def tap(iX, iY):
"""[点击手势]
[点击屏幕上某个点坐标]
Args:
iX ([int]): [点击的坐标x]
iY ([int]): [点击的坐标y]
"""
osPopen('adb %s shell input tap %d %d' % (get_devices_str(), iX, iY))
return
def move(iStartX, iStartY, iEndX, iEndY, dura=800):
"""[滑动手势,从起点滑动到终点]
Args:
iStartX ([int]): [开始坐标x]
iStartY ([int]): [开始坐标y]
iEndX ([int]): [终点坐标x]
iEndY ([int]): [终点坐标y]
dura (int, optional): [滑动时长ms]. Defaults to 800ms.
"""
osPopen('adb %s shell input swipe %d %d %d %d %d' %
(get_devices_str(), iStartX, iStartY, iEndX, iEndY, dura))
return
def scan_polypyrimidines(self):
""" """
intronseq = self.dnasequence()
co = osPopen(""" echo ">intron\n%s\n" | %s %s """ % (
intronseq,PYTHON_PATH,EXECUTABE_SCAN_POLYPYRIMIDINES ) )
gfflines = parsegfftxt( co.read(), offset=self.start )
co.close()
return gfflines
def _parse_cexpander_string(fname, verbose=False):
"""
@attention: deprecated function, not used in any of the functions above
"""
command = """ cat %s | grep "\$start_values" -A 1000 | grep "\$end_values" -m 1 -B 1000 | sed 's/^.*_values$//' | sed '/^$/d' | tr -d "\\t" | tr -d "\\n" """ % fname
if verbose: print command
co = osPopen(command)
cexpanderstring = co.read().strip()
co.close()
return cexpanderstring
def _parse_cexpander_string(fname,verbose=False):
"""
@attention: deprecated function, not used in any of the functions above
"""
command = """ cat %s | grep "\$start_values" -A 1000 | grep "\$end_values" -m 1 -B 1000 | sed 's/^.*_values$//' | sed '/^$/d' | tr -d "\\t" | tr -d "\\n" """ % fname
if verbose: print command
co = osPopen(command)
cexpanderstring = co.read().strip()
co.close()
return cexpanderstring
def WAS_scan_branchpoint(self):
""" """
intronseq = self.dnasequence()
co = osPopen(""" echo ">intron\n%s\n" | %s %s """ % (
intronseq,EXECUTABE_SCAN_BRANCHPOINT, EXECUTABLE_SFM ) )
gfflines = parsegfftxt( co.read(), offset=self.start )
co.close()
orderable = [ ( int(line[3]), line ) for line in gfflines ]
orderable.sort()
orderable.reverse()
return [ gffline for pos,gffline in orderable ]
def getConnectedDevices():
"""[获取当前已连接的设备]
Returns:
[list]: [设备列表]
"""
connected = []
osPopen('adb devices > t.txt')
with open('t.txt') as f:
lines = f.read().splitlines()
lines.remove(lines[-1])
lines.remove(lines[0])
for i in lines:
a = str(i).partition('\tdevic')[0]
connected.append(a)
osOs.remove('t.txt')
print(connected)
try:
return connected
except:
return
def ligtPhone():
osPopen('adb %s shell input keyevent 224' % (get_devices_str()))
def vmSize():
sVmSize = osPopen('adb shell wm size').read()
aVmSize = osRe.search(r'(\d+)x(\d+)', sVmSize)
return {'w': aVmSize.group(1), 'h': aVmSize.group(2)}
def closeApp(sVal):
osPopen('adb %s shell am force-stop %s' % (get_devices_str(), sVal))
def callApp(sVal):
osPopen('adb %s shell am start -D -S -n %s' % (get_devices_str(), sVal))
def backKey():
"""[返回键]
"""
osPopen('adb %s shell input keyevent 4' % (get_devices_str()))
return
def keyCode(number):
osPopen('adb %s shell input keyevent %d' % (get_devices_str(), number))
def closePhone():
osPopen('adb %s shell reboot -p' % (get_devices_str()))
def rebootPhone():
osPopen('adb %s reboot -p' % (get_devices_str()))
def closeScreen():
osPopen('adb %s shell input keyevent 26' % (get_devices_str()))
def screen_brightness_mod(isAuto=1):
osPopen('adb %s shell settings put system screen_brightness_mode %d' %
(get_devices_str(), isAuto))
def screen_brightness(iLen=255):
osPopen('adb %s shell settings put system screen_brightness %d ' %
(get_devices_str(), iLen))
def _merge_pacbporfs_by_tinyexon_and_two_introns(pacbporfD,pacbporfA,
