def update_boids(boids, time):
for index in range(len(boids)):
b = boids[index]
b[2] += cohesion(index, boids)[0]*10
b[3] += cohesion(index, boids)[1]*10
b[2] += separate(index, boids)[0]*5
b[3] += separate(index, boids)[1]*5
b[2] += align(index, boids)[0]
b[3] += align(index, boids)[1]
# Limit velocity to 500 pixels per second horizontally and vertically
b[2] = speed_limit(b[2], 500)
b[3] = speed_limit(b[3], 500)
# Update the boid's position based on its velocity and the
# time that has passed since the last update.
b[0] += float(b[2])/1000 * time
b[1] += float(b[3])/1000 * time
# Make the boid bounce off the walls.
if b[0] < 0:
b[0] = 0
b[2] = -b[2]
elif b[0] > WIDTH:
b[0] = WIDTH
b[2] = -b[2]
if b[1] < 0:
b[1] = 0
b[3] = -b[3]
elif b[1] > HEIGHT:
b[1] = HEIGHT
b[3] = -b[3]
def update_boids(boids, time, SEPARATION_MULTIPLIER, COHESION_MULTIPLIER, align_on, sl):
for index in range(len(boids)):
b = boids[index]
b[2] += cohesion(index, boids)[0] * COHESION_MULTIPLIER
b[3] += cohesion(index, boids)[1] * COHESION_MULTIPLIER
b[2] += separate(index, boids, random_color, b[4])[0] * SEPARATION_MULTIPLIER
b[3] += separate(index, boids, random_color, b[4])[1] * SEPARATION_MULTIPLIER
if align_on == "y" or align_on == "Y":
b[2] += align(index, boids)[0]
b[3] += align(index, boids)[1]
b[4] = separate(index, boids, random_color, b[4])[2]
# Limit velocity to 500 pixels per second horizontally and vertically
b[2] = speed_limit(b[2], sl)
b[3] = speed_limit(b[3], sl)
# Update the boid's position based on its velocity and the
# time that has passed since the last update.
b[0] += float(b[2]) / 1000 * time
b[1] += float(b[3]) / 1000 * time
# Make the boid bounce off the walls.
if b[0] < 0:
b[0] = 0
b[2] = -b[2]
elif b[0] > WIDTH:
b[0] = WIDTH
b[2] = -b[2]
if b[1] < 0:
b[1] = 0
b[3] = -b[3]
elif b[1] > HEIGHT:
b[1] = HEIGHT
b[3] = -b[3]
def main():
# parse command
command_log = 'CIRCexplorer parameters: ' + ' '.join(sys.argv)
if len(sys.argv) == 1:
sys.exit(help_doc)
elif sys.argv[1] == '--version' or sys.argv[1] == '-v':
sys.exit(__version__)
elif sys.argv[1] == 'align':
import align
align.align(docopt(align.__doc__, version=__version__),
command=command_log, name='align')
elif sys.argv[1] == 'parse':
import parse
parse.parse(docopt(parse.__doc__, version=__version__),
command=command_log, name='parse')
elif sys.argv[1] == 'annotate':
import annotate
annotate.annotate(docopt(annotate.__doc__, version=__version__),
command=command_log, name='annotate')
elif sys.argv[1] == 'assemble':
import assemble
assemble.assemble(docopt(assemble.__doc__, version=__version__),
command=command_log, name='assemble')
elif sys.argv[1] == 'denovo':
import denovo
denovo.denovo(docopt(denovo.__doc__, version=__version__),
command=command_log, name='denovo')
else:
sys.exit(help_doc)
def align_command(options, command_log):
from align import align
options['--bw'] = True
options['--scale'] = True
options['--skip-tophat'] = False
options['--skip-tophat-fusion'] = False
align(options, command=command_log, name='align')
def main():
# parse command
command_log = 'CIRCexplorer parameters: ' + ' '.join(sys.argv)
if len(sys.argv) == 1:
sys.exit(help_doc)
elif sys.argv[1] == '--version' or sys.argv[1] == '-v':
sys.exit(__version__)
elif sys.argv[1] == 'align':
import align
align.align(docopt(align.__doc__, version=__version__),
command=command_log,
name='align')
elif sys.argv[1] == 'parse':
import parse
parse.parse(docopt(parse.__doc__, version=__version__),
command=command_log,
name='parse')
elif sys.argv[1] == 'annotate':
import annotate
annotate.annotate(docopt(annotate.__doc__, version=__version__),
command=command_log,
name='annotate')
elif sys.argv[1] == 'assemble':
import assemble
assemble.assemble(docopt(assemble.__doc__, version=__version__),
command=command_log,
name='assemble')
elif sys.argv[1] == 'denovo':
import denovo
denovo.denovo(docopt(denovo.__doc__, version=__version__),
command=command_log,
name='denovo')
else:
sys.exit(help_doc)
def zstruct2(mol1, mol2, r1, r2, b1, doOne=True, doTwo=False):
obconversion = ob.OBConversion()
obconversion.SetOutFormat("xyz")
i = 0
# generate all one-permutations of r1 and r2
if (doOne == True):
z = []
for atom in r2:
for atom2 in r1:
z.append([(atom, atom2)])
#print(z)
for isomer in z:
output_path = os.getcwd() + "/initial%04d.xyz" % i
omol = align.align(mol1, mol2, 1, list(isomer[0]))
fname = str("ISOMERS%04d" % i)
s1 = " ".join([str(j) for j in isomer[0]])
