src/docker_modules/TopHat/2.1.1/Dockerfile

-FROM ubuntu:18.04
-MAINTAINER Laurent Modolo
-
-ENV TOPHAT_VERSION=2.1.1
-ENV PACKAGES tophat=${BOWTIE2_VERSION}*
-
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends ${PACKAGES} && \
-    apt-get clean

src/docker_modules/TopHat/2.1.1/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/TopHat/2.1.1 -t 'tophat:2.1.1'

src/docker_modules/Trimmomatic/0.36/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/Trimmomatic/0.36 -t 'trimmomatic:0.36'

src/docker_modules/UrQt/d62c1f8/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/UrQt/d62c1f8 -t 'urqt:62c1f8'

src/docker_modules/UrQt/tests/tests.sh

-nextflow src/nf_modules/UrQt/tests/trimming_paired.nf \
-  -c src/nf_modules/UrQt/urqt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/UrQt/tests/trimming_single.nf \
-  -c src/nf_modules/UrQt/urqt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"

src/docker_modules/canu/1.6/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/canu/1.6 -t 'canu:1.6'

src/docker_modules/cutadapt/1.14/Dockerfile

-FROM ubuntu:18.04
-MAINTAINER Laurent Modolo
-
-ENV CUTADAPT_VERSION=1.14
-ENV PACKAGES build-essential=12.4* \
-             python3-pip=9.0.1* \
-             python3-setuptools=39.0.1* \
-             python3-dev=3.6.5* \
-             python3-wheel=0.30.0*
-
-RUN apt-get update && \
-    apt-get install -y --no-install-recommends ${PACKAGES} && \
-    apt-get clean
-
-RUN pip3 install cutadapt==${CUTADAPT_VERSION}

src/docker_modules/cutadapt/1.14/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/cutadapt/1.14 -t 'cutadapt:1.14'

src/docker_modules/cutadapt/tests/tests.sh

-nextflow src/nf_modules/cutadapt/tests/adaptor_removal_paired.nf \
-  -c src/nf_modules/cutadapt/cutadapt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/adaptor_removal_single.nf \
-  -c src/nf_modules/cutadapt/cutadapt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/trimming_paired.nf \
-  -c src/nf_modules/cutadapt/cutadapt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"
-
-nextflow src/nf_modules/cutadapt/tests/trimming_single.nf \
-  -c src/nf_modules/cutadapt/cutadapt.config \
-  -profile docker \
-  --fastq "data/tiny_dataset/fastq/tiny_R{1,2}.fastq"

src/docker_modules/deepTools/3.0.2/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/deepTools/3.0.2 -t 'deeptools:3.0.2'

src/docker_modules/file_handle/0.1.1/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/file_handle/0.1.1 -t 'file_handle:0.1.1'

src/docker_modules/pigz/2.4/docker_init.sh

-#!/bin/sh
-docker build src/nf_modules/pigz/2.4 -t 'pigz:2.4'

