# First confirm that you have the program 'git' installed in your system
> cd
> git clone -b 'v0.0.9-beta' --single-branch --depth 1 https://github.com/vetscience/Assemblosis
> cd Assemblosis
> bash install.sh

> cd
> export PATH=~/miniconda3/bin:$PATH
> cd Assemblosis/Run
> cp ../Examples/assemblyCele.yml .

"Edit assemblyCele.yml to fit your computing environment and to define the location for the read files, databases and Illumina adapters"

> mkdir RepeatSimple; mkdir RepeatTransp; mkdir RepeatCustom
> cwltool --tmpdir-prefix /home/<username>/Tmp --beta-conda-dependencies --cachedir /home/<username>/Cache --user-space-docker-cmd udocker --leave-tmpdir assembly.cwl assemblyCele.yml

## Top level directory, which contains the PacBio raw data
# NOTE! The software looks for all .h5 files recursively in given directory
pacBioDataDir:
  class: Directory
  location: /home/<username>/Dna

## Prefix for the resultant assembly files
prefix: cele

## Maximum number of threads used in the pipeline
threads: 24

### Parameters for the program Canu are described in https://canu.readthedocs.io/en/latest/parameter-reference.html
## Expected genome size. This parameter is forwarded to Canu assembler.
genomeSize: 100m

## Minimum length for the PacBio reads used for the assembly. This parameter is forwarded to Canu assembler.
# The maximum resolvable repeat regions becomes 2 x minReadLength
minReadLen: 6000

## Parameter for Canu assembler to adjust to GC-content. Should be 0.15 for high or low GC content.
corMaxEvidenceErate: 0.20

### Parameters for the program Trimmomatic are described in http://www.usadellab.org/cms/?page=trimmomatic
## Paired-end (PE) reads of Illumina raw data. These files are given to the program Trimmomatic.
# NOTE! Data for two paired libraries is given below.
readsPe1:
  - class: File
    format: edam:format_1930  # fastq
    path: /home/<username>/Dna/SRR2598966_1.fastq.gz
  - class: File
    format: edam:format_1930  # fastq
    path: /home/<username>/Dna/SRR2598967_1.fastq.gz
readsPe2:
  - class: File
    format: edam:format_1930  # fastq
    path: /home/<username>/Dna/SRR2598966_2.fastq.gz
  - class: File
    format: edam:format_1930  # fastq
    path: /home/<username>/Dna/SRR2598967_2.fastq.gz

## Phred coding of Illumina data. This parameter is forwarded to Trimmomatic.
# NOTE! Each read-pair needs one phred value.
phredsPe: ['33','33']

## Sliding window and illuminaClip parameters for Trimmomatic
slidingWindow:
    windowSize: 4
    requiredQuality: 25
illuminaClip:
    adapters:
        class: File
        path: <path to Illumina adapter file>
    seedMismatches: 2
    palindromeClipThreshold: 30
    simpleClipThreshold: 10
    minAdapterLength: 20
    keepBothReads: true
## Further parameters for Trimmomatic
# Required phred-quality for leading 5 nucleotides
leading: 25
# Required phred-quality for trailing 5 nucleotides
trailing: 25
# Minimum accepted read-length to keep the read after trimming
minlen: 40

### Parameters for the program bowtie2 are described in http://bowtie-bio.sourceforge.net/bowtie2/manual.shtml
## Illumina PE fragment length. Program bowtie2 parameter -X.
# NOTE! Each read-pair needs one phred value.
maxFragmentLens: [500, 600]
# Orientation of pair-end reads e.g. 'fr', 'rf', 'ff': Program bowtie2 parameters --fr, --rf or --ff
orientation: 'fr'

### Parameters for the program Pilon are described in https://github.com/broadinstitute/pilon/wiki/Requirements-&-Usage
# Prefix for the resultant pilon polished assembly. Pilon parameter --output
polishedAssembly: celePilon
# This is set 'true' for an organism with diploid genome: Pilon parameter --diploid
diploidOrganism: true
# Value 'bases' fixes snps and indels: Pilon parameter --fix
fix: bases

### Parameters for the program centrifuge are described in http://www.ccb.jhu.edu/software/centrifuge/manual.shtml
# Path to the directory, that contains NCBI nt database in nt.?.cf files. Centrifuge parameter -x
database:
  class: Directory
  path:  /home/<username>/ntDatabase
# Lenght of the identical match in nucleotides required to infer a read as contaminant. Centrifuge parameter --min-hitlen
partialMatch: 100
# NCBI taxon root identifers for the species considered contaminants: e.g. bacteria (=2), viruses (=10239), fungi (=4751), mammals (=40674), artificial seqs (=81077). Pipeline specific parameter.
taxons: [2,10239,4751,40674,81077]

## Parameters for the RepeatModeler and RepeatMasker are described in http://www.repeatmasker.org
repBaseLibrary:
  class: File
  # This is the RepBase file from https://www.girinst.org/repbase. RepeatMasker parameter -lib
  path: /home/<username>/RepBaseLibrary/RMRBSeqs.embl
# Directories for inferred custom repeats (inferred by RepeatModeler), tandem repeats (simple repeats) and interspersed repeats (transposons)'
# RepeatMasker parameter -dir
repeatWorkDir:
  - class: Directory
    location: RepeatCustom
  - class: Directory
    location: RepeatSimple
  - class: Directory
    location: RepeatTransp
# Represents -noint parameter for masking custom, tandem and interspersed repeats
noInterspersed: [false, true, false]
# Represents -nolow parameter for masking custom, tandem and interspersed repeats
noLowComplexity: [true, false, true]