def Expand(self):
if not self.mIsExpanded:
self.mMapQuery2Sbjct = alignlib_lite.py_makeAlignataVector()
alignlib_lite.py_fillAlignataCompressed(self.mMapQuery2Sbjct,
self.mQueryFrom, self.mQueryAli,
self.mSbjctFrom, self.mSbjctAli)
self.mIsExpanded = True
def MapAlignment(self, map_query=None, map_sbjct=None):
self.Expand()
tmp = alignlib_lite.py_makeAlignataVector()
if map_query:
tmp.Clear()
map_query.Expand()
alignlib_lite.py_combineAlignata(tmp,
map_query.mMapQuery2Sbjct,
self.mMapQuery2Sbjct,
alignlib_lite.py_RR)
map_query.Clear()
alignlib_lite.py_copyAlignata(self.mMapQuery2Sbjct, tmp)
self.mQueryToken = map_query.mSbjctToken
if map_sbjct:
tmp.Clear()
map_sbjct.Expand()
alignlib_lite.py_combineAlignata(tmp,
self.mMapQuery2Sbjct,
map_sbjct.mMapQuery2Sbjct,
alignlib_lite.py_CR)
map_sbjct.Clear()
alignlib_lite.py_copyAlignata(self.mMapQuery2Sbjct, tmp)
self.mSbjctToken = map_sbjct.mSbjctToken
self.Contract()
return self.IsOk()
def MapRange(self, query_token, query_from, query_to):
"""map something."""
map_query2sbjct = alignlib_lite.py_makeAlignataVector()
alignlib_lite.py_fillAlignataCompressed(map_query2sbjct,
self.mQueryFrom, self.mQueryAli,
self.mSbjctFrom, self.mSbjctAli)
new_from = 0
if query_from <= map_query2sbjct.getRowTo():
x = max(query_from, self.mQueryFrom)
while map_query2sbjct.mapRowToCol(x) == 0:
x += 1
if x > map_query2sbjct.getRowTo():
break
else:
new_from = map_query2sbjct.mapRowToCol(x)
new_to = 0
if query_to >= map_query2sbjct.getRowFrom():
x = min(query_to, self.mQueryTo)
while map_query2sbjct.mapRowToCol(x) == 0:
x -= 1
if x < map_query2sbjct.getRowFrom():
break
else:
new_to = map_query2sbjct.mapRowToCol(x)
return self.mSbjctToken, new_from, new_to
def Expand(self):
if not self.mIsExpanded:
self.mMapQuery2Sbjct = alignlib_lite.py_makeAlignataVector()
alignlib_lite.py_fillAlignataCompressed(self.mMapQuery2Sbjct,
self.mQueryFrom, self.mQueryAli,
self.mSbjctFrom, self.mSbjctAli)
self.mIsExpanded = True
def MapAlignment(self, map_query=None, map_sbjct=None):
self.Expand()
tmp = alignlib_lite.py_makeAlignataVector()
if map_query:
tmp.Clear()
map_query.Expand()
alignlib_lite.py_combineAlignata(tmp,
map_query.mMapQuery2Sbjct,
self.mMapQuery2Sbjct,
alignlib_lite.py_RR)
map_query.Clear()
alignlib_lite.py_copyAlignata(self.mMapQuery2Sbjct, tmp)
self.mQueryToken = map_query.mSbjctToken
if map_sbjct:
tmp.Clear()
map_sbjct.Expand()
alignlib_lite.py_combineAlignata(tmp,
self.mMapQuery2Sbjct,
map_sbjct.mMapQuery2Sbjct,
alignlib_lite.py_CR)
map_sbjct.Clear()
alignlib_lite.py_copyAlignata(self.mMapQuery2Sbjct, tmp)
self.mSbjctToken = map_sbjct.mSbjctToken
self.Contract()
return self.IsOk()
def MapRange(self, query_token, query_from, query_to):
"""map something."""
map_query2sbjct = alignlib_lite.py_makeAlignataVector()
alignlib_lite.py_fillAlignataCompressed(map_query2sbjct,
self.mQueryFrom, self.mQueryAli,
self.mSbjctFrom, self.mSbjctAli)
new_from = 0
if query_from <= map_query2sbjct.getRowTo():
x = max(query_from, self.mQueryFrom)
while map_query2sbjct.mapRowToCol(x) == 0:
x += 1
if x > map_query2sbjct.getRowTo():
break
else:
new_from = map_query2sbjct.mapRowToCol(x)
new_to = 0
if query_to >= map_query2sbjct.getRowFrom():
x = min(query_to, self.mQueryTo)
while map_query2sbjct.mapRowToCol(x) == 0:
x -= 1
if x < map_query2sbjct.getRowFrom():
break
else:
new_to = map_query2sbjct.mapRowToCol(x)
return self.mSbjctToken, new_from, new_to
def GetClone( self ):
"""get copy of self.
