App-Anchr

 view release on metacpan or  search on metacpan

doc/bacteria_2_3.md  view on Meta::CPAN

| Name   | N50SR |   Sum |   # | N50Anchor |   Sum |   # | N50Others |    Sum |   # |   RunTime |
|:-------|------:|------:|----:|----------:|------:|----:|----------:|-------:|----:|----------:|
| Q20L60 |  8637 | 4.26M | 778 |      8821 | 4.17M | 660 |       765 | 87.11K | 118 | 0:00'51'' |
| Q20L90 |  9406 | 4.26M | 725 |      9482 | 4.18M | 615 |       766 | 80.73K | 110 | 0:00'53'' |
| Q25L60 | 19847 | 4.22M | 398 |     20462 | 4.18M | 337 |       770 | 44.81K |  61 | 0:00'58'' |
| Q25L90 | 21495 | 4.22M | 378 |     21517 | 4.18M | 321 |       765 | 41.64K |  57 | 0:00'56'' |
| Q30L60 | 29285 | 4.22M | 316 |     29285 | 4.18M | 264 |       760 | 37.42K |  52 | 0:00'57'' |
| Q30L90 | 29285 | 4.22M | 314 |     29570 | 4.18M | 261 |       760 | 37.88K |  53 | 0:00'56'' |

## Sfle: merge anchors

```bash
BASE_DIR=$HOME/data/anchr/Sfle
cd ${BASE_DIR}

# merge anchors
mkdir -p merge
anchr contained \
    Q20L60/anchor/pe.anchor.fa \
    Q20L90/anchor/pe.anchor.fa \
    Q25L60/anchor/pe.anchor.fa \
    Q25L90/anchor/pe.anchor.fa \
    Q30L60/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 \
    Q20L90/anchor/pe.others.fa \
    Q25L60/anchor/pe.others.fa \
    Q25L90/anchor/pe.others.fa \
    Q30L60/anchor/pe.others.fa \
    Q30L90/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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Sfle: 3GS

```bash
BASE_DIR=$HOME/data/anchr/Sfle
cd ${BASE_DIR}

canu \
    -p Sfle -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=4.8m \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p Sfle -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=4.8m \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/Sfle.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/Sfle.trimmedReads.fasta.gz

```

## Sfle: expand anchors

* anchorLong

```bash
BASE_DIR=$HOME/data/anchr/Sfle
cd ${BASE_DIR}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/Sfle.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/Sfle.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \
    -o stdout \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/Sfle.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd ${BASE_DIR}/contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_DIR=$HOME/data/anchr/Sfle
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |   # |
|:-------------|--------:|--------:|----:|
| Genome       | 4607202 | 4828820 |   2 |
| Paralogs     |    1377 |  543111 | 334 |
| anchor.merge |   29718 | 4177514 | 258 |
| others.merge |    1013 |    5268 |   5 |
| anchor.cover |   21445 | 4065033 | 337 |
| anchorLong   |   21727 | 4064559 | 333 |
| contigTrim   |   59768 | 4286051 | 140 |

* Clear QxxLxxx.

```bash
BASE_DIR=$HOME/data/anchr/Sfle
cd ${BASE_DIR}

rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q30L60_1000000 | 179300 | 5.05M | 110 |    179300 | 5.04M |  82 |       656 | 18.77K | 28 | 0:00'53'' |
| Q30L60_2000000 | 175008 | 5.06M | 100 |    175008 | 5.04M |  77 |       710 | 16.14K | 23 | 0:01'22'' |
| Q30L60_3000000 | 155751 | 5.06M | 106 |    155751 | 5.04M |  82 |       693 | 16.62K | 24 | 0:01'46'' |
| Q30L60_4000000 | 123854 | 5.05M | 107 |    123854 | 5.04M |  84 |       710 | 16.14K | 23 | 0:02'14'' |
| Q30L60_5000000 |  99637 | 5.05M | 123 |     99637 | 5.04M |  99 |       697 | 16.64K | 24 | 0:02'38'' |

## Vpar: merge anchors

