def load_human_shape(hg38_parseTrans,
shape_name='low_shape.out',
rev_hist=False):
icSHAPE_ROOT_DIR = '/Share/home/zhangqf8/lipan/DYNAMIC/shape_score/%s/' + shape_name
ch_icshape_file = icSHAPE_ROOT_DIR % ("hek_ch_vivo", )
np_icshape_file = icSHAPE_ROOT_DIR % ("hek_np_vivo", )
cy_icshape_file = icSHAPE_ROOT_DIR % ("hek_cy_vivo", )
wc_icshape_file = icSHAPE_ROOT_DIR % ("hek_wc_vivo", )
ch_icshape = tools.loadicSHAPE(ch_icshape_file)
np_icshape = tools.loadicSHAPE(np_icshape_file)
cy_icshape = tools.loadicSHAPE(cy_icshape_file)
wc_icshape = tools.loadicSHAPE(wc_icshape_file)
if rev_hist:
remove_hist_genes(ch_icshape, hg38_parseTrans)
remove_hist_genes(np_icshape, hg38_parseTrans)
remove_hist_genes(cy_icshape, hg38_parseTrans)
remove_hist_genes(wc_icshape, hg38_parseTrans)
human_shape = {
'ch': ch_icshape,
'np': np_icshape,
'cy': cy_icshape,
'wc': wc_icshape
}
return human_shape
def load_mouse_shape(mm10_parseTrans, rev_hist=False):
icSHAPE_ROOT_DIR = '/Share/home/zhangqf8/lipan/DYNAMIC/shape_score/%s/shape.out'
ch_icshape_file = icSHAPE_ROOT_DIR % ("mes_ch_vivo", )
np_icshape_file = icSHAPE_ROOT_DIR % ("mes_np_vivo", )
cy_icshape_file = icSHAPE_ROOT_DIR % ("mes_cy_vivo", )
wc_icshape_file = icSHAPE_ROOT_DIR % ("mes_wc_vivo", )
ch_icshape = tools.loadicSHAPE(ch_icshape_file)
np_icshape = tools.loadicSHAPE(np_icshape_file)
cy_icshape = tools.loadicSHAPE(cy_icshape_file)
wc_icshape = tools.loadicSHAPE(wc_icshape_file)
if rev_hist:
remove_hist_genes(ch_icshape, mm10_parseTrans)
remove_hist_genes(np_icshape, mm10_parseTrans)
remove_hist_genes(cy_icshape, mm10_parseTrans)
remove_hist_genes(wc_icshape, mm10_parseTrans)
mouse_shape = {
'ch': ch_icshape,
'np': np_icshape,
'cy': cy_icshape,
'wc': wc_icshape
}
return mouse_shape
###### Load Human Transcriptome
human_seq = tools.readSeq(
"/Share/home/zhangqf8/lipan/DYNAMIC/GTF/transcriptome.fa")
human_gtf = icSHAPE.loadGTFBed(
"/Share/home/zhangqf8/lipan/DYNAMIC/GTF/Homo_sapiens.transCoordinate.bed")
###### Load Human icSHAPE Data
icSHAPE_ROOT_DIR = '/Share/home/zhangqf8/lipan/DYNAMIC/shape_score/%s/shape.out'
ch_icshape_file = icSHAPE_ROOT_DIR % ("hek_ch_vivo", )
np_icshape_file = icSHAPE_ROOT_DIR % ("hek_np_vivo", )
cy_icshape_file = icSHAPE_ROOT_DIR % ("hek_cy_vivo", )
ch_icshape = tools.loadicSHAPE(ch_icshape_file)
np_icshape = tools.loadicSHAPE(np_icshape_file)
cy_icshape = tools.loadicSHAPE(cy_icshape_file)
Shape = {'ch': ch_icshape, 'np': np_icshape, 'cy': cy_icshape}
###### Load RBP Data
clip_file = '/Share/home/zhangqf8/lipan/DYNAMIC/modification/HEK293/m6A/choose_good_protein/clipDB.merged.transCoor.bed'
pbr_ensembl = read_pbr(clip_file, human_seq)
# Filter out 10-50 regions
filt_pbr_ensembl = filterPBR(pbr_ensembl,
minLen=10,
maxLen=50,
for s, e in raw_geneRBP[gid]:
new_geneRBP[gid].append([max(s - extend, 0), e + extend])
return new_geneRBP
#########
### Load data
#########
hg38_parser = ParseTrans.ParseTransClass(
"/Share/home/zhangqf8/lipan/DYNAMIC/GTF/hg38.genomeCoor.bed")
mm10_parser = ParseTrans.ParseTransClass(
"/Share/home/zhangqf8/lipan/DYNAMIC/GTF/mm10.genomeCoor.bed")
input_path = "/Share/home/zhangqf8/lipan/DYNAMIC/shape_score/%s/shape.out"
hg_ch_vivo = tools.loadicSHAPE(input_path % ("hek_gene_ch_vivo", ))
hg_ch_vitro = tools.loadicSHAPE(input_path % ("hek_gene_ch_vitro", ))
mm_ch_vivo = tools.loadicSHAPE(input_path % ("mes_gene_ch_vivo", ))
mm_ch_vitro = tools.loadicSHAPE(input_path % ("mes_gene_ch_vitro", ))
#########
### Calc Mouse GINI
#########
mm_vivo_intron, mm_vivo_exon = calcIntronExonGINI(mm_ch_vivo, mm10_parser)
print numpy.mean(mm_vivo_intron), numpy.mean(mm_vivo_exon)
mm_vitro_intron, mm_vitro_exon = calcIntronExonGINI(mm_ch_vitro, mm10_parser)
print numpy.mean(mm_vitro_intron), numpy.mean(mm_vitro_exon)
writeFile("/tmp/mm_gini.txt", mm_vivo_exon, mm_vivo_intron, mm_vitro_exon,
if mutation_num <= max_mutation:
neighbor_strain_ids.append(trans_id)
return neighbor_strain_ids, sorted(mutation_num_list)
################################################################
# 尝试计数窗口中突变个数来判定变化区域
################################################################
######### MAC
key59, key766 = ['KU501215.1', 'AY632535.2']
Sequence = tools.readSeq(
"/Users/lee/Desktop/Projects/Virus/Virus_Genome/final_virus_genome.fa")
Shape = tools.loadicSHAPE(
"/Users/lee/Desktop/Projects/Virus/Virus_Genome/final_virus_icSHAPE.out")
del Shape[key59 + '_vitro']
del Shape[key766 + '_vitro']
Align = tools.readSeq(
"/Users/lee/pCloud Drive/Virus_Structure/Covariation/Zika_358.afa")
#Align = tools.readSeq("/tmp/dengue.afa")
CodonTable = tools.loadCodon(
"/Users/lee/Desktop/Projects/Virus/Virus_Genome/Sequence/Codon_Table.txt")
######### Linux
key59, key766 = ['KU501215.1', 'AY632535.2']
Sequence = tools.readSeq(
"/Share/home/zhangqf8/lipan/virus/final_virus_genome.fa")