App-Anchr
view release on metacpan or search on metacpan
doc/gage_b.md view on Meta::CPAN
| Name | SumCor | CovCor | N50SR | Sum | # | N50Anchor | Sum | # | N50Others | Sum | # | Kmer | RunTimeKU | RunTimeAN |
|:-------|--------:|-------:|------:|------:|----:|----------:|------:|----:|----------:|-------:|---:|--------------------------:|----------:|:----------|
| Q25L60 | 343.49M | 63.2 | 34827 | 5.35M | 275 | 34827 | 5.33M | 245 | 806 | 26.22K | 30 | "31,41,51,59,61,71,81,91" | 0:05'15'' | 0:01'42'' |
| Q30L60 | 348.42M | 64.1 | 43794 | 5.37M | 245 | 43794 | 5.31M | 212 | 16156 | 55.94K | 33 | "31,41,51,59,61,71,81,91" | 0:05'18'' | 0:02'15'' |
## Bcer: merge anchors
```bash
BASE_NAME=Bcer
cd ${HOME}/data/anchr/${BASE_NAME}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}/anchor/pe.anchor.fa
fi
" ::: 25 30 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o merge/anchor.merge0.fasta
anchr contained merge/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.others.fa ]; then
echo Q{1}L{2}/anchor/pe.others.fa
fi
" ::: 25 30 35 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
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 \
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 \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
```bash
BASE_NAME=Bcer
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr superreads
mkdir -p superreads
perl -MApp::Fasops::Common -e '
BEGIN { our $count = 0; }
my $seq_of = App::Fasops::Common::read_fasta( q{merge/anchor.merge.fasta} );
for my $key (keys %{$seq_of}) {
printf qq{>%s length:%d\n}, $count, length($seq_of->{$key});
printf qq{%s\n}, $seq_of->{$key};
}
' \
> superreads/merged_kunitigs.fasta
perl ~/Scripts/cpan/App-Anchr/share/createSuperReadsForDirectory.perl \
superreads \
superreads/merged_kunitigs.fasta \
2_illumina/Q30L60/pe.cor.fa \
2_illumina/Q30L60/meanAndStdevByPrefix.pe.txt
```
* Stats
```bash
BASE_DIR=$HOME/data/anchr/Bcer
cd ${BASE_DIR}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
doc/gage_b.md view on Meta::CPAN
|:-------|--------:|-------:|------:|------:|-----:|----------:|------:|----:|----------:|--------:|----:|--------------------:|----------:|:----------|
| Q20L60 | 154.91M | 33.7 | 21566 | 4.55M | 432 | 21854 | 4.51M | 376 | 796 | 42.42K | 56 | "31,41,51,61,71,81" | 0:02'04'' | 0:01'42'' |
| Q25L60 | 138.36M | 30.1 | 17440 | 4.53M | 498 | 17460 | 4.48M | 429 | 755 | 51.28K | 69 | "31,41,51,61,71,81" | 0:01'56'' | 0:01'36'' |
| Q30L60 | 123.22M | 26.8 | 10535 | 4.52M | 725 | 10753 | 4.44M | 624 | 758 | 74.44K | 101 | "31,41,51,61,71,81" | 0:01'45'' | 0:01'31'' |
## Rsph: merge anchors
```bash
BASE_DIR=$HOME/data/anchr/Rsph
cd ${BASE_DIR}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}/anchor/pe.anchor.fa
fi
" ::: 20 25 30 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o merge/anchor.merge0.fasta
anchr contained merge/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.others.fa ]; then
echo Q{1}L{2}/anchor/pe.others.fa
fi
" ::: 25 30 35 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_DIR=$HOME/data/anchr/Rsph
cd ${BASE_DIR}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 3188524 | 4602977 | 7 |
| Paralogs | 2337 | 147155 | 66 |
| anchor.merge | 27741 | 4516953 | 291 |
| others.merge | 1099 | 9245 | 8 |
* Clear QxxLxxx.