orfSetObject,queryorsbjct,verbose = False, **kwargs):
"""
Merge 2 PacbPORF objects by introns
@attention: see pacb.connecting.merge_orfs_with_intron for **kwargs)
@type pacbporfD: PacbPORF object
@param pacbporfD: PacbPORF object that has to deliver PSSM donor objects
@type pacbporfA: PacbPORF object
@param pacbporfA: PacbPORF object that has to deliver PSSM acceptor objects
@type orfSetObject: object with elegiable Orfs
@param orfSetObject: object with elegiable Orfs
@type queryorsbjct: string
@param queryorsbjct: literal string 'query' or 'sbjct'
@type verbose: Boolean
@param verbose: print debugging info to STDOUT when True
@rtype: list
@return: list with ( intron, ExonOnOrf, intron ) on the query sequence
"""
# input validation
IsPacbPORF(pacbporfD)
IsPacbPORF(pacbporfA)
# edit **kwargs dictionary for some forced attributes
_update_kwargs(kwargs,KWARGS_PROJECTED_TINYEXON)
MAX_TINYEXON_NT_LENGTH = 33
MIN_TINYEXON_NT_LENGTH = 6
tinyexons = []
if queryorsbjct == "query":
donorOrf = pacbporfD.orfQ
accepOrf = pacbporfA.orfQ
prjctOrf = pacbporfD.orfS
alignedDonorRange = pacbporfD.alignment_dna_range_query()
alignedAccepRange = pacbporfA.alignment_dna_range_query()
elif queryorsbjct == "sbjct":
donorOrf = pacbporfD.orfS
accepOrf = pacbporfA.orfS
prjctOrf = pacbporfD.orfQ
alignedDonorRange = pacbporfD.alignment_dna_range_sbjct()
alignedAccepRange = pacbporfA.alignment_dna_range_sbjct()
else:
message = "'queryorsbjct' (%s), not 'query' or 'sbjct'" % queryorsbjct
raise InproperlyAppliedArgument, message
for dObj in donorOrf._donor_sites:
# do not make a projection OVER the aligned area
if dObj.pos < min(alignedDonorRange): continue
if queryorsbjct == "query":
(dPos,dPhase) = pacbporfD.dnaposition_query(dObj.pos,forced_return=True)
else:
(dPos,dPhase) = pacbporfD.dnaposition_sbjct(dObj.pos,forced_return=True)
try:
algDobj = pacbporfD._positions[dPos]
except IndexError:
# site out of range of PacbPORF -> break
break
for aObj in accepOrf._acceptor_sites:
# do not make a projection OVER the aligned area
if aObj.pos > max(alignedAccepRange): continue
if queryorsbjct == "query":
(aPos,aPhase) = pacbporfA.dnaposition_query(aObj.pos,forced_return=True)
else:
(aPos,aPhase) = pacbporfA.dnaposition_sbjct(aObj.pos,forced_return=True)
try:
algAobj = pacbporfA._positions[aPos]
except IndexError:
# site out of range of PacbPORF -> break
break
if queryorsbjct == "query":
posDsbjct = algDobj.sbjct_dna_start + dPhase
posAsbjct = algAobj.sbjct_dna_start + aPhase
else:
posDsbjct = algDobj.query_dna_start + dPhase
posAsbjct = algAobj.query_dna_start + aPhase
distance = posAsbjct - posDsbjct
if distance >= MAX_TINYEXON_NT_LENGTH:
break
if distance < MIN_TINYEXON_NT_LENGTH:
continue
####################################################
# generate a ScanForMatches pattern file
####################################################
# example pattern: 6...6 AG NNGNNANNANNGN[2,0,0] GT 3...3
query = list(prjctOrf.inputgenomicsequence[posDsbjct:posAsbjct])
# mask all non-phase0 nucleotides to N residues;
# this represents the regularexpression for a specific
# peptide sequence
firstphasepositions = range( 3-dPhase % 3, len(query), 3)
for pos in range(0,len(query)):
if pos not in firstphasepositions:
query[pos] = "N"
# calculate a ~50% mismatch number
mismatches = max([ 0, (len(query) - query.count("N"))/2 ])
# write the pattern to string and subsequently to file
# example pattern: 6...6 AG NNGNNANNANNGN[2,0,0] GT 3...3
if kwargs['allow_non_canonical_donor']:
sfmpat = "%s...%s AG %s[%s,0,0] G (T | C) %s...%s" % (
