App-Anchr
view release on metacpan or search on metacpan
doc/bacteria_2_3.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Sfle: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_DIR=$HOME/data/anchr/Sfle
cd ${BASE_DIR}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Sfle.contigs.fasta \
canu-raw-80x/Sfle.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
1_genome/paralogs.fas \
--label "merge,paralogs" \
-o 9_qa
```
## Vpar: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_DIR=$HOME/data/anchr/Vpar
cd ${BASE_DIR}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Vpar.contigs.fasta \
canu-raw-80x/Vpar.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Lpne: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_DIR=$HOME/data/anchr/Lpne
cd ${BASE_DIR}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Lpne.contigs.fasta \
canu-raw-80x/Lpne.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Ngon: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_DIR=$HOME/data/anchr/Ngon
cd ${BASE_DIR}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Ngon.contigs.fasta \
canu-raw-80x/Ngon.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Nmen: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_NAME=Nmen
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Nmen.contigs.fasta \
canu-raw-80x/Nmen.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
* Stats
doc/bacteria_2_3.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Cdip: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_NAME=Cdip
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
canu-raw-80x/${BASE_NAME}.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/bacteria_2_3.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## Ftul: 3GS
doc/bacteria_2_3.md view on Meta::CPAN
```
* quast
```bash
BASE_NAME=Ftul
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/Ftul.contigs.fasta \
canu-raw-80x/Ftul.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-40x,canu-80x,paralogs" \
-o 9_qa_contig
doc/dazzler.md view on Meta::CPAN
# sequences from the original file
faops some -l 0 renamed.fasta <(DBshow -n myDB 1-10 102 100-101 | sed 's/^>//') stdout
```
## daligner
`HPC.daligner`
* local alignments involving at least `-l` base pairs (default 1000)
* An average correlation rate of `-e` (default 70%) set to 80%
* The default number of threads is 4, set by `-T` option (power of 2)
* Set the `-t` parameter which suppresses the use of any *k*-mer that occurs more than *t* times in
either the subject or target block.
* Let the program automatically select a value of *t* that meets a given memory usage limit
specified (in Gb) by the `-M` parameter
* one or more interval tracks specified with the `-m` option (m for mask)
### Create jobs by `HPC.daligner` and execute it
Three .las (`myDB.[1-3].las`) files are generated then concatenated to `myDB.las`.
doc/e_coli.md view on Meta::CPAN
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin mergeL${L}/anchor.contained.fasta
anchr orient mergeL${L}/anchor.contained.fasta --len 1000 --idt 0.98 -o mergeL${L}/anchor.orient.fasta
anchr merge mergeL${L}/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin mergeL${L}/anchor.merge.fasta
done
# quast
rm -fr 9_qa_mergeQL
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
mergeQ20/anchor.merge.fasta \
mergeQ25/anchor.merge.fasta \
mergeQ30/anchor.merge.fasta \
mergeQ35/anchor.merge.fasta \
mergeL30/anchor.merge.fasta \
mergeL60/anchor.merge.fasta \
mergeL90/anchor.merge.fasta \
mergeL120/anchor.merge.fasta \
1_genome/paralogs.fas \
doc/e_coli.md view on Meta::CPAN
-o stdout \
| faops filter -a 1000 -l 0 stdin mergeQ${Q}L${L}/anchor.contained.fasta
anchr orient mergeQ${Q}L${L}/anchor.contained.fasta --len 1000 --idt 0.98 -o mergeQ${Q}L${L}/anchor.orient.fasta