"""
m = Map()
(m.mQueryToken, m.mSbjctToken, m.mEvalue,
m.mQueryFrom, m.mQueryTo, m.mQueryAli,
m.mSbjctFrom, m.mSbjctTo, m.mSbjctAli,
m.mIsExpanded) = \
(self.mQueryToken, self.mSbjctToken, self.mEvalue,
self.mQueryFrom, self.mQueryTo, self.mQueryAli,
self.mSbjctFrom, self.mSbjctTo, self.mSbjctAli,
self.mIsExpanded)
if self.mIsExpanded:
m.mMapQuery2Sbjct = alignlib_lite.py_makeAlignataVector()
alignlib_lite.py_copyAlignata( m.mMapQuery2Sbjct, self.mMapQuery2Sbjct )
return m
def getMapFromMali(seq1, seq2, gap_char="-"):
"""build map of positions between mali."""
xpos = 0
ypos = 0
map_a2b = alignlib_lite.py_makeAlignataVector()
# build map between genomic sequences:
for p in range(len(seq1)):
if seq1[p] != gap_char and \
seq2[p] != gap_char and \
seq1[p] in string.uppercase and \
seq2[p] in string.uppercase:
map_a2b.addPairExplicit(xpos + 1, ypos + 1, 0)
if seq1[p] != gap_char:
xpos += 1
if seq2[p] != gap_char:
ypos += 1
return map_a2b
def getMapFromMali(seq1, seq2, gap_char="-"):
"""build map of positions between mali."""
xpos = 0
ypos = 0
map_a2b = alignlib_lite.py_makeAlignataVector()
# build map between genomic sequences:
for p in range(len(seq1)):
if seq1[p] != gap_char and \
seq2[p] != gap_char and \
seq1[p] in string.uppercase and \
seq2[p] in string.uppercase:
map_a2b.addPairExplicit(xpos + 1, ypos + 1, 0)
if seq1[p] != gap_char:
xpos += 1
if seq2[p] != gap_char:
ypos += 1
return map_a2b
print "master alignment does no exist in the alignment."
print globals()["__doc__"]
sys.exit(1)
master_from, master_ali, master_to, master_id = lines[param_master]
print "# master=", master_id
for index in range(len(lines)):
if param_master == index:
continue
sbjct_from, sbjct_ali, sbjct_to, sbjct_id = lines[index]
print "#", sbjct_id
map_master2sbjct = alignlib_lite.py_makeAlignataVector()
sbjct_index = string.atoi(sbjct_from)
master_index = string.atoi(master_from)
map_sbjct2residue = {}
for x in range(len(master_ali)):
if master_ali[x] not in GAPCHARS and sbjct_ali[x] not in GAPCHARS:
map_master2sbjct.addPairExplicit(master_index, sbjct_index, 0)
map_sbjct2residue[sbjct_index] = sbjct_ali[x]
if master_ali[x] not in GAPCHARS:
master_index += 1
def main( argv = None ):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser( version = "%prog version: $Id: blast2fasta.py 2782 2009-09-10 11:40:29Z andreas $",
usage = globals()["__doc__"] )
parser.add_option("-s", "--sequences", dest="filename_sequences", type="string",
help="filename with sequences." )
parser.add_option("-f", "--format", dest="format", type="string",
help="output format." )
parser.set_defaults(
filename_sequences = None,
format = "fasta",
)
(options, args) = E.Start( parser )
if not options.filename_sequences:
raise "please supply filename with sequences."