AUSO,AUSO,"".join(query),mismatches,DDSO,DDSO)
else:
sfmpat = "%s...%s AG %s[%s,0,0] GT %s...%s" % (
AUSO,AUSO,"".join(query),mismatches,DDSO,DDSO)
####################################################
if verbose:
print (pacbporfD.orfQ.id,pacbporfA.orfQ.id),
print distance, dObj, aObj
print sfmpat
####################################################
fname = "sfmpat_tinyexon_%s_%s_%s_%s" % (
donorOrf.id,
accepOrf.id,
posDsbjct,
posAsbjct,
)
fh = open(fname,'w')
fh.write(sfmpat+"\n")
fh.close()
####################################################
# run ScanForMatches
####################################################
command = """echo ">myseq\n%s" | %s %s | tr "[,]" "\t\t#" | """ +\
"""tr -d "\n " | sed "s/>/\\n>/g" | tr "#" "\t" | """ +\
"""awk -F'\t' '{ if (NF==4 && $2>%s && $3<%s) """ +\
"""{ print $1"["$2","$3"]\\n"$4 } }' """
command = command % (
donorOrf.inputgenomicsequence,
EXECUTABLE_SFM,fname,
dObj.pos+(kwargs['min_intron_nt_length']-3),
aObj.pos-(kwargs['min_intron_nt_length']-3) )
co = osPopen(command)
matches = parseFasta(co.readlines())
co.close()
# filter matches for:
# (1) correct donor & acceptor phase
# (2) high enough donor & acceptor site scores
for hdr,seqmatch in matches.iteritems():
startQ,stopQ = [ int(item) for item in hdr.split(":")[1][1:-1].split(",") ]
exonQstart = startQ + AUSO + 2 - 1
exonQstop = stopQ - DDSO - 2
####################################
# get Orf object of tinyexon
####################################
tinyexonorf = None
# select the Orf on which the tinyexon is located
for orfObj in orfSetObject.get_elegiable_orfs(
max_orf_start=exonQstart,min_orf_end=exonQstop):
orfPhase = (exonQstart - orfObj.startPY) % 3
if orfPhase == dPhase:
tinyexonorf = orfObj
break
else:
# No tinyexonorf assigned!! Iin case a regex matched
# over a STOP-codon or the regex length is smaller
# then the smallest Orf, no Orf can be assigned
continue
# filter for donor & acceptor score
dScore = _score_splice_site(seqmatch[-9:],splicetype='donor')
aScore = _score_splice_site(seqmatch[0:11],splicetype='acceptor')
if dScore < kwargs['min_donor_pssm_score']:
continue
if aScore < kwargs['min_acceptor_pssm_score']:
continue
# scan Orf for splicesites
tinyexonorf.scan_orf_for_pssm_splice_sites(
splicetype="donor",
min_pssm_score=kwargs['min_donor_pssm_score'],
allow_non_canonical=kwargs['allow_non_canonical_donor'],
non_canonical_min_pssm_score=kwargs['non_canonical_min_donor_pssm_score'])
tinyexonorf.scan_orf_for_pssm_splice_sites(
splicetype="acceptor",
min_pssm_score=kwargs['min_acceptor_pssm_score'],
allow_non_canonical=kwargs['allow_non_canonical_acceptor'],
non_canonical_min_pssm_score=kwargs['non_canonical_min_acceptor_pssm_score'])
# get 1th intron donor object
intron1_aObj = None
for a in tinyexonorf._acceptor_sites:
if a.pos == exonQstart:
intron1_aObj = a
break
else:
# pseudo-acceptorsite as found be SFM regex
# is not a valid acceptor site of high enough score
# continue to next iteration of (hdr,seqmatch) pair
continue
# get 2th intron donor object
intron2_dObj = None
for d in tinyexonorf._donor_sites:
if d.pos == exonQstop:
intron2_dObj = d
break
else:
# pseudo-donorsite as found be SFM regex
# is not a valid acceptor site of high enough score
# continue to next iteration of (hdr,seqmatch) pair
continue
# check if introns are of elegiable lengths
if (intron1_aObj.pos-dObj.pos) > kwargs['max_intron_nt_length']:
continue
if (aObj.pos-intron2_dObj.pos) > kwargs['max_intron_nt_length']:
continue
####################################################
if True or verbose:
# if here, a candidate!!!
print (pacbporfD.orfQ.id,tinyexonorf.id,pacbporfA.orfQ.id),
print hdr, dScore, aScore
print seqmatch
####################################################
# append to found tinyexons
query_data = ( tinyexonorf, exonQstart, exonQstop )
sbjct_data = ( prjctOrf, posDsbjct, posAsbjct )
splicesite_data = ( dObj,intron1_aObj, intron2_dObj, aObj )
tinyexons.append( ( query_data, sbjct_data, splicesite_data ) )
# file cleanup
osRemove(fname)
# return - End Of Function - if no tinyexons are found
if not tinyexons:
return []
####################################
# select the **best** tinyexon
####################################
(query_data,sbjct_data,splicesite_data) = tinyexons[0]
orfQ,query_dna_start,query_dna_end = query_data
orfS,sbjct_dna_start,sbjct_dna_end = sbjct_data
(intron1_dObj,intron1_aObj,intron2_dObj,intron2_aObj) = splicesite_data
####################################################
if verbose:
print "tinyexon orf:", orfQ
print "tinyexon orf:", intron1_aObj
print "tinyexon orf:", intron2_dObj
####################################################
####################################
# make tinyexon PacbPORF
####################################
startQaa = orfQ.dnapos2aapos(query_dna_start) -1
startSaa = orfS.dnapos2aapos(sbjct_dna_start) -1
stopQaa = orfQ.dnapos2aapos(query_dna_end) +1
stopSaa = orfS.dnapos2aapos(sbjct_dna_end) +1
# check for directly leading stop codon on tinyexon
while startQaa <= orfQ.protein_startPY:
startQaa+=1
startSaa+=1
query_dna_start+=3
sbjct_dna_start+=3
while startSaa <= orfS.protein_startPY:
startQaa+=1
startSaa+=1
query_dna_start+=3
sbjct_dna_start+=3
# check for directly tailing stop codon on tinyexon
while stopQaa > orfQ.protein_endPY:
stopQaa-=1
stopSaa-=1
query_dna_end-=3
sbjct_dna_end-=3
while stopSaa > orfS.protein_endPY:
stopQaa-=1
stopSaa-=1
query_dna_end-=3
sbjct_dna_end-=3
# get sequences
qAAseq = orfQ.getaas(abs_pos_start=startQaa,abs_pos_end=stopQaa)
sAAseq = orfS.getaas(abs_pos_start=startSaa,abs_pos_end=stopSaa)
####################################################
if verbose or len(qAAseq) != len(sAAseq):
# if unequal lengths, error will be raised upon PacbP.__init__()
print orfQ, qAAseq, startQaa, stopQaa, (stopQaa-startQaa),
print (query_dna_start,query_dna_end)
print orfS, sAAseq, startSaa, stopSaa, (stopSaa-startSaa),
print (sbjct_dna_start,sbjct_dna_end)
print orfQ.inputgenomicsequence[query_dna_start-2:query_dna_end+2]
print orfS.inputgenomicsequence[sbjct_dna_start-2:sbjct_dna_end+2]
####################################################
# initialize extended tinyexon PacbPORF
from pacb import PacbP
pacbp = PacbP(input=( qAAseq, sAAseq, startQaa, startSaa ) )
pacbp.strip_unmatched_ends()
pacbporf = pacbp2pacbporf(pacbp,orfQ,orfS)
pacbporf.extend_pacbporf_after_stops()
pacbporf.source = 'ABGPprojectingTE'
####################################
# make introns
####################################
intron1 = IntronConnectingOrfs(
