def checkRF(snp):
#this function will check the other 2 bases in the reading frame to see whether fixing them may result in a quiet result
if snp.readingFrame=="1":
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(snp.snpID, zero_seq5, zero_seq3, zero_wt, zero_mutation, 1, 1, 1, 1)
first_seq5=snp.seq5+snp.mutation
first_mutation=snp.seq3[0]
first_wt=find_cor(first_mutation)
first_seq3=snp.seq3[1:]
snp1=BEseqType(snp.snpID,first_seq5,first_seq3,first_wt,first_mutation,2,1,1,1)
second_seq5 = snp.seq5 + snp.mutation+snp.seq3[0]
second_mutation = snp.seq3[1]
second_wt = find_cor(second_mutation)
second_seq3 = snp.seq3[2:]
snp2 = BEseqType(snp.snpID, second_seq5, second_seq3, second_wt,second_mutation, 3,1,1,1)
return snp0, snp1,snp2
elif snp.readingFrame=="2":
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(snp.snpID, zero_seq5, zero_seq3, zero_wt, zero_mutation, 2, 1, 1, 1)
first_seq5=snp.seq5[:-1]
first_mutation=snp.seq5[-1]
first_wt=find_cor(first_mutation)
first_seq3=snp.mutation+snp.seq3
snp1=BEseqType(snp.snpID,first_seq5,first_seq3,first_wt,first_mutation,1,1,1,1)
second_seq5 = snp.seq5 + snp.mutation
second_mutation = snp.seq3[0]
second_wt = find_cor(second_mutation)
second_seq3 = snp.seq3[1:]
snp2 = BEseqType(snp.snpID, second_seq5, second_seq3, second_wt,second_mutation, 3,1,1,1)
return snp0,snp1,snp2
# elif snp.readingFrame==3:
else:
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(snp.snpID, zero_seq5, zero_seq3, zero_wt, zero_mutation, 3, 1, 1, 1)
first_seq5=snp.seq5[:-2]
first_mutation=snp.seq5[-2]
first_wt=find_cor(first_mutation)
first_seq3=snp.seq5[-1]+snp.mutation+snp.seq3
snp1=BEseqType(snp.snpID,first_seq5,first_seq3,first_wt,first_mutation,1,1,1,1)
second_seq5 = snp.seq5[:-1]
second_mutation = snp.seq5[-1]
second_wt = find_cor(second_mutation)
second_seq3 = snp.mutation+snp.seq3
snp2 = BEseqType(snp.snpID, second_seq5, second_seq3,second_wt, second_mutation,2,1,1,1)
return snp0, snp1,snp2
def checkRF(snp):
if snp.readingFrame=='1':
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(12, zero_seq5, zero_seq3, zero_wt, zero_mutation, 1, 1, 1, 1)
first_seq5=snp.seq5+snp.mutation
first_mutation=snp.seq3[0]
first_wt=find_cor(first_mutation)
first_seq3=snp.seq3[1:]
snp1=BEseqType(12,first_seq5,first_seq3,first_wt,first_mutation,2,1,1,1)
second_seq5 = snp.seq5 + snp.mutation+snp.seq3[0]
second_mutation = snp.seq3[1]
second_wt = find_cor(second_mutation)
second_seq3 = snp.seq3[2:]
snp2 = BEseqType(12, second_seq5, second_seq3, second_wt,second_mutation, 3,1,1,1)
return snp0, snp1,snp2
elif snp.readingFrame=='2':
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(12, zero_seq5, zero_seq3, zero_wt, zero_mutation, 2, 1, 1, 1)
first_seq5=snp.seq5[:-1]
first_mutation=snp.seq5[-1]
first_wt=find_cor(first_mutation)
first_seq3=snp.mutation+snp.seq3
snp1=BEseqType(12,first_seq5,first_seq3,first_wt,first_mutation,1,1,1,1)
second_seq5 = snp.seq5 + snp.mutation
second_mutation = snp.seq3[0]
second_wt = find_cor(second_mutation)
