Dpuiu CA - Revision history

Dpuiu: /* Meryl */

2011-07-26T20:16:47Z

Meryl

← Older revision		Revision as of 20:16, 26 July 2011
Line 267:		Line 267:
	meryl -M sub -s ref.22mers -s qry.22mers -o diff.22mers		meryl -M sub -s ref.22mers -s qry.22mers -o diff.22mers
	meryl -Dt -s diff.22mers > diff.22mers.seq		meryl -Dt -s diff.22mers > diff.22mers.seq

			# Combine mers

	* jellyfish		* jellyfish

Dpuiu: /* Meryl */

2011-06-28T20:08:52Z

Meryl

← Older revision		Revision as of 20:08, 28 June 2011
Line 254:		Line 254:

	# Get mer frequencies		# Get mer frequencies
	meryl -C -B -m 22 -s prefix.seq -o prefix.22mers		meryl -C -B -m 22 -s prefix.seq -o prefix.22mers

	# Dump mer sequences		# Dump mer sequences
	meryl -Dt -s prefix.22mers		meryl -Dt -s prefix.22mers > prefix.22mers.seq

	# Dump histogram		# Dump histogram
	meryl -Dh -s prefix.22mers \| sort -nk2 -r ~~\| more~~		meryl -Dh -s prefix.22mers \| sort -nk2 -r > prefix.22mers.histo

			# Get missing mers
			meryl -C -B -m 22 -s ref.fasta -o ref.22mers
			meryl -C -B -m 22 -s qry.fasta -o qry.22mers
			meryl -M sub -s ref.22mers -s qry.22mers -o diff.22mers
			meryl -Dt -s diff.22mers > diff.22mers.seq

	* jellyfish		* jellyfish

Dpuiu: /* Meryl */

2011-06-17T14:45:10Z

Meryl

← Older revision		Revision as of 14:45, 17 June 2011
Line 253:		Line 253:
	= Meryl =		= Meryl =

	* Get mer frequencies		# Get mer frequencies
	meryl -C -B -m 22 -s prefix.seq -o prefix.22mers		meryl -C -B -m 22 -s prefix.seq -o prefix.22mers

	* Dump mer sequences		# Dump mer sequences
	meryl -Dt -s prefix.22mers		meryl -Dt -s prefix.22mers

	* Dump histogram		# Dump histogram
	meryl -Dh -s prefix.22mers \| sort -nk2 -r \| more		meryl -Dh -s prefix.22mers \| sort -nk2 -r \| more

	* ~~Other programs~~		* jellyfish
			# Get mer frequencies
			jellyfish count -s 1000000000 -m 18 --both-strands -t 16 -o prefix.jf prefix.fastq [prefix.seq]
			jellyfish merge prefix.jf_? -o prefix.jf

			# Dump histogram
			jellyfish histo prefix.jf



			* countKmers.pl (other)
	cat lib.seq \| ~/bin/countKmers.pl -k 22 \| head -20 \| grep -v "^>" > 22mers.fwd.grep		cat lib.seq \| ~/bin/countKmers.pl -k 22 \| head -20 \| grep -v "^>" > 22mers.fwd.grep
	cat lib.seq \| ~/bin/countKmers.pl -k 22 \| head -20 \| revseq \| grep -v "^>" > 22mers.rev.grep		cat lib.seq \| ~/bin/countKmers.pl -k 22 \| head -20 \| revseq \| grep -v "^>" > 22mers.rev.grep
	cat 22mers.fwd.grep 22mers.rev.grep > 22mers.grep		cat 22mers.fwd.grep 22mers.rev.grep > 22mers.grep
	cat lib.seq \| ~/bin/fgrep.pl -f 22mer.grep \| count.pl		cat lib.seq \| ~/bin/fgrep.pl -f 22mer.grep \| count.pl



			----

			meryl -C -B -m 12 -s prefix.seq -o prefix.12mers
			meryl -Dh -s prefix.12mers \| sort -nk2 -r \| more

	= OBT =		= OBT =

Dpuiu: /* Posmap */

2011-02-24T18:07:17Z

Posmap

← Older revision		Revision as of 18:07, 24 February 2011
Line 574:		Line 574:
	# one of ...		# one of ...
	cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sou frg -fea frg -p > genome.posmap.frgscf.gff		cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sou frg -fea frg -p > genome.posmap.frgscf.gff
	#cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p \| sed 's/[ab]//' > genome.posmap.frgscf.gff		cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p \| sed 's/[ab]//' > genome.posmap.frgscf.gff
	cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p >! genome.posmap.frgscf.gff		cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p >! genome.posmap.frgscf.gff