```bash
BASE_DIR=$HOME/data/anchr/Rsph
cd ${BASE_DIR}
#rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*
```
# *Mycobacterium abscessus* 6G-0125-R
## Mabs: download
doc/gage_b.md view on Meta::CPAN
|:-------|--------:|-------:|------:|------:|-----:|----------:|------:|-----:|----------:|--------:|----:|-----------------------:|----------:|:----------|
| Q20L60 | 228.29M | 44.8 | 6493 | 5.21M | 1213 | 6642 | 5.07M | 1046 | 815 | 141.92K | 167 | "31,41,45,51,61,71,81" | 0:02'44'' | 0:01'44'' |
| Q25L60 | 210.79M | 41.4 | 8980 | 5.17M | 885 | 9075 | 5.1M | 796 | 764 | 64.25K | 89 | "31,41,45,51,61,71,81" | 0:02'36'' | 0:01'38'' |
| Q30L60 | 194.38M | 38.2 | 14939 | 5.2M | 616 | 15113 | 5.11M | 561 | 9075 | 93.7K | 55 | "31,41,45,51,61,71,81" | 0:02'30'' | 0:01'40'' |
## Mabs: merge anchors
```bash
BASE_DIR=$HOME/data/anchr/Mabs
cd ${BASE_DIR}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}/anchor/pe.anchor.fa
fi
" ::: 20 25 30 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o merge/anchor.merge0.fasta
anchr contained merge/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}/anchor/pe.others.fa ]; then
echo Q{1}L{2}/anchor/pe.others.fa
fi
" ::: 25 30 35 ::: 60
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_DIR=$HOME/data/anchr/Mabs
cd ${BASE_DIR}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 5067172 | 5090491 | 2 |
| Paralogs | 1580 | 83364 | 53 |
| anchor.merge | 16004 | 5148343 | 519 |
| others.merge | 40761 | 49228 | 3 |
* Clear QxxLxxx.
```bash
BASE_DIR=$HOME/data/anchr/Mabs
cd ${BASE_DIR}
#rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*
```
# *Vibrio cholerae* CP1032(5)
## Vcho: download
doc/gage_b.md view on Meta::CPAN
## Vcho: results
| Name | SumCor | CovCor | N50SR | Sum | # | N50Anchor | Sum | # | N50Others | Sum | # | Kmer | RunTimeKU | RunTimeAN |
|:-------|--------:|-------:|------:|------:|----:|----------:|------:|----:|----------:|-------:|----:|----------------------------------:|----------:|:----------|
| Q20L60 | 224.36M | 55.6 | 9312 | 3.99M | 737 | 9549 | 3.89M | 608 | 771 | 96.04K | 129 | "31,41,51,57,61,63,71,81,101,121" | 0:03'18'' | 0:01'37'' |
| Q20L90 | 220.69M | 54.7 | 9312 | 3.99M | 730 | 9549 | 3.89M | 598 | 765 | 97.45K | 132 | "31,41,51,57,61,63,71,81,101,121" | 0:03'24'' | 0:01'25'' |
| Q25L60 | 217.57M | 53.9 | 24544 | 3.96M | 355 | 24583 | 3.91M | 289 | 789 | 49.08K | 66 | "31,41,51,57,61,63,71,81,101,121" | 0:03'22'' | 0:01'39'' |
| Q25L90 | 212.22M | 52.6 | 23725 | 3.96M | 362 | 24544 | 3.91M | 294 | 772 | 49.93K | 68 | "31,41,51,57,61,63,71,81,101,121" | 0:03'22'' | 0:01'29'' |
| Q30L60 | 205.43M | 50.9 | 29588 | 3.96M | 329 | 29684 | 3.91M | 266 | 765 | 45.76K | 63 | "31,41,51,57,61,63,71,81,101,121" | 0:03'14'' | 0:01'36'' |
| Q30L90 | 201.7M | 50.0 | 29588 | 3.96M | 329 | 29684 | 3.91M | 266 | 765 | 45.76K | 63 | "31,41,51,57,61,63,71,81,101,121" | 0:03'15'' | 0:01'36'' |
## Vcho: merge anchors
```bash
BASE_DIR=$HOME/data/anchr/Vcho
cd ${BASE_DIR}
# merge anchors
mkdir -p merge
anchr contained \
Q20L60/anchor/pe.anchor.fa \
Q25L60/anchor/pe.anchor.fa \
Q30L60/anchor/pe.anchor.fa \
Q20L90/anchor/pe.anchor.fa \
Q25L90/anchor/pe.anchor.fa \
Q30L90/anchor/pe.anchor.fa \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
anchr contained \
Q20L60/anchor/pe.others.fa \
Q25L60/anchor/pe.others.fa \
Q30L60/anchor/pe.others.fa \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
mummerplot -png out.delta -p anchor.sort --large
# mummerplot files
rm *.[fr]plot
rm out.delta
rm *.gp
mv anchor.sort.png merge/
# quast
rm -fr 9_qa
quast --no-check --threads 16 \
-R 1_genome/genome.fa \
8_competitor/abyss_ctg.fasta \
8_competitor/cabog_ctg.fasta \
8_competitor/mira_ctg.fasta \
8_competitor/msrca_ctg.fasta \
8_competitor/sga_ctg.fasta \
8_competitor/soap_ctg.fasta \
8_competitor/spades_ctg.fasta \
8_competitor/velvet_ctg.fasta \
merge/anchor.merge.fasta \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_DIR=$HOME/data/anchr/Vcho
cd ${BASE_DIR}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 2961149 | 4033464 | 2 |
| Paralogs | 3483 | 114707 | 48 |
| anchor.merge | 32909 | 3910957 | 235 |
| others.merge | 1068 | 5516 | 5 |
* Clear QxxLxxx.
