def get_genes(self):
"""
Get the genes of the Phamily
"""
results = get_db().query(
"SELECT `gene`.`GeneID`, `gene`.`phageID`, " +
" `Length`, `Start`, `Stop`, `Orientation`" + " FROM `gene`"
" JOIN `pham` ON `gene`.`GeneID` = `pham`.`GeneID`" +
" WHERE `pham`.`name` =%s; ", self.pham_no)
genes = {}
self.count = len(results)
for gene_info in results:
gene_id = gene_info[0]
phage_id = gene_info[1]
start = gene_info[3]
stop = gene_info[4]
orientation = gene_info[5]
gene = new_PhamGene(gene_id, start, stop, orientation, phage_id)
if gene.has_valid_start():
genes[gene.gene_id] = gene
if len(genes) < 1:
raise StarteratorError(
"Pham Number %s not found or all genes fail validation!" %
self.pham_no)
return genes
def _execute(self, cursor, query, params):
try:
return cursor.execute(query, params)
except MySQLdb.OperationalError:
print "Error connecting to MySQL on %s", self.host
self.close()
raise StarteratorError(
"Error connecting to database! Please enter correct login credentials in Preferences menu."
)
def make_gene(self, start, stop, orientation):
sequence = self.get_sequence()
try:
gene = phamgene.UnPhamGene(self.number, start, stop, orientation,
self.name, sequence)
except:
raise StarteratorError(
"The gene could not be made! Check coordinates: Start: %s, Stop: %s, Orientation: %s"
% (start, stop, orientation))
self.pham_no = gene.blast()
self.get_pham(self.pham_no, gene)
def get_color(self):
"""
Get the color of the phamily from the database
"""
try:
result = get_db().get(
"SELECT `name`, `color`\n\
FROM `pham_color` WHERE `name` = %s;", self.pham_no)
return result[1]
except:
raise StarteratorError("Pham number %s not found in database!" %
self.pham_no)
def get_sequence(self):
if not self.sequence:
try:
with open(self.fasta, "rb") as fasta_file:
fasta_file.next()
sequence = ""
for line in fasta_file:
sequence += (line.strip())
self.sequence = sequence
self.seq_length = len(sequence)
except:
raise StarteratorError(
"The fasta file (%s) could not be opened!" % self.fasta)
return self.sequence
def get_pham_no(phage_name, gene_number):
"""
Gets the pham number of a gene, given the phage name and the gene number
"""
print phage_name, gene_number
db = DB()
query = "SELECT pham.Name \n\
FROM gene JOIN pham ON gene.GeneID = pham.GeneID \n\
JOIN phage ON gene.PhageID = phage.PhageID \n\
WHERE (phage.Name LIKE %s or phage.PhageID = %s) AND gene.Name RLIKE %s \n\
" % (phage_name + "%", phage_name,
'^[:alpha:]*(_)*%s$' % str(gene_number))
print query
try:
results = db.query(
"SELECT pham.Name \n\
FROM gene JOIN pham ON gene.GeneID = pham.GeneID \n\
JOIN phage ON gene.PhageID = phage.PhageID \n\
WHERE (phage.Name LIKE %s or phage.PhageID = %s) AND gene.Name RLIKE %s",
(phage_name + "%", phage_name,
'^([[:alnum:]]*_)*([[:alpha:]])*%s$' % str(gene_number)))
print "DB query 1"
if len(results) < 1:
print "DB query 1 failed, try search 2"
results = db.query(
"SELECT pham.Name \n\
FROM gene JOIN pham ON gene.GeneID = pham.GeneID \n\
JOIN phage ON gene.PhageID = phage.PhageID \n\
WHERE (phage.Name LIKE %s or phage.PhageID = %s) AND gene.geneID RLIKE %s",
(phage_name + "%", phage_name,
'^([[:alnum:]]*_)*([[:alpha:]])*%s$' % str(gene_number)))
if len(results) < 1:
#try to determine root of gene names since they are
print "DB query 2 failed, try search 3"
results = db.query(
"SELECT pham.Name \n\
FROM gene JOIN pham ON gene.GeneID = pham.GeneID \n\
JOIN phage ON gene.PhageID = phage.PhageID \n\
WHERE gene.geneid LIKE %s AND gene.geneID RLIKE %s",
(phage_name + "%",
'^([[:alnum:]]*_)*([[:alpha:]])*%s$' % str(gene_number)))
print results
row = results[0]
pham_no = row[0]
return str(pham_no)
except:
raise StarteratorError("Gene %s of Phage %s not found in database!" %
(gene_number, phage_name))
def get_pham_number(phage_name, gene_number):
try:
db = DB()
results = db.query(
"SELECT pham.Name \n\
FROM gene JOIN pham ON gene.GeneID = pham.Gene \n\
JOIN phage ON gene.PhageID = phage.PhageID \n\
WHERE phage.Name LIKE %s AND gene.Name LIKE %s \n\
ESCAPE '!'", (phage_name + "%", '%' + str(gene_number)))
row = results[0]
pham_no = row[0]
return str(pham_no)
except:
raise StarteratorError("Gene %s of Phage %s not found in database!" %
(gene_number, phage_name))
def blast(self):
