def writeGene(self, genomeFileName, geneFileName, pureGeneID=False, onlyChr=True, verbose=True):
"""从注释文件个基因组文件中解析出基因文件（包含内含子）
测试：
# Gencode下载的基因组
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.gene.fa", hg38_gtf_container, pureGeneID=True)
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.gene.fa", mm10_gtf_container, pureGeneID=True)
# GENCODE 下载的基因组
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_GENCODE.gene.fa", hg38_gtf_container, pureGeneID=True)
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_GENCODE.gene.fa", mm10_gtf_container, pureGeneID=True)
注意：这个文件可能和GENCODE上直接下载的文件不一样，GENCODE上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
OUT = open(geneFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for gene_ID in self.gtf_container['gene']:
count += 1
if count % 1000 == 0: print '\tProcessed %.2f%% ...' % (100.0*count/len(self.gtf_container['gene']))
"strand, chromosome, "
strand = self.gtf_container['gene'][gene_ID]['strand']
Chr = self.gtf_container['gene'][gene_ID]['chr']
if onlyChr and not Chr.startswith('chr'): continue
"Transcript ID"
GeneID = gene_ID.split('.')[0] if pureGeneID else gene_ID
start = int(self.gtf_container['gene'][gene_ID]['start'])
end = int(self.gtf_container['gene'][gene_ID]['end'])
gene_seq = Seq.fetch(Chr, start-1, end, strand)
gene_name = self.gtf_container['gene'][gene_ID]['gene_name']
print >>OUT, '>%s\t%s\t%d\t%s:%d-%d:%s\n%s' % (GeneID, gene_name, len(gene_seq), Chr, start, end, strand, SeqFunc.cutSeq(gene_seq))
OUT.close()
def writeTranscriptome(self,
genomeFileName,
transcriptomeFileName,
genomeChrSym='chr',
pureTransID=False,
verbose=True):
"""从注释文件个基因组文件中解析出转录组文件
测试：
# Gencode下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.fa", hg38_gff3_container, genomeChrSym='chr', pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.fa", mm10_gff3_container, genomeChrSym='chr', pureTransID=True)
# NCBI 下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/ncbi/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_ncbi.fa", hg38_gff3_container, genomeChrSym='chr', pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/ncbi/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_ncbi.fa", mm10_gff3_container, genomeChrSym='chr', pureTransID=True)
注意：这个文件可能和NCBI上直接下载的文件不一样，NCBI上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
if genomeChrSym == 'chr':
NCToChr = self.build_NC_To_chr_dict(pureNCID=False)
OUT = open(transcriptomeFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for rna_ID in self.gff3_container['RNA']:
count += 1
if count % 1000 == 0:
print '\tProcessed %.2f%% ...' % (
100.0 * count / len(self.gff3_container['RNA']))
"strand, chromosome, "
strand = self.gff3_container['RNA'][rna_ID]['strand']
Chr = self.gff3_container['RNA'][rna_ID]['chr']
if not Chr.startswith('NC'): continue
if genomeChrSym == 'chr': Chr = NCToChr[Chr]
"Transcript ID"
"""
try:
TransID = self.gff3_container['RNA'][rna_ID]['transcript_id']
except KeyError:
if self.gff3_container['RNA'][rna_ID]['gbkey'] in ('tRNA', 'rRNA'):
TransID = self.gff3_container['RNA'][rna_ID]['gene']+'_'+self.gff3_container['RNA'][rna_ID]['gbkey']
else:
continue
"""
TransID = self.rnaid_2_transID[rna_ID]
if pureTransID: TransID = TransID.split('.')[0]
RNA_seq = ''
exons = self.gff3_container['exon'][rna_ID]
exonsList = [[int(exon['start']),
int(exon['end'])] for exon in exons]
for exon in exonsList:
try:
RNA_seq += Seq.fetch(Chr, exon[0] - 1, exon[1], strand)
except KeyError:
if verbose:
print 'Warning: KeyError -> %s\t%d\t%d\t%s' % (