sequences = Genomics.ReadPeptideSequences( open(options.filename_sequences, "r") )
if options.loglevel >= 1:
print "# read %i sequences" % len(sequences)
for k in sequences.keys():
sequences[k] = alignlib_lite.py_makeSequence( sequences[k] )
if options.loglevel >= 2:
print "# converted %i sequences" % len(sequences)
ninput, noutput, nskipped, nfailed = 0, 0, 0, 0
link = BlastAlignments.Link()
ali = alignlib_lite.py_makeAlignataVector()
for line in sys.stdin:
if line[0] == "#": continue
link.Read( line )
ninput += 1
if link.mQueryToken not in sequences or link.mSbjctToken not in sequences:
nskipped += 1
continue
ali.Clear()
alignlib_lite.py_fillAlignataCompressed( ali, link.mQueryFrom, link.mQueryAli, link.mSbjctFrom, link.mSbjctAli )
result = alignlib_lite.py_writePairAlignment( sequences[link.mQueryToken], sequences[link.mSbjctToken], ali ).split("\n")
if len(result) != 3:
nfailed += 1
if options.format == "fasta":
print ">%s %i-%i\n%s\n>%s %i-%i\n%s\n" %\
(link.mQueryToken, link.mQueryFrom, link.mQueryTo, result[0].split("\t")[1],
link.mSbjctToken, link.mSbjctFrom, link.mSbjctTo, result[1].split("\t")[1] )
noutput += 1
E.info( "ninput=%i, noutput=%i, nskipped=%i, nfailed=%i" % (ninput, noutput, nskipped, nfailed) )
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: sequences2mali.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-i",
"--input-format",
dest="input_format",
type="choice",
choices=("plain", "fasta", "clustal", "stockholm",
"phylip"),
help="input format of multiple alignment")
parser.add_option("-o",
"--output-format",
dest="output_format",
type="choice",
choices=("plain", "fasta", "stockholm", "phylip"),
help="output format of multiple alignment")
parser.add_option("-m",
"--method",
dest="method",
type="choice",
choices=("add", ),
help="""method to use to build multiple alignment.""")
parser.add_option("-p",
"--parameters",
dest="parameters",
type="string",
help="parameter stack for methods that require one.")
parser.add_option("-a",
"--alignment-method",
dest="alignment_method",
type="choice",
choices=("sw", "nw"),
help="alignment_method [%default].")
parser.set_defaults(
input_format="fasta",
output_format="fasta",
method=None,
parameters="",
gop=-10.0,
gep=-1.0,
alignment_method="sw",
)
(options, args) = E.Start(parser)
options.parameters = options.parameters.split(",")
iterator = FastaIterator.iterate(sys.stdin)
if options.method == "add":
mali = Mali.Mali()
mali.readFromFile(open(options.parameters[0], "r"),
format=options.input_format)
del options.parameters[0]
old_length = mali.getLength()
new_mali = convertMali2Mali(mali)
if options.alignment_method == "sw":
alignator = alignlib_lite.py_makeAlignatorFullDP(
options.gop, options.gep)
else:
alignator = alignlib_lite.py_makeAlignatorFullDPGlobal(
options.gop, options.gep)
while 1:
cur_record = iterator.next()
if cur_record is None: break
map_mali2seq = alignlib_lite.py_makeAlignataVector()
sequence = alignlib_lite.py_makeSequence(cur_record.sequence)
profile = alignlib_lite.py_makeProfileFromMali(new_mali)
if options.loglevel >= 4:
options.stdlog.write(profile.Write())
alignator.Align(profile, sequence, map_mali2seq)
if options.loglevel >= 3:
options.stdlog.write(map_mali2seq.Write())
## add sequence to mali
a = alignlib_lite.py_makeAlignatumFromString(cur_record.sequence)
a.thisown = 0
new_mali.addAlignatum(a, map_mali2seq, 1, 1, 1, 1, 1)
id = cur_record.title
mali.mIdentifiers.append(id)
mali.mMali[id] = Mali.AlignedString(
id, 0, len(cur_record.sequence),
new_mali.getRow(new_mali.getWidth() - 1).getString())
# substitute
for x in range(old_length):
mali.mMali[mali.mIdentifiers[x]].mString = new_mali.getRow(
x).getString()
mali.writeToFile(sys.stdout, format=options.output_format)
E.Stop()
def main(argv=None):
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: align_all_vs_all.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-s",
"--sequences",
dest="filename_sequences",
type="string",
help="input file with sequences")
parser.set_defaults(
filename_sequences=None,
gop=-10.0,
gep=-1.0,
)
(options, args) = E.Start(parser, add_pipe_options=True)
if options.filename_sequences:
infile = open(options.filename_sequences, "r")
else:
infile = sys.stdin
parser = FastaIterator.FastaIterator(infile)
sequences = []
while 1:
cur_record = iterator.next()
if cur_record is None:
break
sequences.append(
(cur_record.title,
alignlib_lite.py_makeSequence(re.sub(" ", "",
cur_record.sequence))))
if options.filename_sequences:
infile.close()
alignator = alignlib_lite.py_makeAlignatorFullDP(options.gop, options.gep)
map_a2b = alignlib_lite.py_makeAlignataVector()
nsequences = len(sequences)
for x in range(0, nsequences - 1):
for y in range(x + 1, nsequences):
alignator.Align(sequences[x][1], sequences[y][1], map_a2b)
row_ali, col_ali = alignlib_lite.py_writeAlignataCompressed(
map_a2b)
options.stdout.write(
"%s\t%s\t%i\t%i\t%i\t%s\t%i\t%i\t%s\t%i\t%i\t%i\t%i\n" %
(sequences[x][0], sequences[y][0], map_a2b.getScore(),
map_a2b.getRowFrom(), map_a2b.getRowTo(), row_ali,
map_a2b.getColFrom(), map_a2b.getColTo(), col_ali,
map_a2b.getScore(),
100 * alignlib_lite.py_calculatePercentIdentity(
map_a2b, sequences[x][1], sequences[y][1]),
sequences[x][1].getLength(), sequences[y][1].getLength()))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv == None: argv = sys.argv
parser = E.OptionParser(
version=
"%prog version: $Id: blast2fasta.py 2782 2009-09-10 11:40:29Z andreas $",
usage=globals()["__doc__"])
parser.add_option("-s",
"--sequences",
dest="filename_sequences",
type="string",
help="filename with sequences.")