src/example_chipseq.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+nextflow.enable.dsl=2
+
+include {
+  fastp
+} from './nf_modules/fastp/main'
+
+workflow csv_parsing {
+  if (params.csv_path.size() > 0) {
+    log.info "loading local csv files"
+    Channel
+      .fromPath(params.csv_path, checkIfExists: true)
+      .ifEmpty { error 
+      log.error """
+    =============================================================
+      WARNING! No csv input file precised.
+      Use '--csv_path <file.csv>'
+      Or '--help' for more informations
+    =============================================================
+    """
+      }
+      .splitCsv(header: true, sep: ";", strip: true)
+      .flatMap{
+        it -> [
+          [(it.IP + it.WCE).md5(), "IP", "w", file(it.IP)],
+          [(it.IP + it.WCE).md5(), "WCE", "w", file(it.WCE)]
+        ]
+      }
+      .map{ it ->
+        if (it[1] instanceof List){
+          it
+        } else {
+          [it[0], [it[1]], it[2], it[3], [it[4]]]
+        }
+      }
+      .map{
+        it ->
+        if (it[1].size() == 2){ // if data are paired_end
+          [
+            "index": it[0],
+            "group": ref_order(it),
+            "ip": it[2],
+            "type": it[3],
+            "id": read_order(it)[0],
+            "file": read_order(it)
+          ]
+        } else {
+          [
+            "index": it[0],
+            "group": it[1].simpleName,
+            "ip": it[2],
+            "type": it[3],
+            "id": it[4].simpleName,
+            "file": [it[4].simpleName, it[4]]
+          ]
+        }
+      }
+      .set{input_csv}
+  } else {
+    log.info "loading remotes SRA csv files"
+    Channel
+      .fromPath(params.csv_sra, checkIfExists: true)
+      .ifEmpty { error 
+      log.error """
+    =============================================================
+      WARNING! No csv input file precised.
+      Use '--csv_path <file.csv>' or
+      Use '--csv_SRA <file.csv>'
+      Or '--help' for more informations
+    =============================================================
+    """
+      }
+      .splitCsv(header: true, sep: ";", strip: true)
+      .flatMap{
+        it -> [
+          [[it.IP_w + it.WCE_w + it.IP_m + it.WCE_m], t.IP_w, "IP", "w", it.IP_w],
+          [[it.IP_w + it.WCE_w + it.IP_m + it.WCE_m], it.IP_w, "WCE", "w", it.WCE_w],
+          [[it.IP_w + it.WCE_w + it.IP_m + it.WCE_m], it.IP_w, "IP", "m", it.IP_m],
+          [[it.IP_w + it.WCE_w + it.IP_m + it.WCE_m], it.IP_w, "WCE", "m", it.WCE_m]
+        ]
+      }
+      .map{
+        it ->
+        if (it[1].size() == 2){ // if data are paired_end
+          [
+            "index": (
+              it[0][0][0].simpleName +
+              it[0][0][1].simpleName +
+              it[0][0][2].simpleName +
+              it[0][0][3].simpleName
+            ).md5(),
+            "group": it[1][0].simpleName,
+            "ip": it[2],
+            "type": it[3],
+            "id": it[4][0].simpleName[0..-4],
+            "file": [it[4][0].simpleName[0..-4], it[4]]
+          ]
+        } else {
+          [
+            "index": (
+              it[0][0].simpleName +
+              it[0][1].simpleName +
+              it[0][2].simpleName +
+              it[0][3].simpleName
+            ).md5(),
+            "group": it[1].simpleName,
+            "ip": it[2],
+            "type": it[3],
+            "id": it[4].simpleName,
+            "file": [it[4].simpleName, it[4]]
+          ]
+        }
+      }
+      .set{input_csv}
+  }
+  emit:
+  input_csv
+}
+
+
+workflow {
+
+}
\ No newline at end of file

src/example_marseq.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+nextflow.enable.dsl=2
+
+/*
+Testing pipeline for marseq scRNASeq analysis
+*/
+
+include { adaptor_removal} from "./nf_modules/cutadapt/main.nf"
+include {
+  index_fasta;
+  count;
+  index_fasta_velocity;
+  count_velocity
+} from "./nf_modules/kb/main.nf" addParams(
+  kb_protocol: "marsseq",
+  count_out: "quantification/",
+  count_velocity_out: "quantification_velocity/"
+)
+
+params.fasta = "http://ftp.ensembl.org/pub/release-98/fasta/gallus_gallus/dna/Gallus_gallus.GRCg6a.dna.toplevel.fa.gz"
+params.fastq = "data/CF42_45/*/*R{1,2}.fastq.gz"
+params.gtf = "http://ftp.ensembl.org/pub/release-98/gtf/gallus_gallus/Gallus_gallus.GRCg6a.98.gtf.gz"
+params.transcript_to_gene = ""
+params.whitelist = "data/expected_whitelist.txt"
+params.config = "data/marseq_flexi_splitter.yaml"
+params.workflow_type = "classic"
+
+log.info "fastq files (--fastq): ${params.fastq}"
+log.info "fasta file (--fasta): ${params.fasta}"
+log.info "gtf file (--gtf): ${params.gtf}"
+log.info "transcript_to_gene file (--transcript_to_gene): ${params.transcript_to_gene}"
+log.info "whitelist file (--whitelist): ${params.whitelist}"
+log.info "config file (--config): ${params.config}"
+
+channel
+  .fromFilePairs( params.fastq, size: -1)
+  .set { fastq_files }
+channel
+  .fromPath( params.fasta )
+  .ifEmpty { error "Cannot find any fasta files matching: ${params.fasta}" }
+  .map { it -> [it.simpleName, it]}
+  .set { fasta_files }
+channel
+  .fromPath( params.gtf )
+  .ifEmpty { error "Cannot find any gtf files matching: ${params.gtf}" }
+  .map { it -> [it.simpleName, it]}
+  .set { gtf_files }
+if (params.whitelist == "") {
+  channel.empty()
+    .set { whitelist_files }
+} else {
+  channel
+    .fromPath( params.whitelist )
+    .map { it -> [it.simpleName, it]}
+    .set { whitelist_files }
+}
+channel
+  .fromPath( params.config )
+  .ifEmpty { error "Cannot find any config files matching: ${params.config}" }
+  .map { it -> [it.simpleName, it]}
+  .set { config_files }
+
+workflow {
+  adaptor_removal(fastq_files)
+  if (params.workflow_type == "classic") {
+    index_fasta(
+      fasta_files,
+      gtf_files
+    )
+    count(
+      index_fasta.out.index,
+      adaptor_removal.out.fastq,
+      index_fasta.out.t2g, whitelist_files,config_files
+    )
+  } else {
+    index_fasta_velocity(
+      fasta_files,
+      gtf_files
+    )
+    count_velocity(
+      index_fasta_velocity.out.index,
+      adaptor_removal.out.fastq,
+      index_fasta_velocity.out.t2g,
+      whitelist_files,
+      config_files
+    )
+  }
+}

