class TestMaize(unittest.TestCase):
def setUp(self):
handle = open(
'/Users/gturco/code/freeling_lab/find_cns_gturco/pipeline/tests/blast_3.txt'
)
fh = handle.readlines()
self.blast_str = ' , '.join(fh)
self.unmasked_fasta = Fasta('/Users/gturco/find_cns/maize_v2_UM.fasta')
self.qbed = Bed('/Users/gturco/rice_maize/rice_v6.bed')
self.qbed.fill_dict()
self.sbed = Bed('/Users/gturco/maize/maize_v2.bed',
'/Users/gturco/maize/maize_v2.fasta')
self.sbed.fill_dict()
self.sfeat = self.sbed.accn('GRMZM2G086714')
self.qfeat = self.qbed.accn('Os09g27050')
def test_get_cmd(self):
sfasta = 'data/rice_v6_maize_v2/maize_v2_split/2.fasta'
qfasta = 'data/rice_v6_maize_v2/rice_v6_split/4.fasta'
def test_parse_balse(self):
orientaion = -1
cns = parse_blast(self.blast_str, orientaion, self.qfeat, self.sfeat,
self.qbed, self.sbed, 12000, 26000,
self.unmasked_fasta)
print cns
class TestPseudo(unittest.TestCase):
def setUp(self):
self.qallbed = Bed("data/rice_v6_setaria64/rice_v6.all.bed", "data/rice_v6_setaria64/rice_v6.fasta")
self.qallbed.fill_dict()
self.sallbed = Bed("data/rice_v6_setaria64/setaria64.all.bed", "data/rice_v6_setaria64/setaria64.fasta")
self.sallbed.fill_dict()
self.saccn = self.sallbed.accn("Si000834m")
blastfh = open("blast_res")
self.blast = blastfh.read()
self.d, self.pseudo = group_cds(self.blast, self.saccn)
def test_group_cds_1(self):
self.assertEqual(len(self.d.keys()), 4)
total_values = []
for key in self.d.keys():
values = len(self.d[key])
total_values.append(values)
self.assertEqual(sum(total_values), 38)
def test_group_cds_2(self):
blast_2fh = open("blast_2")
blast_2 = blast_2fh.read()
d, pseudo = group_cds(blast_2, self.sallbed.accn("Si002524m"))
self.assertEqual(len(d.keys()), 5)
for key in d.keys():
# logging.info('key: {0}'.format(key))
self.assertEqual(1, len(d[key]))
def test_append_to_included_groups(self):
locs = [1, 2, 3, 4]
group_dict = {(2, 5): [], (3, 6): [], (9, 8): []}
result_dict = append_to_included_groups(locs, group_dict)
expected = {(2, 5): [(1, 2, 3, 4)], (3, 6): [(1, 2, 3, 4)], (9, 8): []}
self.assertEquals(expected, result_dict)
def test_remove_crossing_hit(self):
qaccn = self.qallbed.accn("Os01g01890")
for group_key in self.d.keys():
exon_hits = self.d[group_key]
non_crossing = remove_crossing_hits(exon_hits, qaccn, self.saccn)
if len(non_crossing) > 1:
mid, start, stop = bites(non_crossing)
def test_find_orf(self):
qaccn = self.qallbed.accn("Os01g01295")
orf = find_orf(self.qallbed, qaccn)
self.assertEqual(orf + 1, 141084)
def test_find_orf_neg(self):
saccn = self.sallbed.accn("Si001539m")
orf = find_orf(self.sallbed, saccn)
self.assertEqual(orf, 7662777)
def main(cns_path, fmt, query_bed_path, subject_bed_path):
cns_dic = cns_to_dic(cns_path, fmt)
query_bed = Bed(query_bed_path)
subject_bed = Bed(subject_bed_path)
utr_dict = {}
for cns in cns_dic:
cns['qstop'] = int(cns['qstop'])
cns['qstart'] = int(cns['qstart'])
