404 results from the CPAN

App-Anchr

    independentLong.fasta

find . -type d -name "correction" | xargs rm -fr

# localCor
gzip -d -c -f $(find group -type f -name "*.correctedReads.fasta.gz") \
    | faops filter -l 0 stdin stdout \
    | grep -E '^>long' -A 1 \
    | sed '/^--$/d' \
    | faops dazz -a -l 0 stdin stdout \
    | pigz -c > localCor.fasta.gz

canu \
    -p ${BASE_NAME} -d localCor \
    gnuplotTested=true \
    genomeSize=${REAL_G} \
    -pacbio-corrected localCor.fasta.gz \
    -pacbio-corrected anchor.fasta

canu \
    -p ${BASE_NAME} -d localCorRaw \
    gnuplotTested=true \
    genomeSize=${REAL_G} \
    -pacbio-raw localCor.fasta.gz \
    -pacbio-raw anchor.fasta

canu \
    -p ${BASE_NAME} -d localCorIndep \
    gnuplotTested=true \
    genomeSize=${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

find . -type d -name "correction" | xargs rm -fr

```

## s288c: expand anchors

åœ¨é…¿é…’é…µæ¯ä¸, æœ‰ä¸‹åˆ—å‡ ç»„å®Œå…¨ç›¸åŒçš„åºåˆ—, å®ƒä»¬éƒ½æ˜¯æ–°è¿‘å‘ç”Ÿçš„ç‰‡æ®µé‡å¤:

* I:216563-218385, VIII:537165-538987
* I:223713-224783, VIII:550350-551420
* IV:528442-530427, IV:532327-534312, IV:536212-538197
* IV:530324-531519, IV:534209-535404
* IV:5645-7725, X:738076-740156
* IV:7810-9432, X:736368-737990
* IX:9683-11043, X:9666-11026
* IV:1244112-1245373, XV:575980-577241
* VIII:212266-214124, VIII:214264-216122
* IX:11366-14953, X:11349-14936
* XII:468935-470576, XII:472587-474228, XII:482167-483808, XII:485819-487460,
* XII:483798-485798, XII:487450-489450

* anchorLong

```bash
BASE_NAME=s288c
cd ${HOME}/data/anchr/${BASE_NAME}

rm -fr anchorLong
anchr overlap2 \
    --parallel 16 \
    merge/anchor.merge.fasta \
    3_pacbio/pacbio.40x.trim.fasta \
    -d anchorLong \
    -b 20 --len 1000 --idt 0.85 --all

pushd anchorLong

anchr cover \
    --range "1-$(faops n50 -H -N 0 -C anchor.fasta)" \
    --len 1000 --idt 0.85 -c 2 \
    anchorLong.ovlp.tsv \
    -o anchor.cover.json
cat anchor.cover.json | jq "." > environment.json

anchr overlap \
    anchor.fasta \
    --serial --len 20 --idt 0.9999 \
    -o stdout \
    | perl -nla -e '
        BEGIN {
            our %seen;
            our %count_of;
        }

        @F == 13 or next;
        $F[3] > 0.9999 or next;

        my $pair = join( "-", sort { $a <=> $b } ( $F[0], $F[1], ) );
        next if $seen{$pair};
        $seen{$pair} = $_;

        $count_of{ $F[0] }++;
        $count_of{ $F[1] }++;

        END {
            for my $pair ( keys %seen ) {
                my ($f_id, $g_id) = split "-", $pair;
                next if $count_of{$f_id} > 2;
                next if $count_of{$g_id} > 2;
                print $seen{$pair};
            }
        }

doc/model_organisms.md view on Meta::CPAN

            -o group/{}.contig.fasta
    '
popd

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

```

## iso_1: final stats

* Stats

```bash
BASE_NAME=iso_1
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 "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
printf "| %s | %s | %s | %s |\n" \
    $(echo "spades.contig"; faops n50 -H -S -C 8_spades/contigs.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "spades.scaffold"; faops n50 -H -S -C 8_spades/scaffolds.fasta;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "platanus.contig"; faops n50 -H -S -C 8_platanus/out_contig.fa;) >> stat3.md
printf "| %s | %s | %s | %s |\n" \
    $(echo "platanus.scaffold"; faops n50 -H -S -C 8_platanus/out_gapClosed.fa;) >> stat3.md

cat stat3.md
```

| Name              |      N50 |       Sum |      # |
|:------------------|---------:|----------:|-------:|
| Genome            | 25286936 | 137567477 |      8 |
| Paralogs          |     4031 |  13665900 |   4492 |
| anchor.merge      |    26860 | 117041459 |   9566 |
| others.merge      |     8732 |   3092289 |   1004 |
| anchor.cover      |    26199 | 116199529 |   9576 |
| anchorLong        |    69814 | 115806088 |   4924 |
| contigTrim        |  1238480 | 123572499 |    603 |
| spades.contig     |   108756 | 132705321 |  61620 |
| spades.scaffold   |   142273 | 132725706 |  61182 |
| 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 \
    1_genome/paralogs.fas \
    --label "merge,contig,contigTrim,canu-40x,canu-40x.trim,spades,platanus,paralogs" \
    -o 9_qa_contig

```

* Clear QxxLxxXxx.

```bash
BASE_NAME=iso_1
cd ${HOME}/data/anchr/${BASE_NAME}

rm -fr 2_illumina/Q{20,25,30,35}L{30,60,90,120}X*
rm -fr Q{20,25,30,35}L{30,60,90,120}X*
```

# *Caenorhabditis elegans* N2

* Genome: [Ensembl 82](http://sep2015.archive.ensembl.org/Caenorhabditis_elegans/Info/Index)
* Proportion of paralogs (> 1000 bp): 0.0472

## n2: download

* Reference genome

```bash
mkdir -p ~/data/anchr/n2/1_genome
cd ~/data/anchr/n2/1_genome

wget -N ftp://ftp.ensembl.org/pub/release-82/fasta/caenorhabditis_elegans/dna/Caenorhabditis_elegans.WBcel235.dna_sm.toplevel.fa.gz
faops order Caenorhabditis_elegans.WBcel235.dna_sm.toplevel.fa.gz \
    <(for chr in {I,II,III,IV,V,X,MtDNA}; do echo $chr; done) \
    genome.fa

cp ~/data/anchr/paralogs/model/Results/n2/n2.multi.fas 1_genome/paralogs.fas
```

* Illumina

    * Other SRA
        * SRX770040 - [insert size](https://www.ncbi.nlm.nih.gov/sra/SRX770040[accn]) is 500-600 bp

( run in 1.159 second using v1.01-cache-2.11-cpan-75ffa21a3d4 )