def test_to_string():
f = "tests/data/tabd.blast"
for line in open(f):
a = BlastLine(line)
b = BlastLine(a.to_blast_line())
# works better than string comparison because of floats.
for attr in some_attrs:
assert getattr(a, attr) == getattr(b, attr), (a, b, attr)
def test_query_subject_props():
f = "tests/data/tabd.blast"
line = BlastLine(open(f).readline())
line.query = "asdf"
line.subject = "dddd"
assert line.query == "asdf"
assert line.subject == "dddd"
assert "asdf" in line.to_blast_line()
assert "dddd" in line.to_blast_line()
def test_to_string():
f = "tests/data/tabd.blast"
for line in open(f):
a = BlastLine(line)
b = BlastLine(a.to_blast_line())
# works better than string comparison because of floats.
for attr in some_attrs:
assert getattr(a, attr) == getattr(b, attr), (a, b, attr)
def test_query_subject_props():
f = "tests/data/tabd.blast"
line = BlastLine(open(f).readline())
line.query = "asdf"
line.subject = "dddd"
assert line.query == "asdf"
assert line.subject == "dddd"
assert "asdf" in line.to_blast_line()
assert "dddd" in line.to_blast_line()
def test_blastline():
f = "tests/data/tabd.blast"
blasts = []
for line in open(f):
b = BlastLine(line)
blasts.append(BlastLine(line))
yield check_type, blasts, ('qstart', 'qstop', 'sstart', 'sstop',
'nmismatch', 'ngaps'), int
yield check_type, blasts, ('evalue', 'score', 'pctid'), float
yield check_type, blasts, ('query', 'subject'), str
def grouper(blast_file):
"""\
group all subjects to a single query. so for
grape.features_vs_papaya.genomic.masked.blast
group all the papaya hits to the grape query"""
g = collections.defaultdict(dict)
for sline in open(blast_file):
b = BlastLine(sline)
# this removes low-copy transposons (length > 200, percent_id > 98)
if b.pctid > 98.0 and b.hitlen > 200: continue
if not b.subject in g[b.query]: g[b.query][b.subject] = []
g[b.query][b.subject].append(b)
return g
def test_pickle():
import cPickle
f = "tests/data/tabd.blast"
line = BlastLine(open(f).readline())
d = cPickle.dumps(line, -1)
loaded = cPickle.loads(d)
for k in BlastLine.attrs:
assert getattr(loaded, k) == getattr(line, k)
loaded.query = "asdf"
assert loaded.query != line.query
def test_blastfile():
f = "tests/data/tabd.blast"
bf = BlastFile(f)
fh = open(f, 'r')
# iterate via python and c and check each line is the same.
for line, b in zip(fh, bf):
bl = BlastLine(line)
assert isinstance(b, BlastLine)
assert bl == b
i = 0
for c in bf:
i += 1
assert isinstance(c, BlastLine)
assert i == len(open(f).readlines())
del bf
sys.path.insert(0, "scripts2/")
from make_genelist import is_ortho, parse_orthos
from biostuff import BlastLine
ortho = parse_orthos(forthology, is_same=True)
gff = gtpym.FeatureIndexMemory(fgff)
xs = []
ys = []
QSEQ = '2'
SSEQ = '4'
print >>sys.stderr, ortho[(QSEQ, SSEQ)]
for line in open(fblast):
b = BlastLine(line)
q = gff[b.query]
s = gff[b.subject]
if not (q.seqid == QSEQ and s.seqid == SSEQ): continue
b.qstart += q.start
b.qstop += q.start
b.sstart += s.start
b.sstop += s.start
print b.to_blast_line()
xs.append(b.qstart)
ys.append(b.sstart)
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle
sys.path.insert(0, "scripts2/")
from make_genelist import is_ortho, parse_orthos
from biostuff import BlastLine
ortho = parse_orthos(forthology, is_same=True)
gff = gtpym.FeatureIndexMemory(fgff)
xs = []
ys = []
QSEQ = '2'
SSEQ = '4'
print >> sys.stderr, ortho[(QSEQ, SSEQ)]
for line in open(fblast):
b = BlastLine(line)
q = gff[b.query]
s = gff[b.subject]
if not (q.seqid == QSEQ and s.seqid == SSEQ): continue
b.qstart += q.start
b.qstop += q.start
b.sstart += s.start
b.sstop += s.start
print b.to_blast_line()
xs.append(b.qstart)
ys.append(b.sstart)
import matplotlib.pyplot as plt
from matplotlib.patches import Rectangle