```bash
BASE_DIR=$HOME/data/anchr/Vpar
cd ${BASE_DIR}

# merge anchors
mkdir -p merge
anchr contained \
    Q20L60_2000000/anchor/pe.anchor.fa \
    Q20L60_3000000/anchor/pe.anchor.fa \
    Q20L60_4000000/anchor/pe.anchor.fa \
    Q20L60_5000000/anchor/pe.anchor.fa \
    Q25L60_2000000/anchor/pe.anchor.fa \
    Q25L60_3000000/anchor/pe.anchor.fa \
    Q25L60_4000000/anchor/pe.anchor.fa \
    Q25L60_5000000/anchor/pe.anchor.fa \
    Q30L60_2000000/anchor/pe.anchor.fa \
    Q30L60_3000000/anchor/pe.anchor.fa \
    Q30L60_4000000/anchor/pe.anchor.fa \
    Q30L60_5000000/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_2000000/anchor/pe.others.fa \
    Q25L60_2000000/anchor/pe.others.fa \
    Q30L60_2000000/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 \
    merge/anchor.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,paralogs" \
    -o 9_qa

```

## Vpar: 3GS

```bash
BASE_DIR=$HOME/data/anchr/Vpar
cd ${BASE_DIR}

canu \
    -p Vpar -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=5.2m \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p Vpar -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=5.2m \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/Vpar.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/Vpar.trimmedReads.fasta.gz

```

## Vpar: expand anchors

* anchorLong

```bash
BASE_DIR=$HOME/data/anchr/Vpar
cd ${BASE_DIR}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/Vpar.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/Vpar.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \
    -o stdout \
    | perl -nla -e '

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/Vpar.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd ${BASE_DIR}/contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_DIR=$HOME/data/anchr/Vpar
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |  # |
|:-------------|--------:|--------:|---:|
| Genome       | 3288558 | 5165770 |  2 |
| Paralogs     |    3333 |  155714 | 62 |
| anchor.merge |  175008 | 5047543 | 73 |
| others.merge |   20100 |   20100 |  1 |
| anchor.cover |  175008 | 5024576 | 78 |
| anchorLong   |  208183 | 5023596 | 63 |
| contigTrim   | 1488730 | 5148305 | 11 |

* Clear QxxLxxx.

```bash
BASE_DIR=$HOME/data/anchr/Vpar
cd ${BASE_DIR}

rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q25L60_4000000 |  20322 | 3.43M | 304 |     20440 | 3.38M | 273 |     14979 |  50.13K |  31 | 0:04'18'' |
| Q30L60_1000000 | 219482 | 3.41M |  83 |    219482 |  3.4M |  56 |       734 |  18.18K |  27 | 0:01'41'' |
| Q30L60_2000000 | 128845 | 3.42M |  93 |    128845 | 3.36M |  68 |     21578 |  59.28K |  25 | 0:02'42'' |
| Q30L60_3000000 |  68045 | 3.42M | 123 |     68045 | 3.37M |  97 |     15040 |   46.9K |  26 | 0:03'30'' |
| Q30L60_4000000 |  49793 | 3.42M | 146 |     49793 | 3.38M | 126 |     15040 |  42.66K |  20 | 0:03'54'' |

## Lpne: merge anchors