anchr merge mergeQ${Q}L${L}/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin mergeQ${Q}L${L}/anchor.merge.fasta
done
done
# quast
rm -fr 9_qa_mergeQxxLxx
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
mergeQ20L30/anchor.merge.fasta \
mergeQ20L60/anchor.merge.fasta \
mergeQ20L90/anchor.merge.fasta \
mergeQ25L30/anchor.merge.fasta \
mergeQ25L60/anchor.merge.fasta \
mergeQ25L90/anchor.merge.fasta \
mergeQ30L30/anchor.merge.fasta \
mergeQ30L60/anchor.merge.fasta \
mergeQ30L90/anchor.merge.fasta \
doc/e_coli.md view on Meta::CPAN
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# minidot
minimap merge/anchor.sort.fa 1_genome/genome.fa \
| minidot - > merge/anchor.minidot.eps
# quast
rm -fr 9_qa_merge
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_spades/contigs.fasta \
8_spades/scaffolds.fasta \
8_spades_Q30L60/scaffolds.fasta \
8_platanus/out_contig.fa \
8_platanus/out_gapClosed.fa \
8_platanus_quorum/out_gapClosed.fa \
8_platanus_Q30L60/out_gapClosed.fa \
merge/anchor.merge.fasta \
merge/scaffold/out_scaffold.fa \
doc/e_coli.md view on Meta::CPAN
Q25L60K111/anchor/pe.anchor.fa \
Q25L60K121/anchor/pe.anchor.fa \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin Q25L60Kmerge/anchor.contained.fasta
anchr orient Q25L60Kmerge/anchor.contained.fasta --len 1000 --idt 0.98 -o Q25L60Kmerge/anchor.orient.fasta
anchr merge Q25L60Kmerge/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin Q25L60Kmerge/anchor.merge.fasta
rm -fr 9_qa_kmer_Q25
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
Q25L60K21/anchor/pe.anchor.fa \
Q25L60K31/anchor/pe.anchor.fa \
Q25L60K41/anchor/pe.anchor.fa \
Q25L60K43/anchor/pe.anchor.fa \
Q25L60K51/anchor/pe.anchor.fa \
Q25L60K61/anchor/pe.anchor.fa \
Q25L60K67/anchor/pe.anchor.fa \
Q25L60K71/anchor/pe.anchor.fa \
Q25L60K81/anchor/pe.anchor.fa \
doc/e_coli.md view on Meta::CPAN
Q30L60K111/anchor/pe.anchor.fa \
Q30L60K121/anchor/pe.anchor.fa \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin Q30L60Kmerge/anchor.contained.fasta
anchr orient Q30L60Kmerge/anchor.contained.fasta --len 1000 --idt 0.98 -o Q30L60Kmerge/anchor.orient.fasta
anchr merge Q30L60Kmerge/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin Q30L60Kmerge/anchor.merge.fasta
rm -fr 9_qa_kmer_Q30
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
Q30L60K21/anchor/pe.anchor.fa \
Q30L60K31/anchor/pe.anchor.fa \
Q30L60K41/anchor/pe.anchor.fa \
Q30L60K43/anchor/pe.anchor.fa \
Q30L60K51/anchor/pe.anchor.fa \
Q30L60K61/anchor/pe.anchor.fa \
Q30L60K67/anchor/pe.anchor.fa \
Q30L60K71/anchor/pe.anchor.fa \
Q30L60K81/anchor/pe.anchor.fa \
doc/e_coli.md view on Meta::CPAN
-pacbio-raw 3_pacbio/pacbio.80x.trim.fasta
canu \
-p ${BASE_NAME} -d canu-trim \
gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
genomeSize=${REAL_G} \
-pacbio-raw 3_pacbio/pacbio.trim.fasta
# quast
rm -fr 9_qa_canu
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
canu-raw-20x/${BASE_NAME}.contigs.fasta \
canu-trim-20x/${BASE_NAME}.contigs.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
canu-trim-40x/${BASE_NAME}.contigs.fasta \
canu-raw-80x/${BASE_NAME}.contigs.fasta \
canu-trim-80x/${BASE_NAME}.contigs.fasta \
canu-raw/${BASE_NAME}.contigs.fasta \
canu-trim/${BASE_NAME}.contigs.fasta \
doc/e_coli.md view on Meta::CPAN
find . -type d -name "correction" -path "*canu-*" | xargs rm -fr
```
* miniasm
* `-S skip self and dual mappings`
* `-w INT minizer window size [{-k}*2/3]`
* `-L INT min matching length [40]`
* `-m FLOAT merge two chains if FLOAT fraction of minimizers are shared [0.50]`
* `-t INT number of threads [3]`
```bash
BASE_NAME=e_coli
cd ${HOME}/data/anchr/${BASE_NAME}
mkdir -p miniasm
minimap -Sw5 -L100 -m0 -t16 \
3_pacbio/pacbio.40x.fasta 3_pacbio/pacbio.40x.fasta \