i += 1
with open(fname, 'w') as f:
f.write("ADD " + s1 + "\n")
with open(output_path, 'w') as f:
f.write(obconversion.WriteString(omol))
# ====== generate all one-permutations of add and break ===== #
if not (b1 is None):
zb = [[x[0], b1] for x in z]
#print(zb)
for isomer in zb:
output_path = os.getcwd() + "/initial%04d.xyz" % i
fname = str("ISOMERS%04d" % i)
s1 = " ".join([str(j) for j in isomer[0]])
s2 = " ".join([str(j) for j in isomer[1]])
i += 1
omol = align.align(mol1, mol2, 1, list(isomer[0]))
with open(fname, 'w') as f:
f.write("ADD " + s1 + "\n")
f.write("BREAK " + s2 + "\n")
with open(output_path, 'w') as f:
f.write(obconversion.WriteString(omol))
# ========generate all two-permutations of r1 and r2 ====== #
if (doTwo == True):
z2 = [zip(x, r1) for x in itertools.permutations(r2, len(r1))]
for isomer in z2:
output_path = os.getcwd() + "/initial%04d.xyz" % i
fname = str("ISOMERS%04d" % i)
s1 = " ".join([str(j) for j in isomer[0]])
s2 = " ".join([str(j) for j in isomer[1]])
isom_list = list(isomer[0]) + list(isomer[1])
i += 1
omol = align.align(mol1, mol2, 2, isom_list)
with open(fname, 'w') as f:
f.write("ADD " + s1 + "\n")
f.write("ADD " + s2 + "\n")
with open(output_path, 'w') as f:
f.write(obconversion.WriteString(omol))
def smith_waterman(seq0, seq1):
"""
gap_score: # of gaps / length of aligned sequence (lower number => better alignment)
"""
score, gap_score, a0, a1 = align.align(seq0, seq1, local=False)
return gap_score
def realign_filter(rec, inslib):
S = -np.ones((256, 256)) + 2 * np.identity(256)
S = S.astype(np.int16)
seqn = rec['Superfamily'] + ':' + rec['Subfamily']
if seqn not in inslib:
return False
seq_headers = ['Genomic_Consensus_5p', 'Genomic_Consensus_3p', 'Insert_Consensus_5p', 'Insert_Consensus_3p']
for seqtype in seq_headers:
s1 = align.string_to_alignment(rec[seqtype])
s2 = align.string_to_alignment(inslib[seqn])
(s, a1, a2) = align.align(s1, s2, -2, -2, S, local=True)
a1 = align.alignment_to_string(a1)
a2 = ''.join([b for b in list(align.alignment_to_string(a2)) if b != '-'])
score = 0.0
if len(a1) > 0:
score = float(len(a1) - (len(a1)-s)) / float(len(a1))
#print seqtype, score, len(a1)
if score > 0.9 and len(a1) > 25:
return False
return True
def compare_fingerprint_to_database(filename):
file1 = fingerprint.location_fingerprint(filename)
fingerprints = session.query(model.Fingerprint)
database_iteration = []
max_offset = 0
for row in fingerprints:
file2 = pickle.loads(row.fingerprint)
ranked_matches = align.align(file1, file2)
current_song = {}
song_match = {}
#assorted song information
current_song["title"] = row.title
current_song["artist"] = row.artist
current_song["album"] = row.album
current_song["offset"] = ranked_matches[0][1]
database_iteration.append(current_song)
for current_song in database_iteration:
if current_song["offset"] > max_offset:
max_offset = current_song["offset"]
#information for most likely match
for current_song in database_iteration:
if current_song["offset"] == max_offset:
song_match["title"] = current_song["title"]
song_match["artist"] = current_song["artist"]
song_match["album"] = current_song["album"]
return song_match
def realign_filter(rec, inslib):
S = -np.ones((256, 256)) + 2 * np.identity(256)
S = S.astype(np.int16)
seqn = rec['Superfamily'] + ':' + rec['Subfamily']
if seqn not in inslib:
return False
seq_headers = [
'Genomic_Consensus_5p', 'Genomic_Consensus_3p', 'Insert_Consensus_5p',
'Insert_Consensus_3p'
]
for seqtype in seq_headers:
s1 = align.string_to_alignment(rec[seqtype])
s2 = align.string_to_alignment(inslib[seqn])
(s, a1, a2) = align.align(s1, s2, -2, -2, S, local=True)
a1 = align.alignment_to_string(a1)
a2 = ''.join(
[b for b in list(align.alignment_to_string(a2)) if b != '-'])
score = 0.0
if len(a1) > 0:
score = float(len(a1) - (len(a1) - s)) / float(len(a1))
#print seqtype, score, len(a1)
if score > 0.9 and len(a1) > 25:
return False
return True
def test_align1():
print 'peak: ' + str(peak1)
print 'mean: ' + str(mean1)
(i, score) = align.align(peak1, meanWords1, -1)
print 'index is ' + str(i) + ', should be 0?'
print 'score is ' + str(score)
return
def smith_waterman(seq0, seq1):
"""
gap_score: # of gaps / length of aligned sequence (lower number => better alignment)
"""
score, gap_score, a0, a1 = align.align(seq0, seq1, local=False)
return gap_score
def test_padded_align_odd() -> None:
"""
Test the padded cross-correlation method with two gaussian pulses of odd length.