Line 582:		Line 582:
	cat genome.posmap.scflen \| perl -ane 'print "$F[0]\t$F[0]\t0\t$F[1]\tf\n";' \| posmap2gff.pl -sou scf >> genome.posmap.scflen.gff		cat genome.posmap.scflen \| perl -ane 'print "$F[0]\t$F[0]\t0\t$F[1]\tf\n";' \| posmap2gff.pl -sou scf >> genome.posmap.scflen.gff

	cat genome*gff \| p 'print $_ if($F[8]==~~1374988~~);' >! ~/~~1374988~~.gff		setenv SEQID 1374988
			cat genome*gff \| p 'print $_ if($F[8]==$ENV{SEQID});' >! $SEQID.gff

			~/szdevel/Apollo/apollo -i gff -f $SEQID.gff

	* Get 0cvg regions		* Get 0cvg regions

Dpuiu: /* Posmap */

2011-02-24T18:01:03Z

Posmap

← Older revision		Revision as of 18:01, 24 February 2011
Line 580:		Line 580:
	cat genome.posmap.ctgscf \| ~/bin/posmap2gff.pl -sou ctg -p >! genome.posmap.ctgscf.gff		cat genome.posmap.ctgscf \| ~/bin/posmap2gff.pl -sou ctg -p >! genome.posmap.ctgscf.gff

	cat genome*gff \| p 'print $_ if($F[8]==1374988);' >! ~/1374988.gff		cat genome.posmap.scflen \| perl -ane 'print "$F[0]\t$F[0]\t0\t$F[1]\tf\n";' \| posmap2gff.pl -sou scf >> genome.posmap.scflen.gff

			cat genome*gff \| p 'print $_ if($F[8]==1374988);' >! ~/1374988.gff

	* Get 0cvg regions		* Get 0cvg regions

Dpuiu: /* Posmap */

2011-02-24T17:56:26Z

Posmap

← Older revision		Revision as of 17:56, 24 February 2011
Line 555:		Line 555:
	posmap2cvg.pl < prefix.posmap.ctgscf > prefix.posmap.scfctgcvg		posmap2cvg.pl < prefix.posmap.ctgscf > prefix.posmap.scfctgcvg

	* Lib assembly stats		* Lib assembly stats *

	gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1		cd 9-*
	gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2		gatekeeper -dumplibraries -tabular ../genome.gkpStore \| pretty > genome.gkpStore.libinfo1
			gatekeeper -dumpinfo ../genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2

	gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib		gdt genome.gkpStore \| p 'print "$F[0] $F[5]\n" unless($F[6]);' > genome.gkpStore.frg2lib
	paste genome.gkpStore.frg2lib ~~9-terminator/~~genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount		paste genome.gkpStore.frg2lib genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount
	gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount		gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount
	cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount		cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount

	more genome.gkpStore.lib*		more genome.gkpStore.lib*

			* Posmap2gff
			#getting frglib info
			gdt ../genome.gkpStore \| p 'print "$F[0] $F[5]\n" unless($F[6]);' > genome.gkpStore.frg2lib

			# one of ...
			cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sou frg -fea frg -p > genome.posmap.frgscf.gff
			#cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p \| sed 's/[ab]//' > genome.posmap.frgscf.gff
			cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p >! genome.posmap.frgscf.gff

			cat genome.posmap.utgscf \| ~/bin/posmap2gff.pl -sou utg -p >! genome.posmap.utgscf.gff
			cat genome.posmap.ctgscf \| ~/bin/posmap2gff.pl -sou ctg -p >! genome.posmap.ctgscf.gff

			cat genome*gff \| p 'print $_ if($F[8]==1374988);' >! ~/1374988.gff

	* Get 0cvg regions		* Get 0cvg regions

Dpuiu: /* Posmap */

2011-02-24T15:28:44Z

Posmap

← Older revision		Revision as of 15:28, 24 February 2011
Line 559:		Line 559:
	gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1		gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1
	gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2		gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2

	gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib		gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib
	paste genome.gkpStore.frg2lib 9-terminator/genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount		paste genome.gkpStore.frg2lib 9-terminator/genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount
	gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount		gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount
	cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount		cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount

			more genome.gkpStore.lib*

	* Get 0cvg regions		* Get 0cvg regions

Dpuiu: /* Posmap */

2011-02-23T19:18:49Z

Posmap

@@ Line 554: / Line 554: @@
    OLD/posmap2cvg.4.pl -mates prefix.posmap.mates < prefix.posmap.frgscf > prefix.posmap.scfmatecvg
    posmap2cvg.pl                                  < prefix.posmap.ctgscf > prefix.posmap.scfctgcvg
 * Get 0cvg regions