cns['sstop'] = int(cns['sstop'])
cns['sstart'] = int(cns['sstart'])
qfeat = query_bed.accn(cns['qaccn'])
sfeat = subject_bed.accn(cns['saccn'])
qgene_space_start = min(qfeat['locs'])[0]
qgene_space_end = max(qfeat['locs'])[1]
qgene_space_poly = LineString([(0.0, qgene_space_start),
(0.0, qgene_space_end)])
qgene_poly = LineString([(0.0, qfeat['start']), (0.0, qfeat['end'])])
sgene_poly = LineString([(0.0, sfeat['start']), (0.0, sfeat['end'])])
# if intron of one dont need to check other
qcns = LineString([(0, cns['qstart']), (0, cns['qstop'])])
scns = LineString([(0, cns['sstart']), (0, cns['sstop'])])
cns_type(cns, qgene_space_poly, qgene_poly, sgene_poly, scns, qcns,
qgene_space_start, qfeat)
create_utr_list(utr_dict, qfeat, cns, "q")
create_utr_list(utr_dict, sfeat, cns, "s")
for cns in cns_dic:
if cns['type'] == "5-prox_dist":
qgene_start = min(utr_dict[cns['qaccn']])
qgene_stop = max(utr_dict[cns['qaccn']])
# sstart = min(utr_dict[cns['saccn']])
# sstop = max(utr_dict[cns['saccn']])
five_diff_pos = abs(qgene_start - cns["qstop"])
five_diff_neg = abs(qgene_stop - cns["qstart"])
if five_diff_pos <= 1000 and cns[
"qstrand"] == "+" or five_diff_neg <= 1000 and cns[
"qstrand"] == "-":
cns["type"] = "5-proximal"
elif five_diff_pos > 1000 and cns[
"qstrand"] == "+" or five_diff_neg > 1000 and cns[
"qstrand"] == "-":
cns["type"] = "5-distal"
elif cns['type'] == "3-prox_dist":
qgene_start = min(utr_dict[cns['qaccn']])
qgene_stop = max(utr_dict[cns['qaccn']])
three_diff_pos = abs(cns["qstart"] - qgene_stop)
three_diff_neg = abs(cns["qstop"] - qgene_start)
if three_diff_pos <= 1000 and cns[
"qstrand"] == "+" or three_diff_neg <= 1000 and cns[
"qstrand"] == "-":
cns["type"] = "3-proximal"
elif three_diff_pos > 1000 and cns[
"qstrand"] == "+" or three_diff_neg > 1000 and cns[
"qstrand"] == "-":
cns["type"] = "3-distal"
return cns_dic
def utr_present(cns_pck,query_bed_path, UTR):
"checks to see if qaccn has utr region"
db = MySQLdb.connect(host="127.0.0.1", user="******", db = "rice_gene_table")
cursor = db.cursor()
cns_handle = open(cns_pck)
cns_pickle = pickle.load(cns_handle)
query_bed = Bed(query_bed_path)
for cns in cns_pickle:
qfeat = query_bed.accn(cns['qaccn'])
if qfeat['strand'] == "+":
end = qfeat['end']
start = qfeat["start"]
else:
end = qfeat['start']
start = qfeat["end"]
if UTR == 3:
if end == min(qfeat['locs'])[0] or end == max(qfeat['locs'])[1]:
stmt = "update MUSA_GENE_LIST_copy set MUSA_GENE_LIST_copy.3_UTR = 'ND' where MUSA_GENE_LIST_copy.Rice_MSU6_genes = '{0}'".format(cns['qaccn'])
print stmt
cursor.execute(stmt)
elif UTR == 5:
if start == min(qfeat['locs'])[0] or start == max(qfeat['locs'])[1]:
stmt = "update MUSA_GENE_LIST_copy set MUSA_GENE_LIST_copy.5_UTR = 'ND' where MUSA_GENE_LIST_copy.Rice_MSU6_genes = '{0}'".format(cns['qaccn'])
print stmt
cursor.execute(stmt)
def utr_present(cns_pck, query_bed_path, UTR):
"checks to see if qaccn has utr region"
