def __init__(self, tumor_seq, tsp_list, mao_file):
Align = MegaAlignment()
self.tumor_list, self.tumor2seq = Align.name2seq(tumor_seq)
self.Len = len(self.tumor2seq[self.tumor_list[0]])
self.mao_file = mao_file
self.tsp_list = tsp_list
TSPinfo = tsp_information(tsp_list)
self.Tu2SNV = TSPinfo.tumor2alt_frequency()
def __init__(self, ini_seq_builder, tsp_list, clone_frequencies, CNV,
freq_cutoff):
self.tsp_list = tsp_list
self.freq_cutoff = freq_cutoff
self.Tu2CloFre = clone_frequencies
self.all_tsp = tsp_information(tsp_list)
self.CloFreCutOff = self.freq_cutoff
self.v_obs = self.all_tsp.tumor2alt_frequency()
Align = MegaAlignment()
self.clone_order, self.clone_seq = Align.name2seq(ini_seq_builder)
self._CNV_file = CNV
def __init__(self, cluster_information, original_seq, tumor_seq, tsp_list,
clone_frequency_cutoff, CNV_info, ReadCountTable):
self.Tu2Cluster = cluster_information
self.CNV_info = CNV_info
self.ReadCountTable = ReadCountTable
Align = MegaAlignment()
self.OriAncOrder, self.OriAnc2Seq0 = Align.name2seq(original_seq)
self.TOrder, self.T2Seq = Align.name2seq(tumor_seq)
self.SharePosi = Align.GetSharePosi1(self.OriAnc2Seq0, 'T')
self.all_tsp = tsp_information(tsp_list)
self.CloFreCutOff = clone_frequency_cutoff
self.v_obs = self.all_tsp.tumor2alt_frequency()
identical_seq_list = Align.identify_similar_seq(tumor_seq, 0)
self.identical_seq = Align.make_similar_seq_dic(identical_seq_list)
self.freq_cutoff = self.CloFreCutOff
def add_back_CNVSNV(self, DecomTu2Seq_builder_sub, CNV_information,
original_seqs_builder_all,
original_Tumor2Clone_frequency, tsp_list):
all_tsp = tsp_information(tsp_list)
v_obs = all_tsp.tumor2alt_frequency()
Seq_all_dic = {}
Align = MegaAlignment()
Original_clols, Original_clodic_all = Align.name2seq(
original_seqs_builder_all)
for Tumor in DecomTu2Seq_builder_sub:
Seq_builder_sub = DecomTu2Seq_builder_sub[Tumor]
if Seq_builder_sub != []:
SNVfre_list = v_obs[Tumor]
CloLs, Clo2Seq = Align.name2seq(Seq_builder_sub)
CNVinfo = CNV_information[Tumor]
Len = len(CNVinfo)
# print Tumor, Clo2Seq.keys()
for Clo in Clo2Seq:
Seq_sub = Clo2Seq[Clo]
c_seq = 0
c_all = 0
Seq_all = ''
while c_all < Len:
if CNVinfo[c_all] == 'normal':
Seq_all += Seq_sub[c_seq]
c_seq += 1
else:
if SNVfre_list[c_all] == 0: Seq_all += 'A'
else: Seq_all += '?'