```bash
BASE_DIR=$HOME/data/anchr/Vcho
cd ${BASE_DIR}
#rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*
```
# *Mycobacterium abscessus* 6G-0125-R Full
## MabsF: download
doc/gage_b.md view on Meta::CPAN
| Q25L60X80P000 | 407.24M | 80.0 | 8476 | 5.18M | 940 | 8614 | 5.11M | 839 | 816 | 76.51K | 101 | "31,41,51,61,71,81" | 0:05'50'' | 0:03'30'' |
| Q30L60X40P000 | 203.62M | 40.0 | 18298 | 5.17M | 464 | 18420 | 5.13M | 424 | 914 | 35.4K | 40 | "31,41,51,61,71,81" | 0:03'49'' | 0:02'13'' |
| Q35L60X40P000 | 203.62M | 40.0 | 20655 | 5.14M | 434 | 20681 | 5.11M | 396 | 757 | 29.91K | 38 | "31,41,51,61,71,81" | 0:04'09'' | 0:02'28'' |
## MabsF: merge anchors
```bash
BASE_NAME=MabsF
cd ${HOME}/data/anchr/${BASE_NAME}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa
fi
" ::: 25 30 35 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o merge/anchor.merge0.fasta
anchr contained merge/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.others.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.others.fa
fi
" ::: 25 30 35 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
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 \
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 \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_NAME=MabsF
cd ${HOME}/data/anchr/${BASE_NAME}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 5067172 | 5090491 | 2 |
| Paralogs | 1580 | 83364 | 53 |
| anchor.merge | 81639 | 5155449 | 122 |
| others.merge | 13061 | 39393 | 7 |
* Clear QxxLxxXxx.
```bash
BASE_NAME=MabsF
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 2_illumina/Q{20,25,30}L{1,60,90,120}X*
rm -fr Q{20,25,30}L{1,60,90,120}X*
```
# *Rhodobacter sphaeroides* 2.4.1 Full
## RsphF: download
doc/gage_b.md view on Meta::CPAN
| Q25L60X40P001 | 184.12M | 40.0 | 20582 | 4.54M | 418 | 20698 | 4.5M | 372 | 752 | 33.9K | 46 | "31,41,51,61,71,81" | 0:03'40'' | 0:02'30'' |
| Q25L60X80P000 | 368.24M | 80.0 | 27777 | 4.55M | 344 | 27802 | 4.51M | 292 | 755 | 41.02K | 52 | "31,41,51,61,71,81" | 0:07'09'' | 0:03'46'' |
| Q30L60X40P000 | 184.12M | 40.0 | 12285 | 4.53M | 656 | 12365 | 4.46M | 564 | 757 | 67.6K | 92 | "31,41,51,61,71,81" | 0:05'18'' | 0:02'46'' |
| Q30L60X40P001 | 184.12M | 40.0 | 13794 | 4.54M | 584 | 13944 | 4.49M | 520 | 788 | 46.32K | 64 | "31,41,51,61,71,81" | 0:05'11'' | 0:02'51'' |
| Q30L60X80P000 | 368.24M | 80.0 | 18881 | 4.55M | 444 | 18924 | 4.51M | 395 | 773 | 36.98K | 49 | "31,41,51,61,71,81" | 0:07'00'' | 0:03'14'' |
## RsphF: merge anchors
```bash
BASE_NAME=RsphF
cd ${HOME}/data/anchr/${BASE_NAME}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa
fi
" ::: 20 25 30 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.others.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.others.fa
fi
" ::: 20 25 30 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
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 \
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 \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_NAME=RsphF
cd ${HOME}/data/anchr/${BASE_NAME}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 3188524 | 4602977 | 7 |
| Paralogs | 2337 | 147155 | 66 |
| anchor.merge | 44642 | 4539106 | 206 |
| others.merge | 1154 | 21928 | 18 |
* Clear QxxLxxXxx.