second_seq3 = snp.seq3[1:]
snp2 = BEseqType(12, second_seq5, second_seq3, second_wt,second_mutation, 3,1,1,1)
return snp0,snp1,snp2
# elif snp.readingFrame==3:
else:
zero_seq5 = snp.seq5
zero_mutation = snp.mutation
zero_wt = find_cor(zero_mutation)
zero_seq3 = snp.seq3
snp0 = BEseqType(12, zero_seq5, zero_seq3, zero_wt, zero_mutation, 3, 1, 1, 1)
first_seq5=snp.seq5[:-2]
first_mutation=snp.seq5[-2]
first_wt=find_cor(first_mutation)
first_seq3=snp.seq5[-1]+snp.mutation+snp.seq3
snp1=BEseqType(12,first_seq5,first_seq3,first_wt,first_mutation,1,1,1,1)
second_seq5 = snp.seq5[:-1]
second_mutation = snp.seq5[-1]
second_wt = find_cor(second_mutation)
second_seq3 = snp.mutation+snp.seq3
snp2 = BEseqType(12, second_seq5, second_seq3,second_wt, second_mutation,2,1,1,1)
return snp0, snp1,snp2
def importSNPS(SNPfile):
rslts = []
with open(SNPfile, "r") as csv_file:
try:
csv_read = csv.reader(csv_file, delimiter=",")
except MemoryError:
print("MemoryError, try splitting your file into smaller files")
exit()
for row in csv_read:
snpID = row[0]
find_mut_len = len(row[9])
"""
the sequence is given as a string, with 25 bases before mutation and 25 after.
need to find length of mutation to splice properly
"""
mut_len = (find_mut_len - 1) / 2
mutation = row[9][2]
wt = row[9][0]
sequence5 = row[7][0:25]
sequence3 = row[7][26:]
readingFrame = row[14]
aaPosition = row[15]
geneName = row[12]
geneID = row[13]
newSNP = BEseqType(snpID, sequence5, sequence3, wt, mutation,
readingFrame, aaPosition, geneName, geneID)
rslts.append(newSNP)
rsltsDic = {}
num = 0
for snp in rslts:
rsltsDic[snp.snpID] = snp.geneName
num = num + 1
return rslts, rsltsDic
def importSNPS(SNPfile):
rslts=[]
with open(SNPfile,"r") as csv_file:
try:
csv_read = csv.reader(csv_file, delimiter=",")
except MemoryError:
print("MemoryError, try splitting your file into smaller files")
exit()
for row in csv_read:
if row[0]=="Sample ID/ name":
continue
snpID=row[0]
if len(row[2])>1:
continue
mutation=row[2]
wt=row[1][25]
sequence5 = row[1][0:25]
sequence3 = row[1][26:]
readingFrame=row[3]
aaPosition=0
geneName=0
geneID=0
newSNP=BEseqType(snpID,sequence5, sequence3, wt, mutation, readingFrame, aaPosition, geneName, geneID)
rslts.append(newSNP)
rsltsDic={}
num=0
for snp in rslts:
rsltsDic[snp.snpID]=snp.geneName
num=num+1
return rslts, rsltsDic
def getRevComp(snp):
len3=len(snp.seq3)
totalSeq= snp.seq5+snp.mutation+snp.seq3
total_seq=Seq(totalSeq)
rc_seq=total_seq.reverse_complement()
seq5=str(rc_seq[0:len3])
seq3=str(rc_seq[len3+1:])
new_snp=BEseqType(snp.snpID,seq5 ,seq3,snp.mutation,snp.wt, snp.readingFrame, snp.aaPosition,snp.geneName,snp.geneID)
return new_snp
def checkRF(snp):
#this function will check the other 2 bases in the reading frame to see whether fixing them may result in a quiet result
if snp.readingFrame == 1:
first_seq5 = snp.seq5 + snp.mutation
first_mutation = snp.seq3[0]
first_wt = str(Seq(snp.mutation).reverse_complement())
first_seq3 = snp.seq3[1:]
snp1 = BEseqType(12, first_seq5, first_seq3, first_wt, first_mutation,