parser.add_option("-f",
"--format",
dest="format",
type="string",
help="output format.")
parser.set_defaults(
filename_sequences=None,
format="fasta",
)
(options, args) = E.Start(parser)
if not options.filename_sequences:
raise "please supply filename with sequences."
sequences = Genomics.ReadPeptideSequences(
open(options.filename_sequences, "r"))
if options.loglevel >= 1:
print "# read %i sequences" % len(sequences)
for k in sequences.keys():
sequences[k] = alignlib_lite.py_makeSequence(sequences[k])
if options.loglevel >= 2:
print "# converted %i sequences" % len(sequences)
ninput, noutput, nskipped, nfailed = 0, 0, 0, 0
link = BlastAlignments.Link()
ali = alignlib_lite.py_makeAlignataVector()
for line in sys.stdin:
if line[0] == "#": continue
link.Read(line)
ninput += 1
if link.mQueryToken not in sequences or link.mSbjctToken not in sequences:
nskipped += 1
continue
ali.Clear()
alignlib_lite.py_fillAlignataCompressed(ali, link.mQueryFrom,
link.mQueryAli,
link.mSbjctFrom,
link.mSbjctAli)
result = alignlib_lite.py_writePairAlignment(
sequences[link.mQueryToken], sequences[link.mSbjctToken],
ali).split("\n")
if len(result) != 3:
nfailed += 1
if options.format == "fasta":
print ">%s %i-%i\n%s\n>%s %i-%i\n%s\n" %\
(link.mQueryToken, link.mQueryFrom, link.mQueryTo, result[0].split("\t")[1],
link.mSbjctToken, link.mSbjctFrom, link.mSbjctTo, result[1].split("\t")[1] )
noutput += 1
E.info("ninput=%i, noutput=%i, nskipped=%i, nfailed=%i" %
(ninput, noutput, nskipped, nfailed))
E.Stop()
def main(argv=None):
"""script main.
parses command line options in sys.argv, unless *argv* is given.
"""
if argv is None:
argv = sys.argv
parser = E.OptionParser(
version="%prog version: $Id: sequences2mali.py 2782 2009-09-10 11:40:29Z andreas $", usage=globals()["__doc__"])
parser.add_option("-i", "--input-format", dest="input_format", type="choice",
choices=(
"plain", "fasta", "clustal", "stockholm", "phylip"),
help="input format of multiple alignment")
parser.add_option("-o", "--output-format", dest="output_format", type="choice",
choices=("plain", "fasta", "stockholm", "phylip"),
help="output format of multiple alignment")
parser.add_option("-m", "--method", dest="method", type="choice",
choices=("add",),
help="""method to use to build multiple alignment.""")
parser.add_option("-p", "--parameters", dest="parameters", type="string",
help="parameter stack for methods that require one.")
parser.add_option("-a", "--alignment-method", dest="alignment_method", type="choice",
choices=("sw", "nw"),
help="alignment_method [%default].")