```bash
BASE_DIR=$HOME/data/anchr/Lpne
cd ${BASE_DIR}

# merge anchors
mkdir -p merge
anchr contained \
    Q20L60_1000000/anchor/pe.anchor.fa \
    Q20L60_2000000/anchor/pe.anchor.fa \
    Q20L60_3000000/anchor/pe.anchor.fa \
    Q20L60_4000000/anchor/pe.anchor.fa \
    Q25L60_1000000/anchor/pe.anchor.fa \
    Q25L60_2000000/anchor/pe.anchor.fa \
    Q25L60_3000000/anchor/pe.anchor.fa \
    Q25L60_4000000/anchor/pe.anchor.fa \
    Q30L60_1000000/anchor/pe.anchor.fa \
    Q30L60_2000000/anchor/pe.anchor.fa \
    Q30L60_3000000/anchor/pe.anchor.fa \
    Q30L60_4000000/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_2000000/anchor/pe.others.fa \
    Q25L60_2000000/anchor/pe.others.fa \
    Q30L60_2000000/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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Lpne: 3GS

```bash
BASE_DIR=$HOME/data/anchr/Lpne
cd ${BASE_DIR}

canu \
    -p Lpne -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=3.4m \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p Lpne -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=3.4m \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/Lpne.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/Lpne.trimmedReads.fasta.gz

```

## Lpne: expand anchors

* anchorLong

```bash
BASE_DIR=$HOME/data/anchr/Lpne
cd ${BASE_DIR}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/Lpne.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/Lpne.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \
    -o stdout \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/Lpne.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd ${BASE_DIR}/contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_DIR=$HOME/data/anchr/Lpne
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |  # |
|:-------------|--------:|--------:|---:|
| Genome       | 3397754 | 3397754 |  1 |
| Paralogs     |    2793 |  100722 | 43 |
| anchor.merge |  248586 | 3426711 | 53 |
| others.merge |   43054 |   47381 |  5 |
| anchor.cover |  248586 | 3375327 | 45 |
| anchorLong   |  261851 | 3373001 | 39 |
| contigTrim   | 3408430 | 3418287 |  7 |

* Clear QxxLxxx.

```bash
BASE_DIR=$HOME/data/anchr/Lpne
cd ${BASE_DIR}

rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q25L60_3000000 |  3585 | 2.03M |  824 |      3879 |   1.88M | 611 |       765 | 155.13K |  213 | 0:02'58'' |
| Q25L60_4000000 |  2270 |    2M | 1139 |      2532 |   1.72M | 757 |       786 | 283.29K |  382 | 0:03'38'' |
| Q30L60_1000000 | 20872 | 2.04M |  205 |     20872 |   2.01M | 165 |       721 |  28.47K |   40 | 0:01'57'' |
| Q30L60_2000000 | 20188 | 2.04M |  219 |     20628 |   2.01M | 178 |       762 |  31.84K |   41 | 0:02'36'' |
| Q30L60_3000000 | 16937 | 2.04M |  242 |     17918 |   2.01M | 201 |       726 |  29.25K |   41 | 0:03'19'' |
| Q30L60_4000000 | 14239 | 2.03M |  279 |     14269 |      2M | 228 |       752 |  37.14K |   51 | 0:03'35'' |

## Ngon: merge anchors

```bash
BASE_DIR=$HOME/data/anchr/Ngon
cd ${BASE_DIR}

# merge anchors
mkdir -p merge
anchr contained \
    Q20L60_1000000/anchor/pe.anchor.fa \
    Q20L60_2000000/anchor/pe.anchor.fa \
    Q20L60_3000000/anchor/pe.anchor.fa \
    Q25L60_1000000/anchor/pe.anchor.fa \
    Q25L60_2000000/anchor/pe.anchor.fa \
    Q25L60_3000000/anchor/pe.anchor.fa \
    Q25L60_4000000/anchor/pe.anchor.fa \
    Q30L60_1000000/anchor/pe.anchor.fa \
    Q30L60_2000000/anchor/pe.anchor.fa \
    Q30L60_3000000/anchor/pe.anchor.fa \
    Q30L60_4000000/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_2000000/anchor/pe.others.fa \
    Q25L60_2000000/anchor/pe.others.fa \
    Q30L60_2000000/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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Ngon: 3GS

```bash
BASE_DIR=$HOME/data/anchr/Ngon
cd ${BASE_DIR}

canu \
    -p Ngon -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=2.3m \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p Ngon -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=2.3m \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/Ngon.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/Ngon.trimmedReads.fasta.gz

```

## Ngon: expand anchors

* anchorLong