2, 1, 1, 1)
second_seq5 = snp.seq5 + snp.mutation + snp.seq3[0]
second_mutation = snp.seq3[1]
second_wt = str(Seq(snp.mutation).reverse_complement())
second_seq3 = snp.seq3[2:]
snp2 = BEseqType(12, second_seq5, second_seq3, second_wt,
second_mutation, 3, 1, 1, 1)
return snp1, snp2
elif snp.readingFrame == 2:
first_seq5 = snp.seq5[:-1]
first_mutation = snp.seq5[-1]
first_wt = str(Seq(snp.mutation).reverse_complement())
first_seq3 = snp.mutation + snp.seq3
snp1 = BEseqType(12, first_seq5, first_seq3, first_wt, first_mutation,
1, 1, 1, 1)
second_seq5 = snp.seq5 + snp.mutation
second_mutation = snp.seq3[0]
second_wt = str(Seq(snp.mutation).reverse_complement())
second_seq3 = snp.seq3[1:]
snp2 = BEseqType(12, second_seq5, second_seq3, second_wt,
second_mutation, 3, 1, 1, 1)
return snp1, snp2
# elif snp.readingFrame==3:
else:
first_seq5 = snp.seq5[:-2]
first_mutation = snp.seq5[-2]
first_wt = str(Seq(snp.mutation).reverse_complement())
first_seq3 = snp.seq5[-1] + snp.mutation + snp.seq3
snp1 = BEseqType(12, first_seq5, first_seq3, first_wt, first_mutation,
1, 1, 1, 1)
second_seq5 = snp.seq5[:-1]
second_mutation = snp.seq3[-1]
second_wt = str(Seq(snp.mutation).reverse_complement())
second_seq3 = snp.mutation + snp.seq3
snp2 = BEseqType(12, second_seq5, second_seq3, second_wt,
second_mutation, 2, 1, 1, 1)
return snp1, snp2
def MainBE(upSeq, downSeq, mutation, wt, readingFrame=2):
upSeq = upSeq.upper()
downSeq = downSeq.upper()
mutation = mutation.upper()
wt = wt.upper()
snp = BEseqType(1234, upSeq, downSeq, wt, mutation, readingFrame, 1, 12,
12)
refSeq = snp.seq5 + "<b>" + snp.wt + "</b>" + snp.seq3
mutSeq = snp.seq5 + "<b>" + snp.mutation + "</b>" + snp.seq3
rev = False
if snp.mutation == "C" and snp.wt == "T":
BElist = CBElist
MinorBElist = CBElistMinor
elif snp.mutation == "A" and snp.wt == "G":
BElist = ABElist
MinorBElist = ABElistMinor
elif snp.mutation == "T" and snp.wt == "C":
snp = getRevComp(snp)
rev = True
snp.mutation = "A"
snp.wt = "G"
BElist = ABElist
MinorBElist = ABElistMinor
elif snp.mutation == "G" and snp.wt == "A":
snp = getRevComp(snp)
rev = True
snp.mutation = "C"
snp.wt = "T"
BElist = CBElist
MinorBElist = CBElistMinor
snp2, snp3 = checkRF(snp)
print(2, 3)
if snp2.mutation == "C":
BElist2 = CBElist
elif snp2.mutation == "A":
BElist2 = ABElist
elif snp2.mutation == "T":
snp2 = getRevComp(snp)
rev = True
snp2.mutation = "A"
snp2.wt = "G"
BElist2 = ABElist
elif snp2.mutation == "G":
snp2 = getRevComp(snp)
rev = True
snp2.mutation = "C"
snp2.wt = "T"
BElist2 = CBElist
if snp3.mutation == "C":
BElist3 = CBElist
elif snp3.mutation == "A":
BElist3 = ABElist
elif snp3.mutation == "T":
snp3 = getRevComp(snp)
rev = True
snp3.mutation = "A"
snp3.wt = "G"
BElist3 = ABElist
elif snp3.mutation == "G":
snp3 = getRevComp(snp)
rev = True
snp3.mutation = "C"
snp3.wt = "T"
BElist3 = CBElist
try:
#check for matches in major window
check_match = matchBE(snp, BElist)
check_match2 = matchBE(snp2, BElist2)