"""
# make some time arrays and define a time delta
t = np.linspace(-2 * np.pi, 2 * np.pi, 100)
dt = 3.675 * (t[1] - t[0])
t = np.linspace(-1, 1, 199, endpoint=False)
# construct two identical gaussian pulses
x = np.real(signal.gausspulse(t, fc=5))
y = np.real(signal.gausspulse(t + dt, fc=5))
# compute the delay without any upsampling
d = align.xcorr_delay(x, y, 30)
# and apply the delay
y = align.apply_delay(y, d)
# and test the top-level call
ynew = align.align(x, y, method="xcorr", factor=30)
# and check that the alignment is within a certain known accuracy
assert np.std(np.abs(x - y)) < 0.005
assert np.std(np.abs(y - ynew)) < 5e-5
def align_test(s, m):
S = np.array([[1 if i == j else -1 for i in range(256)] for j in range(256)], dtype=np.short)
score, p, _ = align.align(list(align.string_to_alignment(s)),
list(align.string_to_alignment(m)),
-1, -1, S, True, True)
p = align.alignment_to_string(p).replace('-', '')
return score, s.find(p)
def testUnalignedText(self):
left_text = \
"""シャーロックホームズにとって、彼女はいつも「あの女」である。ホームズが彼女を他の名前で呼ぶのはほとんど聞いたことがない。彼の目には、 彼女がそびえ立って女という性全体を覆い隠している。しかし、彼はアイリーン・アドラーに愛のような激情は一切感じていなかった。すべての激情は、そして特に愛というものは、 相容れなかった、彼の冷静で厳格だが見事に調整された心とは。
"""
right_text = \
"""TO SHERLOCK HOLMES she is always the woman. I have seldom heard him mention her under any other name. In his eyes she eclipses and predominates the whole of her sex. It was not that he felt any emotion akin to love for Irene Adler. All emotions, and that one particularly, were abhorrent to his cold, precise but admirably balanced mind.
"""
split_text = align(left_text, right_text)
split_text = list(split_text)
self.assertEqual(split_text, [
('シャーロックホームズにとって、彼女はいつも「あの女」である。',
'TO SHERLOCK HOLMES she is always the woman.'),
('ホームズが彼女を他の名前で呼ぶのはほとんど聞いたことがない。',
'I have seldom heard him mention her under any other name.'),
('彼の目には、 彼女がそびえ立って女という性全体を覆い隠している。',
'In his eyes she eclipses and predominates the whole of her sex.'
),
('しかし、彼はアイリーン・アドラーに愛のような激情は一切感じていなかった。',
'It was not that he felt any emotion akin to love for Irene Adler.'
),
('すべての激情は、そして特に愛というものは、 相容れなかった、彼の冷静で厳格だが見事に調整された心とは。',
'All emotions, and that one particularly, were abhorrent to his cold, '
'precise but admirably balanced mind.'), ('', '')
])
def test_gauss_align() -> None:
"""
Test Gaussian interpolation of unpadded cross correlation.
"""
# make some time arrays and define a time delta
t = np.linspace(-2 * np.pi, 2 * np.pi, 100)
dt = 3.675 * (t[1] - t[0])
t = np.linspace(-1, 1, 200, endpoint=False)
# construct two identical gaussian pulses
x = np.real(signal.gausspulse(t, fc=5))
y = np.real(signal.gausspulse(t + dt, fc=5))
# compute the delay with upsampling
d_padded = align.xcorr_delay(x, y, 30)
# compute the delay without any upsampling
d = align.xcorr_delay(x, y, fit="gauss")
# compute the new signal
y = align.apply_delay(y, d)
# and test the top-level call
ynew = align.align(x, y, method="xcorr", factor=30)
# and check that the alignment is within a certain known accuracy
assert np.abs(d - d_padded) < 0.05
assert np.mean(np.abs(x - y)) < 7e-4
assert np.mean(np.abs(x - ynew)) < 7e-4
assert np.mean(np.abs(y - ynew)) < 5e-5
def pnp_3d3d_with_num(model_points,
image_points,
image_pts_3d,
K,
n,
dists=np.zeros((4, 1))):
_, rotation_vector, translation_vector, mask = cv2.solvePnPRansac(
model_points, image_points, K, dists)
pt3d = model_points[mask.ravel()]
pt2d = image_points[mask.ravel()]
pt3d_img = image_pts_3d[mask.ravel()]
if pt3d.shape[0] < n:
print('3d-2d few inliers number {} < N = {}'.format(pt3d.shape[0], n))
return None, None
s = np.int32(pt3d.shape[0] / n)
pt3d = pt3d[::s]
pt2d = pt2d[::s]
pt3d_img = pt3d_img[::s]
R, t, _ = al.align(np.asmatrix(pt3d.transpose()),
np.asmatrix(pt3d_img.transpose()))
return np.array(R), np.array(t)
def test_fft_align() -> None:
"""
Test FFT phase shift alignment
"""
for N in [178, 179, 200, 201]:
# make some time arrays and define a time delta
t = np.linspace(-2 * np.pi, 2 * np.pi, N // 2)
dt = 3.675 * (t[1] - t[0])
t = np.linspace(-1, 1, N, endpoint=False)
true = dt / (t[1] - t[0])
# construct two identical gaussian pulses
x = np.real(signal.gausspulse(t, fc=5))
y = np.real(signal.gausspulse(t + dt, fc=5))
# compute the delay with upsampling
delay = align.fft_delay(x, y)
# and apply the delay
y = align.apply_delay(y, delay)
# use the top-level call
ynew = align.align(x, y, method="fft")
# and check that the alignment is within a certain known accuracy
assert np.abs(true - delay) < 1e-3
assert np.mean(np.abs(x - y)) < 1e-3
assert np.mean(np.abs(x - ynew)) < 2e-4
assert np.mean(np.abs(y - ynew)) < 3e-5
def download(person, url, bb):
imgName = os.path.basename(url)
rawPersonPath = os.path.join(args.raw, person)
rawImgPath = os.path.join(rawPersonPath, imgName)
alignedPersonPath = os.path.join(args.aligned, person)
alignedImgPath = os.path.join(alignedPersonPath,
