六、reads distribution (m6a在基因上的分布——另一种QC)
1.input normalize ## 消除背景噪音
ChIP=C57BL6_Brain_Sample_1_MeRIP-SYSY.hisat2
Input=C57BL6_Brain_Sample_1_Non-IP_Control.hisat2
operation=log2
bigwigCompare -p 50 -b1 ${ChIP}.bw -b2 ${Input}.bw \
--operation ${operation} --binSize 10 --pseudocount 1 \
-o ${ChIP}_${operation}_${Input}.bw --outFileFormat bigwig \
> ${ChIP}_${operation}_${Input}.log &
#——————————————————————–
2.prepare matrix
cd /home4/sjshen/project/m6a/GSE29714_Cell/1.1_hisat2/mouse/position_sorted_bam/deeptools_profile/result
bw_dir1=/home4/sjshen/project/m6a/GSE29714_Cell/1.1_hisat2/mouse/position_sorted_bam/deeptools_bw/assemble_bw
region_dir1=/home4/sjshen/project/m6a/GSE29714_Cell/1.1_hisat2/mouse/position_sorted_bam/deeptools_profile/bed_home
bw_files="
$bw_dir1/C57BL6_Brain_Sample_1_MeRIP-SYSY.hisat2_log2ratio_C57BL6_Brain_Sample_1_Non-IP_Control.hisat2.bw
$bw_dir1/C57BL6_Brain_Sample_2_MeRIP-NEB.hisat2_log2ratio_C57BL6_Brain_Sample_2_Non-IP_Control.hisat2.bw
$bw_dir1/C57BL6_Brain_Sample_2_MeRIP-SYSY.hisat2_log2ratio_C57BL6_Brain_Sample_2_Non-IP_Control.hisat2.bw
"
region_files="
$region_dir1/mm10.RefSeq.cds.bed
"
try=MeIRP_profile_on_cds_mm10_input_norm
nohup computeMatrix scale-regions -p 100 -b 1000 -a 1000 --regionBodyLength 3000 -R $region_files \
-S $bw_files --startLabel cdsStart --endLabel cdsEnd --binSize 50 \
--samplesLabel SYSY-MeRIP-rep1 NEB-MeRIP-rep2 SYSY-MeRIP-rep2 \
-o ./${try}_computeMatrix.gz --outFileNameMatrix ./${try}_computeMatrix.matrix.tab \
--outFileSortedRegions ./${try}_computeMatrix.SortedRegions.bed > ./${try}_computeMatrix.log &
#——————————————————————–
3.display graph
try=MeIRP_profile_on_cds_mm10_input_norm
plotProfile --matrixFile ${try}_computeMatrix.gz --outFileName ${try}_profile_1.pdf --outFileNameData ${try}_profile_1.tab --dpi 720 --perGroup --numPlotsPerRow 2 --plotHeight 12 --plotWidth 16 &
plotProfile --matrixFile ${try}_computeMatrix.gz --outFileName ${try}_profile_2.pdf --outFileNameData ${try}_profile_2.tab --dpi 720 --numPlotsPerRow 2 --plotHeight 12 --plotWidth 16 &
Tips:主要查看基因CDS区域上带有m6a的reads的分布
也可以展示每个基因的情况
plotHeatmap --matrixFile ./${try}_computeMatrix.gz --outFileName ./${try}_peak.pdf --colorList "white,blue" --whatToShow "plot, heatmap and colorbar" --dpi 720 --missingDataColor white \
--refPointLabel "center" --regionsLabel " " --xAxisLabel " " --sortRegions descend --sortUsing mean --heatmapHeight 30 --heatmapWidth 4 &
Dependencies
- Softwares