intron1_dObj, intron1_aObj, None,
donorOrf,pacbporf.orfQ )
intron2 = IntronConnectingOrfs(
intron2_dObj, intron2_aObj, None,
pacbporf.orfQ, accepOrf )
################################################################
# set some meta-data properties to the intron objects
################################################################
# add distance score to intron
intron1._distance = 0
intron2._distance = 0
# add Alignment Positional Periphery Score into objects
if queryorsbjct == "query":
succes = set_apps_intron_query(intron1,pacbporfD,pacbporf)
succes = set_apps_intron_query(intron2,pacbporf,pacbporfA)
else:
succes = set_apps_intron_sbjct(intron1,pacbporfD,pacbporf)
succes = set_apps_intron_sbjct(intron2,pacbporf,pacbporfA)
# set GFF fsource attribute for recognition of intron sources
intron1._gff['fsource'] = "ABGPprojectingTE"
intron2._gff['fsource'] = "ABGPprojectingTE"
# create _linked_to_xxx attributes
intron1._linked_to_pacbporfs = [ pacbporf ]
intron2._linked_to_pacbporfs = [ pacbporf ]
intron1._linked_to_introns = [ intron2 ]
intron2._linked_to_introns = [ intron1 ]
####################################################
if verbose:
print pacbporf
pacbporf.print_protein_and_dna()
print intron1
print intron2
if False:
# printing data when this function needs to be debugged:
print ""
print intron1
print intron2
print ""
print pacbporfD
pacbporfD.print_protein_and_dna()
print ""
print pacbporf
pacbporf.print_protein_and_dna()
print ""
print pacbporfA
pacbporfA.print_protein_and_dna()
import sys
sys.exit()
####################################################
# return introns and intermediate tinyexon PacbPORF
return [(intron1,intron2,pacbporf)]
def _merge_pacbporfs_by_tinyexon_and_two_introns(pacbporfD,
pacbporfA,
orfSetObject,
queryorsbjct,
verbose=False,
**kwargs):
"""
Merge 2 PacbPORF objects by introns
@attention: see pacb.connecting.merge_orfs_with_intron for **kwargs)
@type pacbporfD: PacbPORF object
@param pacbporfD: PacbPORF object that has to deliver PSSM donor objects
@type pacbporfA: PacbPORF object
@param pacbporfA: PacbPORF object that has to deliver PSSM acceptor objects
@type orfSetObject: object with elegiable Orfs
@param orfSetObject: object with elegiable Orfs
@type queryorsbjct: string
@param queryorsbjct: literal string 'query' or 'sbjct'
@type verbose: Boolean
@param verbose: print debugging info to STDOUT when True
@rtype: list
@return: list with ( intron, ExonOnOrf, intron ) on the query sequence
"""
# input validation
IsPacbPORF(pacbporfD)
IsPacbPORF(pacbporfA)
# edit **kwargs dictionary for some forced attributes
_update_kwargs(kwargs, KWARGS_PROJECTED_TINYEXON)
MAX_TINYEXON_NT_LENGTH = 33
MIN_TINYEXON_NT_LENGTH = 6
tinyexons = []
if queryorsbjct == "query":
donorOrf = pacbporfD.orfQ
accepOrf = pacbporfA.orfQ
prjctOrf = pacbporfD.orfS
alignedDonorRange = pacbporfD.alignment_dna_range_query()
alignedAccepRange = pacbporfA.alignment_dna_range_query()
elif queryorsbjct == "sbjct":