hashlib.md5(imgName).hexdigest() + ".png")
mkdirP(rawPersonPath)
mkdirP(alignedPersonPath)
if not os.path.isfile(rawImgPath):
print url
urlF = urllib2.urlopen(url, timeout=5)
with open(rawImgPath, 'wb') as f:
f.write(urlF.read())
if not os.path.isfile(alignedImgPath):
bgr = cv2.imread(rawImgPath)
if bgr is None:
return
rgb = cv2.cvtColor(bgr, cv2.COLOR_BGR2RGB)
dlibBB = dlib.rectangle(*bb)
outRgb = align.align(64,
rgb,
bb=dlibBB,
landmarkIndices=landmarkIndices)
if outRgb is not None:
outBgr = cv2.cvtColor(outRgb, cv2.COLOR_RGB2BGR)
cv2.imwrite(alignedImgPath, outBgr)
def scsp(s, t):
# extend
#
# Add missing characters to start
#
# Parameters: extend_me List from alignment
# original Original before alignmnet
# pad_me Companion - will be padded with leading spaces
#
# Returns: two strings, the first extended, the second padded
def extend(extend_me, original, pad_me):
extension = []
i = 0
while extend_me[0] != original[i] and extend_me[0] != '-':
w.append(original[i])
i += 1
return extension + extend_me, i * ['-'] + pad_me
_, b, c = align(s,
t,
replace_score=createSimpleDNASubst(subst=len(s) + len(t)),
indel_cost=0)
b1, c1 = extend(b, s, c)
c2, b2 = extend(c1, t, b1)
super_sequence = [aa if bb == '-' else bb for aa, bb in zip(b2, c2)]
return ''.join(super_sequence)
def compareDomStrs(cluster1,cluster2,match,mismatch,gap,scale):
#first index each cluster
clus1Strs = dict(enumerate(cluster1))
clus2Strs = dict(enumerate(cluster2))
clus1Size = len(cluster1)
clus2Size = len(cluster2)
scoreMatrix,word2num,num2word = aligntools.buildScoringDictScaled(chain(*(cluster1+cluster2)),match,mismatch,scale)
alignScores = np.ndarray((clus1Size,clus2Size))
# score each pairwise alignment of domain strings to populate a alignment scores matrix
for i,domStr1 in enumerate(cluster1):
for j,domStr2 in enumerate(cluster2):
num1 = [word2num[x] for x in domStr1]
num2 = [word2num[x] for x in domStr2]
alignScore,a1,a2 = align.align(num1,num2,gap,gap,scoreMatrix,local=True)
alignScores[i,j] = alignScore
#prepare scoring matrix for hungarian algorithm: negate scores and pad matrix
if clus1Size < clus2Size:
costMatrix = -np.vstack((copy(alignScores),np.zeros((clus2Size-clus1Size,clus2Size))))
elif clus2Size < clus1Size:
costMatrix = -np.hstack((copy(alignScores),np.zeros((clus1Size,clus1Size-clus2Size))))
else:
costMatrix = -copy(alignScores)
# apply hungarian algorithm for matching
pairings = [(x,y) for x,y in zip(*linear_sum_assignment(costMatrix)) if (x<clus1Size) and (y<clus2Size)]
clusterScore = sum(alignScores[pairing] for pairing in pairings)
pairStrings = [(alignScores[(x,y)],clus1Strs[x],clus2Strs[y]) for x,y in pairings]
pairStrings.sort(reverse=True)
return clusterScore,pairStrings
def consensus(self, minscore = 0.9):
''' build consensus from sorted aligned reads iteratively '''
S = -np.ones((256, 256)) + 2 * np.identity(256)
S = S.astype(np.int16)
minqual = self.reads[0].minqual
sortable_reads = [SortableRead(sr.read) for sr in self.reads]
seqs = [qualtrim(sorted_read.read, minqual=minqual) for sorted_read in sorted(sortable_reads)]
seqs = [s for s in seqs if len(s) > 20]
if len(seqs) == 0:
return '', 0.0
if len(seqs) == 1: # no consensus necessary
return seqs[0], 1.0
uniq_seqs = [seqs[0]]
for i, seq in enumerate(seqs[1:], start=1):
if seq != seqs[i-1]:
uniq_seqs.append(seq)
if len(uniq_seqs) == 1: # all seqs were the same!
return uniq_seqs[0], 1.0
cons = uniq_seqs[0]
scores = []
if len(uniq_seqs) > 1000:
uniq_seqs = [uniq_seqs[u] for u in sorted(np.random.choice(range(len(uniq_seqs)), size=1000))]
for seq in uniq_seqs[1:]:
s1 = align.string_to_alignment(cons)
s2 = align.string_to_alignment(seq)
(s, a1, a2) = align.align(s1, s2, -2, -2, S, local=True)
a1 = align.alignment_to_string(a1)
a2 = ''.join([b for b in list(align.alignment_to_string(a2)) if b != '-'])
score = 0.0
if len(a1) > 0:
score = float(len(a1) - (len(a1)-s)) / float(len(a1))
if re.search(a1, cons):
cons_start, cons_end = locate_subseq(cons, a1)
if score >= minscore and cons_end > len(cons)-5:
scores.append(score)
align_end = locate_subseq(seq, a2)[1]
cons += seq[align_end:]
#print self.start, self.end, cons
if scores:
return cons, np.mean(scores)
else:
return cons, 0.0
def main():
#Upload images
uploaded_file = st.file_uploader("Choose a picture", type=['jpg', 'png'])
if uploaded_file is not None:
st.image(uploaded_file, width=200)
second_uploaded_file = st.file_uploader("Choose another picture", type=['jpg', 'png'])
if second_uploaded_file is not None:
st.image(second_uploaded_file, width=200)
img1 = np.array(uploaded_file)
img2 = np.array(second_uploaded_file)
image1 = PIL.Image.open(uploaded_file)
image2 = PIL.Image.open(second_uploaded_file)
images = [image1, image2]
if st.button('Align images'):
align(images)
def test_basic(self):
"""Verify that the aligner is putting out the correct score.
