python lncrna_分析指令备份.sh

最新推荐文章于 2020-12-10 17:44:06 发布
最新推荐文章于 2020-12-10 17:44:06 发布
阅读量245 收藏
点赞数
文章标签： python lncrna

#分别筛选出known和novel,集群

cd /disk/zhw/CRClncRNA/filter/lncRNA

cat lncRNA.final.v2.gtf|grep 'known' >lncRNA.final.v2.known.gtf

cat lncRNA.final.v2.gtf|grep 'novel'>lncRNA.final.v2.novel.gtf

#转为bed文件，zuo

cd /data1/users/zzuo/xulab/CRC_lncRNA/hongwan

gtf2bed < lncRNA.final.v2.known.gtf|sort-bed - > lncRNA.final.v2.known.bed

gtf2bed < lncRNA.final.v2.novel.gtf|sort-bed - > lncRNA.final.v2.novel.bed

#RSEM 集群

cd /disk/zhw/CRClncRNA/fastq_data/first

ls *_1.clean.fq.gz|sed 's/_1.clean.fq.gz//g'>SRR.txt

/disk/soft/CPAT-1.2.3/bin/cpat.py -r /disk/database/human/hg38/Gencode/genome.fa -g /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.bed

#fastp clean data

cd /disk/zhw/CRClncRNA/fastq_data/sec

fastp -i D6_HKNNLCCXX_L4_1.fq.gz -o D6_HKNNLCCXX_L4_1.clean.fq.gz -I D6_HKNNLCCXX_L4_2.fq.gz -O D6_HKNNLCCXX_L4_2.clean.fq.gz -w 8

#集群

#转为三列bed

cd /disk/zhw/CRClncRNA/filter/lncRNA

cat lncRNA.final.v2.known.gtf|awk '{print $1,$4,$5}'|sort -u |sed 's/ /\t/g'>lncRNA.final.v2.known2.bed

cat lncRNA.final.v2.novel.gtf|awk '{print $1,$4,$5}'|sort -u |sed 's/ /\t/g'>lncRNA.final.v2.novel2.bed

cat protein_coding.final.gtf|awk '{print $1,$4,$5}'|sort -u |sed 's/ /\t/g'>protein_coding.final2.bed

#34fuwuq

#novel

cd /data2/zhw/CRC_lncRNA

less lncRNA.final.v2.novel2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' >lncRNA.final.v2.novel3.bed

/data/software/bwtool-master/bwtool extract bed lncRNA.final.v2.novel3.bed /data/database/hg38/hg38.phastCons100way.bw novel_bwtools

less -S novel_bwtools| perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' >novel.mean.txt

#known

less lncRNA.final.v2.known2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' >lncRNA.final.v2.known3.bed

/data/software/bwtool-master/bwtool extract bed lncRNA.final.v2.known3.bed /data/database/hg38/hg38.phastCons100way.bw known_bwtools

less -S known_bwtools| perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' >knonw.mean.txt

#protein

less protein_coding.final2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' >protein_coding.final3.bed

/data/software/bwtool-master/bwtool extract bed protein_coding.final3.bed /data/database/hg38/hg38.phastCons100way.bw protein_bwtools

less -S protein_bwtools| perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' >protein.mean.txt

#合并(集群)

cd /disk/zhw/CRClncRNA/filter/RSEM

python pcRNA_RSEM_merge.py 5 pcRNA.rsem.count

python pcRNA_RSEM_merge.py 6 pcRNA.rsem.TPM

python pcRNA_RSEM_merge.py 7 pcRNA.rsem.FPKM

python lncRNA_RSEM_merge.py 5 lncRNA.rsem.count

python lncRNA_RSEM_merge.py 6 lncRNA.rsem.TPM

python lncRNA_RSEM_merge.py 7 lncRNA.rsem.FPKM

cd /disk/zhw/CRClncRNA/filter/lncRNA

cat lncRNA.final.v2.gtf|awk '{print $1,$2,$4,$5,$10}'|sed 's/"//g'|sed 's/;//g'|sed 's/ /\t/g' >lncRNA.final.v2.cp.2.txt

#画circos图

#分类

#运行D:\CRC_lncRNA目录的distinguish_known_novel.R

#node1 root

#test

head -1000 hs_exp_data/hs_normal_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_normal_know_gtf_data3.txt

head -1000 hs_exp_data/hs_normal_novel_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_normal_novel_gtf_data3.txt

head -1000 hs_exp_data/hs_unrecurrence_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_unrecurrence_know_gtf_data3.txt

head -1000 hs_exp_data/hs_unrecurrence_novel_gtf_data.txt | awk {'print $1,$2,$3,$4'}>hs_unrecurrence_novel_gtf_data3.txt

head -1000 hs_exp_data/hs_recurrence_novel_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_recurrence_novel_gtf_data3.txt

head -1000 hs_exp_data/hs_recurrence_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_recurrence_know_gtf_data3.txt

/disk/soft/circos-0.69-6/bin/circos -conf circoshhj_test.conf

cat hs_exp_data/hs_normal_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_normal_know_gtf_data2.txt

cat hs_exp_data/hs_normal_novel_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_normal_novel_gtf_data2.txt

cat hs_exp_data/hs_unrecurrence_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_unrecurrence_know_gtf_data2.txt

cat hs_exp_data/hs_unrecurrence_novel_gtf_data.txt | awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_unrecurrence_novel_gtf_data2.txt

cat hs_exp_data/hs_recurrence_novel_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_recurrence_novel_gtf_data2.txt

cat hs_exp_data/hs_recurrence_know_gtf_data.txt| awk {'print $1,$2,$3,$4'}>hs_exp_data/hs_recurrence_know_gtf_data2.txt

/disk/soft/circos-0.69-6/bin/circos -conf circoshhj.conf

#编码能力分析

#集群节点2

#把gtf转为fa文件

cd /disk/zhw/CRClncRNA/filter/lncRNA

gffread lncRNA.final.v2.known.gtf -o-|gffread - -g /disk/database/human/hg38/Gencode/genome.fa -w lncRNA.final.v2.known.fa -W

gffread lncRNA.final.v2.novel.gtf -o-|gffread - -g /disk/database/human/hg38/Gencode/genome.fa -w lncRNA.final.v2.novel.fa -W

gffread protein_coding.final.gtf -o-|gffread - -g /disk/database/human/hg38/Gencode/genome.fa -w protein_coding.final.fa -W

#CPAT

cd /disk/zhw/CRClncRNA/CPAT

cpat.py -g /disk/zhw/CRClncRNA/filter/lncRNA/protein_coding.final.fa -d Human_logitModel.RData -x Human_Hexamer.tsv -o CPAT_protein_coding.final

cpat.py -g /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel.fa -d Human_logitModel.RData -x Human_Hexamer.tsv -o CPAT_lncRNA.final.v2.novel

cpat.py -g /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.fa -d Human_logitModel.RData -x Human_Hexamer.tsv -o CPAT_lncRNA.final.v2.known

#CNCI

cd /disk/zhw/CRClncRNA/CNCI

python /disk/soft/CNCI-master/CNCI.py -f /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel.fa -o CNCI_lncRNA.final.v2.novel -m ve -p 4

python /disk/soft/CNCI-master/CNCI.py -f /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.fa -o CNCI_lncRNA.final.v2.known -m ve -p 4

python /disk/soft/CNCI-master/CNCI.py -f /disk/zhw/CRClncRNA/filter/lncRNA/protein_coding.final.fa -o CNCI_protein_coding.final -m ve -p 4

#bwtool

#去除长度为0的

cd /disk/zhw/CRClncRNA/bwtools

less /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' > lncRNA.final.v2.known_filt.bed

less /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' > lncRNA.final.v2.novel_filt.bed

less /disk/zhw/CRClncRNA/filter/lncRNA/protein_coding.final2.bed | perl -wanle'$b++;$a=$F[2]-$F[1];print $_ unless $a==0' > protein_coding.final_filt.bed

/disk/soft/bwtool/bwtool extract bed lncRNA.final.v2.known_filt.bed /disk/database/human/hg38/hg38.phastCons100way.bw lncRNA.final.v2.known

/disk/soft/bwtool/bwtool extract bed lncRNA.final.v2.novel_filt.bed /disk/database/human/hg38/hg38.phastCons100way.bw lncRNA.final.v2.novel

/disk/soft/bwtool/bwtool extract bed protein_coding.final_filt.bed /disk/database/human/hg38/hg38.phastCons100way.bw protein_coding.final

#求平均值

less -S protein_coding.final | perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' > bwtool_protein_coding.final_mean.txt

less -S lncRNA.final.v2.known | perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' > bwtool_lncRNA.final.v2.known_mean.txt

less -S lncRNA.final.v2.novel | perl -wanle'my @G=split /,/,$F[4];my $a=0;my $b=0;for(@G){next if /NA/;$a+=$_;$b++}if($b==0){$c="NA"}else{$c=$a/$b}print join "\t", @F[0..3], $c' > bwtool_lncRNA.final.v2.novel_mean.txt

#找出lncRNA附件的蛋白质基因名字

cd /disk/zhw/CRClncRNA/filter/lncRN

cat lncRNA.final.v2.gtf |awk '{print $10}'|sed 's/"//g'|sed 's/;//g'|sed 's/ /\t/g'|uniq > lncRNA.final.v2.gtf.genename.txt

#画ecdf图

#运行 D:\CRC_lncRNA\coding_potential\coding_potential_ecdf.R

#画密度曲线图

D:\CRC_lncRNA\filter\lncRNA\\exon_length.py

D:\CRC_lncRNA\filter\lncRNA\\length_desitny.R

#差异表达

#表达箱线图

D:\CRC_lncRNA\filter\RSEM_expression

boxplot.R

#kegg富集分析

#excell 分割出基因symbol,david分析，excell画图

####CNV

cd /disk/zhw/CRClncRNA/filter/lncRNA

sort -k 1V,1 -k 2n,2 lncRNA.final.v2.novel.bed >lncRNA.final.v2.novel.sorted.bed

sort -k 1V,1 -k 2n,2 lncRNA.final.v2.known.bed >lncRNA.final.v2.known.sorted.bed

#所有novel/known lncRNA 基因id

less lncRNA.final.v2.novel.sorted.bed | perl -wanle'next if $F[0]=~/_/;print $_' >lncRNA.final.v2.novel.sorted2.bed

less lncRNA.final.v2.known.sorted.bed | perl -wanle'next if $F[0]=~/_/;print $_' >lncRNA.final.v2.known.sorted2.bed

mv lncRNA.final.v2.novel.sorted2.bed lncRNA.final.v2.novel.sorted.bed

mv lncRNA.final.v2.known.sorted2.bed lncRNA.final.v2.known.sorted.bed

cat lncRNA.final.v2.novel.sorted.bed|awk '{print $11}'|sed 's/";//g'|sed 's/"//g'|uniq >lncRNA.final.v2.novel.geneid2.txt

cat lncRNA.final.v2.known.sorted.bed|awk '{print $11}'|sed 's/";//g'|sed 's/"//g'|uniq >lncRNA.final.v2.known.geneid2.txt

sort lncRNA.final.v2.novel.geneid2.txt |uniq >lncRNA.final.v2.novel.geneid.txt

sort lncRNA.final.v2.known.geneid2.txt |uniq >lncRNA.final.v2.known.geneid.txt

#所有novel/known lncRNA 转录本id

cat lncRNA.final.v2.novel.sorted2.bed|awk '{print $13}'|sed 's/";//g'|sed 's/"//g'|uniq >lncRNA.final.v2.novel.transcriptid.txt

cat lncRNA.final.v2.known.sorted2.bed|awk '{print $13}'|sed 's/";//g'|sed 's/"//g'|uniq >lncRNA.final.v2.known.transcriptid.txt

cd /disk/zhw/CRClncRNA/cnv

cat scores.gistic |awk '{print "chr"$2,$3,$4,$1,$8}'|sed 's/ /\t/g'>scores.gistic.bed

/disk/soft/CrossMap-0.2.7/bin/CrossMap.py bed /disk/database/human/convert_chain/hg19ToHg38.over.chain.gz scores.gistic.bed 19_38scores.gistic

sort -k 1V,1 -k 2n,2 19_38scores.gistic >19_38scores.sorted.gistic

#分为Amp Del

cat 19_38scores.sorted.gistic|grep "Amp"|awk '{print $1,$2,$3,$5}' |sed 's/chr/hs/g'>Amp_19_38scores.sorted.gistic

cat 19_38scores.sorted.gistic|grep "Del"|awk '{print $1,$2,$3,$5}' |sed 's/chr/hs/g'>Del_19_38scores.sorted.gistic

bedtools intersect -a 19_38scores.sorted.gistic -b /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel.sorted.bed -wb >novel_scores.gistic.bed

bedtools intersect -a 19_38scores.sorted.gistic -b /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.sorted.bed -wb >known_scores.gistic.bed

#circos图使用，不要了

#cat novel_scores.gistic.bed |grep "Amp"|awk {'print $1,$7,$8,$5*100'}|sed 's/chr/hs/g'>Amp_novel_scores.gistic.bed

#cat novel_scores.gistic.bed |grep "Del"|awk {'print $1,$7,$8,$5*100'}|sed 's/chr/hs/g'>Del_novel_scores.gistic.bed

#cat known_scores.gistic.bed |grep "Amp"|awk {'print $1,$7,$8,$5*100'}|sed 's/chr/hs/g'>Amp_known_scores.gistic.bed

#cat known_scores.gistic.bed |grep "Del"|awk {'print $1,$7,$8,$5*100'}|sed 's/chr/hs/g'>Del_known_scores.gistic.bed

#取位点中点和+1

#le novel_scores.gistic.bed |grep "Amp"| perl -wanle'$mean = int($F[6]+$F[7]);$mean2 = $mean+1;$haha=$F[4]*100;$F[0]=~s/chr/hs/;print "$F[0] $mean $mean2 $haha"'|uniq>Amp_novel_scores.gistic.bed

#le novel_scores.gistic.bed |grep "Del"| perl -wanle'$mean = int($F[6]+$F[7]);$mean2 = $mean+1;$haha=$F[4]*100;$F[0]=~s/chr/hs/;print "$F[0] $mean $mean2 $haha"'|uniq>Del_novel_scores.gistic.bed

#le known_scores.gistic.bed |grep "Amp"| perl -wanle'$mean = int($F[6]+$F[7]);$mean2 = $mean+1;$haha=$F[4]*100;$F[0]=~s/chr/hs/;print "$F[0] $mean $mean2 $haha"'|uniq>Amp_known_scores.gistic.bed

#le known_scores.gistic.bed |grep "Del"| perl -wanle'$mean = int($F[6]+$F[7]);$mean2 = $mean+1;$haha=$F[4]*100;$F[0]=~s/chr/hs/;print "$F[0] $mean $mean2 $haha"'|uniq>Del_known_scores.gistic.bed

#绘制circos图

cd /disk/zhw/CRClncRNA/cnv/circos

/disk/soft/circos-0.69-6/bin/circos -conf circoscnv.conf

#test:

#/disk/soft/circos-0.69-6/bin/circos -conf circos2.conf

#head -1000 novel_scores.gistic.bed |grep "Amp"|awk {'print $1,$2,$3,$5*100'}|sed 's/chr/hs/g'>Amp_novel_scores.gistic2.bed

#head -1000 known_scores.gistic.bed |grep "Amp"|awk {'print $1,$2,$3,$5*100'}|sed 's/chr/hs/g'>Amp_known_scores.gistic2.bed

#head -1000 novel_scores.gistic.bed |grep "Del"|awk {'print $1,$2,$3,$5*100'}|sed 's/chr/hs/g'>Del_novel_scores.gistic2.bed

#head -1000 known_scores.gistic.bed |grep "Del"|awk {'print $1,$2,$3,$5*100'}|sed 's/chr/hs/g'>Del_known_scores.gistic2.bed

#筛选percent大于25的、绘制柱状图、做overlap

cat novel_scores.gistic.bed|awk -F"\t" '$5>0.25{print $0}'>percentages25novel_scores.gistic.bed

cat known_scores.gistic.bed|awk -F"\t" '$5>0.25{print $0}'>percentages25known_scores.gistic.bed

#novel/known lncRNA 转录本id

cat percentages25novel_scores.gistic.bed |awk '{print $18}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25novel.transcriptid.txt

cat percentages25known_scores.gistic.bed |awk '{print $18}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25known.transcriptid.txt

#novel/known lncRNA 基因id

cat percentages25novel_scores.gistic.bed |awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25novel.geneid.txt

cat percentages25known_scores.gistic.bed |awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25known.geneid.txt

#分别提取出novel和known的基因id和对应的CNV频率(Amp和Del分开)

cat novel_scores.gistic.bed|grep "Amp"|awk '{print $1,$2,$3,$4,$5,$16}'|sed 's/";//g'|sed 's/"//g'|sort|uniq>rep_all_novel.Amp.geneid_precent.gistic

cat novel_scores.gistic.bed|grep "Del"|awk '{print $1,$2,$3,$4,$5,$16}'|sed 's/";//g'|sed 's/"//g'|sort|uniq>rep_all_novel.Del.geneid_precent.gistic

cat known_scores.gistic.bed|grep "Amp"|awk '{print $1,$2,$3,$4,$5,$16}'|sed 's/";//g'|sed 's/"//g'|sort|uniq>rep_all_known.Amp.geneid_precent.gistic

cat known_scores.gistic.bed|grep "Del"|awk '{print $1,$2,$3,$4,$5,$16}'|sed 's/";//g'|sed 's/"//g'|sort|uniq>rep_all_known.Del.geneid_precent.gistic

#python获取到没有比对部分，合并两个文件#获取到有cnv的 取到没有CNV变异的复制为0 合并 #排序

#cd /disk/zhw/CRClncRNA/cnv/heatmap

#perl uniq_mean.pl ../rep_all_novel.Amp.geneid_precent.gistic >rep_all_novel.Amp.geneid_precent_gene_num.gistic

#python addzero_lncRNA2.py /disk/zhw/CRClncRNA/cnv/rep_all_novel.Amp.geneid_precent.gistic novel_Amp_no_bedtools_lncRNA.bed

#cat rep_all_novel.Amp.geneid_precent_gene_num.gistic novel_Amp_no_bedtools_lncRNA.bed > all_novel.Amp.geneid_precent2.gistic

#sort -k1,1V -k2,2n all_novel.Amp.geneid_precent2.gistic>all_novel.Amp.geneid_precent2_dorted.gistic3

#Del

#perl uniq_mean.pl ../rep_all_novel.Del.geneid_precent.gistic >rep_all_novel.Del.geneid_precent_gene_num.gistic

#python addzero_lncRNA2.py /disk/zhw/CRClncRNA/cnv/rep_all_novel.Del.geneid_precent.gistic novel_Del_no_bedtools_lncRNA.bed

#cat rep_all_novel.Del.geneid_precent_gene_num.gistic novel_Del_no_bedtools_lncRNA.bed > all_novel.Del.geneid_precent2.gistic

#sort -k1,1V -k2,2n all_novel.Del.geneid_precent2.gistic>all_novel.Del.geneid_precent2_dorted.gistic3

#perl uniq_mean.pl all_novel.Del.geneid_precent2.gistic >all_novel.Del.geneid_precent_gene_num.gistic

#perl uniq_mean.pl all_known.Amp.geneid_precent2.gistic >all_known.Amp.geneid_precent_gene_num.gistic

#perl uniq_mean.pl all_known.Del.geneid_precent2.gistic >all_known.Del.geneid_precent_gene_num.gistic

ls | awk -F "_" '{print $1}' >../cancer.txt

#生成矩阵

sh foralllcancer.sh

#把Del改为负数

sh Del_negetive_num.sh

#合并known\novel

sh bind_knownnovel.sh

运行R文件D:\CRC_lncRNA\cnv\percentCNV\allcancer_chro_heatmap.R

cat percentages25novel_scores.gistic.bed|grep "Del"|awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25novel.Del.geneid.txt

cat percentages25novel_scores.gistic.bed|grep "Amp"|awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25novel.Amp.geneid.txt

cat percentages25known_scores.gistic.bed|grep "Del"|awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25known.Del.geneid.txt

cat percentages25known_scores.gistic.bed|grep "Amp"|awk '{print $16}'|sed 's/";//g'|sed 's/"//g'|uniq >percentages25known.Amp.geneid.txt

cat percentages25novel.Del.geneid.txt percentages25known.Del.geneid.txt>percentages25.Del.geneid.txt

cat percentages25novel.Amp.geneid.txt percentages25known.Amp.geneid.txt>percentages25.Amp.geneid.txt

#运行D:\CRC_lncRNA\diffexp\gtf_bind_same_lncNRA.py

#先将D:\CRC_lncRNA\filter\lncRNA\lncRNA.final.v2.gtf文件only_min_max_position_lncRNA.final.v2.gtf,只有最大最小的位置，将一个lncRNA多个位置合并为一个

#运行：D:\CRC_lncRNA\diffexp\different_gene_position_log2FoldChange_for_circos.py

#cat rec_DESeq2_edgeR_up_gene_for_circos.txt |sort -k 1V,1 -k 2n,2 |uniq >uniq_rec_DESeq2_edgeR_up_gene_for_circos.txt

#cat rec_DESeq2_edgeR_down_gene_for_circos.txt |sort -k 1V,1 -k 2n,2 |uniq >uniq_rec_DESeq2_edgeR_down_gene_for_circos.txt

#cat normal_DESeq2_edgeR_up_gene_for_circos.txt |sort -k 1V,1 -k 2n,2 |uniq >uniq_normal_DESeq2_edgeR_up_gene_for_circos.txt

#cat normal_DESeq2_edgeR_down_gene_for_circos.txt |sort -k 1V,1 -k 2n,2 |uniq >uniq_normal_DESeq2_edgeR_down_gene_for_circos.txt

/disk/soft/circos-0.69-6/bin/circos -conf circoscnvright.conf

head -100 uniq_rec_DESeq2_edgeR_up_gene_for_circos.txt>uniq_rec_DESeq2_edgeR_up_gene_for_circos2.txt

head -100 uniq_rec_DESeq2_edgeR_down_gene_for_circos.txt> uniq_rec_DESeq2_edgeR_down_gene_for_circos2.txt

head -100 uniq_normal_DESeq2_edgeR_up_gene_for_circos.txt>uniq_normal_DESeq2_edgeR_up_gene_for_circos2.txt

head -100 uniq_normal_DESeq2_edgeR_down_gene_for_circos.txt >uniq_normal_DESeq2_edgeR_down_gene_for_circos2.txt

head -10000 ../Del_19_38scores.sorted.gistic >../Del_19_38scores.sorted.gistic2

head -10000 ../Amp_19_38scores.sorted.gistic >../Amp_19_38scores.sorted.gistic2

/disk/soft/circos-0.69-6/bin/circos -conf circoscnvtest.conf

#差异lncRNA在13种癌症中的热图，上为上调，下为下调，logFC排序

#将bed 文件和gist文件比对获取差异lncRNA的score值

bedtools intersect -a /disk/zhw/CRClncRNA/cnv/19_38scores.sorted.gistic -b intersect_normal_cnv_up_down_gtf.bed -wb | awk '{print $1,$2,$3,$4,$5,$9}'|sed 's/\t/ /g'>intersect_normal_cnv_up_down_scores.gistic.bed

dos2unix intersect_normal_cnv_up_down_scores.gistic.bed

#对应多个去平均值合并

perl /disk/zhw/CRClncRNA/cnv/CNV_gistic_data/uniq_mean.pl /disk/zhw/CRClncRNA/cnv/differentgene_updown_heatmap/intersect_normal_cnv_up_down_scores.gistic.bed >uniq_intersect_normal_cnv_up_down_scores.gistic.bed

cat /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel.sorted.bed /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.sorted.bed >/disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel_knoiwn.sorted.bed

cat /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel.geneid.txt /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.known.geneid.txt > /disk/zhw/CRClncRNA/filter/lncRNA/lncRNA.final.v2.novel_known.geneid.txt

#############################

#单个流程

cat /disk/zhw/CRClncRNA/cnv/CNV_gistic_data/gistic/BRCA_scores.gistic|awk '{print "chr"$2,$3,$4,$1,$8}'|sed 's/ /\t/g'>BRCA_scores.gistic.bed

/disk/soft/CrossMap-0.2.7/bin/CrossMap.py bed /disk/database/human/convert_chain/hg19ToHg38.over.chain.gz BRCA_scores.gistic.bed BRCA.19_38scores.gistic

sort -k 1V,1 -k 2n,2 BRCA.19_38scores.gistic >BRCA.19_38scores.sorted.gistic

bedtools intersect -a BRCA.19_38scores.sorted.gistic -b /disk/zhw/CRClncRNA/cnv/differentgene_updown_heatmap/intersect_normal_cnv_up_down_gtf.bed -wb | awk '{print $1,$2,$3,$4,$5,$9}'|sed 's/\t/ /g'>BRCA_scores.gistic.bed

dos2unix BRCA_scores.gistic.bed

cat BRCA_scores.gistic.bed |grep "Amp"|sed 's/";//g'|sed 's/"//g'|sort|uniq>BRCA.rep_all.Amp.geneid_precent.gistic

cat BRCA_scores.gistic.bed |grep "Del"|sed 's/";//g'|sed 's/"//g'|sort|uniq>BRCA.rep_all.Del.geneid_precent.gistic

perl /disk/zhw/CRClncRNA/cnv/CNV_gistic_data/uniq_mean.pl BRCA.rep_all.Amp.geneid_precent.gistic >BRCA.rep_all_Amp.geneid_precent_gene_num.gistic

perl /disk/zhw/CRClncRNA/cnv/CNV_gistic_data/uniq_mean.pl BRCA.rep_all.Del.geneid_precent.gistic >BRCA.rep_all_Del.geneid_precent_gene_num.gistic

python addzero_lncRNA2.py BRCA.rep_all_Amp.geneid_precent_gene_num.gistic BRCA.Amp_no_bedtools_lncRNA.bed

python addzero_lncRNA2.py BRCA.rep_all_Del.geneid_precent_gene_num.gistic BRCA.Del_no_bedtools_lncRNA.bed

cat UVM.rep_all_Amp.geneid_precent_gene_num.gistic UVM.Amp_no_bedtools_lncRNA.bed>UVM.res_novel_known.Amp.geneid_precent_sorted.gistic

cat UVM.rep_all_Del.geneid_precent_gene_num.gistic UVM.Del_no_bedtools_lncRNA.bed>UVM.res_novel_known.Del.geneid_precent_sorted.gistic

cat UCEC.res_novel_known.Del.geneid_precent_sorted.gistic | awk '{print $1"\t"$2"\t"$3"\t-"$4}'> UCEC.res_novel_known.Del.geneid_precent_sorted2.gistic

##############################

#单个

sh pineline.sh

#批量：

cd /disk/zhw/CRClncRNA/cnv/differentgene_updown_heatmap

sh foralllcancer13.sh

sh Del_negetive_num.sh

#Del改为负数

一键复制

编辑

Web IDE

原始数据

按行查看

历史

weixin_39954682
关注
  • 0
    点赞
  • 踩
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
CNCI的使用--RNA蛋白编码预测软件
m0_45248682的博客
01-18 5758
（生信）RNA蛋白编码预测软件-CNCI的使用 CNCI简介： CNCI是由中科院研发的一款基于SVM（支持向量机）的LncRNA预测软件，它可以不依赖于已知的RNA注释信息来进行预测，同时其对不完全转录和反义的RNA有着良好的分类效果，本文将根据github的说明总结一些简单的操作。 软件安装与准备： linux 32位或者linux 64位系统 python 2.74或者2.0版本（详细安装...
python lncrna_【云计算】LncRNA生信分析案例
weixin_39783915的博客
12-10 586
本文主要向大家介绍了【云计算】LncRNA生信分析案例，通过具体的内容向大家展现，希望对大家学习云计算有所帮助。LncRNA的筛选做个笔记，哈哈哈这个流程是处于链特异性建库(dUTP)的RNA-seq流程，对于非链特异性建库需要修改一些参数。一、qc和reads质量过滤，fastqc，multiqc，trim_galore就可以了1.fastqc得到质量报告ls*gz|xargs-I{}...
linux之sed用法
u012485320的专栏
12-11 615
sed是一个很好的文件处理工具，本身是一个管道命令，主要是以行为单位进行处理，可以将数据行进行替换、删除、新增、选取等特定工作，下面先了解一下sed的用法 sed命令行格式为： sed [-nefri] ‘command’ 输入文本 常用选项： -n∶使用安静(silent)模式。在一般 sed 的用法中，所有来自 STDIN的资料一般都会被列出到萤幕上。但如果加上 -n 参数后，则只
BED文件如何排序，sort按列排序
GeekFocus
05-21 5012
1，第一列按照染色体编号进行排序，排序后应该是chr1, chr2, chr4, chr5, chr10, chr20, chrX. 使用-V 2， 第二列和第三列按照数字序进行排序。使用-n sort -k1,1V -k2,2n -k3,3n target_interval.bed > sort.bed 其中-k选项是指定第几列。 ...
BW Extract Data 综合分析
sap_arron的专栏
12-31 687
Dimensions of Data Extraction ( 数据抽取的维数)     数据抽取的过程通常可以由四种不同的维度来进行描述和分类。       首先是抽取模式，抽取模式通常分为完全抽取和动态抽取。两者意思很明确，完全抽取是每次抽取的时候讲数据源可用的所有数据都抽取过来，而动态抽取则是每次抽取的时候只抽取更新和增加了的新的数据。     其次是按照抽取的情景作为抽取的
calculate_R_matrix.rar_As One_edge computing_lncRNA_miRNA_transf
07-13
By which, the resource transfer process, as one of the weighting methods for one-mode projection of a bipartite network [73], was used to weight the miRNA projection of the lncRNA-miRNA and miRNA-EF ...
PhyloCSF.zip_coservation_lncRNA_phyloCSF分析_phylocsf值分析_rna保守性分析
09-23
在"PhyloCSF.zip"这个压缩包中，包含了一个名为"PhyloCSF.py"的Python脚本，这很可能是用于执行PhyloCSF分析的代码。在进行lncRNA的保守性分析时，用户可能需要准备多物种的基因组序列数据，以及待分析的lncRNA候选...
EPLMI-master.zip_EPLMI_lncRNA_lncRNA-miRNA_预测
07-15
通过分析和应用EPLMI-master中的资源，研究者可以对新的lncRNA和miRNA组合进行预测，探索未知的生物学功能。此外，该模型的开发和应用也有助于优化现有的预测方法，提高预测效率，进一步推动lncRNA-miRNA相互作用...
LncRNA芯片分析-自己总结.pdf
最新发布
08-14
LncRNA 芯片分析 LncRNA 芯片分析是指 Long Non-Coding RNA（长非编码 RNA）的微阵列分析。LncRNA 是一类功能性 RNA 分子，长度超过 200 个核苷酸，但不编码蛋白质。LncRNA 的功能包括调控基因表达、 RNA 处理和...
(lncRNA)介绍.pdf.pdf
04-06
生物信息入门知识，RNA测序分析，适合生命科学生物信息学相关专业本科生研究生，LNCrna与肿瘤分析
CPAT:RNA编码潜力评估工具-开源
04-28
使用RNA序列，已鉴定出数以万计的新转录本和同工型（Djebali等，自然，2012； Carbili等，基因与发展，2011）。这些隐藏的转录组的发现使区分编码和非编码RNA的需求重新焕发活力。 。 但是，大多数以前的编码潜力预测方法都严重依赖于比对，即成对比对以搜索蛋白质证据或多重比对以计算系统发育保守性得分（例如CPC，PhyloCSF和RNACode）。 这是因为大多数以前鉴定的转录本，包括蛋白质编码RNA和短的管家/调控RNA（例如snRNA，snoRNA和tRNA）都是高度保守的。 尽管仍然非常有用，但是这些方法有一些局限性：大多数lncRNA保守性较低，并且倾向于谱系特异性，这极大地限制了基于比对的方法的区分能力。 例如，从斑马鱼中检测到550个lncRNA，其中只有29个具有可检测序列
python lncrna_使用CPAT分析lncRNA
weixin_39820136的博客
12-10 729
CPAT(Coding Potential Assessment Tool)可以从RNA-Seq分析得到的转录本中筛选出编码的和非编码的RNA。文章发表在Nucleic Acids Research：http://nar.oxfordjournals.org/content/41/6/e74.long代码托管在SourceForge：http://rna-cpat.sourceforge.net/...
生信（一）对BED文件进行排序
生信了
10-22 5671
原创：hxj7 关键词：bed; sort; cmp; key; alpha-numeric 问题 在处理NGS数据时，经常要对BED文件进行排序。比如BED文件长这样，分隔符是’\t’： 我们想按照如下规则进行排序： 第一列按照染色体编号进行排序，排序后应该是chr1, chr2, chr4, chr5, chr10, chr20, chrX。 第二列和第三列按照数字序进行排序。 第一个子...
bed文件格式详解
热门推荐
高锦的博客
02-07 1万+
BED 文件格式是一个可变方式的数据线，用来描述注释的数据。BED线有3个要求的字段和9个额外的字段。每条线的字段数目必须是任意单条数据的在注释上一致。可选字段的序试结合低数字的字段必须流行如果高位字段被使用。 首先是三个要求的BED字段 1,chrom, 染色体或scafflold 的名字(eg chr3， chrY, chr2_random, scaffold0671
0084-【生信软件】-ANNOVAR-使用
leadingsci的博客
10-07 5438
文章目录ANNOVAR的程序模块ANNOVAR的输入文件ANNOVAR输入文件的格式转换ANNOVAR注释功能下载数据库Annotate_variation.plAnnotate_variation.pl 实例Region-based annotationFilter-based annotation下面给大家介绍常用的两种过滤注释dbSNP annotations ANNOVAR的程序模块 (A...
python lncrna_LncRNA生信分析案例
weixin_39583655的博客
12-10 933
LncRNA的筛选做个笔记，哈哈哈这个流程是处于链特异性建库(dUTP)的RNA-seq流程，对于非链特异性建库需要修改一些参数。一、qc和reads质量过滤，fastqc，multiqc，trim_galore就可以了1.fastqc得到质量报告ls *gz |xargs -I {} echo 'nohup fastqc {} &'>fastqc.shbash fastqc.sh上...
安装CPAT--使用CPAT分析lncRNA
mengjiaoduan的博客
08-10 5860
CPAT(Coding Potential Assessment Tool)可以从RNA-Seq分析得到的转录本中筛选出编码的和非编码的RNA。 文章发表在Nucleic Acids Research：http://nar.oxfordjournals.org/content/41/6/e74.long 代码托管在SourceForge：http://rna-cpat.sourceforge.
python解析gff文件中的转录本
Cassiel60的博客
05-27 6485
1.下载基因组注释文件，选择对应的版本：ftp://ftp.ncbi.nlm.nih.gov/genomes/Homo_sapiens/ARCHIVE/BUILD.37.3/GFF/ 2.GTF 为General Transfer Format ，熟悉格式http://www.huoyunjn.com/wuliuxinwen/2/33709819.htm。 第三列feature- 后面...
python lncrna_[转载]lncrna分析流程
06-08
以下是一般的 lncRNA 分析流程： 1. 数据获取：从公共数据库（如NCBI、ENSEMBL）下载RNA-seq数据。 2. 质量控制：使用FASTQC或其他软件对RNA-seq原始数据进行质量评估，删去低质量序列。 3. 数据预处理：使用...

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值