App-Anchr

 view release on metacpan or  search on metacpan

doc/e_coli.md  view on Meta::CPAN

    -c out_scaffold.fa \
    -ip1 pe.fa \
    2>&1 | tee gap_log.txt

```

```text
#### PROCESS INFORMATION ####
VmPeak:          65.317 GByte
VmHWM:            7.030 GByte
```

## Quorum

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

parallel --no-run-if-empty -j 1 "
    cd 2_illumina/Q{1}L{2}
    echo >&2 '==> Group Q{1}L{2} <=='

    if [ ! -e R1.fq.gz ]; then
        echo >&2 '    R1.fq.gz not exists'
        exit;
    fi

    if [ -e pe.cor.fa ]; then
        echo >&2 '    pe.cor.fa exists'
        exit;
    fi

    if [[ {1} -ge '30' ]]; then
        anchr quorum \
            R1.fq.gz R2.fq.gz Rs.fq.gz \
            -p 16 \
            -o quorum.sh
    else
        anchr quorum \
            R1.fq.gz R2.fq.gz \
            -p 16 \
            -o quorum.sh
    fi

    bash quorum.sh
    
    echo >&2
    " ::: 20 25 30 35 ::: 30 60 90 120

```

Clear intermediate files.

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

find 2_illumina -type f -name "quorum_mer_db.jf" | xargs rm
find 2_illumina -type f -name "k_u_hash_0"       | xargs rm
find 2_illumina -type f -name "*.tmp"            | xargs rm
find 2_illumina -type f -name "pe.renamed.fastq" | xargs rm
find 2_illumina -type f -name "se.renamed.fastq" | xargs rm
find 2_illumina -type f -name "pe.cor.sub.fa"    | xargs rm
```

* Stats of processed reads

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

REAL_G=4641652

bash ~/Scripts/cpan/App-Anchr/share/sr_stat.sh 1 header \
    > stat1.md

parallel -k --no-run-if-empty -j 3 "
    if [ ! -d 2_illumina/Q{1}L{2} ]; then
        exit;
    fi

    bash ~/Scripts/cpan/App-Anchr/share/sr_stat.sh 1 2_illumina/Q{1}L{2} ${REAL_G}
    " ::: 20 25 30 35 ::: 30 60 90 120 \
     >> stat1.md

cat stat1.md
```

| Name    |   SumIn | CovIn |  SumOut | CovOut | Discard% | AvgRead |  Kmer | RealG |   EstG | Est/Real |   RunTime |
|:--------|--------:|------:|--------:|-------:|---------:|--------:|------:|------:|-------:|---------:|----------:|
| Q20L30  |   1.51G | 326.3 |   1.32G |  284.1 |  12.941% |     136 |  "65" | 4.64M |  4.85M |     1.04 | 0:05'15'' |
| Q20L60  |   1.47G | 316.4 |   1.28G |  275.6 |  12.888% |     139 |  "67" | 4.64M |  4.82M |     1.04 | 0:19'45'' |
| Q20L90  |   1.37G | 295.2 |   1.19G |  256.8 |  13.001% |     143 |  "95" | 4.64M |  4.69M |     1.01 | 0:21'17'' |
| Q20L120 |   1.14G | 244.6 | 988.43M |  212.9 |  12.937% |     147 | "105" | 4.64M |  4.63M |     1.00 | 0:19'36'' |
| Q25L30  |   1.38G | 297.9 |    1.3G |  280.6 |   5.808% |     128 |  "79" | 4.64M |  4.59M |     0.99 | 0:22'37'' |
| Q25L60  |   1.32G | 283.9 |   1.24G |  267.4 |   5.801% |     133 |  "83" | 4.64M |  4.58M |     0.99 | 0:22'07'' |
| Q25L90  |   1.18G | 253.6 |   1.11G |  238.8 |   5.832% |     138 |  "87" | 4.64M |  4.57M |     0.99 | 0:20'45'' |
| Q25L120 | 837.11M | 180.3 | 786.11M |  169.4 |   6.093% |     144 |  "95" | 4.64M |  4.56M |     0.98 | 0:16'54'' |
| Q30L30  |   1.19G | 257.0 |   1.16G |  250.7 |   2.437% |     115 |  "65" | 4.64M |  4.56M |     0.98 | 0:22'42'' |
| Q30L60  |   1.15G | 247.7 |   1.12G |  241.6 |   2.484% |     120 |  "71" | 4.64M |  4.56M |     0.98 | 0:19'50'' |
| Q30L90  |   1.02G | 220.4 | 996.45M |  214.7 |   2.605% |     128 |  "79" | 4.64M |  4.56M |     0.98 | 0:04'04'' |
| Q30L120 | 695.91M | 149.9 | 674.79M |  145.4 |   3.035% |     139 |  "91" | 4.64M |  4.56M |     0.98 | 0:03'30'' |
| Q35L30  | 589.03M | 126.9 | 582.15M |  125.4 |   1.169% |      62 |  "35" | 4.64M |  4.56M |     0.98 | 0:07'08'' |
| Q35L60  | 369.07M |  79.5 | 362.78M |   78.2 |   1.705% |      73 |  "45" | 4.64M |  4.51M |     0.97 | 0:05'58'' |
| Q35L90  |  35.58M |   7.7 |  32.82M |    7.1 |   7.770% |      98 |  "65" | 4.64M |  2.03M |     0.44 | 0:00'14'' |
| Q35L120 | 652.49K |   0.1 | 293.98K |    0.1 |  54.945% |     126 |  "85" | 4.64M | 47.62K |     0.01 | 0:00'07'' |

* kmergenie

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

mkdir -p 2_illumina/kmergenie
cd 2_illumina/kmergenie

kmergenie -l 21 -k 151 -s 10 -t 8 ../R1.fq.gz -o oriR1
kmergenie -l 21 -k 151 -s 10 -t 8 ../R2.fq.gz -o oriR2
kmergenie -l 21 -k 151 -s 10 -t 8 ../Q25L60/pe.cor.fa -o Q25L60

```



( run in 0.736 second using v1.01-cache-2.11-cpan-5b529ec07f3 )