Chr, exon[0] - 1, exon[1], strand)
continue
print >> OUT, '>%s\n%s' % (TransID, SeqFunc.cutSeq(RNA_seq))
OUT.close()
def writeTranscriptome(self,
genomeFileName,
transcriptomeFileName,
pureTransID=False,
onlyChr=True,
verbose=True):
"""从注释文件个基因组文件中解析出转录组文件
测试：
# Gencode下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.fa", hg38_gtf_container, pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.fa", mm10_gtf_container, pureTransID=True)
# GENCODE 下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_GENCODE.fa", hg38_gtf_container, pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_GENCODE.fa", mm10_gtf_container, pureTransID=True)
注意：这个文件可能和GENCODE上直接下载的文件不一样，GENCODE上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
OUT = open(transcriptomeFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for rna_ID in self.gtf_container['RNA']:
count += 1
if count % 1000 == 0:
print '\tProcessed %.2f%% ...' % (
100.0 * count / len(self.gtf_container['RNA']))
"trancript information"
GeneID = self.gtf_container['RNA'][rna_ID]['gene_id']
GeneName = self.gtf_container['RNA'][rna_ID]['gene_name']
GeneType = self.gtf_container['RNA'][rna_ID]['trans_type']
RNA_info = GeneID + '|' + GeneName + '|' + GeneType
"strand, chromosome, "
strand = self.gtf_container['RNA'][rna_ID]['strand']
Chr = self.gtf_container['RNA'][rna_ID]['chr']
if onlyChr and not Chr.startswith('chr'): continue
"Transcript ID"
TransID = rna_ID.split('.')[0] if pureTransID else rna_ID
RNA_seq = ''
exons = self.gtf_container['exon'][rna_ID]
exonsList = [[int(exon['start']),
int(exon['end'])] for exon in exons]
for exon in exonsList:
try:
RNA_seq += Seq.fetch(Chr, exon[0] - 1, exon[1], strand)
except KeyError:
if verbose:
print 'Warning: KeyError -> %s\t%d\t%d\t%s' % (
Chr, exon[0] - 1, exon[1], strand)
continue
print >> OUT, '>%s\t%s\n%s' % (TransID, RNA_info,
SeqFunc.cutSeq(RNA_seq))
OUT.close()
def writeTranscriptome(self, genomeFileName, transcriptomeFileName, genomeChrSym='chr', pureTransID=False, verbose=True):
"""从注释文件个基因组文件中解析出转录组文件
测试：
# Gencode下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.fa", hg38_gff3_container, genomeChrSym='chr', pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.fa", mm10_gff3_container, genomeChrSym='chr', pureTransID=True)
# NCBI 下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/ncbi/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_ncbi.fa", hg38_gff3_container, genomeChrSym='chr', pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/ncbi/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_ncbi.fa", mm10_gff3_container, genomeChrSym='chr', pureTransID=True)
注意：这个文件可能和NCBI上直接下载的文件不一样，NCBI上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
if genomeChrSym == 'chr':
NCToChr = self.build_NC_To_chr_dict(pureNCID=False)
OUT = open(transcriptomeFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for rna_ID in self.gff3_container['RNA']:
count += 1
if count % 1000 == 0: print '\tProcessed %.2f%% ...' % (100.0*count/len(self.gff3_container['RNA']))
"strand, chromosome, "
strand = self.gff3_container['RNA'][rna_ID]['strand']
Chr = self.gff3_container['RNA'][rna_ID]['chr']
if not Chr.startswith('NC'): continue
if genomeChrSym == 'chr': Chr = NCToChr[Chr]
"Transcript ID"
"""
try:
TransID = self.gff3_container['RNA'][rna_ID]['transcript_id']
except KeyError:
if self.gff3_container['RNA'][rna_ID]['gbkey'] in ('tRNA', 'rRNA'):
TransID = self.gff3_container['RNA'][rna_ID]['gene']+'_'+self.gff3_container['RNA'][rna_ID]['gbkey']
else:
continue
"""