> miniasm/pacbio.40x.paf
doc/e_coli.md view on Meta::CPAN
-p ${BASE_NAME} -d globalTrim \
gnuplotTested=true \
genomeSize=${REAL_G} \
-pacbio-corrected ../canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
-pacbio-corrected anchor.fasta
popd
# quast
rm -fr 9_qa_localCor
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
localCor/anchor.fasta \
localCor/localCor/${BASE_NAME}.contigs.fasta \
localCor/localCorIndep/${BASE_NAME}.contigs.fasta \
localCor/localTrim/${BASE_NAME}.contigs.fasta \
localCor/globalTrim/${BASE_NAME}.contigs.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
canu-trim-40x/${BASE_NAME}.contigs.fasta \
1_genome/paralogs.fas \
doc/e_coli.md view on Meta::CPAN
| platanus.contig | 15090 | 4683012 | 1069 |
| platanus.scaffold | 133014 | 4575941 | 137 |
* quast
```bash
BASE_NAME=e_coli
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
8_spades/scaffolds.fasta \
8_platanus/out_gapClosed.fa \
1_genome/paralogs.fas \
--label "merge,contig,contigTrim,canu-40x,spades,platanus,paralogs" \
-o 9_qa_contig
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/gage_b.md view on Meta::CPAN
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
doc/model_organisms.md view on Meta::CPAN
anchr orient mergeQ${Q}X${X}/anchor.contained.fasta --len 1000 --idt 0.98 -o mergeQ${Q}X${X}/anchor.orient.fasta
anchr merge mergeQ${Q}X${X}/anchor.orient.fasta --len 1000 --idt 0.999 -o mergeQ${Q}X${X}/anchor.merge0.fasta
anchr contained mergeQ${Q}X${X}/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin mergeQ${Q}X${X}/anchor.merge.fasta
done
done
# quast
rm -fr 9_qa_mergeQX
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
mergeQ20/anchor.merge.fasta \
mergeQ25/anchor.merge.fasta \
mergeQ30/anchor.merge.fasta \
mergeQ35/anchor.merge.fasta \
mergeQ20X40/anchor.merge.fasta \
mergeQ20X80/anchor.merge.fasta \
mergeQ25X40/anchor.merge.fasta \
mergeQ25X80/anchor.merge.fasta \
doc/model_organisms.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
## s288c: 3GS
doc/model_organisms.md view on Meta::CPAN
-pacbio-raw 3_pacbio/pacbio.40x.trim.fasta
canu \
-p ${BASE_NAME} -d canu-trim-80x \
gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
genomeSize=${REAL_G} \
-pacbio-raw 3_pacbio/pacbio.80x.trim.fasta
# quast
rm -fr 9_qa_canu
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
canu-raw-20x/${BASE_NAME}.contigs.fasta \
canu-trim-20x/${BASE_NAME}.contigs.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
canu-trim-40x/${BASE_NAME}.contigs.fasta \
canu-raw-80x/${BASE_NAME}.contigs.fasta \
canu-trim-80x/${BASE_NAME}.contigs.fasta \
1_genome/paralogs.fas \
--label "20x,20x.trim,40x,40x.trim,80x,80x.trim,paralogs" \
doc/model_organisms.md view on Meta::CPAN
gnuplotTested=true \
genomeSize=${REAL_G} \
-pacbio-raw localCor.fasta.gz \
-pacbio-raw anchor.fasta \
-pacbio-raw independentLong.fasta
popd
# quast
rm -fr 9_qa_localCor
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
localCor/anchor.fasta \
localCor/localCor/${BASE_NAME}.contigs.fasta \
localCor/localCorRaw/${BASE_NAME}.contigs.fasta \
localCor/localCorIndep/${BASE_NAME}.contigs.fasta \
1_genome/paralogs.fas \
--label "anchor,localCor,localCorRaw,localCorIndep,paralogs" \
-o 9_qa_localCor
doc/model_organisms.md view on Meta::CPAN
| platanus.contig | 5983 | 12437850 | 7727 |
| platanus.scaffold | 55443 | 12073445 | 4735 |
* quast
```bash
BASE_NAME=s288c
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
--eukaryote \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-trim-40x/${BASE_NAME}.contigs.fasta \
8_spades/scaffolds.fasta \
8_platanus/out_gapClosed.fa \
1_genome/paralogs.fas \
--label "merge,contig,contigTrim,canu-40x,spades,platanus,paralogs" \
doc/model_organisms.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