Example on smith-waterman wikipedia page.
"""
s0 = 'ACACACTA'
s1 = 'AGCACACA'
score, normalized_score, a0, a1 = align.align(s0, s1, local=True)
self.assertEqual(score, 12)
def test_long_align(self):
d = _fasta_dict('example.fa')
r0 = 'm150213_074729_42177R_c100777662550000001823160908051505_s1_p0/70715/9957_22166'
r1 = 'm150126_093705_42156_c100779662550000001823165208251525_s1_p0/144605/28461_40297'
s0 = d[r0]
s1 = d[r1]
score, normalized_score, a0, a1 = align.align(s0, s1, local=False)
print(score)
print(normalized_score)
def align_shortlist(seq, shortlist):
result = []
nseq = list(align.string_to_alignment(seq))
for sh in shortlist:
score, nr, shr = align.align(nseq, list(align.string_to_alignment(sh)),
-1, -1, S, True, True)
result.append((align.alignment_to_string(nr),
align.alignment_to_string(shr)))
return result
def _build_aligned_data(data, limit):
limited_data = [d[:limit] for d in data]
aligned_data = []
longest = limited_data[np.argmax(map(len, limited_data))][::-1]
for d in limited_data:
(_, _, a) = align.align(longest, d[::-1], 0, -2, scoring.S,
mutual=False)
aligned_data.append(a[::-1])
return aligned_data
def intake(geometry):
file = open(geometry, "r")
text = file.read()
file.close()
words = text.split()
coords = []
for i in range(6):
coords.append([])
for j in range(3):
coords[i].append(float(words[i*4+j+1]))
return align.align(coords)
def test_fix1():
data = align.load_from_file(open('fixtures/1.points'))
expected = fixture_from_file(open("fixtures/1.solution"))
res = align.align(data)
if not np.array_equal(res, expected):
print(res)
print("---")
print(expected)
assert False
def step2(dist_mapping, profile):
f_main_log = profile["main_log_fd"]
f_main_log.write("\n[*] Futher Investigate on the following TID:\n")
for k2, v2 in dist_mapping.iteritems():
if v2["match"] == 0:
f_main_log.write("[*] Compromised TID (%s)\n\t%s\n" %
(k2, profile["groups"][1][k2]))
f_main_log.write(" with TID=%s and Dist=%s\n" %
(v2["all"][0][0], v2["all"][0][1]))
candidates = [[k2, v2["all"][0]] for k2, v2 in dist_mapping.iteritems()
if v2["match"] == 0]
sort_by_min_dist = sorted(candidates,
key=lambda (x): x[1][1],
reverse=True)
f_main_log.write("\n\n")
f_main_log.write("[*] TOP 3 TID Candidates are:\n\t")
f_main_log.write("\n\t".join([
"Mal_TID(%s) Clostest TID(%s) w/ Dist=%s" % (p[0], p[1][0], p[1][1])
for p in sort_by_min_dist[:3]
]))
f_main_log.write("\n\n")
return None
for k2, v2 in dist_mapping.iteritems():
if len(v2["exact"]) == 0:
sort_dist = sorted(v2["all"].iteritems(), key=lambda (k, v): v)
rtn = " ".join(["%s:%s" % (kk, vv) for kk, vv in sort_dist])
f_main_log.write("[*] Compromised TID (%s)\n\tDistance [%s]\n" %
(k2, rtn))
if sort_dist[0][1] > 10000:
continue
try:
f_main_log.write("(%s - %s)\n" % (k2, sort_dist[0][0]))
f_main_log.write(" ".join(profile["groups"][1][k2]) + "\n")
f_main_log.write(
" ".join(profile["groups"][0][sort_dist[0][0]]) + "\n")
enc1, enc2, v = align.align(
profile["groups"][1][k2],
profile["groups"][0][sort_dist[0][0]])
score, encodeds = align.score(enc1, enc2, v)
for encoded in encodeds[0:1]:
alignment = v.decodeSequenceAlignment(encoded)
print "(%s - %s)\n" % (k2, sort_dist[0][0])
print alignment
f_main_log.write(
"\tSimilarity:%s (%s - %s)\n" %
(alignment.percentIdentity(), k2, sort_dist[0][0]))
f_main_log.write(str(alignment))
f_main_log.write("\n\n")
except:
break
def test_fix1():
data = align.load_from_file(open('fixtures/1.points'))
expected = fixture_from_file(open("fixtures/1.solution"))
res = align.align(data)
if not np.array_equal(res, expected):
print(res)
print("---")
print(expected)
assert False
def run_single_test(data_dir, output_dir):
from align import align
from skimage.io import imread, imsave
parts = open(join(data_dir, 'g_coord.csv')).read().rstrip('\n').split(',')
g_coord = (int(parts[0]), int(parts[1]))
img = imread(join(data_dir, 'img.png'), plugin='matplotlib')
aligned_img, (b_row, b_col), (r_row, r_col) = align(img, g_coord)
with open(join(output_dir, 'output.csv'), 'w') as fhandle:
print('%d,%d,%d,%d' % (b_row, b_col, r_row, r_col), file=fhandle)
imsave(join(output_dir, 'aligned_img.png'), aligned_img)
def local_check(*zipped):
for x, y in list(*zipped):
nx = list(align.string_to_alignment(x.replace("-", "")))
ny = list(align.string_to_alignment(y))