src/example_variant_calling.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+nextflow.enable.dsl=2
+
+/*
+Testing pipeline for marseq scRNASeq analysis
+*/
+
+include {
+  mapping;
+} from "./nf_modules/bwa/main.nf"
+
+include {
+  sort_bam;
+} from "./nf_modules/samtools/main.nf"
+
+include {
+  germline_cohort_data_variant_calling;
+} from "./nf_modules/gatk4/main.nf" addParams(
+  variant_calling_out: "vcf/",
+)
+
+params.fastq = ""
+params.fasta = ""
+
+channel
+  .fromFilePairs( params.fastq, size: -1)
+  .set { fastq_files }
+channel
+  .fromPath( params.fasta )
+  .map { it -> [it.simpleName, it]}
+  .set { fasta_files }
+
+workflow {
+  mapping(fasta_files, fastq_files)
+  sort_bam(mapping.out.bam)
+  germline_cohort_data_variant_calling(sort_bam.out.bam, fasta_files)
+}

src/fasta_sampler.nf

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+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
+"""
+}

src/in2p3.pbs

+#!/bin/sh
+
+# SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+#
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
+#SBATCH --job-name=nextflow
+
+#SBATCH --ntasks=1
+#SBATCH --output=results/nextflow_%j.log
+#SBATCH --licenses=sps
+
+####################################
+
+# change to your path 
+SCRATCH=/sps/lbmc/lmodolo/nextflow
+
+${SCRATCH}/nextflow run ${SCRATCH}/src/solution_RNASeq.nf -profile ccin2p3 \
+--fastq "${SCRATCH}/data/tiny_dataset/fastq/*_R{1,2}.fastq" \
+--fasta "${SCRATCH}/data/tiny_dataset/fasta/tiny_v2.fasta" \
+--bed "${SCRATCH}/data/tiny_dataset/annot/tiny.bed" \
+-ansi-log \
+-w "${SCRATCH}/work/"
+
+wait

src/install_nextflow.sh

 #!/bin/sh
 
+# SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+#
+# SPDX-License-Identifier: AGPL-3.0-or-later
+
 java -version
 curl -s https://get.nextflow.io | bash