check_match3 = matchBE(snp3, BElist3)
#check for clean match
clean_dic, quiet_dic, origMutSeq, origRevSeq, locations_dic = cleanMatch(
snp, check_match, BElist, rev)
clean_dic2, quiet_dic2, origMutSeq2, origRevSeq2, locations_dic2 = cleanMatch(
snp2, check_match2, BElist, rev)
clean_dic3, quiet_dic3, origMutSeq3, origRevSeq3, locations_dic3 = cleanMatch(
snp3, check_match3, BElist, rev)
for key in quiet_dic2:
if key not in quiet_dic:
quiet_dic[key] = quiet_dic2[key]
for key in quiet_dic3:
if key not in quiet_dic:
quiet_dic[key] = quiet_dic3[key]
except:
return [], [], [], [], [], [], []
return clean_dic, quiet_dic, refSeq, mutSeq, origMutSeq, origRevSeq, locations_dic
def MainBE(upSeq, downSeq, mutation, wt, readingFrame,personalPAM,start,end,fromto,stream):
upSeq_=delete_chars(upSeq.upper())
downSeq_=delete_chars(downSeq.upper())
wt_=delete_chars(wt.upper())
mutation_=delete_chars(mutation.upper())
snp=BEseqType(1234,upSeq_, downSeq_, wt_, mutation_, readingFrame, 1, 12, 12)
refSeq=snp.seq5+"<b>"+snp.wt+"</b>"+snp.seq3
mutSeq = snp.seq5 + "<b>" + snp.mutation + "</b>" + snp.seq3
## initiating vars
minor_clean_list=[]
minor_quiet_list=[]
origMutSeq = {}
locations_dic = {}
rev,rev0,rev2,rev3=False,False,False,False
snp=beginningCut(snp)
if snp.mutation == "C" and snp.wt == "T":
BElist = CBElist
MinorBElist=CBElistMinor
if fromto == '1' and personalPAM!="" and start!="" and end!="":
BElist.update({'User customized BE': [personalPAM, start, end, 'C', 'T', stream]})
elif snp.mutation == "A" and snp.wt == "G":
BElist = ABElist
MinorBElist = ABElistMinor
if fromto == '2' and personalPAM!="" and start!="" and end!="":
BElist.update({'User customized BE': [personalPAM, start, end, 'A', 'G', stream]})
elif snp.mutation == "T" and snp.wt == "C":
snp=getRevComp(snp)
rev=True
snp.mutation = "A"
snp.wt="G"
BElist = ABElist
MinorBElist = ABElistMinor
elif snp.mutation == "G" and snp.wt == "A":
snp = getRevComp(snp)
rev=True
snp.mutation = "C"
snp.wt="T"
BElist = CBElist
MinorBElist = CBElistMinor
else:
BElist={}
MinorBElist = None
snp0,snp2,snp3=checkRF(snp)
rev0, rev2, rev3 = False, False, False
BElist0,BElist2,BElist3={},{},{}
if snp0.mutation == "C":
BElist0 = CBElist
if fromto == '1' and personalPAM!="" and start!="" and end!="":
BElist0.update({'User customized BE': [personalPAM, start, end, 'C', 'T', stream]})
elif snp0.mutation == "A":
BElist0 = ABElist
if fromto == '2' and personalPAM!="" and start!="" and end!="":
BElist0.update({'User customized BE': [personalPAM, start, end, 'A', 'G', stream]})
elif snp0.mutation == "T":
snp0 = getRevComp(snp0)
rev0 = True
snp0.mutation = "A"
snp0.wt = "G"
BElist0 = ABElist
elif snp0.mutation == "G":
snp0 = getRevComp(snp0)
rev0 = True
snp0.mutation = "C"
snp0.wt = "T"
BElist0 = CBElist
if snp2.mutation == "C":
BElist2 = CBElist
if fromto == '1' and personalPAM!="" and start!="" and end!="":
BElist2.update({'User customized BE': [personalPAM, start, end, 'C', 'T', stream]})
elif snp2.mutation == "A":
BElist2 = ABElist
if fromto == '2' and personalPAM!="" and start!="" and end!="":
BElist2.update({'User customized BE': [personalPAM, start, end, 'A', 'G', stream]})
elif snp2.mutation == "T":
snp2 = getRevComp(snp2)
rev2 = True
snp2.mutation = "A"
snp2.wt = "G"
BElist2 = ABElist
elif snp2.mutation == "G":
snp2 = getRevComp(snp2)
rev2 = True
snp2.mutation = "C"
snp2.wt = "T"
BElist2 = CBElist
if snp3.mutation == "C":
BElist3 = CBElist
if fromto == '1' and personalPAM!="" and start!="" and end!="":
BElist3.update({'User customized BE': [personalPAM, start, end, 'C', 'T', stream]})
elif snp3.mutation == "A":
BElist3 = ABElist
if fromto == '2' and personalPAM!="" and start!="" and end!="":
BElist3.update({'User customized BE': [personalPAM, start, end, 'A', 'G', stream]})
elif snp3.mutation =="T":
snp3 = getRevComp(snp3)
rev3 = True
snp3.mutation = "A"
snp3.wt = "G"
BElist3 = ABElist
elif snp3.mutation == "G":
snp3 = getRevComp(snp3)
rev3 = True
snp3.mutation = "C"
snp3.wt = "T"
BElist3 = CBElist
try:
check_match = matchBE(snp, BElist)
except:
pass
try:
check_match_minor = matchBE(snp, MinorBElist)
except:
pass
try:
check_match0 = matchBE(snp0, BElist0)
except:
pass
try:
check_match2=matchBE(snp2,BElist2)
except:
pass
try:
check_match3=matchBE(snp3,BElist3)
except:
pass
#check for clean match
try:
clean_dic,quiet_dic,origMutSeq, locations_dic,orig_protein= cleanMatch(snp, check_match, BElist,rev)
except:
clean_dic = {}
quiet_dic = {}
orig_protein = origPro(snp, rev)
try:
clean_dic_m, quiet_dic_m, origMutSeq_m, locations_dic_m, orig_protein_m = cleanMatch(snp, check_match_minor, MinorBElist, rev)
for BE in clean_dic_m:
if BE in clean_dic:
minor_clean_list.append(BE)
for BE in clean_dic_m:
if BE in clean_dic:
minor_quiet_list.append(BE)
except:
pass
try:
clean_dic0,quiet_dic0,origMutSeq0,locations_dic0 = SpecialCleanMatch(snp0, check_match0, BElist0, rev0, orig_protein)
except:
quiet_dic0={}
try:
clean_dic2,quiet_dic2,origMutSeq2,locations_dic2 = SpecialCleanMatch(snp2, check_match2, BElist2, rev2, orig_protein)
except:
quiet_dic2={}
try:
clean_dic3,quiet_dic3,origMutSeq3,locations_dic3 = SpecialCleanMatch(snp3, check_match3, BElist3, rev3, orig_protein)
except:
quiet_dic3={}
## FOR VISUAL OUTPUT
syn_quiet={}
for key in quiet_dic0:
if key in quiet_dic:
for loc in quiet_dic0[key][5]:
if loc not in quiet_dic[key][5]:
syn_quiet.update({key:quiet_dic0[key]})
else:
syn_quiet.update({key: quiet_dic0[key]})
for key in quiet_dic2:
if key in quiet_dic:
for loc in quiet_dic2[key][5]:
if loc not in quiet_dic[key][5]:
syn_quiet.update({key: quiet_dic2[key]})
elif key not in syn_quiet:
syn_quiet.update({key: quiet_dic2[key]})
for key in quiet_dic3:
if key in quiet_dic:
for loc in quiet_dic3[key][5]:
if loc not in quiet_dic[key][5]:
syn_quiet.update({key:quiet_dic3[key]})
elif key not in syn_quiet:
syn_quiet.update({key: quiet_dic3[key]})
try:
return clean_dic, quiet_dic,refSeq,mutSeq, origMutSeq,locations_dic,syn_quiet,minor_clean_list,minor_quiet_list
except:
return [],[],[],[],[],[],[],[]