```bash
BASE_DIR=$HOME/data/anchr/Ngon
cd ${BASE_DIR}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/Ngon.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/Ngon.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \
    -o stdout \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/Ngon.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd ${BASE_DIR}/contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_DIR=$HOME/data/anchr/Ngon
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |   # |
|:-------------|--------:|--------:|----:|
| Genome       | 2153922 | 2153922 |   1 |
| Paralogs     |    4318 |  142093 |  53 |
| anchor.merge |   23012 | 2014543 | 152 |
| others.merge |    2347 |    2347 |   1 |
| anchor.cover |   19415 | 1876453 | 161 |
| anchorLong   |   29718 | 1874102 | 124 |
| contigTrim   |  465723 | 1839660 |  22 |

* Clear QxxLxxx.

```bash
BASE_DIR=$HOME/data/anchr/Ngon
cd ${BASE_DIR}

rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q25L60X40P002  |  90.89M |   40.0 |  8424 | 2.16M | 401 |      8526 | 2.03M | 320 |      5808 | 138.15K |  81 | "31,41,51,61,71,81" | 0:02'47'' | 0:01'12'' |
| Q25L60X80P000  | 181.79M |   80.0 |  8256 | 2.14M | 424 |      8379 | 2.05M | 347 |       951 |  84.91K |  77 | "31,41,51,61,71,81" | 0:04'33'' | 0:01'37'' |
| Q25L60X120P000 | 272.68M |  120.0 |  7764 | 2.15M | 477 |      7854 | 2.05M | 372 |       832 |  98.28K | 105 | "31,41,51,61,71,81" | 0:05'58'' | 0:02'04'' |
| Q30L60X40P000  |  90.89M |   40.0 |  8732 | 2.12M | 392 |      8901 | 2.04M | 310 |       867 |  76.48K |  82 | "31,41,51,61,71,81" | 0:03'06'' | 0:01'17'' |
| Q30L60X40P001  |  90.89M |   40.0 |  8720 | 2.11M | 392 |      8871 | 2.06M | 315 |       706 |  55.09K |  77 | "31,41,51,61,71,81" | 0:02'44'' | 0:01'05'' |
| Q30L60X80P000  | 181.79M |   80.0 |  9268 | 2.13M | 369 |      9632 | 2.05M | 302 |       935 |  76.24K |  67 | "31,41,51,61,71,81" | 0:02'41'' | 0:01'29'' |

## Nmen: merge anchors

```bash
BASE_NAME=Nmen
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 ::: 60 ::: 40 80 120 160 ::: 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
            " ::: 25 30 ::: 60 ::: 40 80 120 160 ::: 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

# anchors sorted 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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Nmen: 3GS

```bash
BASE_DIR=$HOME/data/anchr/Nmen
cd ${BASE_DIR}

canu \
    -p Nmen -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=2.3m \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p Nmen -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=2.3m \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/Nmen.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/Nmen.trimmedReads.fasta.gz

```

## Nmen: expand anchors

* anchorLong

```bash
BASE_NAME=Nmen
cd ${HOME}/data/anchr/${BASE_NAME}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \
    -o stdout \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/${BASE_NAME}.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 --all \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_NAME=Nmen
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |   # |
|:-------------|--------:|--------:|----:|
| Genome       | 2272360 | 2272360 |   1 |
| Paralogs     |       0 |       0 |   0 |
| anchor.merge |    9877 | 2075643 | 295 |
| others.merge |    9917 |   47940 |  11 |
| anchor.cover |    6814 | 1583544 | 313 |
| anchorLong   |    7239 | 1582929 | 302 |
| contigTrim   |   15255 | 1826314 | 225 |

* Clear QxxLxxXxx.

```bash
BASE_NAME=Nmen
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*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q25L60_3000000 |  2914 | 3.53M | 1679 |      3223 | 3.14M | 1148 |       766 | 391.06K |  531 | 0:02'53'' |
| Q25L60_4000000 |  2532 | 3.58M | 1905 |      2838 |  3.1M | 1247 |       767 | 482.46K |  658 | 0:03'36'' |
| Q25L60_5000000 |  2192 | 3.61M | 2149 |      2563 | 3.01M | 1333 |       759 |  592.4K |  816 | 0:04'09'' |
| Q30L60_1000000 |  2433 | 3.16M | 1703 |      2778 |  2.7M | 1076 |       758 | 459.36K |  627 | 0:01'29'' |
| Q30L60_2000000 |  2858 | 3.36M | 1610 |      3251 | 2.98M | 1087 |       731 | 372.53K |  523 | 0:01'44'' |
| Q30L60_3000000 |  3136 | 3.46M | 1580 |      3503 |  3.1M | 1088 |       742 | 353.88K |  492 | 0:02'18'' |

## Bper: merge anchors

```bash
BASE_DIR=$HOME/data/anchr/Bper
cd ${BASE_DIR}

# merge anchors
mkdir -p merge
anchr contained \
    Q20L60_1000000/anchor/pe.anchor.fa \
    Q20L60_2000000/anchor/pe.anchor.fa \
    Q20L60_3000000/anchor/pe.anchor.fa \
    Q20L60_4000000/anchor/pe.anchor.fa \
    Q25L60_1000000/anchor/pe.anchor.fa \
    Q25L60_2000000/anchor/pe.anchor.fa \
    Q25L60_3000000/anchor/pe.anchor.fa \
    Q25L60_4000000/anchor/pe.anchor.fa \
    Q30L60_1000000/anchor/pe.anchor.fa \
    Q30L60_2000000/anchor/pe.anchor.fa \
    Q30L60_3000000/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_2000000/anchor/pe.others.fa \
    Q25L60_2000000/anchor/pe.others.fa \
    Q30L60_2000000/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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

* Stats

```bash
BASE_DIR=$HOME/data/anchr/Bper
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       | 4086189 | 4086189 |   1 |
| Paralogs     |         |         |     |
| anchor.merge |    4674 | 3478267 | 986 |
| others.merge |    1024 |   52609 |  49 |

* Clear QxxLxxx.

```bash
BASE_DIR=$HOME/data/anchr/Bper
cd ${BASE_DIR}

rm -fr 2_illumina/Q{20,25,30}L*
rm -fr Q{20,25,30}L*
```

# Corynebacterium diphtheriae FDAARGOS_197, 白喉杆菌

* Project
[SRP040661](https://trace.ncbi.nlm.nih.gov/Traces/sra/?study=SRP040661)

* Other name: ATCC 700971D-5; NCTC 13129;

* BioSample: [SAMN04875534](https://www.ncbi.nlm.nih.gov/biosample/SAMN04875534)

## Cdip: download

doc/bacteria_2_3.md  view on Meta::CPAN

| Q30L60X80P001  | 199.09M |   80.0 | 68973 | 2.45M |  64 |     68973 | 2.45M |  57 |       844 |  5.27K |   7 | "31,41,51,61,71,81" | 0:04'02'' | 0:02'00'' |
| Q30L60X80P002  | 199.09M |   80.0 | 89791 | 2.45M |  65 |     89791 | 2.45M |  58 |       809 |  5.53K |   7 | "31,41,51,61,71,81" | 0:04'01'' | 0:02'08'' |
| Q30L60X120P000 | 298.64M |  120.0 | 60425 | 2.45M |  74 |     60427 | 2.45M |  67 |       727 |  5.37K |   7 | "31,41,51,61,71,81" | 0:05'23'' | 0:02'27'' |
| Q30L60X120P001 | 298.64M |  120.0 | 71924 | 2.45M |  62 |     71924 | 2.44M |  56 |       844 |   4.9K |   6 | "31,41,51,61,71,81" | 0:05'18'' | 0:02'36'' |
| Q30L60X160P000 | 398.18M |  160.0 | 60427 | 2.45M |  75 |     60427 | 2.45M |  68 |       727 |  5.37K |   7 | "31,41,51,61,71,81" | 0:06'26'' | 0:03'04'' |
| Q30L60X240P000 | 597.27M |  240.0 | 57594 | 2.45M |  86 |     59198 | 2.44M |  74 |       844 |  9.05K |  12 | "31,41,51,61,71,81" | 0:06'47'' | 0:03'28'' |

## Cdip: merge anchors

```bash
BASE_NAME=Cdip
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 ::: 60 ::: 40 80 120 160 240 ::: 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
            " ::: 25 30 ::: 60 ::: 40 80 120 160 240 ::: 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

# anchors sorted 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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Cdip: 3GS

```bash
BASE_NAME=Cdip
REAL_G=2488635
cd $HOME/data/anchr/${BASE_NAME}

canu \
    -p ${BASE_NAME} -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=${REAL_G} \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p ${BASE_NAME} -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=${REAL_G} \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/${BASE_NAME}.trimmedReads.fasta.gz

```

## Cdip: expand anchors

* anchorLong

```bash
BASE_NAME=Cdip
cd ${HOME}/data/anchr/${BASE_NAME}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/${BASE_NAME}.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 --all \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_NAME=Cdip
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |  # |
|:-------------|--------:|--------:|---:|
| Genome       | 2488635 | 2488635 |  1 |
| Paralogs     |    5635 |   56210 | 18 |
| anchor.merge |  115948 | 2447558 | 46 |
| others.merge |    2541 |   23728 | 10 |
| anchor.cover |  108033 | 2442070 | 45 |
| anchorLong   |  125030 | 2441001 | 30 |
| contigTrim   | 2488479 | 2488479 |  1 |

* Clear QxxLxxXxx.

```bash
BASE_NAME=Cdip
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*

doc/bacteria_2_3.md  view on Meta::CPAN

| Q30L60X40P002  |  75.71M |   40.0 | 32751 |  1.8M | 73 |     32751 |  1.8M | 72 |       855 |    855 | 1 | "31,41,51,61,71,81" | 0:01'13'' | 0:00'44'' |
| Q30L60X40P003  |  75.71M |   40.0 | 32741 |  1.8M | 75 |     32741 |  1.8M | 74 |       865 |    865 | 1 | "31,41,51,61,71,81" | 0:01'13'' | 0:00'45'' |
| Q30L60X80P000  | 151.42M |   80.0 | 32751 |  1.8M | 74 |     32751 |  1.8M | 73 |       865 |    865 | 1 | "31,41,51,61,71,81" | 0:01'49'' | 0:01'08'' |
| Q30L60X80P001  | 151.42M |   80.0 | 32751 |  1.8M | 74 |     32751 |  1.8M | 73 |       865 |    865 | 1 | "31,41,51,61,71,81" | 0:01'50'' | 0:01'12'' |
| Q30L60X120P000 | 227.13M |  120.0 | 32751 |  1.8M | 77 |     32751 |  1.8M | 75 |       865 |  1.49K | 2 | "31,41,51,61,71,81" | 0:02'26'' | 0:01'32'' |
| Q30L60X160P000 | 302.84M |  160.0 | 32404 |  1.8M | 79 |     32404 |  1.8M | 77 |       865 |  1.49K | 2 | "31,41,51,61,71,81" | 0:03'00'' | 0:01'37'' |

## Ftul: merge anchors

```bash
BASE_NAME=Ftul
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 ::: 60 ::: 40 80 120 160 ::: 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
            " ::: 25 30 ::: 60 ::: 40 80 120 160 ::: 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

# anchors sorted 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 \
    merge/anchor.merge.fasta \
    merge/others.merge.fasta \
    1_genome/paralogs.fas \
    --label "merge,others,paralogs" \
    -o 9_qa

```

## Ftul: 3GS