doc/model_organisms.md view on Meta::CPAN
| platanus.contig | 11503 | 156820565 | 359399 |
| platanus.scaffold | 146404 | 129134232 | 71416 |
* quast
```bash
BASE_NAME=iso_1
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
canu-trim-40x/${BASE_NAME}.contigs.fasta \
8_spades/scaffolds.fasta \
8_platanus/out_gapClosed.fa \
doc/model_organisms.md view on Meta::CPAN
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
doc/model_organisms.md view on Meta::CPAN
| platanus.contig | 9540 | 108908253 | 143264 |
| platanus.scaffold | 28158 | 99589056 | 35182 |
* quast
```bash
BASE_NAME=n2
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-raw-40x/${BASE_NAME}.contigs.fasta \
8_spades/scaffolds.fasta \
8_platanus/out_gapClosed.fa \
doc/model_organisms.md view on Meta::CPAN
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# minidot
minimap 1_genome/genome.fa merge/anchor.sort.fa | minidot - > merge/anchor.minidot.eps
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/others.merge.fasta \
1_genome/paralogs.fas \
--label "merge,others,paralogs" \
-o 9_qa
```
doc/model_organisms.md view on Meta::CPAN
| platanus.contig | 15019 | 139807772 | 106870 |
| platanus.scaffold | 192019 | 128497152 | 67429 |
* quast
```bash
BASE_NAME=col_0
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 9_qa_contig
quast --no-check --threads 16 \
--eukaryote \
--no-icarus \
-R 1_genome/genome.fa \
merge/anchor.merge.fasta \
merge/anchor.cover.fasta \
anchorLong/contig.fasta \
contigTrim/contig.fasta \
canu-trim-80x/${BASE_NAME}.contigs.fasta \
1_genome/paralogs.fas \
--label "merge,cover,contig,contigTrim,canu-trim,paralogs" \
lib/App/Anchr/Command/anchors.pm view on Meta::CPAN
use App::Anchr -command;
use App::Anchr::Common;
use constant abstract => "selete anchors from k-unitigs or superreads";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", { default => "anchors.sh" }, ],
[ 'min=i', 'minimal length of anchors', { default => 1000, }, ],
[ 'unambi=i', 'minimal coverage of unambiguous reads', { default => 2, }, ],
[ 'parallel|p=i', 'number of threads', { default => 8, }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr anchors [options] <k_unitigs.fasta> <pe.cor.fa>";
}
sub description {
my $desc;
lib/App/Anchr/Command/anchors.pm view on Meta::CPAN
faops size SR.fasta > sr.chr.sizes
#----------------------------#
# unambiguous
#----------------------------#
log_info "Unambiguous regions"
log_debug "bbmap"
bbmap.sh \
maxindel=0 strictmaxindel perfectmode \
threads=[% opt.parallel %] \
ambiguous=toss \
nodisk \
ref=SR.fasta in=pe.cor.fa \
outm=unambiguous.sam outu=unmapped.sam \
basecov=basecov.txt \
1>bbmap.err 2>&1
# at least [% opt.unambi %] unambiguous reads covered
# Pos is 0-based
#RefName Pos Coverage
lib/App/Anchr/Command/break.pm view on Meta::CPAN
use constant abstract => "break long reads by anthors";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ 'range|r=s', 'ranges of anchors', { required => 1 }, ],
[ 'border=i', 'length of borders in anchors', { default => 100 }, ],
[ 'power=f', 'multiplying power', { default => 3 }, ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.85 }, ],
[ "parallel|p=i", "number of threads", { default => 4 }, ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr break [options] <dazz DB> <ovlp file>";
}
sub description {
lib/App/Anchr/Command/contained.pm view on Meta::CPAN
use constant abstract => "discard contained super-reads, k-unitigs, or anchors";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ "len|l=i", "minimal length of overlaps", { default => 500 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.98 }, ],
[ "proportion=f", "nearly contained proportion", { default => 0.98 }, ],