src/nextflow.config

+// SPDX-FileCopyrightText: 2022 Laurent Modolo <laurent.modolo@ens-lyon.fr>
+//
+// SPDX-License-Identifier: AGPL-3.0-or-later
+
+nextflowVersion = '>=20'
+
+manifest {
+    homePage = 'https://gitbio.ens-lyon.fr/LBMC/nextflow'
+    description = 'pipeline to '
+    mainScript = 'main.nf'
+    version = '0.0.0'
+}
+
+report {
+  enabled = true
+  file = "$baseDir/../results/report.html"
+}
+
+profiles {
+  docker {
+    docker.temp = "auto"
+    docker.enabled = true
+    process {
+      errorStrategy = 'finish'
+      memory = '16GB'
+      withLabel: big_mem_mono_cpus {
+        cpus = 1
+      }
+      withLabel: big_mem_multi_cpus {
+        cpus = 4
+      }
+      withLabel: small_mem_mono_cpus {
+        cpus = 1
+        memory = '2GB'
+      }
+      withLabel: small_mem_multi_cpus {
+        cpus = 4
+        memory = '2GB'
+      }
+    }
+  }
+  podman {
+    charliecloud.enabled = true
+    charliecloud.cacheDir = "./bin/"
+    process {
+      errorStrategy = 'finish'
+      memory = '16GB'
+      withLabel: big_mem_mono_cpus {
+        cpus = 1
+      }
+      withLabel: big_mem_multi_cpus {
+        cpus = 4
+      }
+      withLabel: small_mem_mono_cpus {
+        cpus = 1
+        memory = '2GB'
+      }
+      withLabel: small_mem_multi_cpus {
+        cpus = 4
+        memory = '2GB'
+      }
+    }
+  }
+  singularity {
+    singularity.enabled = true
+    singularity.cacheDir = "./bin/"
+    process {
+      errorStrategy = 'finish'
+      memory = '16GB'
+      withLabel: big_mem_mono_cpus {
+        cpus = 1
+      }
+      withLabel: big_mem_multi_cpus {
+        cpus = 4
+      }
+      withLabel: small_mem_mono_cpus {
+        cpus = 1
+        memory = '2GB'
+      }
+      withLabel: small_mem_multi_cpus {
+        cpus = 4
+        memory = '2GB'
+      }
+    }
+  }
+  psmn {
+    charliecloud.enabled = true
+    charliecloud.cacheDir = "/Xnfs/abc/charliecloud"
+    charliecloud.runOptions = "--bind /scratch:/scratch --bind /Xnfs:/Xnfs --bind /home:/home"
+    charliecloud.readOnlyInputs = true
+    process{
+      errorStrategy = { sleep(Math.pow(2, task.attempt) * 200 as long); return 'retry' }
+      maxRetries = 3
+      executor = "slurm"
+      queue = "Lake"
+      withLabel: big_mem_mono_cpus {
+        cpus = 1
+        memory = "128GB"
+        time = "24h"
+      }
+      withLabel: big_mem_multi_cpus {
+        cpus = 32
+        memory = "192GB"
+        time = "24h"
+      }
+      withLabel: small_mem_mono_cpus {
+        cpus = 1
+        memory = "16GB"
+        time = "24h"
+      }
+      withLabel: small_mem_multi_cpus {
+        cpus = 32
+        memory = "16GB"
+        time = "24h"
+      }
+    }
+  }
+  ccin2p3 {
+    singularity.enabled = true
+    singularity.cacheDir = "$baseDir/../bin/"
+    singularity.runOptions = "--bind /pbs,/sps,/scratch,/tmp"
+    process{
+      maxRetries = 3
+      withLabel: big_mem_mono_cpus {
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "slurm"
+        clusterOptions = "--licenses=sps"
+        cpus = 1
+        memory = "8GB"
+        queue = "htc"
+      }
+      withLabel: big_mem_multi_cpus {
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "slurm"
+        clusterOptions = "--licenses=sps"
+        cpus = 1
+        memory = "8GB"
+        queue = "htc"
+      }
+      withLabel: small_mem_mono_cpus {
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "slurm"
+        clusterOptions = "--licenses=sps"
+        cpus = 1
+        memory = "8GB"
+        queue = "htc"
+      }
+      withLabel: small_mem_multi_cpus {
+        scratch = true
+        stageInMode = "copy"
+        stageOutMode = "rsync"
+        executor = "slurm"
+        clusterOptions = "--licenses=sps"
+        cpus = 1
+        memory = "8GB"
+        queue = "htc"
+      }
+    }
+  }
+}

src/nf_modules/Bowtie2/bowtie2.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $index_fasta {
-        container = "bowtie2:2.3.4.1"
-      }
-      $mapping_fastq {
-        container = "bowtie2:2.3.4.1"
-      }
-    }
-  }
-  sge {
-    process{
-      $index_fasta {
-        beforeScript = "module purge; module load Bowtie2/2.3.4.1"
-      }
-      $mapping_fastq {
-        beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie2/2.3.4.1"
-      }
-    }
-  }
-}