```bash
BASE_NAME=RsphF
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 2_illumina/Q{20,25,30}L{1,60,90,120}X*
rm -fr Q{20,25,30}L{1,60,90,120}X*
```
# *Vibrio cholerae* CP1032(5) Full
## VchoF: download
doc/gage_b.md view on Meta::CPAN
| Q30L60X40P001 | 161.34M | 40.0 | 16194 | 3.93M | 482 | 16458 | 3.86M | 383 | 708 | 70.7K | 99 | "31,41,51,61,71,81" | 0:02'28'' | 0:01'02'' |
| Q30L60X80P000 | 322.68M | 80.0 | 9140 | 3.94M | 756 | 9270 | 3.84M | 622 | 766 | 98.53K | 134 | "31,41,51,61,71,81" | 0:03'49'' | 0:01'27'' |
| Q35L60X40P000 | 161.34M | 40.0 | 29728 | 3.93M | 318 | 30761 | 3.88M | 245 | 728 | 51.21K | 73 | "31,41,51,61,71,81" | 0:03'18'' | 0:01'07'' |
## VchoF: merge anchors
```bash
BASE_NAME=VchoF
cd ${HOME}/data/anchr/${BASE_NAME}
# merge anchors
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.anchor.fa
fi
" ::: 20 25 30 35 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.contained.fasta
anchr orient merge/anchor.contained.fasta --len 1000 --idt 0.98 -o merge/anchor.orient.fasta
anchr merge merge/anchor.orient.fasta --len 1000 --idt 0.999 -o merge/anchor.merge0.fasta
anchr contained merge/anchor.merge0.fasta --len 1000 --idt 0.98 \
--proportion 0.99 --parallel 16 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/anchor.merge.fasta
# merge others
mkdir -p merge
anchr contained \
$(
parallel -k --no-run-if-empty -j 6 "
if [ -e Q{1}L{2}X{3}P{4}/anchor/pe.others.fa ]; then
echo Q{1}L{2}X{3}P{4}/anchor/pe.others.fa
fi
" ::: 20 25 30 35 ::: 60 ::: 40 80 ::: 000 001 002 003 004 005 006
) \
--len 1000 --idt 0.98 --proportion 0.99999 --parallel 16 \
-o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.contained.fasta
anchr orient merge/others.contained.fasta --len 1000 --idt 0.98 -o merge/others.orient.fasta
anchr merge merge/others.orient.fasta --len 1000 --idt 0.999 -o stdout \
| faops filter -a 1000 -l 0 stdin merge/others.merge.fasta
# sort on ref
bash ~/Scripts/cpan/App-Anchr/share/sort_on_ref.sh merge/anchor.merge.fasta 1_genome/genome.fa merge/anchor.sort
nucmer -l 200 1_genome/genome.fa merge/anchor.sort.fa
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 \
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 \
1_genome/paralogs.fas \
--label "abyss,cabog,mira,msrca,sga,soap,spades,velvet,merge,paralogs" \
-o 9_qa
```
* Stats
```bash
BASE_NAME=VchoF
cd ${HOME}/data/anchr/${BASE_NAME}
printf "| %s | %s | %s | %s |\n" \
"Name" "N50" "Sum" "#" \
> stat3.md
printf "|:--|--:|--:|--:|\n" >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Genome"; faops n50 -H -S -C 1_genome/genome.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "Paralogs"; faops n50 -H -S -C 1_genome/paralogs.fas;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "anchor.merge"; faops n50 -H -S -C merge/anchor.merge.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
$(echo "others.merge"; faops n50 -H -S -C merge/others.merge.fasta;) >> stat3.md
cat stat3.md
```
| Name | N50 | Sum | # |
|:-------------|--------:|--------:|----:|
| Genome | 2961149 | 4033464 | 2 |
| Paralogs | 3483 | 114707 | 48 |
| anchor.merge | 59780 | 3893974 | 136 |
| others.merge | 1058 | 24575 | 17 |
* Clear QxxLxxXxx.
```bash
BASE_NAME=VchoF
cd ${HOME}/data/anchr/${BASE_NAME}
rm -fr 2_illumina/Q{20,25,30,35}L{1,60,90,120}X*
rm -fr Q{20,25,30,35}L{1,60,90,120}X*
```
( run in 0.546 second using v1.01-cache-2.11-cpan-39bf76dae61 )