donorOrf = pacbporfD.orfS
accepOrf = pacbporfA.orfS
prjctOrf = pacbporfD.orfQ
alignedDonorRange = pacbporfD.alignment_dna_range_sbjct()
alignedAccepRange = pacbporfA.alignment_dna_range_sbjct()
else:
message = "'queryorsbjct' (%s), not 'query' or 'sbjct'" % queryorsbjct
raise InproperlyAppliedArgument, message
for dObj in donorOrf._donor_sites:
# do not make a projection OVER the aligned area
if dObj.pos < min(alignedDonorRange): continue
if queryorsbjct == "query":
(dPos, dPhase) = pacbporfD.dnaposition_query(dObj.pos,
forced_return=True)
else:
(dPos, dPhase) = pacbporfD.dnaposition_sbjct(dObj.pos,
forced_return=True)
try:
algDobj = pacbporfD._positions[dPos]
except IndexError:
# site out of range of PacbPORF -> break
break
for aObj in accepOrf._acceptor_sites:
# do not make a projection OVER the aligned area
if aObj.pos > max(alignedAccepRange): continue
if queryorsbjct == "query":
(aPos,
aPhase) = pacbporfA.dnaposition_query(aObj.pos,
forced_return=True)
else:
(aPos,
aPhase) = pacbporfA.dnaposition_sbjct(aObj.pos,
forced_return=True)
try:
algAobj = pacbporfA._positions[aPos]
except IndexError:
# site out of range of PacbPORF -> break
break
if queryorsbjct == "query":
posDsbjct = algDobj.sbjct_dna_start + dPhase
posAsbjct = algAobj.sbjct_dna_start + aPhase
else:
posDsbjct = algDobj.query_dna_start + dPhase
posAsbjct = algAobj.query_dna_start + aPhase
distance = posAsbjct - posDsbjct
if distance >= MAX_TINYEXON_NT_LENGTH:
break
if distance < MIN_TINYEXON_NT_LENGTH:
continue
####################################################
# generate a ScanForMatches pattern file
####################################################
# example pattern: 6...6 AG NNGNNANNANNGN[2,0,0] GT 3...3
query = list(prjctOrf.inputgenomicsequence[posDsbjct:posAsbjct])
# mask all non-phase0 nucleotides to N residues;
# this represents the regularexpression for a specific
# peptide sequence
firstphasepositions = range(3 - dPhase % 3, len(query), 3)
for pos in range(0, len(query)):
if pos not in firstphasepositions:
query[pos] = "N"
# calculate a ~50% mismatch number
mismatches = max([0, (len(query) - query.count("N")) / 2])
# write the pattern to string and subsequently to file
# example pattern: 6...6 AG NNGNNANNANNGN[2,0,0] GT 3...3
if kwargs['allow_non_canonical_donor']:
sfmpat = "%s...%s AG %s[%s,0,0] G (T | C) %s...%s" % (
AUSO, AUSO, "".join(query), mismatches, DDSO, DDSO)
else:
sfmpat = "%s...%s AG %s[%s,0,0] GT %s...%s" % (
AUSO, AUSO, "".join(query), mismatches, DDSO, DDSO)
####################################################
if verbose:
print(pacbporfD.orfQ.id, pacbporfA.orfQ.id),
print distance, dObj, aObj
print sfmpat
####################################################
fname = "sfmpat_tinyexon_%s_%s_%s_%s" % (
donorOrf.id,
accepOrf.id,
posDsbjct,
posAsbjct,
)
fh = open(fname, 'w')
fh.write(sfmpat + "\n")
fh.close()
####################################################
# run ScanForMatches
####################################################