score, xr, yr = align.align(nx, ny, -1, -1, S, True, True)
xr = align.alignment_to_string(xr)
yr = align.alignment_to_string(yr)
# diff = abs(len(y.replace("-", "")) - len(xr.replace("-", "")))
# if diff > 1:
# return False
if hamming_dist(y, xr) > 1:
# print(y, xr, yr, hamming_dist(y, xr))
return False
return True
def main():
parser = argparse.ArgumentParser(description='The seqAnn application')
parser.add_argument('-i', action="store", dest="i", help="The input file is fasta with a single sequence")
parser.add_argument('-g', action="store", dest="g", help="The gene type to process. It includes most of HLA and KIR types.For example: HLA-A, KIR")
options = parser.parse_args()
config.geneType = GeneType(options.g)
print("Annotating\n")
blast.blast(options.i, config.get_blast_file())
print("The input sequence best matched with "+blast.get_match_gene()+"\n")
alignHelp = align(options.i)
alignHelp.searchGene(blast.get_match_gene())
alignHelp.writeInputFile()
alignHelp.runAlign()
splitGeneHelp = splitGene(alignHelp.gene)
splitGeneHelp.runSplit()
def align(self, other,
_pad=lambda d: di.Dimension._NullDimension(d[0]),
_key=lambda t: t[0]):
di00 = other.labels
di10 = self.labels
di01, di11 = al.align(di00, di10, key=_key, pad=_pad)
def maybe_update(brick, olddims, newdims):
return brick if olddims == newdims \
else HyperBrick(brick._data, newdims)
return tuple(maybe_update(b, d0, d1)
for b, d0, d1 in zip((self, other),
(di10, di00),
(di11, di01)))
def align(self, seq1, seq2, local = False):
s1 = align.string_to_alignment(seq1)
s2 = align.string_to_alignment(seq2)
score, a1, a2 = align.align(s1, s2, self.gap_open, self.gap_extend,
self.subs, local)
res1, res2 = align.alignment_to_string(a1), align.alignment_to_string(a2)
if local:
strip1, strip2 = res1.replace("-", ""), res2.replace("-", "")
start1, start2 = seq1.index(strip1), seq2.index(strip2)
start_flank = max(start1, start2)
end_flank = max(len(seq1) - len(strip1) - start1,
len(seq2) - len(strip2) - start2)
res1 = "-" * start_flank + res1 + "-" * end_flank
res2 = "-" * start_flank + res2 + "-" * end_flank
return res1, res2, score
def align(self, seq1, seq2, local=False):
s1 = align.string_to_alignment(seq1)
s2 = align.string_to_alignment(seq2)
score, a1, a2 = align.align(s1, s2, self.gap_open, self.gap_extend,
self.subs, local)
res1, res2 = align.alignment_to_string(a1), align.alignment_to_string(
a2)
if local:
strip1, strip2 = res1.replace("-", ""), res2.replace("-", "")
start1, start2 = seq1.index(strip1), seq2.index(strip2)
start_flank = max(start1, start2)
end_flank = max(len(seq1) - len(strip1) - start1,
len(seq2) - len(strip2) - start2)
res1 = "-" * start_flank + res1 + "-" * end_flank
res2 = "-" * start_flank + res2 + "-" * end_flank
return res1, res2, score
def main(left, right):
score, traceback = align(left, right)
print 'Score: {0}'.format(score)
sequence_l, sequence_r = construct_alignment(left, right, traceback)
sequence_l = ''.join(sequence_l)
sequence_r = ''.join(sequence_r)
print 'Alignment:'
while len(sequence_l) > 0:
head_l, head_r = sequence_l[:60], sequence_r[:60]
sequence_l, sequence_r = sequence_l[60:], sequence_r[60:]
print head_l
print head_r
print
def item_iter(self):
for i, index in enumerate(range(len(self.st_sents))):
st_sent = self.st_sents[index]
vecs = self.vec_manager.get_vector(st_sent['sentid'])
old_toks = [wd['word'] for wd in st_sent['words']]
new_toks = vecs['tokens']
alignment = align(old_toks, new_toks)
if alignment is not None:
for i, word in enumerate(st_sent['words']):
if 'sense' in word:
sense_inst = SenseInstance(old_toks, i, word['sense'],
word['tag'])
(projection_start, projection_stop) = alignment[i]
embeddings = []
for j in range(projection_start, projection_stop):
embeddings.append(tensor(vecs['vecs'][j]))
embedding = torch.stack(embeddings).sum(dim=0).tolist()
sense_inst.add_embedding('embed', embedding)
yield sense_inst
def consensus(seqs, minscore=0.95):
''' build consensus from sorted aligned reads iteratively, expects seqs to be sorted in ref genome order '''
S = -np.ones((256, 256)) + 2 * np.identity(256)
S = S.astype(np.int16)
if len(seqs) == 1: # no consensus necessary
return seqs[0], 1.0
uniq_seqs = [seqs[0]]
for i, seq in enumerate(seqs[1:], start=1):
if seq != seqs[i-1]:
uniq_seqs.append(seq)
if len(uniq_seqs) == 1: # all seqs were the same!
