = genome.Genome()
test_phage3.name = self.names[2]
self.genomes = [test_phage1, test_phage2, test_phage3]
#Creates test Cds objects
test_cds1 = cds.Cds()
test_cds1.start = 1
test_cds1.stop = 2
test_cds1.coordinate_format = "0_half_open"
test_cds1.orientation = 1
test_cds2 = cds.Cds()
test_cds2.start = 2
test_cds2.stop = 3
test_cds2.coordinate_format = "0_half_open"
test_cds2.orientation = 1
test_cds3 = cds.Cds()
test_cds3.start = 3
test_cds3.stop = 4
test_cds3.coordinate_format = "0_half_open"
test_cds3.orientation = 1
self.cds_list = [test_cds1, test_cds2, test_cds3]
#Creates a test SeqRecord object
seq = Seq("ATGC")
seqrecord = SeqRecord(seq)
seqrecord.annotations.update({"comment": ()})
self.test_seqrecord = seqrecord
self.test_version_dictionary = \
{"Version" : "Test", "SchemaVersion": "Test"}
def setUp(self):
self.ticket1 = ticket.ImportTicket()
self.src1 = source.Source()
self.src1.id = "L5_SRC_1"
self.src2 = source.Source()
self.src2.id = "L5_SRC_2"
self.src3 = source.Source()
self.src3.id = "L5_SRC_3"
self.cds1 = cds.Cds()
self.cds1.id = "L5_CDS_1"
self.cds2 = cds.Cds()
self.cds2.id = "L5_CDS_2"
self.cds3 = cds.Cds()
self.cds3.id = "L5_CDS_3"
self.genome1 = genome.Genome()
self.genome1.type = "flat_file"
self.genome1.cds_features.append(self.cds1)
self.genome1.cds_features.append(self.cds2)
self.genome1.source_features.append(self.src1)
self.genome1.source_features.append(self.src2)
self.genome2 = genome.Genome()
self.genome2.type = "mysql"
self.genome_pair1 = genomepair.GenomePair()
self.genome_pair2 = genomepair.GenomePair()
self.bndl = bundle.Bundle()
self.bndl.ticket = self.ticket1
self.bndl.genome_dict[self.genome1.type] = self.genome1
self.bndl.genome_dict[self.genome2.type] = self.genome2
self.bndl.genome_pair_dict["genome_pair1"] = self.genome_pair1
self.bndl.genome_pair_dict["genome_pair2"] = self.genome_pair2
self.eval_correct1 = eval.Eval(status="correct")
self.eval_correct2 = eval.Eval(status="correct")
self.eval_error1 = eval.Eval(status="error")
self.eval_error2 = eval.Eval(status="error")
def setUp(self):
self.cds_pair = cdspair.CdsPair()
self.cds1 = cds.Cds()
self.cds2 = cds.Cds()
def parse_cds_seqfeature(seqfeature):
"""Parse data from a Biopython CDS SeqFeature object into a Cds object.
:param seqfeature: Biopython SeqFeature
:type seqfeature: SeqFeature
:param genome_id:
An identifier for the genome in which the seqfeature
is defined.
:type genome_id: str
:returns: A pdm_utils Cds object
:rtype: Cds
"""
generic_words = {"gp", "orf", ""}
cds_ftr = cds.Cds()
cds_ftr.seqfeature = seqfeature
try:
locus_tag = seqfeature.qualifiers["locus_tag"][0]
except:
locus_tag = ""
finally:
cds_ftr.set_locus_tag(locus_tag)
cds_ftr.set_orientation(seqfeature.strand, "fr_short", case = True)
cds_ftr.start, cds_ftr.stop, cds_ftr.parts = parse_coordinates(seqfeature)
# Coordinate format for GenBank flat file features parsed by Biopython
# are 0-based half open intervals.
cds_ftr.coordinate_format = "0_half_open"
# For translation, convert it to a Biopython Seq object.
try:
translation = seqfeature.qualifiers["translation"][0]
except:
translation = ""
finally:
translation = Seq(translation, Alphabet.IUPAC.protein)
cds_ftr.set_translation(translation)
cds_ftr.set_nucleotide_length()
try:
translation_table = seqfeature.qualifiers["transl_table"][0]
except:
translation_table = 0
finally:
cds_ftr.set_translation_table(translation_table)
try:
product = seqfeature.qualifiers["product"][0]
except:
product = ""
finally:
cds_ftr.set_description_field("product", product, generic_words)
try:
function = seqfeature.qualifiers["function"][0]
except:
function = ""
finally:
cds_ftr.set_description_field("function", function, generic_words)
try:
note = seqfeature.qualifiers["note"][0]
except:
note = ""
finally:
cds_ftr.set_description_field("note", note, generic_words)
try:
cds_ftr.gene = seqfeature.qualifiers["gene"][0]
except:
cds_ftr.gene = ""
cds_ftr.set_name()
return cds_ftr
def setUp(self):
self.cds_ftr = cds.Cds()
self.src_ftr = source.Source()
self.gnm = genome.Genome()
def parse_gene_table_data(data_dict, trans_table=11):
"""Parse a MySQL database dictionary to create a Cds object.