db = MySQLdb.connect(host="127.0.0.1", user="******", db="rice_gene_table")
cursor = db.cursor()
cns_handle = open(cns_pck)
cns_pickle = pickle.load(cns_handle)
query_bed = Bed(query_bed_path)
for cns in cns_pickle:
qfeat = query_bed.accn(cns['qaccn'])
if qfeat['strand'] == "+":
end = qfeat['end']
start = qfeat["start"]
else:
end = qfeat['start']
start = qfeat["end"]
if UTR == 3:
if end == min(qfeat['locs'])[0] or end == max(qfeat['locs'])[1]:
stmt = "update MUSA_GENE_LIST_copy set MUSA_GENE_LIST_copy.3_UTR = 'ND' where MUSA_GENE_LIST_copy.Rice_MSU6_genes = '{0}'".format(
cns['qaccn'])
print stmt
cursor.execute(stmt)
elif UTR == 5:
if start == min(qfeat['locs'])[0] or start == max(
qfeat['locs'])[1]:
stmt = "update MUSA_GENE_LIST_copy set MUSA_GENE_LIST_copy.5_UTR = 'ND' where MUSA_GENE_LIST_copy.Rice_MSU6_genes = '{0}'".format(
cns['qaccn'])
print stmt
cursor.execute(stmt)
def main(cns_path, fmt, query_bed_path, subject_bed_path):
cns_dic = cns_to_dic(cns_path,fmt)
query_bed = Bed(query_bed_path)
subject_bed = Bed(subject_bed_path)
utr_dict = {}
for cns in cns_dic:
cns['qstop'] = int(cns['qstop'])
cns['qstart'] = int(cns['qstart'])
cns['sstop'] = int(cns['sstop'])
cns['sstart'] = int(cns['sstart'])
qfeat = query_bed.accn(cns['qaccn'])
sfeat = subject_bed.accn(cns['saccn'])
qgene_space_start = min(qfeat['locs'])[0]
qgene_space_end = max(qfeat['locs'])[1]
qgene_space_poly = LineString([(0.0, qgene_space_start), (0.0, qgene_space_end)])
qgene_poly = LineString([(0.0, qfeat['start']), (0.0, qfeat['end'])])
sgene_poly = LineString([(0.0, sfeat['start']), (0.0, sfeat['end'])])
# if intron of one dont need to check other
qcns = LineString([(0,cns['qstart']),(0,cns['qstop'])])
scns = LineString([(0,cns['sstart']),(0,cns['sstop'])])
cns_type(cns,qgene_space_poly, qgene_poly, sgene_poly, scns, qcns,qgene_space_start,qfeat)
create_utr_list(utr_dict,qfeat, cns,"q")
create_utr_list(utr_dict,sfeat, cns,"s")
for cns in cns_dic:
if cns['type'] == "5-prox_dist":
qgene_start = min(utr_dict[cns['qaccn']])
qgene_stop = max(utr_dict[cns['qaccn']])
# sstart = min(utr_dict[cns['saccn']])
# sstop = max(utr_dict[cns['saccn']])
five_diff_pos = abs(qgene_start - cns["qstop"])
five_diff_neg = abs(qgene_stop - cns["qstart"])
if five_diff_pos <=1000 and cns["qstrand"] == "+" or five_diff_neg <=1000 and cns["qstrand"] == "-":
cns["type"] = "5-proximal"
elif five_diff_pos >1000 and cns["qstrand"] == "+" or five_diff_neg >1000 and cns["qstrand"] == "-":
cns["type"] = "5-distal"
elif cns['type'] == "3-prox_dist":
qgene_start = min(utr_dict[cns['qaccn']])
qgene_stop = max(utr_dict[cns['qaccn']])
three_diff_pos = abs(cns["qstart"] - qgene_stop)
three_diff_neg = abs(cns["qstop"] - qgene_start)
if three_diff_pos <=1000 and cns["qstrand"] == "+" or three_diff_neg <=1000 and cns["qstrand"] == "-":
cns["type"] = "3-proximal"
elif three_diff_pos > 1000 and cns["qstrand"] == "+" or three_diff_neg > 1000 and cns["qstrand"] == "-":