return uniq_seqs[0], 1.0
cons = uniq_seqs[0]
scores = []
if len(uniq_seqs) > 1000: uniq_seqs = np.random.choice(uniq_seqs, size=1000)
for seq in uniq_seqs[1:]:
s1 = align.string_to_alignment(cons)
s2 = align.string_to_alignment(seq)
(s, a1, a2) = align.align(s1, s2, -2, -2, S, local=True)
a1 = align.alignment_to_string(a1)
a2 = ''.join([b for b in list(align.alignment_to_string(a2)) if b != '-'])
score = float(len(a1) - (len(a1)-s)) / float(len(a1))
scores.append(score)
if re.search(a1, cons):
cons_start, cons_end = locate_subseq(cons, a1)
if score >= minscore and cons_end > len(cons)-5:
align_end = locate_subseq(seq, a2)[1]
cons += seq[align_end:]
return cons, np.mean(scores)
def run_single_test(data_dir, output_dir):
from align import align
from numpy import ndarray
from skimage.io import imread, imsave
parts = open(join(data_dir, 'g_coord.csv')).read().rstrip('\n').split(',')
g_coord = (int(parts[0]), int(parts[1]))
img = imread(join(data_dir, 'img.png'), plugin='matplotlib')
n_rows, n_cols = img.shape[:2]
min_n_rows, min_n_cols = n_rows / 4.5, n_cols / 1.5
aligned_img, (b_row, b_col), (r_row, r_col) = align(img, g_coord)
assert type(aligned_img) is ndarray, 'aligned image is not ndarray'
n_rows, n_cols = aligned_img.shape[:2]
assert n_rows > min_n_rows and n_cols > min_n_cols, 'aligned image is too small'
with open(join(output_dir, 'output.csv'), 'w') as fhandle:
print('%d,%d,%d,%d' % (b_row, b_col, r_row, r_col), file=fhandle)
imsave(join(output_dir, 'aligned_img.png'), aligned_img)
def upload_file():
if request.method == 'POST':
#check if the post request has the file part
# if ('filewav' or 'filemid') not in request.files:
# print('No file part')
# return redirect(request.url)
filewav = request.files['filewav']
filexml = request.files['filexml']
# if user does not select file, browser also
# submit an empty part without filename
# if filewav.filename == '':
# print('No selected file')
# return redirect(request.url)
wavname = secure_filename(filewav.filename)
filewav.save(os.path.join(app.config['UPLOAD_FOLDER'], wavname))
xmlname = secure_filename(filexml.filename)
filexml.save(os.path.join(app.config['UPLOAD_FOLDER'], xmlname))
(f, wavext) = os.path.splitext(wavname)
(xname, xmlext) = os.path.splitext(xmlname)
midi_file = xname+'.mid'
if (wavext == '.wav') and (xmlext == '.xml'):
os.chdir(app.config['UPLOAD_FOLDER'])
res1 = subprocess.call(['C:/Program Files/MuseScore 3/bin/MuseScore3.exe','-o'+midi_file , xmlname])
res2 = subprocess.call(['C:/Program Files/MuseScore 3/bin/MuseScore3.exe','-o'+xname+'.mpos', xmlname])
print(res1,res2)
Y_pred = transcript(wavname)
print(Y_pred.shape)
ld = listdir(app.config['UPLOAD_FOLDER'])
print(ld)
p , q = align(midi_file , Y_pred.T)
p = list(p)
q = list(q)
return render_template('audio_TFG.html' , filename = wavname , p = p , q = q )
def register(face_detector, model, input_shape, frame, detections):
print("Registering")
l = len(detections)
if l > 1:
print("You should only register one user")
return None
elif l < 1:
print("No face is found")
return None
cv2.imwrite(f"{img_dir}{os.path.sep}registered.jpg", frame)
print(detections[0])
img_aln = align.align(detections[0], frame)
img_rep = represent.represent(img_aln, input_shape)
retrieved_img = img_rep[0][:, :, ::-1]
plt.imshow(retrieved_img)
plt.show()
return "Registered"
def gen_vector(landmark_predictor, origin_img, vector_predictor):
h, w, _ = origin_img.shape
img = cv2.resize(origin_img, (RECOG_SIZE, RECOG_SIZE))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img - 127.5
img = img * 0.0078125
landmarks = landmark_predictor.predict(np.expand_dims(img, axis=0))[0]
landmarks = np.asarray([(int(landmark[0] * w), int(landmark[1] * h))
for landmark in landmarks])
align_face_img = align(origin_img, landmarks, LANDMARK_SIZE)
# cv2.imwrite('output.jpg', align_face_img)
# exit(0)
align_face_img = cv2.cvtColor(align_face_img, cv2.COLOR_BGR2RGB)
align_face_img = align_face_img - 127.5
img = align_face_img * 0.0078125
img = img.transpose([2, 0, 1])
img = np.expand_dims(img, axis=0)
img = torch.from_numpy(img).float()
img = torch.autograd.Variable(img, requires_grad=False).to('cpu')
with torch.no_grad():
vector = vector_predictor.forward(img)
return np.asarray(vector)
def register(face_detector, model, input_shape, frame, detections):
print("Registering")
l = len(detections)
if l > 1:
print("You should only register one user")
return None
elif l < 1:
print("No face is found")
return None
cv2.imwrite(
"C:\\development\\surveilance\\code\\deepface\\img\\image_registered.jpg",
frame)
print(detections[0])
img_aln = align.align(detections[0], frame)
img_rep = represent.represent(img_aln, input_shape)
retrieved_img = img_rep[0][:, :, ::-1]
plt.imshow(retrieved_img)
plt.show()
return "Registered"
## python script that aligns to the reference outputting a sam file
import sys
import os
import logging
logging.basicConfig(format='%(levelname)s:%(message)s', level=logging.DEBUG)
sys.path.insert(0, os.path.abspath('../src'))
from optparse import OptionParser
