src/docker_modules/samblaster/0.1.24/docker_init.sh

-#!/bin/sh
-docker build src/docker_modules/samblaster/0.1.24 -t 'samblaster:0.1.24'

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/intersect_SNP.R

-#!/usr/bin/Rscript
-rm(list = ls())
-library("tidyverse")
-library("seqinr")
-
-args <- c(
-  "results/SNP/vcf_samtools/normal_sample_filtered.csv",
-  "results/SNP/vcf_samtools/tumor_sample_filtered.csv",
-  "results/fasta/DBG2OLC_output2_filtered.fasta",
-  "data/list_of_enzymes.csv"
-  )
-seq_restric_size <- 21
-
-args <- commandArgs(trailingOnly = TRUE)
-snp_a <- read_delim(args[1], delim = "\t") %>%
-  mutate(cords = paste0(CHROM, POS))
-snp_b <- read_delim(args[2], delim = "\t") %>%
-  mutate(cords = paste0(CHROM, POS))
-
-only_b <- snp_b %>%
-  select(cords) %>%
-  setdiff(snp_a %>% select(cords)) %>%
-  pull(cords)
-
-snp <- snp_b %>%
-  filter(cords %in% only_b) %>%
-  filter(tumor_sample.GT %in% c("A/A", "T/T", "G/G", "C/C")) %>%
-  mutate(REF = do.call(rbind, strsplit(AD, split = ",", fixed = TRUE))[,1],
-         VAR = do.call(rbind, strsplit(AD, split = ",", fixed = TRUE))[,2],
-         REF = as.integer(REF),
-         VAR = as.integer(VAR),
-         tumor_sample.AD = NULL,
-         cords = NULL
-  ) %>%
-  filter(REF == 0) %>%
-  filter(VAR >= 10) %>%
-  arrange(CHROM, desc(VAR))
-
-fastafile <- read.fasta(file = args[3],
-                        as.string = TRUE)
-
-snp$seq_list <- snp %>%
-  apply(1, FUN = function(x, fastafile, POS, CHROM, seq_restric_size){
-      begin <- as.integer(x[ POS ]) - ((seq_restric_size - 1) / 2)
-      end <- as.integer(x[ POS ]) + ((seq_restric_size - 1) / 2)
-      chrom <- x[ CHROM ]
-      seq_restric <- fastafile[[ chrom ]] %>%
-        c2s() %>%
-        substr(begin, end) %>%
-        s2c()
-      seq_restric[((seq_restric_size - 1) / 2) + 1] <-
-        toupper(seq_restric[((seq_restric_size - 1) / 2) + 1])
-      print(paste0(chrom, ":", begin, "-", end, " ", seq_restric %>% c2s()))
-      return(seq_restric %>% c2s())
-    },
-    fastafile = fastafile,
-    POS = which(colnames(snp) %in% "POS"),
-    CHROM = which(colnames(snp) %in% "CHROM")
-  )
-
-snp %>%
-  write_csv(paste0(args[2], "only.csv" ))
-
-
-snp <- read_csv(paste0(args[2], "only.csv" ))
-enzyme_list <- read_csv(args[4]) %>%
-  mutate(size = nchar(seq))
-
-snp <- snp %>%
-  mutate(enzyme = NA,
-         enzyme_pos = NA,
-         enzyme_seq = NA)
-for (i in seq_len(nrow(enzyme_list))) {
-  enzyme <- enzyme_list[i, ]
-  enzyme_search <- gregexpr(toupper(enzyme$seq),
-                            toupper(snp$seq_list),
-                            fixed = TRUE) %>%
-    lapply(FUN = function(x, enzyme, seq_restric_size) {
-      if (x[1] < 0) {
-        return(c(NA, NA, NA))
-      } else {
-        if (x[1] <= (seq_restric_size - 1) / 2 + 1 &
-            x[1] + enzyme$size >=  (seq_restric_size - 1) / 2 + 1) {
-        return(c(enzyme$enzyme, x[1], enzyme$seq))
-        }
-        return(c(NA, NA, NA))
-      }
-    },
-    enzyme = enzyme,
-    seq_restric_size = seq_restric_size)
-  enzyme_search <- do.call(rbind, enzyme_search)
-  snp[is.na(snp$enzyme), c("enzyme", "enzyme_pos", "enzyme_seq")] <-
-    enzyme_search[is.na(snp$enzyme), ]
-}
-
-snp %>%
-  filter(!is.na(enzyme)) %>%
-  write_csv(paste0(args[2], "only_enzyme.csv" ))
-

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/BEDtools/fasta_from_bed.config

-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'
-      }
-    }
-  }
-}

src/nf_modules/BEDtools/fasta_from_bed.nf

-/*
-* bedtools :
-* Imputs : fasta files
-* Imputs : bed files
-* Output : fasta 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
-"""
-}

src/nf_modules/BEDtools/tests.sh

-./nextflow src/nf_modules/BEDtools/fasta_from_bed.nf \
-  -c src/nf_modules/BEDtools/fasta_from_bed.config \
-  -profile docker \
-  --fasta "data/tiny_dataset/fasta/tiny_v2.fasta" \
-  --bed "data/tiny_dataset/annot/tiny.bed" \

src/nf_modules/BWA/indexing.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $index_fasta {
-        container = "bwa:0.7.17"
-      }
-    }
-  }
-  sge {
-    process{
-      $index_fasta {
-        beforeScript = "module purge; module load BWA/0.7.17"
-        executor = "sge"
-        cpus = 1
-        memory = "5GB"
-        time = "6h"
-        queueSize = 1000
-        pollInterval = '60sec'
-        queue = 'h6-E5-2667v4deb128'
-        penv = 'openmp8'
-      }
-    }
-  }
-}

src/nf_modules/BWA/indexing.nf

-params.fasta = "$baseDir/data/bam/*.fasta"
-
-log.info "fasta files : ${params.fasta}"
-
-Channel
-  .fromPath( params.fasta )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .set { fasta_file }
-
-process index_fasta {
-  tag "$fasta_id"
-  cpus 4
-  publishDir "results/mapping/index/", mode: 'copy'
-
-  input:
-    set fasta_id, file(fasta) from fasta_file
-
-  output:
-    set fasta_id, "${fasta.baseName}.*" into index_files
-    file "*_bwa_report.txt" into index_files_report
-
-  script:
-"""
-bwa index -p ${fasta.baseName} ${fasta} \
-&> ${fasta.baseName}_bwa_report.txt
-"""
-}
-

src/nf_modules/BWA/mapping_paired.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $mapping_fastq {
-        container = "bwa:0.7.17"
-      }
-    }
-  }
-  sge {
-    process{
-      $mapping_fastq {
-        beforeScript = "module purge; module load BWA/0.7.17"
-        executor = "sge"
-        cpus = 4
-        memory = "5GB"
-        time = "6h"
-        queueSize = 1000
-        pollInterval = '60sec'
-        queue = 'h6-E5-2667v4deb128'
-        penv = 'openmp8'
-      }
-    }
-  }
-}

src/nf_modules/BWA/mapping_paired.nf

-params.fastq = "$baseDir/data/fastq/*_{1,2}.fastq"
-params.index = "$baseDir/data/index/*.index.*"
-
-log.info "fastq files : ${params.fastq}"
-log.info "index files : ${params.index}"
-
-Channel
-  .fromFilePairs( params.fastq )
-  .ifEmpty { error "Cannot find any fastq files matching: ${params.fastq}" }
-  .set { fastq_files }
-Channel
-  .fromPath( params.index )
-  .ifEmpty { error "Cannot find any index files matching: ${params.index}" }
-  .map { it -> [(it.baseName =~ /([^\.]*)/)[0][1], it]}
-  .groupTuple()
-  .set { index_files }
-
-process mapping_fastq {
-  tag "$reads"
-  cpus 4
-  publishDir "results/mapping/sam/", mode: 'copy'
-
-  input:
-  set pair_id, file(reads) from fastq_files
-  set index_id, file(index) from index_files.collect()
-
-  output:
-  file "${pair_id}.sam" into sam_files
-  file "${pair_id}_bwa_report.txt" into mapping_repport_files
-
-  script:
-"""
-bwa mem -t ${task.cpus} \
-${index_id} ${reads[0]} ${reads[1]} \
--o ${pair_id}.sam &> ${pair_id}_bwa_report.txt
-"""
-}
-

src/nf_modules/BWA/tests.sh

-./nextflow src/nf_modules/BWA/indexing.nf \
-  -c src/nf_modules/BWA/indexing.config \
-  -profile docker \
-  --fasta "data/tiny_dataset/fasta/tiny_v2.fasta"
-
-# ./nextflow src/nf_modules/BWA/mapping_single.nf \
-#   -c src/nf_modules/BWA/mapping_single.config \
-#   -profile docker \
-#   --index "results/mapping/index/tiny_v2.index" \
-#   --fastq "data/tiny_dataset/fastq/tiny*_S.fastq"
-
-./nextflow src/nf_modules/BWA/mapping_paired.nf \
-  -c src/nf_modules/BWA/mapping_paired.config \
-  -profile docker \
-  --index "results/mapping/index/tiny_v2*" \
-  --fastq "data/tiny_dataset/fastq/tiny*_R{1,2}.fastq"
-

src/nf_modules/Bowtie/indexing.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $index_fasta {
-        container = "bowtie:1.2.2"
-      }
-    }
-  }
-  sge {
-    process{
-      $index_fasta {
-        beforeScript = "module purge; module load Bowtie/1.2.2"
-      }
-    }
-  }
-}

src/nf_modules/Bowtie/indexing.nf

-/*                      fasta indexing                                     */
-
-params.fasta = "$baseDir/data/bam/*.fasta"
-
-log.info "fasta files : ${params.fasta}"
-
-Channel
-  .fromPath( params.fasta )
-  .ifEmpty { error "Cannot find any bam files matching: ${params.fasta}" }
-  .set { fasta_file }
-
-process index_fasta {
-  tag "$fasta.baseName"
-  cpus 4
-  publishDir "results/mapping/index/", mode: 'copy'
-
-  input:
-    file fasta from fasta_file
-
-  output:
-    file "*.index*" into index_files
-    file "*_report.txt" into indexing_report
-
-  script:
-"""
-bowtie-build --threads ${task.cpus} -f ${fasta} ${fasta.baseName}.index &> ${fasta.baseName}_bowtie_report.txt
-
-if grep -q "Error" ${fasta.baseName}_bowtie_report.txt; then
-  exit 1
-fi
-"""
-}
-

src/nf_modules/Bowtie/mapping_paired.config

-profiles {
-  docker {
-    docker.temp = 'auto'
-    docker.enabled = true
-    process {
-      $mapping_fastq {
-        container = "bowtie:1.2.2"
-      }
-    }
-  }
-  sge {
-    process{
-      $mapping_fastq {
-        beforeScript = "module purge; module load SAMtools/1.7; module load Bowtie/1.2.2"
-      }
-    }
-  }
-}