##TSS(TTS) POSITION CLASSIFIED
HITS : distance < 10
SHIFT : 10<= distance < 50
ALT_E : 50 < distance and peak in Exon
ALT_E : 50 < distance and peak in Intron
COL14 for gene: number of tss, repr string, number of tts
/** | |
* Created with JetBrains WebStorm. | |
* User: zhuxp | |
* Date: 13-4-21 | |
* To change this template use File | Settings | File Templates. | |
*/ | |
function parseStems(ss) | |
{ |
chr1 61735 7035990 CopyNumberRegion_0 2 0 | |
chr1 7036801 7974076 CopyNumberRegion_1 3 0 | |
chr1 7975788 29271013 CopyNumberRegion_2 2 0 | |
chr1 29275883 30265652 CopyNumberRegion_3 4 2 | |
chr1 30271899 31334415 CopyNumberRegion_4 6 2 | |
chr1 31336903 41403766 CopyNumberRegion_5 7 2 | |
chr1 41405663 42601214 CopyNumberRegion_6 4 2 | |
chr1 42602991 44503629 CopyNumberRegion_7 6 2 | |
chr1 44507772 48809180 CopyNumberRegion_8 2 0 | |
chr1 48810111 48824773 CopyNumberRegion_9 7 1 |
#for i in chr1 chr2 chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15chr16 chr17 chr18 chr19 chr20 chr21 chr22 chrX chrY chrM | |
for i in chr3 chr4 chr5 chr6 chr7 chr8 chr9 chr10 chr11 chr12 chr13 chr14 chr15 chr16 chr17 chr18 chr19 chr20 chr21 chrX chrY chrM | |
do | |
echo "samtools mpileup -uf ../hg19.fna ../Mapping/$i.v2.sorted.bam | bcftools view -bvcg - > test_$i.var.raw.bcf" | |
echo "bcftools view test_$i.var.raw.bcf | vcfutils.pl varFilter -D100000 > test_$i.vcf" | |
echo "vcf2var.pl test_$i.vcf > test_$i.variants" | |
echo "samtools view ../Mapping/$i.v2.sorted.bam | extract_hairs --sam stdin --variants test_$i.variants > test_$i.fragments" | |
done |
venn.overlap <- | |
function(r, a, b, target = 0) | |
{ | |
# | |
# calculate the overlap area for circles of radius a and b | |
# with centers separated by r | |
# target is included for the root finding code | |
# | |
pi = acos(-1) | |
if(r >= a + b) { |
#!/bin/sh | |
inputfile=$1 | |
# you can add friendly code to check the extension and use zcat if it's *.fastq.gz or *.fq.gz... | |
[[ "$inputfile" =~ ".*\.(fq\.gz$|fastq\.gz$)" ]] && zcat $inputfile | head -n400 | awk '{if(NR%4==0) printf("%s",$0);}' | od -A n -t u1 | awk 'BEGIN{min=100;max=0;}{for(i=1;i<=NF;i++) {if($i>max) max=$i; if($i<min) min=$i;}}END{if(max<=74 && min<59) print "Phred+33"; else if(max>73 && min>=64) print "Phred+64"; else if(min>=59 && min<64 && max>73) print "Solexa+64"; else print "Unknown score encoding!";}' | |
[[ "$inputfile" =~ ".*\.(fq$|fastq$)" ]] && head -n400 $inputfile | awk '{if(NR%4==0) printf("%s",$0);}' | od -A n -t u1 | awk 'BEGIN{min=100;max=0;}{for(i=1;i<=NF;i++) {if($i>max) max=$i; if($i<min) min=$i;}}END{if(max<=74 && min<59) print "Phred+33"; else if(max>73 && min>=64) print "Phred+64"; else if(min>=59 && min<64 && max>73) print "Solexa+64"; else print "Unknown score encoding!";}' |
#!/bin/bash | |
if [ $# -lt 1 ] | |
then | |
echo "USAGE: test_contamination.sh <fastq_file>" | |
exit 0 | |
fi | |
# modify the following parameters as needed | |
Sample_Size=5000000 |
#!/usr/bin/python | |
# Wei Guifeng, <guifengwei@gmail.com> | |
# Revised By zhuxp <nimezhu@gmail.com> | |
# -- coding: utf-8 -- | |
''' | |
Gencode annotation or Cufflinks transcript.gtf | |
usage: | |
for gene in TableIO.parse("cufflinks.transcript.gtf", 'gtf'): | |
print "{0}\t{1}\t{2}".format(gene.chr, gene.strand, (gene.stop - gene.start)) |
$(function() { | |
Backbone.sync = function(method, model, success, error){ | |
success(); | |
} | |
CausalityView = Backbone.View.extend({ | |
el: $('body'), // el attaches to existing element | |
attributes: {"width":900,"height":700}, | |
events: { | |
'change #csv': 'render', |
#!/usr/bin/env python | |
# a bar plot with errorbars | |
import numpy as np | |
import matplotlib.pyplot as plt | |
N = 5 | |
menMeans = (20, 35, 30, 35, 27) | |
menStd = (2, 3, 4, 1, 2) | |
ind = np.arange(N) # the x locations for the groups |
##TSS(TTS) POSITION CLASSIFIED
HITS : distance < 10
SHIFT : 10<= distance < 50
ALT_E : 50 < distance and peak in Exon
ALT_E : 50 < distance and peak in Intron
COL14 for gene: number of tss, repr string, number of tts