# not sure where to put this... this makes more sense,
# but I wanted to keep the Genes out of file making...
print "Running BLASTp"
try:
result_handle = open("%s/%s.xml" %
(utils.INTERMEDIATE_DIR, self.gene_id))
result_handle.close()
except:
protein = SeqRecord(
self.sequence[self.candidate_starts[0]:].seq.translate(),
id=self.gene_id)
print protein, self.sequence
# short proteins need lower e_value
query_len = (self.stop - self.start) / 3
if query_len < 50:
e_value = math.pow(10, -5)
else:
e_value = math.pow(10, -20)
SeqIO.write(protein,
'%s/%s.fasta' % (utils.INTERMEDIATE_DIR, self.gene_id),
'fasta')
blast_command = Blastp(
query='%s%s.fasta' % (utils.INTERMEDIATE_DIR, self.gene_id),
db="\"%s/\"" % (os.path.abspath(utils.PROTEIN_DB)),
evalue=e_value,
outfmt=5,
out="%s.xml" %
(os.path.join(utils.INTERMEDIATE_DIR, self.gene_id)))
# print self.gene_id, "\"%sProteins\"" % (utils.PROTEIN_DB)
blast_args = [
"%sblastp" % utils.BLAST_DIR, "-out",
'%s/%s.xml' % (utils.INTERMEDIATE_DIR, self.gene_id),
"-outfmt", "5", "-query",
'%s/%s.fasta' % (utils.INTERMEDIATE_DIR, self.gene_id), "-db",
"\"%s/Proteins.fasta\"" % (utils.PROTEIN_DB), "-evalue",
str(e_value)
]
print " ".join(blast_args)
try:
subprocess.check_call(blast_args)
except:
raise StarteratorError("Blast could not run!")
# print blast_command
# stdout, stderr = blast_command()
return self.parse_blast()
def get_phams(self):
if not self._phams:
self._phams = {}
sequence = self.get_sequence()
genes = []
# try:
if self.profile is None:
gene_predictions = annotate.auto_annotate(self.fasta)
for gene in gene_predictions.genes:
gene = phamgene.UnPhamGene(gene.id, gene.start, gene.stop,
gene.orientation, self.name,
sequence)
genes.append(gene)
pham_no = gene.blast()
if pham_no not in self._phams:
self._phams[pham_no] = []
self._phams[pham_no].append(gene)
else:
try:
with open(self.profile, "rbU") as profile:
print self.profile, "has been opened!"
first_line = profile.readline()
first_word = first_line.split()[0]
if first_word == "Profile":
csv_reader = csv.reader(profile)
line = csv_reader.next()
print line
csv_reader.next()
for row in csv_reader:
print row
feature_type = row[7].strip()
print feature_type
if feature_type == "ORF":
number = row[1].replace('"', "")
orientation = row[2]
start = int(row[4])
stop = int(row[5])
print number, start, stop, orientation, self.name
gene = phamgene.UnPhamGene(
number, start, stop, orientation,
self.name, sequence)
genes.append(gene)
pham_no = gene.blast()
if pham_no not in self._phams:
self._phams[pham_no] = []
self._phams[pham_no].append(gene)
else:
if first_word == "CDS":
profile.seek(0)
gene_count = 0
for line in profile:
if line[0:3] == "CDS":
if line[4:8] == 'join':
continue
else:
gene_count += 1
line2 = line.replace("(", "")
line3 = line2.replace(")", "")
line_items = line3.split()
if line_items[1] == "complement":
gene_orientation = "R"
gene_start = int(line_items[2])
gene_end = int(line_items[4])
else:
gene_orientation = "F"
gene_start = int(line_items[1])
gene_end = int(line_items[3])
gene = phamgene.UnPhamGene(
gene_count, gene_start, gene_end,
gene_orientation, self.name,
sequence)
genes.append(gene)
pham_no = gene.blast()
if pham_no not in self._phams:
self._phams[pham_no] = []
self._phams[pham_no].append(gene)
else:
continue
else:
raise StarteratorError(
"The profile file (%s) could not be read correctly! Please make sure it is correct."
% self.profile)
except:
raise StarteratorError(
"The profile file (%s) could not be read correctly! Please make sure it is correct."
% self.profile)
return self._phams