Compare revisions

profiles {

  docker {

    docker.temp = 'auto'

    docker.enabled = true

    process {

      $adaptor_removal {

        container = "cutadapt:1.14"

      }

    }

  }

  sge {

    process{

      $adaptor_removal {

        beforeScript = "module purge; module load cutadapt/1.14"

        executor = "sge"

        cpus = 1

        memory = "5GB"

        time = "6h"

        queueSize = 1000

        pollInterval = '60sec'

        queue = 'h6-E5-2667v4deb128'

        penv = 'openmp8'

      }

    }

  }

}

profiles {

  docker {

    docker.temp = 'auto'

    docker.enabled = true

    process {

      $trimming {

        container = "urqt:d62c1f8"

      }

    }

  }

  sge {

    process{

      $trimming {

        beforeScript = "module purge; module load UrQt/d62c1f8"

        executor = "sge"

        cpus = 4

        memory = "5GB"

        time = "6h"

        queueSize = 1000

        pollInterval = '60sec'

        queue = 'h6-E5-2667v4deb128'

        penv = 'openmp8'

      }

    }

  }

}

profiles {

  docker {

    docker.temp = 'auto'

    docker.enabled = true

    process {

      $fasta_from_bed {

        container = "bedtools:2.25.0"

      }

    }

  }

  sge {

    process{

      $fasta_from_bed {

        beforeScript = "module purge; module load BEDtools/2.25.0"

        executor = "sge"

        cpus = 1

        memory = "5GB"

        time = "6h"

        queueSize = 1000

        pollInterval = '60sec'

        queue = 'h6-E5-2667v4deb128'

        penv = 'openmp8'

      }

    }

  }

}

profiles {

  docker {

    docker.temp = 'auto'

    docker.enabled = true

    process {

      $index_fasta {

        container = "kallisto:0.43.1"

      }

      $mapping_fastq {

        container = "kallisto:0.43.1"

      }

    }

  }

  sge {

    process{

      $index_fasta {

        beforeScript = "module purge; module load Kallisto/0.43.1"

        executor = "sge"

        cpus = 1

        memory = "5GB"

        time = "6h"

        queueSize = 1000

        pollInterval = '60sec'

        queue = 'h6-E5-2667v4deb128'

        penv = 'openmp8'

      }

      $mapping_fastq {

        beforeScript = "module purge; module load Kallisto/0.43.1"

        executor = "sge"

        cpus = 4

        memory = "5GB"

        time = "6h"

        queueSize = 1000

        pollInterval = '60sec'

        queue = 'h6-E5-2667v4deb128'

        penv = 'openmp8'

      }

    }

  }

}

/*

* cutadapt :

* Imputs : fastq files

* Output : fastq files

*/

/*                      Illumina adaptor removal                             */

/*

* for paired-end data

*/

params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"

log.info "fastq files : ${params.fastq}"

Channel

  .fromFilePairs( params.fastq )

  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }

  .set { fastq_files }

process adaptor_removal {

  tag "$pair_id"

  publishDir "results/fastq/adaptor_removal/", mode: 'copy'

  input:

  set pair_id, file(reads) from fastq_files

  output:

  file "*_cut_R{1,2}.fastq.gz" into fastq_files_cut

  script:

  """

  cutadapt -a AGATCGGAAGAG -g CTCTTCCGATCT -A AGATCGGAAGAG -G CTCTTCCGATCT \

  -o ${pair_id}_cut_R1.fastq.gz -p ${pair_id}_cut_R2.fastq.gz \

  ${reads[0]} ${reads[1]} > ${pair_id}_report.txt

  """

}

/*

* urqt :

* Imputs : fastq files

* Output : fastq files

*/

/*                      quality trimming                                     */

/*

* for paired-end data

*/

process trimming {

  tag "${reads}"

  cpus 4

  publishDir "results/fastq/trimming/", mode: 'copy'

  input:

  file reads from fastq_files_cut

  output:

  file "*_trim_R{1,2}.fastq.gz" into fastq_files_trim

  script:

"""

UrQt --t 20 --m ${task.cpus} --gz \

--in ${reads[0]} --inpair ${reads[1]} \

--out ${reads[0].baseName}_trim_R1.fastq.gz --outpair ${reads[1].baseName}_trim_R2.fastq.gz \

> ${reads[0].baseName}_trimming_report.txt

"""

}

/*

* bedtools :

* Imputs : fastq files

* Output : fastq files

*/

/*                      fasta extraction                                     */

params.fasta = "$baseDir/data/fasta/*.fasta"

params.bed = "$baseDir/data/annot/*.bed"

log.info "fasta file : ${params.fasta}"

log.info "bed file : ${params.bed}"

Channel

  .fromPath( params.fasta )

  .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }

  .set { fasta_files }

Channel

  .fromPath( params.bed )

  .ifEmpty { error "Cannot find any bed files matching: ${params.bed}" }

  .set { bed_files }

process fasta_from_bed {

  tag "${bed.baseName}"

  cpus 4

  publishDir "results/fasta/", mode: 'copy'

  input:

  file fasta from fasta_files

  file bed from bed_files

  output:

  file "*_extracted.fasta" into fasta_files_extracted

  script:

"""

bedtools getfasta -name \

-fi ${fasta} -bed ${bed} -fo ${bed.baseName}_extracted.fasta

"""

}

/*

* Kallisto :

* Imputs : fastq files

* Imputs : fasta files

* Output : bam files

*/

/*                      fasta indexing                                     */

process index_fasta {

  tag "$fasta.baseName"

  publishDir "results/mapping/index/", mode: 'copy'

  input:

    file fasta from fasta_files_extracted

  output:

    file "*.index*" into index_files

  script:

"""

kallisto index -k 31 --make-unique -i ${fasta.baseName}.index ${fasta} \

> ${fasta.baseName}_kallisto_report.txt

"""

}

/*

* for paired-end data

*/

process mapping_fastq {

  tag "$reads"

  cpus 4

  publishDir "results/mapping/quantification/", mode: 'copy'

  input:

  file reads from fastq_files_trim

  file index from index_files.toList()

  output:

  file "*" into counts_files

  script:

"""

mkdir ${reads[0].baseName}

kallisto quant -i ${index} -t ${task.cpus} \

--bias --bootstrap-samples 100 -o ${reads[0].baseName} \

${reads[0]} ${reads[1]} &> ${reads[0].baseName}_kallisto_report.txt

"""

}

FROM ubuntu:18.04

MAINTAINER Laurent Modolo

ENV PACKAGES git=1:2.17.0* \

ENV PACKAGES git=1:2.17* \

   build-essential=12.4* \

   ca-certificates=20180409 \

   zlib1g-dev=1:1.2.11*

Channel

  .fromPath( "data/tiny_dataset/fasta/*.fasta" )

  .set { fasta_file }

process sample_fasta {

  publishDir "results/sampling/", mode: 'copy'

  input:

file fasta from fasta_file

  output:

file "*_sample.fasta" into fasta_sample

  script:

"""

head ${fasta} > ${fasta.baseName}_sample.fasta

"""

}