[ "prefix=s", "prefix of names", { default => "infile" }, ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr contained [options] <infile> [more infiles]";
}
sub description {
lib/App/Anchr/Command/group.pm view on Meta::CPAN
sub opt_spec {
return (
[ "dir|d=s", "output directory", ],
[ "range|r=s", "ranges of anchors", { required => 1 }, ],
[ "coverage|c=i", "minimal coverage", { default => 2 }, ],
[ "max=i", "max distance", { default => 5000 }, ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.85 }, ],
[ "keep", "don't remove multi-matched reads", ],
[ 'oa=s', 'overlaps between anchors', ],
[ "parallel|p=i", "number of threads", { default => 4 }, ],
[ "verbose|v", "verbose mode", ],
[ "png", "write a png file via graphviz", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr group [options] <dazz DB> <ovlp file>";
}
lib/App/Anchr/Command/kunitigs.pm view on Meta::CPAN
use constant abstract => "create k-unitigs from corrected reads";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", { default => "kunitigs.sh" }, ],
[ 'jf=s', 'jellyfish hash size', { default => "auto", }, ],
[ 'estsize=s', 'estimated genome size', { default => "auto", }, ],
[ 'kmer=s', 'kmer size to be used for super reads', { default => "auto", }, ],
[ 'min=i', 'minimal length of k-unitigs', { default => 500, }, ],
[ 'parallel|p=i', 'number of threads', { default => 8, }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr kunitigs [options] <pe.cor.fa> <environment.json>";
}
sub description {
my $desc;
lib/App/Anchr/Command/localcor.pm view on Meta::CPAN
use App::Anchr::Common;
use constant abstract => "anchor long reads to anchors";
sub opt_spec {
return (
[ "dir|d=s", "output directory", ],
[ "range|r=s", "ranges of anchors", { required => 1 }, ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.85 }, ],
[ "parallel|p=i", "number of threads", { default => 4 }, ],
[ "miniasm", "estimate assembly sizes by miniasm", ],
[ "trim", "also run canu -trim", ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr localcor [options] <dazz DB> <ovlp file>";
}
lib/App/Anchr/Command/merge.pm view on Meta::CPAN
use App::Anchr - command;
use App::Anchr::Common;
use constant abstract => "merge overlapped super-reads, k-unitigs, or anchors";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.98 }, ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
[ "verbose|v", "verbose mode", ],
[ "png", "write a png file via graphviz", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr merge [options] <infile>";
}
lib/App/Anchr/Command/orient.pm view on Meta::CPAN
use App::Anchr::Common;
use constant abstract => "orient overlapped sequences to the same strand";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ "restrict|r=s", "limit to known pairs", ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.85 }, ],
[ "parallel|p=i", "number of threads", { default => 4 }, ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr orient [options] <infiles>";
}
sub description {
lib/App/Anchr/Command/overlap.pm view on Meta::CPAN
use constant abstract => "detect overlaps by daligner";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ "len|l=i", "minimal length of overlaps", { default => 500 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.7 }, ],
[ "serial", "serials instead of original names in the output file", ],
[ "all", "all overlaps instead of proper overlaps", ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr overlap [options] <infiles>";
}
sub description {
lib/App/Anchr/Command/overlap2.pm view on Meta::CPAN
sub opt_spec {
return (
[ "dir|d=s", "working directory", { default => "." }, ],
[ "p1=s", "prefix of first file", { default => "anchor" }, ],
[ "p2=s", "prefix of second file", { default => "long" }, ],
[ "pd=s", "prefix of result files", ],