cns["type"] = "3-distal"
return cns_dic
def main(bedfile,seqfile, gene_list):
print "position,gene,element"
b = Bed(bedfile)
f = Fasta(seqfile)
for gene_name in gene_list:
gene = b.accn(gene_name)
promf, promr = get_prom(f, gene)
print gene_name
mf = find_seq(promf)
mr = find_seq(promr)
make_graph(mf,mr, gene_name)
class TestMaize(unittest.TestCase):
def setUp(self):
handle = open("/Users/gturco/code/freeling_lab/find_cns_gturco/pipeline/tests/blast_3.txt")
fh = handle.readlines()
self.blast_str = " , ".join(fh)
self.unmasked_fasta = Fasta("/Users/gturco/find_cns/maize_v2_UM.fasta")
self.qbed = Bed("/Users/gturco/rice_maize/rice_v6.bed")
self.qbed.fill_dict()
self.sbed = Bed("/Users/gturco/maize/maize_v2.bed", "/Users/gturco/maize/maize_v2.fasta")
self.sbed.fill_dict()
self.sfeat = self.sbed.accn("GRMZM2G086714")
self.qfeat = self.qbed.accn("Os09g27050")
def test_get_cmd(self):
sfasta = "data/rice_v6_maize_v2/maize_v2_split/2.fasta"
qfasta = "data/rice_v6_maize_v2/rice_v6_split/4.fasta"
def test_parse_balse(self):
orientaion = -1
cns = parse_blast(
self.blast_str, orientaion, self.qfeat, self.sfeat, self.qbed, self.sbed, 12000, 26000, self.unmasked_fasta
)
print cns
def main(cns_file,bedpath,fastapath):
genespace = get_genespace(cns_file)
bed = Bed(bedpath)
f = Fasta(fastapath)
handles = ['3_utr','5_utr','intronic','5_prox','5_distal','3_prox','3_distal']
fhs = open_files(handles)
for gene in genespace.keys():
#cnsspace = genespace[gene]
try:
accn = bed.accn(gene)
except KeyError: continue
cnsspace = [(max(0,accn['start'] - 12000), accn['end'] + 12000)]
#print "GENESPACE {0}".format(cnsspace)
locs = accn['locs']
locs.sort()
cnsspace.sort()
write_to_pos_fasta(bed,accn,locs,cnsspace,fhs,f)
def main(cns_file, bedpath, fastapath):
genespace = get_genespace(cns_file)
bed = Bed(bedpath)
f = Fasta(fastapath)
handles = [
'3_utr', '5_utr', 'intronic', '5_prox', '5_distal', '3_prox',
'3_distal'
]
fhs = open_files(handles)
for gene in genespace.keys():
#cnsspace = genespace[gene]
try:
accn = bed.accn(gene)
except KeyError:
continue
cnsspace = [(max(0, accn['start'] - 12000), accn['end'] + 12000)]
#print "GENESPACE {0}".format(cnsspace)
locs = accn['locs']
locs.sort()
cnsspace.sort()
write_to_pos_fasta(bed, accn, locs, cnsspace, fhs, f)
class TestPerfectTargetRegion(unittest.TestCase):
def setUp(self):
self.gene_name = "Os01g02110"
self.bed = Bed("ricetest.bed")
self.fasta = Fasta("ricetest.fasta")
self.gene = self.bed.accn(self.gene_name)
self.exons = self.gene['locs']
def test_rel_pos(self):
self.assertEqual((376,486),rel_pos(self.gene,self.exons[0]))
self.assertEqual((1289,1789),rel_pos(self.gene,self.exons[-1]))
def test_fasta(self):
exon = self.exons[-1]
seq = self.fasta[self.gene_name][:]
self.assertTrue(1789 <= len(seq))
def test_pattern(self):
e = exons[-1]
start, stop = rel_pos(self.gene,e)
for exon in self.exons:
