Merge branch 'Alia' into 'master'

Alia

See merge request testoni-lab/bolero!3

src/.docker_modules/r-bolero/1.0/HBV_RNAs_count.R

@@ -74,7 +74,7 @@ countSP <- dplyr::inner_join(palette_complete,
 #print(names(countSP))
 
 countSP$nom <- factor(countSP$nom, levels = all_species_name)
-countSP <- mutate(countSP,
+countSP <- dplyr::mutate(countSP,
                   proportion = (as.numeric(n)/sum(as.numeric(n))*100))
 #print(countSP)
 ggplot(countSP, aes(x = "percent", 
@@ -112,7 +112,7 @@ classified_reads <- read.table(file = opt$classification,
                                header = TRUE)
 
 not_spliced <- classified_reads[!(classified_reads$read_ID %in% clean_SP$id),]
-not_spliced <- mutate(not_spliced,
+not_spliced <- dplyr::mutate(not_spliced,
                       species = not_spliced$promoter)
 #print(not_spliced)
 not_spliced <- not_spliced %>% select(read_ID, species)
@@ -124,7 +124,7 @@ colnames(clean_SP_type) <- c("id", "species")
 df_species <- rbind.data.frame(not_spliced, clean_SP_type, 
                                stringsAsFactors = FALSE)
 count_species <- df_species %>% count(species)
-count_species <- mutate(count_species,
+count_species <- dplyr::mutate(count_species,
                         percent = (as.numeric(n)/sum(as.numeric(n))*100))
 #print(count_species)
 write.table(df_species, file = "All_reads_identified.csv", 
@@ -161,7 +161,7 @@ count_species_SPxx <- rbind.data.frame(count_species_SPxx,
                                        stringsAsFactors = FALSE)
 count_species_SPxx <- count_species_SPxx[count_species_SPxx$species %in% 
                                            all_species_name[c(1:3,5,35)],]
-count_species_SPxx <- mutate(count_species_SPxx,
+count_species_SPxx <- dplyr::mutate(count_species_SPxx,
                              percent=(as.numeric(n)/sum(as.numeric(n))*100))
 #print(count_species_SPxx)
 # save the tab:
@@ -229,7 +229,7 @@ ggsave(file = "Count_RNAs_species_clear.png",
 
 # SP composition clear:
 count_clear <- clean_SP[clean_SP$SP_name %in% SPvariants,] %>% count(SP_name)
-count_clear <- mutate(count_clear,
+count_clear <- dplyr::mutate(count_clear,
                       proportion=(as.numeric(n)/sum(as.numeric(n))*100))
 #print(count_clear)
 count_clear <- dplyr::inner_join(palette_complete,

src/.docker_modules/r-bolero/1.0/Junctions_NanoSplicer.R

@@ -36,7 +36,7 @@ df <- df %>%
 df$donor <- str_replace(df$donor, '[(]', '')
 df$acceptor <- str_replace(df$acceptor, '[)]', '')
 
-df <- mutate(df, 
+df <- dplyr::mutate(df, 
              pg_donor = as.numeric(donor)-122,
              pg_acceptor = as.numeric(acceptor)-122)
 
@@ -110,7 +110,7 @@ assignation_acceptor <- function(pg_acceptor) {
 
 df$donor_site <- sapply(df$pg_donor, assignation_donor)
 df$acceptor_site <- sapply(df$pg_acceptor, assignation_acceptor)
-df <- mutate(df,
+df <- dplyr::mutate(df,
              junction = paste0(donor_site, acceptor_site))
 
 write.table(df, file = "JWR_check_parsed.csv", row.names = FALSE, sep = "\t")

src/.docker_modules/r-bolero/1.0/Start_positions.R

@@ -47,9 +47,9 @@ parsingData <- function(df) {
   tmp$Start <- as.numeric(tmp$Start)
   
   df2 <- as_tibble(tmp) %>% 
-    mutate(bin = round(Start/binsize)*binsize) %>% 
+    dplyr::mutate(bin = round(Start/binsize)*binsize) %>% 
     group_by(bin) %>% 
-    summarize(nb_reads = sum(Freq, na.rm = T))
+    dplyr::summarize(nb_reads = sum(Freq, na.rm = T))
   df2[is.na(df2)] <- 0
   df2[3] <- rep(df[1,3], length(df2$bin))
   colnames(df2) <- c("Start_position", "nb_reads", "Barcode")

src/bolero.nf

 #!/usr/bin/env nextflow
 
 nextflow.enable.dsl=2
+//syntax extension DSL2
 
 /*
 ========================================================================================================================
@@ -73,7 +74,7 @@ if (params.help || params.h) {
  ****************************************************************
 */
 