TransID = self.rnaid_2_transID[rna_ID]
if pureTransID: TransID = TransID.split('.')[0]
RNA_seq = ''
exons = self.gff3_container['exon'][rna_ID]
exonsList = [ [int(exon['start']), int(exon['end'])] for exon in exons ]
for exon in exonsList:
try:
RNA_seq += Seq.fetch(Chr, exon[0]-1, exon[1], strand)
except KeyError:
if verbose:
print 'Warning: KeyError -> %s\t%d\t%d\t%s' % (Chr, exon[0]-1, exon[1], strand)
continue
print >>OUT, '>%s\n%s' % (TransID, SeqFunc.cutSeq(RNA_seq))
OUT.close()
def writeTranscriptome(self, genomeFileName, transcriptomeFileName, pureTransID=False, onlyChr=True, verbose=True):
"""从注释文件个基因组文件中解析出转录组文件
测试：
# Gencode下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.fa", hg38_gtf_container, pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.fa", mm10_gtf_container, pureTransID=True)
# GENCODE 下载的基因组
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_GENCODE.fa", hg38_gtf_container, pureTransID=True)
writeTranscriptome(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_GENCODE.fa", mm10_gtf_container, pureTransID=True)
注意：这个文件可能和GENCODE上直接下载的文件不一样，GENCODE上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
OUT = open(transcriptomeFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for rna_ID in self.gtf_container['RNA']:
count += 1
if count % 1000 == 0: print '\tProcessed %.2f%% ...' % (100.0*count/len(self.gtf_container['RNA']))
"trancript information"
GeneID = self.gtf_container['RNA'][rna_ID]['gene_id']
GeneName = self.gtf_container['RNA'][rna_ID]['gene_name']
GeneType = self.gtf_container['RNA'][rna_ID]['trans_type']
RNA_info = GeneID+'|'+GeneName+'|'+GeneType
"strand, chromosome, "
strand = self.gtf_container['RNA'][rna_ID]['strand']
Chr = self.gtf_container['RNA'][rna_ID]['chr']
if onlyChr and not Chr.startswith('chr'): continue
"Transcript ID"
TransID = rna_ID.split('.')[0] if pureTransID else rna_ID
RNA_seq = ''
exons = self.gtf_container['exon'][rna_ID]
exonsList = [ [int(exon['start']), int(exon['end'])] for exon in exons ]
for exon in exonsList:
try:
RNA_seq += Seq.fetch(Chr, exon[0]-1, exon[1], strand)
except KeyError:
if verbose:
print 'Warning: KeyError -> %s\t%d\t%d\t%s' % (Chr, exon[0]-1, exon[1], strand)
continue
print >>OUT, '>%s\t%s\n%s' % (TransID, RNA_info, SeqFunc.cutSeq(RNA_seq))
OUT.close()
def writeGene(self,
genomeFileName,
geneFileName,
pureGeneID=False,
onlyChr=True,
verbose=True):
"""从注释文件个基因组文件中解析出基因文件（包含内含子）
测试：
# Gencode下载的基因组
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/hg38.fa", os.environ.get("HOME")+"/hg38.gene.fa", hg38_gtf_container, pureGeneID=True)
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/mm10.fa", os.environ.get("HOME")+"/mm10.gene.fa", mm10_gtf_container, pureGeneID=True)
# GENCODE 下载的基因组
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCh38.p7.fa", os.environ.get("HOME")+"/hg38_GENCODE.gene.fa", hg38_gtf_container, pureGeneID=True)
writeGene(os.environ.get("HOME")+"/lipan/DYNAMIC/GTF/GENCODE/GRCm38.p4.fa", os.environ.get("HOME")+"/mm10_GENCODE.gene.fa", mm10_gtf_container, pureGeneID=True)
注意：这个文件可能和GENCODE上直接下载的文件不一样，GENCODE上的mRNA喜欢3'UTR加polyA
"""
import seq as SeqFunc
OUT = open(geneFileName, 'w')
Seq = SeqFunc.seqClass(genomeFileName)
count = 0
for gene_ID in self.gtf_container['gene']:
count += 1
if count % 1000 == 0:
print '\tProcessed %.2f%% ...' % (
100.0 * count / len(self.gtf_container['gene']))
"strand, chromosome, "
strand = self.gtf_container['gene'][gene_ID]['strand']
Chr = self.gtf_container['gene'][gene_ID]['chr']
if onlyChr and not Chr.startswith('chr'): continue