```bash
BASE_NAME=Ftul
GENOME_SIZE=1.9m
cd $HOME/data/anchr/${BASE_NAME}

canu \
    -p ${BASE_NAME} -d canu-raw-40x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=${GENOME_SIZE} \
    -pacbio-raw 3_pacbio/pacbio.40x.fasta

canu \
    -p ${BASE_NAME} -d canu-raw-80x \
    gnuplot=$(brew --prefix)/Cellar/$(brew list --versions gnuplot | sed 's/ /\//')/bin/gnuplot \
    genomeSize=${GENOME_SIZE} \
    -pacbio-raw 3_pacbio/pacbio.80x.fasta

faops n50 -S -C canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz
faops n50 -S -C canu-raw-80x/${BASE_NAME}.trimmedReads.fasta.gz

```

## Ftul: expand anchors

* anchorLong

```bash
BASE_NAME=Ftul
cd ${HOME}/data/anchr/${BASE_NAME}

anchr cover \
    --parallel 16 \
    -c 2 -m 40 \
    -b 20 --len 1000 --idt 0.9 \
    merge/anchor.merge.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -o merge/anchor.cover.fasta

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.cover.fasta \
    canu-raw-40x/${BASE_NAME}.trimmedReads.fasta.gz \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.98

anchr overlap \
    merge/anchor.cover.fasta \
    --serial --len 10 --idt 0.9999 \

doc/bacteria_2_3.md  view on Meta::CPAN


rm -fr contigTrim
anchr overlap2 \
    --parallel 16 \
    anchorLong/contig.fasta \
    canu-raw-40x/${BASE_NAME}.contigs.fasta \
    -d contigTrim \
    -b 20 --len 1000 --idt 0.98 --all

CONTIG_COUNT=$(faops n50 -H -N 0 -C contigTrim/anchor.fasta)
echo ${CONTIG_COUNT}

rm -fr contigTrim/group
anchr group \
    --parallel 16 \
    --keep \
    contigTrim/anchorLong.db \
    contigTrim/anchorLong.ovlp.tsv \
    --range "1-${CONTIG_COUNT}" --len 1000 --idt 0.98 --max 20000 -c 1

pushd contigTrim
cat group/groups.txt \
    | parallel --no-run-if-empty -j 8 '
        echo {};
        anchr orient \
            --len 1000 --idt 0.98 \
            group/{}.anchor.fasta \
            group/{}.long.fasta \
            -r group/{}.restrict.tsv \
            -o group/{}.strand.fasta;

        anchr overlap --len 1000 --idt 0.98 --all \
            group/{}.strand.fasta \
            -o stdout \
            | anchr restrict \
                stdin group/{}.restrict.tsv \
                -o group/{}.ovlp.tsv;

        anchr layout \
            group/{}.ovlp.tsv \
            group/{}.relation.tsv \
            group/{}.strand.fasta \
            -o group/{}.contig.fasta
    '
popd

cat \
    contigTrim/group/non_grouped.fasta \
    contigTrim/group/*.contig.fasta \
    >  contigTrim/contig.fasta

```

* 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

```

* Stats

```bash
BASE_NAME=Ftul
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
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchor.cover"; faops n50 -H -S -C merge/anchor.cover.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "anchorLong"; faops n50 -H -S -C anchorLong/contig.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "contigTrim"; faops n50 -H -S -C contigTrim/contig.fasta;) >> stat3.md

cat stat3.md
```

| Name         |     N50 |     Sum |  # |
|:-------------|--------:|--------:|---:|
| Genome       | 1892775 | 1892775 |  1 |
| Paralogs     |   33912 |   93531 | 10 |
| anchor.merge |   32813 | 1801122 | 73 |
| others.merge |   32404 |   64274 |  3 |
| anchor.cover |   32813 | 1796007 | 71 |
| anchorLong   |   35248 | 1795927 | 70 |
| contigTrim   | 1027458 | 1856949 |  4 |

* Clear QxxLxxXxx.

```bash
BASE_NAME=Ftul
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*



( run in 1.035 second using v1.01-cache-2.11-cpan-39bf76dae61 )