command = """echo ">myseq\n%s" | %s %s | tr "[,]" "\t\t#" | """ +\
"""tr -d "\n " | sed "s/>/\\n>/g" | tr "#" "\t" | """ +\
"""awk -F'\t' '{ if (NF==4 && $2>%s && $3<%s) """ +\
"""{ print $1"["$2","$3"]\\n"$4 } }' """
command = command % (donorOrf.inputgenomicsequence, EXECUTABLE_SFM,
fname, dObj.pos +
(kwargs['min_intron_nt_length'] - 3),
aObj.pos -
(kwargs['min_intron_nt_length'] - 3))
co = osPopen(command)
matches = parseFasta(co.readlines())
co.close()
# filter matches for:
# (1) correct donor & acceptor phase
# (2) high enough donor & acceptor site scores
for hdr, seqmatch in matches.iteritems():
startQ, stopQ = [
int(item) for item in hdr.split(":")[1][1:-1].split(",")
]
exonQstart = startQ + AUSO + 2 - 1
exonQstop = stopQ - DDSO - 2
####################################
# get Orf object of tinyexon
####################################
tinyexonorf = None
# select the Orf on which the tinyexon is located
for orfObj in orfSetObject.get_eligible_orfs(
max_orf_start=exonQstart, min_orf_end=exonQstop):
orfPhase = (exonQstart - orfObj.startPY) % 3
if orfPhase == dPhase:
tinyexonorf = orfObj
break
else:
# No tinyexonorf assigned!! Iin case a regex matched
# over a STOP-codon or the regex length is smaller
# then the smallest Orf, no Orf can be assigned
continue
# filter for donor & acceptor score
dScore = _score_splice_site(seqmatch[-9:], splicetype='donor')
aScore = _score_splice_site(seqmatch[0:11],
splicetype='acceptor')
if dScore < kwargs['min_donor_pssm_score']:
continue
if aScore < kwargs['min_acceptor_pssm_score']:
continue
# scan Orf for splicesites
tinyexonorf.scan_orf_for_pssm_splice_sites(
splicetype="donor",
min_pssm_score=kwargs['min_donor_pssm_score'],
allow_non_canonical=kwargs['allow_non_canonical_donor'],
non_canonical_min_pssm_score=kwargs[
'non_canonical_min_donor_pssm_score'])
tinyexonorf.scan_orf_for_pssm_splice_sites(
splicetype="acceptor",
min_pssm_score=kwargs['min_acceptor_pssm_score'],
allow_non_canonical=kwargs['allow_non_canonical_acceptor'],
non_canonical_min_pssm_score=kwargs[
'non_canonical_min_acceptor_pssm_score'])
# get 1th intron donor object
intron1_aObj = None
for a in tinyexonorf._acceptor_sites:
if a.pos == exonQstart:
intron1_aObj = a
break
else:
# pseudo-acceptorsite as found be SFM regex
# is not a valid acceptor site of high enough score
# continue to next iteration of (hdr,seqmatch) pair
continue
# get 2th intron donor object
intron2_dObj = None
for d in tinyexonorf._donor_sites:
if d.pos == exonQstop:
intron2_dObj = d
break
else:
# pseudo-donorsite as found be SFM regex
# is not a valid acceptor site of high enough score
# continue to next iteration of (hdr,seqmatch) pair
continue
# check if introns are of elegiable lengths
if (intron1_aObj.pos -
dObj.pos) > kwargs['max_intron_nt_length']:
continue
if (aObj.pos -
intron2_dObj.pos) > kwargs['max_intron_nt_length']:
continue
####################################################
if True or verbose:
# if here, a candidate!!!
print(pacbporfD.orfQ.id, tinyexonorf.id,
pacbporfA.orfQ.id),
print hdr, dScore, aScore
print seqmatch
####################################################
# append to found tinyexons
query_data = (tinyexonorf, exonQstart, exonQstop)
sbjct_data = (prjctOrf, posDsbjct, posAsbjct)
splicesite_data = (dObj, intron1_aObj, intron2_dObj, aObj)
tinyexons.append((query_data, sbjct_data, splicesite_data))
# file cleanup
osRemove(fname)
# return - End Of Function - if no tinyexons are found
if not tinyexons:
return []
####################################
# select the **best** tinyexon
####################################
(query_data, sbjct_data, splicesite_data) = tinyexons[0]
orfQ, query_dna_start, query_dna_end = query_data
orfS, sbjct_dna_start, sbjct_dna_end = sbjct_data
(intron1_dObj, intron1_aObj, intron2_dObj, intron2_aObj) = splicesite_data
####################################################
if verbose:
print "tinyexon orf:", orfQ
print "tinyexon orf:", intron1_aObj
print "tinyexon orf:", intron2_dObj
####################################################
####################################
# make tinyexon PacbPORF
####################################
startQaa = orfQ.dnapos2aapos(query_dna_start) - 1
startSaa = orfS.dnapos2aapos(sbjct_dna_start) - 1
stopQaa = orfQ.dnapos2aapos(query_dna_end) + 1
stopSaa = orfS.dnapos2aapos(sbjct_dna_end) + 1
# check for directly leading stop codon on tinyexon
while startQaa <= orfQ.protein_startPY:
startQaa += 1
startSaa += 1
query_dna_start += 3
sbjct_dna_start += 3
while startSaa <= orfS.protein_startPY:
startQaa += 1
startSaa += 1
query_dna_start += 3
sbjct_dna_start += 3
# check for directly tailing stop codon on tinyexon
while stopQaa > orfQ.protein_endPY:
stopQaa -= 1
stopSaa -= 1
query_dna_end -= 3
sbjct_dna_end -= 3
while stopSaa > orfS.protein_endPY:
stopQaa -= 1
stopSaa -= 1
query_dna_end -= 3
sbjct_dna_end -= 3
# get sequences
qAAseq = orfQ.getaas(abs_pos_start=startQaa, abs_pos_end=stopQaa)
sAAseq = orfS.getaas(abs_pos_start=startSaa, abs_pos_end=stopSaa)
####################################################
if verbose or len(qAAseq) != len(sAAseq):
# if unequal lengths, error will be raised upon PacbP.__init__()
print orfQ, qAAseq, startQaa, stopQaa, (stopQaa - startQaa),
print(query_dna_start, query_dna_end)
print orfS, sAAseq, startSaa, stopSaa, (stopSaa - startSaa),
print(sbjct_dna_start, sbjct_dna_end)
print orfQ.inputgenomicsequence[query_dna_start - 2:query_dna_end + 2]
print orfS.inputgenomicsequence[sbjct_dna_start - 2:sbjct_dna_end + 2]
####################################################
# initialize extended tinyexon PacbPORF
from pacb import PacbP
pacbp = PacbP(input=(qAAseq, sAAseq, startQaa, startSaa))
pacbp.strip_unmatched_ends()
pacbporf = pacbp2pacbporf(pacbp, orfQ, orfS)
pacbporf.extend_pacbporf_after_stops()
pacbporf.source = 'ABGPprojectingTE'
####################################
# make introns
####################################
intron1 = IntronConnectingOrfs(intron1_dObj, intron1_aObj, None, donorOrf,
pacbporf.orfQ)
intron2 = IntronConnectingOrfs(intron2_dObj, intron2_aObj, None,
pacbporf.orfQ, accepOrf)
################################################################
# set some meta-data properties to the intron objects
################################################################
# add distance score to intron
intron1._distance = 0
intron2._distance = 0
# add Alignment Positional Periphery Score into objects
if queryorsbjct == "query":
succes = set_apps_intron_query(intron1, pacbporfD, pacbporf)
succes = set_apps_intron_query(intron2, pacbporf, pacbporfA)
else:
succes = set_apps_intron_sbjct(intron1, pacbporfD, pacbporf)
succes = set_apps_intron_sbjct(intron2, pacbporf, pacbporfA)
# set GFF fsource attribute for recognition of intron sources
intron1._gff['fsource'] = "ABGPprojectingTE"
intron2._gff['fsource'] = "ABGPprojectingTE"
# create _linked_to_xxx attributes
intron1._linked_to_pacbporfs = [pacbporf]
intron2._linked_to_pacbporfs = [pacbporf]
intron1._linked_to_introns = [intron2]
intron2._linked_to_introns = [intron1]
####################################################
if verbose:
print pacbporf
pacbporf.print_protein_and_dna()
print intron1
print intron2
if False:
# printing data when this function needs to be debugged:
print ""
print intron1
print intron2
print ""
print pacbporfD
pacbporfD.print_protein_and_dna()
print ""
print pacbporf
pacbporf.print_protein_and_dna()
print ""
print pacbporfA
pacbporfA.print_protein_and_dna()
import sys
sys.exit()
####################################################
# return introns and intermediate tinyexon PacbPORF
return [(intron1, intron2, pacbporf)]