Dpuiu: /* Overlap */

2011-02-17T15:05:01Z

Overlap

← Older revision		Revision as of 15:05, 17 February 2011
Line 290:		Line 290:
	overmerry.sh : #frgs/merOverlapperSeedBatchSize jobs -> seeds/ dir		overmerry.sh : #frgs/merOverlapperSeedBatchSize jobs -> seeds/ dir
	olap-from-seeds.sh : #frgs/merOverlapperExtendBatchSize jobs -> olaps/ dir		olap-from-seeds.sh : #frgs/merOverlapperExtendBatchSize jobs -> olaps/ dir

			* Num ber of jobs
			cat 1-overlapper/ovlopts.pl \| grep -c '^"h'

	* Restart in runCA		* Restart in runCA

Dpuiu: /* Unitiger */

2011-02-10T21:38:37Z

Unitiger

← Older revision		Revision as of 21:38, 10 February 2011
Line 361:		Line 361:
	void		void
	MateLocation::buildHappinessGraphs(Unitig utg, DistanceCompute globalStats) {		MateLocation::buildHappinessGraphs(Unitig utg, DistanceCompute globalStats) {

	for (uint32 mleidx=0; mleidx<_table.size(); mleidx++) {		for (uint32 mleidx=0; mleidx<_table.size(); mleidx++) {
	MateLocationEntry &loc = _table[mleidx];		MateLocationEntry &loc = _table[mleidx];

	uint32 lib = _fi->libraryIID(loc.mleFrgID1);		uint32 lib = _fi->libraryIID(loc.mleFrgID1);

	//Aelksey Zimin also do not use short Illumina mate pairs		//Aelksey Zimin also do not use short Illumina mate pairs
	// if (globalStats[lib].samples < 10 )		// if (globalStats[lib].samples < 10 )

← Older revision		Revision as of 17:56, 24 February 2011
Line 555:		Line 555:
	posmap2cvg.pl < prefix.posmap.ctgscf > prefix.posmap.scfctgcvg		posmap2cvg.pl < prefix.posmap.ctgscf > prefix.posmap.scfctgcvg

	* Lib assembly stats		* Lib assembly stats *

	gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1		cd 9-*
	gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2		gatekeeper -dumplibraries -tabular ../genome.gkpStore \| pretty > genome.gkpStore.libinfo1
			gatekeeper -dumpinfo ../genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2

	gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib		gdt genome.gkpStore \| p 'print "$F[0] $F[5]\n" unless($F[6]);' > genome.gkpStore.frg2lib
	paste genome.gkpStore.frg2lib ~~9-terminator/~~genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount		paste genome.gkpStore.frg2lib genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount
	gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount		gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount
	cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount		cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount

	more genome.gkpStore.lib*		more genome.gkpStore.lib*

			* Posmap2gff
			#getting frglib info
			gdt ../genome.gkpStore \| p 'print "$F[0] $F[5]\n" unless($F[6]);' > genome.gkpStore.frg2lib

			# one of ...
			cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sou frg -fea frg -p > genome.posmap.frgscf.gff
			#cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p \| sed 's/[ab]//' > genome.posmap.frgscf.gff
			cat genome.posmap.frgscf \| ~/bin/posmap2gff.pl -sf genome.gkpStore.frg2lib -fea frg -p >! genome.posmap.frgscf.gff

			cat genome.posmap.utgscf \| ~/bin/posmap2gff.pl -sou utg -p >! genome.posmap.utgscf.gff
			cat genome.posmap.ctgscf \| ~/bin/posmap2gff.pl -sou ctg -p >! genome.posmap.ctgscf.gff

			cat genome*gff \| p 'print $_ if($F[8]==1374988);' >! ~/1374988.gff

	* Get 0cvg regions		* Get 0cvg regions

← Older revision		Revision as of 15:28, 24 February 2011
Line 559:		Line 559:
	gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1		gatekeeper -dumplibraries -tabular genome.gkpStore \| pretty > genome.gkpStore.libinfo1
	gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2		gatekeeper -dumpinfo genome.gkpStore \| grep -A 100 ^Lib \| pretty > genome.gkpStore.libinfo2

	gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib		gdt genome.gkpStore \| p 'print "$F[0] $F[4]\n" unless($F[6]);' > genome.gkpStore.frg2lib
	paste genome.gkpStore.frg2lib 9-terminator/genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount		paste genome.gkpStore.frg2lib 9-terminator/genome.posmap.frags \| p ' print "$F[1] $F[5]\n";' \| count.pl > genome.gkpStore.frgcount
	gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount		gdt genome.gkpStore \| p 'print "$F[4] del\n" if($F[6] eq "1");' \| count.pl >> genome.gkpStore.frgcount
	cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount		cat genome.gkpStore.frgcount \| count2col.pl -i 0 -j 1 -k 2 \| awk '{print $1,$4,$2,$3}' \| pretty > genome.gkpStore.libcount

			more genome.gkpStore.lib*

	* Get 0cvg regions		* Get 0cvg regions