import align
parser = OptionParser()
parser.add_option("-r", "--ref", dest="refFilename",help="fasta input ref file",
default="../data/ref.fa")
parser.add_option("-i","--id",dest="simID",help="simulation identifier",
default=os.path.abspath(os.path.join(os.path.curdir,"../data/ref.fa")))
(opt, args) = parser.parse_args()
## Make run ID mandatory
if not opt.simID:
logging.error("Please specify a run ID with -i '''id''' ")
raise ValueError("-i option is mandatory")
## Index to the reference
opt.readFilename = opt.refFilename[:-3] +'.subsampled.'+ opt.simID+'.fq'
logging.info("Indexing reference")
# align.refIndex(file=opt.refFilename)
# ## Align reads to the reference
logging.info("Aligning reads to reference")
samfileName = opt.refFilename[:-3] +'.subsampled.'+ opt.simID + '.sam'
aligned = align.align(reference=opt.refFilename, read_file=opt.readFilename,stdout=samfileName,algorithm='stampy')
def nwalign_wrapper(seq1, seq2, matrix=NUCMATRIX):
s1 = align.string_to_alignment(seq1)
s2 = align.string_to_alignment(seq2)
(score, a1, a2) = align.align(s1, s2, -1, -1, matrix)
return float(score) / len(a1)
def test_align(self):
for case in self.cases:
self.assertEqual(align.align(case[0][0], case[0][1]), case[1])
def test_align_with_japanese(self):
for case in self.jcases:
self.assertEqual(align.align(case[0][0], case[0][1]), case[1])
#!/usr/bin/python
from sys import argv, stdout, exit
from os.path import basename
from glob import iglob
from align import align
from skimage.io import imread, imsave
if len(argv) != 3:
stdout.write('Usage: %s input_dir_path output_dir_path\n' % argv[0])
exit(1)
input_dir_path = argv[1]
output_dir_path = argv[2]
for filename in iglob(input_dir_path + '/*.png'):
img = imread(filename)
img = align(img)
img = img.astype('float64') / 255
imsave(output_dir_path + '/' + basename(filename), img)
def testAlign1(self):
self.assertEqual(hw.align("GCGGAA","GCAA",-3,dnamat), [14, 'GCggAA', 'GC--AA'])
def consensus(seqs, minscore=0.95):
''' build consensus from sorted aligned reads iteratively, expects seqs to be sorted in ref genome order '''
S = -np.ones((256, 256)) + 2 * np.identity(256)
S = S.astype(np.int16)
if len(seqs) == 0:
return '', 0.0
if len(seqs) == 1: # no consensus necessary
return seqs[0], 1.0
uniq_seqs = [seqs[0]]
for i, seq in enumerate(seqs[1:], start=1):
if seq != seqs[i-1]:
uniq_seqs.append(seq)
if len(uniq_seqs) == 1: # all seqs were the same!
return uniq_seqs[0], 1.0
start_index = 0
cons = uniq_seqs[start_index]
scores = []
align_init = False
for i, seq in enumerate(uniq_seqs[1:]):
#print 'oldcons:', cons
#print 'seq :', seq
s1 = align.string_to_alignment(cons)
s2 = align.string_to_alignment(seq)
(s, a1, a2) = align.align(s1, s2, -2, -2, S, local=True)
a1 = align.alignment_to_string(a1)
a2 = ''.join([b for b in list(align.alignment_to_string(a2)) if b != '-'])
score = 0.0
if len(a1) > 0:
score = float(len(a1) - (len(a1)-s)) / float(len(a1))
#print 'score :', score
scores.append(score)
if re.search(a1, cons):
cons_start, cons_end = locate_subseq(cons, a1)
if score >= minscore and cons_end > len(cons)-5:
align_end = locate_subseq(seq, a2)[1]
cons += seq[align_end:]
align_init = True
#print 'newcons:', cons
elif not align_init: # haven't found a scaffold yet
start_index += 1
cons = uniq_seqs[start_index]
#print '****'
return cons, np.mean(scores)
pars['flavor'] = 'passthru' # symbolic link, no fastqc
pp.preprocess(pars)
# *** 03 combine ***
# no need to run if we don't have fastq files to combine
pars['flavor'] = 'combine'
# pars['flavor'] = 'skip'
# c.combine(pars)
# *** 04 align ***
# star - generate bams
pars['alignerIndexDir'] = alignerIndexDir1
pars['flavor'] = 'star'
# pars['flavor'] = 'skip'
a.align(pars)
# pars['alignerIndexDir'] = alignerIndexDir2
# pars['flavor'] = 'salmon'
# a.align(pars)
# *** 05 quantify ***
# cufflinks - generate quantifications from bams
# pars['flavor'] = 'cufflinks'
pars['flavor'] = 'stringtie'
q.quantify(pars)
# *** count ***
# featureCounts
pars['flavor'] = 'featureCounts'
co.count(pars)
def testAlign2(self):
self.assertEqual(hw.align("GATC","AT",-9,dnamat), [-8, 'gATc', '-AT-'])
def testAlign3(self):
self.assertEqual(hw.align("CCAA","AT",-5,dnamat), [-9, 'ccAa', '--At'])
def testAlign4(self):
self.assertEqual(hw.align("ATAACAGA","GAACGAA",-9,dnamat), [8, 'atAACagA', 'g-AACgaA'])
from parse import parsingFunc, toFasta
from align import align
##### Config variables #####
filePath = 'rand.500.4.fq'
wordLength = 30 # See readme if running on 32-bit machine
writePath = 'output.fasta'
############################
reads = parsingFunc(filePath)
result = align(reads, wl=wordLength)
contigs = result[0]
N50 = result[1]
toFasta(contigs, writePath)
print("Complete. n50: " + str(N50))
'''
rand.500.1.fq:
wordLength = 7
n_contigs = 2
n50 = 1
time ~= 540
wordLength = 15
n_contigs = 2
n50 = 1
time ~= 345
wordLength = 30
n_contigs = 2
n50 = 1
time ~= 325
rand.500.2.fq:
def testAlign5(self):
self.assertEqual(hw.align("CAGA","CGAA",-4,dnamat), [8, 'CagA', 'CgaA'])