parser.set_defaults(
input_format="fasta",
output_format="fasta",
method=None,
parameters="",
gop=-10.0,
gep=-1.0,
alignment_method="sw",
)
(options, args) = E.Start(parser)
options.parameters = options.parameters.split(",")
iterator = FastaIterator.iterate(sys.stdin)
if options.method == "add":
mali = Mali.Mali()
mali.readFromFile(
open(options.parameters[0], "r"), format=options.input_format)
del options.parameters[0]
old_length = mali.getLength()
new_mali = convertMali2Mali(mali)
if options.alignment_method == "sw":
alignator = alignlib_lite.py_makeAlignatorFullDP(
options.gop, options.gep)
else:
alignator = alignlib_lite.py_makeAlignatorFullDPGlobal(
options.gop, options.gep)
while 1:
cur_record = iterator.next()
if cur_record is None:
break
map_mali2seq = alignlib_lite.py_makeAlignataVector()
sequence = alignlib_lite.py_makeSequence(cur_record.sequence)
profile = alignlib_lite.py_makeProfileFromMali(new_mali)
if options.loglevel >= 4:
options.stdlog.write(profile.Write())
alignator.Align(profile, sequence, map_mali2seq)
if options.loglevel >= 3:
options.stdlog.write(map_mali2seq.Write())
# add sequence to mali
a = alignlib_lite.py_makeAlignatumFromString(cur_record.sequence)
a.thisown = 0
new_mali.addAlignatum(a, map_mali2seq, 1, 1, 1, 1, 1)
id = cur_record.title
mali.mIdentifiers.append(id)
mali.mMali[id] = Mali.AlignedString(id, 0, len(
cur_record.sequence), new_mali.getRow(new_mali.getWidth() - 1).getString())
# substitute
for x in range(old_length):
mali.mMali[mali.mIdentifiers[x]].mString = new_mali.getRow(
x).getString()
mali.writeToFile(sys.stdout, format=options.output_format)
E.Stop()
print "master alignment does no exist in the alignment."
print globals()["__doc__"]
sys.exit(1)
master_from, master_ali, master_to, master_id = lines[param_master]
print "# master=", master_id
for index in range(len(lines)):
if param_master == index:
continue
sbjct_from, sbjct_ali, sbjct_to, sbjct_id = lines[index]
print "#", sbjct_id
map_master2sbjct = alignlib_lite.py_makeAlignataVector()
sbjct_index = string.atoi(sbjct_from)
master_index = string.atoi(master_from)
map_sbjct2residue = {}
for x in range(len(master_ali)):
if master_ali[x] not in GAPCHARS and sbjct_ali[x] not in GAPCHARS:
map_master2sbjct.addPairExplicit(master_index, sbjct_index, 0)
map_sbjct2residue[sbjct_index] = sbjct_ali[x]
if master_ali[x] not in GAPCHARS:
master_index += 1
def main( argv = None ):
if argv == None: argv = sys.argv
parser = E.OptionParser( version = "%prog version: $Id: align_all_vs_all.py 2782 2009-09-10 11:40:29Z andreas $",
usage = globals()["__doc__"] )
parser.add_option("-s", "--sequences", dest="filename_sequences", type="string",
help="input file with sequences" )
parser.set_defaults(
filename_sequences = None,
gop = -10.0,
gep = -1.0,
)
(options, args) = E.Start( parser, add_pipe_options = True )
if options.filename_sequences:
infile = open(options.filename_sequences, "r")
else:
infile = sys.stdin
parser = FastaIterator.FastaIterator( infile )
sequences = []
while 1:
cur_record = iterator.next()
if cur_record is None: break
sequences.append( (cur_record.title, alignlib_lite.py_makeSequence(re.sub( " ", "", cur_record.sequence)) ) )
if options.filename_sequences:
infile.close()
alignator = alignlib_lite.py_makeAlignatorFullDP( options.gop, options.gep )
map_a2b = alignlib_lite.py_makeAlignataVector()
nsequences = len(sequences)
for x in range(0,nsequences-1):
for y in range(x+1, nsequences):
alignator.Align( sequences[x][1], sequences[y][1], map_a2b)
row_ali, col_ali = alignlib_lite.py_writeAlignataCompressed( map_a2b )
options.stdout.write( "%s\t%s\t%i\t%i\t%i\t%s\t%i\t%i\t%s\t%i\t%i\t%i\t%i\n" % (\
sequences[x][0], sequences[y][0],
map_a2b.getScore(),
map_a2b.getRowFrom(),
map_a2b.getRowTo(),
row_ali,
map_a2b.getColFrom(),
map_a2b.getColTo(),
col_ali,
map_a2b.getScore(),
100 * alignlib_lite.py_calculatePercentIdentity( map_a2b, sequences[x][1], sequences[y][1]),
sequences[x][1].getLength(),
sequences[y][1].getLength() ))
E.Stop()