:param data_dict:
Dictionary of data retrieved from the gene table.
:type data_dict: dict
:param trans_table:
The translation table that can be used to translate CDS features.
:type trans_table: int
:returns: A pdm_utils Cds object.
:rtype: Cds
"""
ftr = cds.Cds()
ftr.type = "CDS"
try:
ftr.id = data_dict["GeneID"]
except:
pass
try:
ftr.genome_id = data_dict["PhageID"]
except:
pass
try:
ftr.start = int(data_dict["Start"])
except:
pass
try:
ftr.stop = int(data_dict["Stop"])
except:
pass
try:
ftr.parts = int(data_dict["Parts"])
except:
pass
ftr.coordinate_format = "0_half_open"
try:
ftr.length = int(data_dict["Length"])
except:
pass
try:
ftr.name = data_dict["Name"]
except:
pass
try:
ftr.set_translation(data_dict["Translation"].decode("utf-8"))
except:
pass
try:
ftr.orientation = data_dict["Orientation"]
except:
pass
try:
ftr.description = data_dict["Notes"].decode("utf-8")
except:
pass
try:
ftr.set_locus_tag(data_dict["LocusTag"])
except:
pass
try:
ftr.pham_id = int(data_dict["PhamID"])
except:
pass
try:
ftr.domain_status = int(data_dict["DomainStatus"])
except:
pass
try:
ftr.translation_table = trans_table
except:
pass
return ftr
def setUp(self):
self.genome1 = genome.Genome()
self.genome1.id = "L5"
self.genome1.name = "L5_Draft"
self.genome1.host_genus = "Mycobacterium"
self.genome1.annotation_status = "final"
self.genome1.accession = "ABC123"
self.genome1.seq = "ATCG"
self.genome1.length = 4
self.genome1.gc = 0.5001
self.genome1.date = '1/1/2000'
self.genome1.retrieve_record = "1"
self.genome1.annotation_author = "1"
self.genome1.cluster = "A"
self.genome1.subcluster = "A2"
self.cds1 = cds.Cds()
self.cds1.genome_id = "L5"
self.cds1.start = 10
self.cds1.stop = 100
self.cds1.parts = 1
self.cds1.length = 1000
self.cds1.name = "1"
self.cds1.type = "CDS"
self.cds1.translation = "AGGPT"
self.cds1.orientation = "F"
self.cds1.description = "description"
self.cds1.locus_tag = "SEA_L5_001"
self.cds2 = cds.Cds()
self.cds2.genome_id = "L5"
self.cds2.start = 100
self.cds2.stop = 1000
self.cds2.parts = 1
self.cds2.length = 10000
self.cds2.name = "2"
self.cds2.type = "CDS"
self.cds2.translation = "AKKQE"
self.cds2.orientation = "R"
self.cds2.description = "description"
self.cds2.locus_tag = "SEA_L5_002"
self.cds_features = [self.cds1, self.cds2]
self.trna1 = trna.Trna()
self.trna1.id = "Trixie_1"
self.trna1.genome_id = "Trixie"
self.trna1.name = "1"
self.trna1.locus_tag = "TAG1"
self.trna1.start = 5
self.trna1.stop = 10
self.trna1.length = 200
self.trna1.orientation = "F"
self.trna1.note = "misc"
self.trna1.amino_acid = "Ala"
self.trna1.anticodon = "AAA"
self.trna1.structure = "random"
self.trna1.use = "aragorn"
self.trna2 = trna.Trna()
self.trna2.id = "Trixie_1"
self.trna2.genome_id = "Trixie"
self.trna2.name = "1"
self.trna2.locus_tag = "TAG1"
self.trna2.start = 5
self.trna2.stop = 10
self.trna2.length = 200
self.trna2.orientation = "F"
self.trna2.note = "misc"
self.trna2.amino_acid = "Ala"
self.trna2.anticodon = "AAA"
self.trna2.structure = "random"
self.trna2.use = "aragorn"
self.trna_features = [self.trna1, self.trna2]
self.tmrna1 = tmrna.Tmrna()
self.tmrna1.id = "Trixie_1"
self.tmrna1.genome_id = "Trixie"
self.tmrna1.name = "1"
self.tmrna1.locus_tag = "TAG1"
self.tmrna1.start = 5
self.tmrna1.stop = 10
self.tmrna1.length = 200
self.tmrna1.orientation = "F"
self.tmrna1.note = "misc"
self.tmrna1.peptide_tag = "random"
self.tmrna2 = tmrna.Tmrna()
self.tmrna2.id = "Trixie_1"
self.tmrna2.genome_id = "Trixie"
self.tmrna2.name = "1"
self.tmrna2.locus_tag = "TAG1"
self.tmrna2.start = 5
self.tmrna2.stop = 10
self.tmrna2.length = 200
self.tmrna2.orientation = "F"
self.tmrna2.note = "misc"
self.tmrna2.peptide_tag = "random"
self.tmrna_features = [self.tmrna1, self.tmrna2]