"Transcript ID"
GeneID = gene_ID.split('.')[0] if pureGeneID else gene_ID
start = int(self.gtf_container['gene'][gene_ID]['start'])
end = int(self.gtf_container['gene'][gene_ID]['end'])
gene_seq = Seq.fetch(Chr, start - 1, end, strand)
gene_name = self.gtf_container['gene'][gene_ID]['gene_name']
print >> OUT, '>%s\t%s\t%d\t%s:%d-%d:%s\n%s' % (
GeneID, gene_name, len(gene_seq), Chr, start, end, strand,
SeqFunc.cutSeq(gene_seq))
OUT.close()
def check_transcriptome_MAF(tMaf_FileName,
sp1_genome_FileName,
sp1_transcriptome_FileName,
sp2_genome_FileName,
sp2_transcriptome_FileName,
verbose=False):
sp1_genomeSeq = seq.seqClass(sp1_genome_FileName)
sp1_transcriptomeSeq = seq.seqClass(sp1_transcriptome_FileName)
sp2_genomeSeq = seq.seqClass(sp2_genome_FileName)
sp2_transcriptomeSeq = seq.seqClass(sp2_transcriptome_FileName)
IN = open(tMaf_FileName)
human = IN.readline()
mouse = IN.readline()
line = IN.readline()
count = 1
last_chr = ''
while line:
(Chr1, genome_s1, genome_e1, strand1, transID1, trans_s1, trans_e1,
seq1) = check_tMaf_Methods.sparse_tMaf_Line(human)
(Chr2, genome_s2, genome_e2, strand2, transID2, trans_s2, trans_e2,
seq2) = check_tMaf_Methods.sparse_tMaf_Line(mouse)
if Chr1 != last_chr:
print 'Now Checking ' + Chr1
last_chr = Chr1
try:
if len(seq1) != len(seq2):
print 'Error 1', count
print human
print mouse
return
if check_tMaf_Methods.base_len(
seq1) != trans_e1 - trans_s1 + 1:
print 'Error 2', count
print human
print mouse
return
if check_tMaf_Methods.base_len(
seq2) != trans_e2 - trans_s2 + 1:
print 'Error 3', count
print human
print mouse
return
if check_tMaf_Methods.base_len(seq1) != genome_e1 - genome_s1:
print 'Error 4', count
print human
print mouse
return
if check_tMaf_Methods.base_len(seq2) != genome_e2 - genome_s2:
print 'Error 5', count
print human
print mouse
return
if sp1_genomeSeq.fetch(
Chr1, genome_s1, genome_e1,
strand1).upper() != sp1_transcriptomeSeq.fetch(
transID1, trans_s1 - 1,
trans_e1).upper() or sp1_transcriptomeSeq.fetch(
transID1, trans_s1 - 1, trans_e1).upper(
) != check_tMaf_Methods.pure_seq(seq1).upper():
print 'Error 6', count
print human
print mouse
return
if sp2_genomeSeq.fetch(
Chr2, genome_s2, genome_e2,
strand2).upper() != sp2_transcriptomeSeq.fetch(
transID2, trans_s2 - 1,
trans_e2).upper() or sp2_transcriptomeSeq.fetch(
transID2, trans_s2 - 1, trans_e2).upper(
) != check_tMaf_Methods.pure_seq(seq2).upper():
print 'Error 7', count
print human
print mouse
return
except KeyError:
if verbose:
print 'Check tMaf: Key Error -> '
print '\t\tsp_1: ', (Chr1, genome_s1, genome_e1, strand1,
transID1, trans_s1, trans_e1)
print '\t\tsp_2: ', (Chr2, genome_s2, genome_e2, strand2,
transID2, trans_s2, trans_e2)
else:
pass
human = IN.readline()
mouse = IN.readline()
line = IN.readline()
count += 1
del sp1_genomeSeq
del sp2_genomeSeq
del sp1_transcriptomeSeq
del sp2_transcriptomeSeq
print 'All Right'
elif m6A_site < hnrnpc_s < hnrnpc_e:
if strand == '+':
s = 100 + (hnrnpc_s - m6A_site)
e = 100 + (hnrnpc_e - m6A_site)
if strand == '-':
s = 100 - (hnrnpc_e - m6A_site)
e = 100 - (hnrnpc_s - m6A_site)
for i in range(s, e + 1):
count[i] += 1
return count
import tools, seq
handle = seq.seqClass(
"/150T/zhangqf/GenomeAnnotation/genome/GRCh37.p13.genome.fa")
count = statistic_HNRNPC_m6A("/tmp/HNRNPC_m6A.hg19.txt", handle)
tools.plt.plot(range(-100, 100), count)
tools.plt.savefig("figs/hnrnpc_m6A.pdf")
tools.plt.show()
####################
# 2. Shuffle m6A or PBR
####################
def read_HNRNPC_m6A(inFile):
HNRNPC = {}
m6A = {}