c_all += 1
if Original_clodic_all.has_key(Clo) == True:
Seq_all_dic[Clo] = Original_clodic_all[Clo]
else:
Seq_all_dic[Clo] = Seq_all
else:
CloFre = original_Tumor2Clone_frequency['T-' + Tumor]
for Clo in CloFre:
if CloFre[Clo] > 0:
if Seq_all_dic.has_key('#' + Clo) != True:
Seq_all_dic['#' + Clo] = Original_clodic_all['#' +
Clo]
decom_all_seq_builder = Align.UpMeg(Seq_all_dic, [])
return decom_all_seq_builder
def BranchDecClone(self, seq_list, clone_frequency, Tu2CNV):
Align = MegaAlignment()
TumorSampleExtract = tsp_information(self.tsp_list)
CloFreAna = CloneFrequencyAnalizer()
CloOrder, Clo2Seq = Align.name2seq(seq_list)
Align.save_mega_alignment_to_file('Test.meg', seq_list)
tree_builder = MegaMP()
tree_builder.mao_file = self.mao_file
id = 'branchdec_mega_alignment'
status = tree_builder.do_mega_mp(seq_list, id)
if status == True:
seqs_with_ancestor, tree, nade_map, mask_seq, Good_posi_info = tree_builder.alignment_least_back_parallel_muts(
True
) # True will execute code to remove redundant seqs (True is default)
else:
print 'failed to run megaMP'
BadPosiLs = [] #multiple mutations
BadPosi2ChnageCloLs = {}
for c in Good_posi_info:
Posi_Inf = Good_posi_info[c]
if Posi_Inf != ['Good']:
if Posi_Inf[0] == 'ToWild':
BadPosiLs.append(c)
BadPosi2ChnageCloLs[c] = Posi_Inf[1][0]
print 'bad positions', BadPosiLs #,BadPosi2ChnageCloLs
if BadPosiLs != []:
NewT2C2F = {}
NewT2Cls = {}
for Tu in clone_frequency:
NewC2F = {}
single_tsp_list = TumorSampleExtract.make_single_tsp_list(Tu)
CloFreDic = clone_frequency[Tu]
CNV = Tu2CNV[Tu[2:]]
Tu = Tu[2:]
TuSeq = self.tumor2seq['#' + Tu]
NewCloLs = []
NewCloLs1 = []
for Clo in CloFreDic: #original hit clo for the tumor
ChangeOptions = 'n'
# print Tu,CloFreDic
if CloFreDic[Clo] > 0:
CSeq0 = Clo2Seq['#' + Clo]
ChangePosi = [] #list to fix multiple mutaitons
NewBadPosi = [
] #remove fixed multiple mutations from BadExtMutPosi
for Bad in BadPosi2ChnageCloLs:
if BadPosi2ChnageCloLs[Bad].count(
'#' + Clo) != 0 and (CNV[Bad] == 'normal'
or CNV[Bad]
== 'Bad-normal'):
Change = 'n'
for Oth in CloFreDic: #find multiple mutations at the external branch
if Oth != Clo and CloFreDic[Oth] > 0:
Soth = Clo2Seq['#' + Oth]
if Soth[Bad] == 'T' and BadPosi2ChnageCloLs[
Bad].count('#' + Oth) == 0:
Change = 'y'
if Change == 'y':
ChangePosi.append(Bad)
else:
NewBadPosi.append(Bad)
print 'change positions', Tu, ChangePosi
if ChangePosi != []: #fix multiple mutaitons
# print 'hhh'
CutCloSeq = Align.ModSeq(CSeq0, ChangePosi, 'A',
self.Len)
NewCloLs.append(Clo + 'Cut' + Tu)
NewC2F[Clo + 'Cut' + Tu] = CloFreDic[Clo]
Clo2Seq['#' + Clo + 'Cut' + Tu] = CutCloSeq
ChangeOptions = 'y'
if ChangeOptions == 'n':
NewC2F[Clo] = 1
NewT2C2F[Tu] = NewC2F
# print Clo2Seq
hitseq_align, hitclone_frequency = CloFreAna.ListHitCloAndSeq(
NewT2C2F, Clo2Seq)
outSeqMaj, outSeqAmb, NewT2C2F = Align.CombSimClo(
hitseq_align, hitclone_frequency, 0.0)
# print outSeqMaj, NewT2C2F
return outSeqMaj, NewT2C2F
else:
return seq_list, clone_frequency
AnalyzeTree = TreeAnalizer()
OutFile = OutputWrite()
Align = MegaAlignment()
CloFreAna = CloneFrequencyAnalizer()
Format = FormatInput()
if parser.parse() == False:
print(parser.messages)
else:
tsp_list = parser.get_tumor_sample_profile_list()
CNV_information = parser_cnv.get_tumor_cnv_profile(params.cnv_data_file)
original_align_builder = FreqToMegaSeq()
original_align_builder.initialize(
tsp_list, True) #True to remove duplicates; False to keep duplicates
num_sites = tsp_list.num_read_counts()
all_tsp = tsp_information(tsp_list)
v_obs = all_tsp.tumor2alt_frequency()
total_read, alt_read, ReadCount_table = all_tsp.tumor2read_count()
tumor_seqs = original_align_builder.get_mega_allalignment()
initial_seq0 = original_align_builder.get_mega_alignment()
initial_seq, A1, A2 = OutFile.ReNameCloFreMeg(initial_seq0, {}, 'number')
CNV_information_test = Format.add_low_quality_SNV_info(
CNV_information, total_read, alt_read, total_read_cut, mutant_read_cut)
print('add initial ancestor')
id = 'mega_alignment' # id will be used internally for file names
status = tree_builder.do_mega_mp(initial_seq, id)
if status != True:
print(
'CloneFinder cannot make inferences, because samples do not have evolutionary structure.'
)
else: