cat cnci.result.file | cut -f 1 | sed -e 's/>//' > cnci.1.tcons
cat cnci.result.file | perl -ne '@t = split(/\t/,$_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $score = $1; print $tid . "\t" . $score . "\n";' > 1.cnci
cat tcons.disap | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 v4.bed 4 | cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > bed.v4.disap
cat fa.v4.disap | perl -ne 'chomp; if(/>(.*)/){ print "\n". $1. "\t";} else{ print $_;}' > fa.v4.disap.1
cat fa.v4.disap.1 | awk 'NR!=1' > fa.v4.disap
cat fa.v4.disap.1 | awk '$0' > fa.v4.disap
awk 'NR > 1000 && NR < 1010' fa.v4.disap fa.v4.disap.1
awk 'NR > 1710 ' fa.v4.disap
|
cat 1.cnci | cut -f 1 | sub.pl - tcons.v4 | perl $CMD/leftJoin.pl - 1 seq.v4.2 1 | awk '{ print ">"$1 "\n" $3;}' > 2.fa
cat 1.cnci | cut -f 1 | sub.pl - tcons.v4 | perl $CMD/leftJoin.pl - 1 seq.v4.2 1 | awk '{ print ">"$1 "\n" $3;}' > 2.fa
cat cnci.result.file | perl -ne '@t = split(/\t/, $_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $score = $1; print $tid . "\t" . $score . "\n";' > 2.cnci
cut -f 1 1.cnci 2.cnci | sub.pl - tcons.v4 | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 seq.v4.2 1 | awk '{print ">" $1 "\n" $3;}' > 3.fa
cat cnci.result.file | perl -ne '@t = split(/\t/, $_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $sc = $1; print $tid . "\t" . $sc . "\n";' > 3.cnci
cat cnci.v4.2 | cut -f 1 | perl $CMD/leftJoin.pl - 1 v4.bed.rmCoding 4 | cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > v4.bed.rmCoding.cnci
cat v4.bed.rmCoding.cnci | getBedSeqLength.sh - | awk '$2 > 200' | perl $CMD/leftJoin.pl - 1 v4.bed.rmCoding.cnci 4 | cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.v4.lnc
for bam in `ls /leofs/biozy/human_16tissue_bam/*.bam` ; do
tag=`basename $bam .bam`;
cufflinks -G loci.combined.gtf -p 10 -o fpkm/$tag $bam 1 >$tag.log 2 > $tag.err;
if [ ! -s xlocId ]; then
cut -f 1 fpkm/$tag/genes.fpkm_tracking| sort -k 1 | awk '{if($1 != "tracking_id") print $0;}' > xlocId
cp xlocId humanLncGene.fpkm
fi
cut -f 1,10 fpkm/$tag/genes.fpkm_tracking| sort -k 1 | cut -f 2 | awk '{if($1 != "FPKM") print $0; }' > humanLoci.fpkm.$tag
paste humanLncGene.fpkm humanLoci.fpkm.$tag > tmp
mv tmp humanLncGene.fpkm
done
rm xlocId
cat LenLt95Percent.fa.blat.bed | getBedSeqLength.sh - | awk '$2>200' | wc -l
cat LenLt95Percent.fa.blat.bed | getBedSeqLength.sh - | awk '$2>200' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 LenLt95Percent.fa.blat.bed 4 | cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.v3.reblat
cat bed.v3.reblat | cut -f 4 | perl $CMD/rmByKey.pl - mouse.bed 4 > bed.v3.1
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 100' | wc -l
cat ncid.1.n | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 bed.lenGt50 4 | awk '$5'| cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > ncid.1.bed
cat ncid.1.bed | cut -f 4 | sub.pl ncid.withBEd - | wc -l
cat m.tracking | perl -ne '@t = split(/\t/,$_); $t[4] =~ /.*?\|(.*?)\|/; $oId = $1; print $t[0] . "\t" .$oId . "\n";' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 bed.v3.more.m 4 | awk '{print $3 "\t" $4 "\t" $5 "\t" $2 "\t" $7 "\t" $8 "\t" $9 "\t" $10 "\t" $11 "\t" $12 "\t" $13 "\t" $14;}' > bed.v3.more.m.1
cuffcompare -r mm9.refseq.nm.gtf v4.combined.gtf -o coding2 -C
cat coding1.tracking coding2.tracking | awk '$4 == "=" { print $5}' | perl -ne '$_ =~ /.*?\|(.*?)\|/; print $1 . "\n";' > tcons.coding
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 < 20' | wc -l
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 50' | wc -l
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 50' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 noncode.mm.bed 4 |cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.lenGt50
awk -F "\t" '{print $1 "\t" $7;}' source.v4 | head
cut -f 4 bed.v4.rmCoding | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 source.v4 1 | awk -F "\t" '{print $1 "\t" $8;}'
cat cnci.result.file | perl -ne '@t = split(/\t/,$_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $score = $1; print $tid . "\t" . $score . "\n";' > 1.cnci
cat tcons.disap | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 v4.bed 4 | cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > bed.v4.disap
cat fa.v4.disap | perl -ne 'chomp; if(/>(.*)/){ print "\n". $1. "\t";} else{ print $_;}' > fa.v4.disap.1
cat fa.v4.disap.1 | awk 'NR!=1' > fa.v4.disap
cat fa.v4.disap.1 | awk '$0' > fa.v4.disap
awk 'NR > 1000 && NR < 1010' fa.v4.disap fa.v4.disap.1
awk 'NR > 1710 ' fa.v4.disap
|
cat 1.cnci | cut -f 1 | sub.pl - tcons.v4 | perl $CMD/leftJoin.pl - 1 seq.v4.2 1 | awk '{ print ">"$1 "\n" $3;}' > 2.fa
cat 1.cnci | cut -f 1 | sub.pl - tcons.v4 | perl $CMD/leftJoin.pl - 1 seq.v4.2 1 | awk '{ print ">"$1 "\n" $3;}' > 2.fa
cat cnci.result.file | perl -ne '@t = split(/\t/, $_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $score = $1; print $tid . "\t" . $score . "\n";' > 2.cnci
cut -f 1 1.cnci 2.cnci | sub.pl - tcons.v4 | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 seq.v4.2 1 | awk '{print ">" $1 "\n" $3;}' > 3.fa
cat cnci.result.file | perl -ne '@t = split(/\t/, $_); $t[0] =~ />(.*)/; $tid = $1; $t[2] =~ /score: (.*)/; $sc = $1; print $tid . "\t" . $sc . "\n";' > 3.cnci
cat cnci.v4.2 | cut -f 1 | perl $CMD/leftJoin.pl - 1 v4.bed.rmCoding 4 | cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > v4.bed.rmCoding.cnci
cat v4.bed.rmCoding.cnci | getBedSeqLength.sh - | awk '$2 > 200' | perl $CMD/leftJoin.pl - 1 v4.bed.rmCoding.cnci 4 | cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.v4.lnc
for bam in `ls /leofs/biozy/human_16tissue_bam/*.bam` ; do
tag=`basename $bam .bam`;
cufflinks -G loci.combined.gtf -p 10 -o fpkm/$tag $bam 1 >$tag.log 2 > $tag.err;
if [ ! -s xlocId ]; then
cut -f 1 fpkm/$tag/genes.fpkm_tracking| sort -k 1 | awk '{if($1 != "tracking_id") print $0;}' > xlocId
cp xlocId humanLncGene.fpkm
fi
cut -f 1,10 fpkm/$tag/genes.fpkm_tracking| sort -k 1 | cut -f 2 | awk '{if($1 != "FPKM") print $0; }' > humanLoci.fpkm.$tag
paste humanLncGene.fpkm humanLoci.fpkm.$tag > tmp
mv tmp humanLncGene.fpkm
done
rm xlocId
cat LenLt95Percent.fa.blat.bed | getBedSeqLength.sh - | awk '$2>200' | wc -l
cat LenLt95Percent.fa.blat.bed | getBedSeqLength.sh - | awk '$2>200' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 LenLt95Percent.fa.blat.bed 4 | cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.v3.reblat
cat bed.v3.reblat | cut -f 4 | perl $CMD/rmByKey.pl - mouse.bed 4 > bed.v3.1
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 100' | wc -l
cat ncid.1.n | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 bed.lenGt50 4 | awk '$5'| cut -f 2,3,4,5,6,7,8,9,10,11,12,13 > ncid.1.bed
cat ncid.1.bed | cut -f 4 | sub.pl ncid.withBEd - | wc -l
cat m.tracking | perl -ne '@t = split(/\t/,$_); $t[4] =~ /.*?\|(.*?)\|/; $oId = $1; print $t[0] . "\t" .$oId . "\n";' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 bed.v3.more.m 4 | awk '{print $3 "\t" $4 "\t" $5 "\t" $2 "\t" $7 "\t" $8 "\t" $9 "\t" $10 "\t" $11 "\t" $12 "\t" $13 "\t" $14;}' > bed.v3.more.m.1
cuffcompare -r mm9.refseq.nm.gtf v4.combined.gtf -o coding2 -C
cat coding1.tracking coding2.tracking | awk '$4 == "=" { print $5}' | perl -ne '$_ =~ /.*?\|(.*?)\|/; print $1 . "\n";' > tcons.coding
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 < 20' | wc -l
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 50' | wc -l
cat noncode.mm.bed| getBedSeqLength.sh - | awk '$2 > 50' | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 noncode.mm.bed 4 |cut -f 3,4,5,6,7,8,9,10,11,12,13,14 > bed.lenGt50
awk -F "\t" '{print $1 "\t" $7;}' source.v4 | head
cut -f 4 bed.v4.rmCoding | perl /leofs/noncode/NONCODEv4/cmds/leftJoin.pl - 1 source.v4 1 | awk -F "\t" '{print $1 "\t" $8;}'