[ "block|b=i", "block size in Mbp", { default => 20 }, ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "idt|i=f", "minimal identity of overlaps", { default => 0.8 }, ],
[ "all", "all overlaps instead of proper overlaps", ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
[ "verbose|v", "verbose mode", ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr overlap2 [options] <infile1> <infile2>";
}
sub description {
lib/App/Anchr/Command/paf2ovlp.pm view on Meta::CPAN
use MCE::Candy;
use App::Anchr -command;
use App::Anchr::Common;
use constant abstract => 'minimap paf to ovelaps';
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen" ],
[ "parallel|p=i", "number of threads", { default => 4 }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr paf2ovlp [options] <minimap outputs>";
}
sub description {
my $desc;
lib/App/Anchr/Command/quorum.pm view on Meta::CPAN
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", { default => "quorum.sh" }, ],
[ 'size|s=i', 'fragment size', { default => 300, }, ],
[ 'std|d=i', 'fragment size standard deviation', { default => 30, }, ],
[ 'jf=i', 'jellyfish hash size', { default => 500_000_000, }, ],
[ 'estsize=s', 'estimated genome size', { default => "auto", }, ],
[ "adapter|a=s", "adapter file",
{ default => File::ShareDir::dist_file( 'App-Anchr', 'adapter.jf' ) },
],
[ 'parallel|p=i', 'number of threads', { default => 8, }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr quorum [options] <PE file1> <PE file2> [SE file]";
}
sub description {
my $desc;
lib/App/Anchr/Command/scaffold.pm view on Meta::CPAN
use autodie;
use App::Anchr -command;
use App::Anchr::Common;
use constant abstract => "scaffold anchors (k-unitigs/contigs) using paired-end reads";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", { default => "scaffold.sh" }, ],
[ 'parallel|p=i', 'number of threads', { default => 8, }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr scaffold [options] <anchor.fasta> <pe.fa>";
}
sub description {
my $desc;
lib/App/Anchr/Command/scaffold.pm view on Meta::CPAN
fi
#----------------------------#
# basecov
#----------------------------#
log_info "basecov"
log_debug "bbmap"
bbmap.sh \
maxindel=0 strictmaxindel perfectmode \
threads=[% opt.parallel %] \
ambiguous=toss \
nodisk \
ref=SR.fasta in=pe.fa \
outm=unambiguous.sam outu=unmapped.sam \
basecov=basecov.txt \
1>bbmap.err 2>&1
# Pos is 0-based
#RefName Pos Coverage
log_debug "coverage"
lib/App/Anchr/Command/trim.pm view on Meta::CPAN
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", { default => "trim.sh" }, ],
[ "basename|b=s", "prefix of fastq filenames", { default => "R" }, ],
[ "len|l=i", "filter reads less or equal to this length", { default => 80 }, ],
[ "qual|q=i", "quality threshold", { default => 20 }, ],
[ "adapter|a=s", "adapter file",
{ default => File::ShareDir::dist_file( 'App-Anchr', 'illumina_adapters.fa' ) },
],
[ "noscythe", "skip the scythe step", ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr trim [options] <PE file1> <PE file2>";
}
sub description {
my $desc;
lib/App/Anchr/Command/trimlong.pm view on Meta::CPAN
use App::Anchr - command;
use App::Anchr::Common;
use constant abstract => "trim long reads with minimap";
sub opt_spec {
return (
[ "outfile|o=s", "output filename, [stdout] for screen", ],
[ "coverage|c=i", "minimal coverage", { default => 3 }, ],
[ "len|l=i", "minimal length of overlaps", { default => 1000 }, ],
[ "parallel|p=i", "number of threads", { default => 8 }, ],
[ "verbose|v", "verbose mode", ],
[ "jvm=s",
"jvm parameters for jrange, e.g. '-d64 -server -Xms1g -Xmx64g -XX:-UseGCOverheadLimit'",
],
{ show_defaults => 1, }
);
}
sub usage_desc {
return "anchr trimlong [options] <infile>";
( run in 1.955 second using v1.01-cache-2.11-cpan-3cd7ad12f66 )