-/* params in */
+/* Params in */
 
 params.skipBC = true
 params.gpu_mode = false
@@ -100,6 +101,8 @@ params.seqkit_grep_out = "03_fastq/"
 params.cutadapt_out = "04_cutadapt/"
 params.minimap2_genome_out = "05_minimap2/"
 params.start_position_counts_out = "06_start_positions/"
+params.nanosplicer_out = "07_nanosplicer/"
+params.rna_count_out = "08_RNA_count/"
 params.pycoQC_out = "pycoQC/"
 
 /*
@@ -108,6 +111,7 @@ params.pycoQC_out = "pycoQC/"
  ****************************************************************
 */
 
+//to print multiline informations
 log.info "fast5/q folder : ${params.input}"
 log.info "5'RACE adapter sequence : ${params.adapt}"
 if(!params.skipBC) log.info "Guppy basecalling calculation using GPU mode : ${params.gpu_mode}."
@@ -161,13 +165,21 @@ if(!params.skipBC) {
 // Replace concatenate by seqkit fct to parallelization:
 // include { concatenate } from "./nf_modules/seqkit/main.nf"
 include { concatenate } from "./nf_modules/concatenate/main.nf"
-
 include { cut_5pRACE } from "./nf_modules/cutadapt/main.nf"
 include { hbv_genome } from "./nf_modules/minimap2/main.nf"
 include { seqkit_grep } from "./nf_modules/seqkit/main.nf"
-include { sort_bam as sort_bam_genome } from './nf_modules/samtools/main.nf' addParams(sort_bam_out: params.minimap2_genome_out)
-include { index_bam as index_bam_genome } from './nf_modules/samtools/main.nf' addParams(index_bam_out: params.minimap2_genome_out)
+include { sort_bam } from './nf_modules/samtools/main.nf' addParams(sort_bam_out: params.minimap2_genome_out)
+include { index_bam } from './nf_modules/samtools/main.nf' addParams(index_bam_out: params.minimap2_genome_out)
+include { sort_index_bam } from './nf_modules/samtools/main.nf' addParams(indexed_bam_out: params.minimap2_genome_out)
 include { start_position_counts } from "./nf_modules/samtools/main.nf"
+include { start_position_individuals } from "./nf_modules/start_positions/main.nf"
+include { jwr_checker } from "./nf_modules/nanosplicer/main.nf"
+include { junctions_nanosplicer } from "./nf_modules/junction_nanosplicer/main.nf"
+include { rna_count } from "./nf_modules/rna_count/main.nf"
+
+/////////////////////////////////////////////////////////
+// script R avec classification des reads par type d'ARN et graphiques associés
+
 
 // creation des fonctions NanoSplicer:
 // include { jwr_check } from "./nf_modules/nanosplicer/main.nf"
@@ -200,19 +212,33 @@ workflow {
   }
   //####################### PREPROCESSING #######################
 
-  /*
+  
+  
+  //Filtration (seqkit_grep looks for the 5'RACE and the gsp patterns in the reads to keep only mature ARNs)
   seqkit_grep(concatenate.out.merged_fastq, params.adapt, params.gsp)
+  
+  //Cut of the 5'RACE sequence
   cut_5pRACE(seqkit_grep.out.filtered_fastq, params.adapt)
 
   //########################## MAPPING ##########################
-
+  
+  
   hbv_genome(cut_5pRACE.out.fastq_cutadapt, genome)
-  sort_bam_genome(hbv_genome.out.bam)
-  index_bam_genome(sort_bam_genome.out.sorted_bam.collect())
+  sort_index_bam(hbv_genome.out.bam)
+  // index_bam(sort_bam_genome.out.sorted_bam.collect())
 
-  //###################### QUANTIFICATION #######################
+  //###################### START POSITIONS #######################
 
-  start_position_counts(sort_bam_genome.out.sorted_bam)
-  */
+  start_position_counts(sort_index_bam.out.indexed_bam)
+  start_position_individuals(start_position_counts.out.count)
 
-}
+  //#################### VARIANTS D'EPISSAGE ####################
\ No newline at end of file
+
+  jwr_checker(sort_index_bam.out.indexed_bam)
+  junctions_nanosplicer(start_position_individuals.out.classification_of_reads, jwr_checker.out.nanosplicer_jwr)
+  
+  //#################### VARIANTS D'EPISSAGE ####################
+
+  rna_count(junctions_nanosplicer.out.identified_SPvariants, start_position_individuals.out.classification_of_reads)
+
+}

src/nf_modules/junction_nanosplicer/main.nf

 version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
 
-params.junctions_out = ""
+params.nanosplicer_out = ""
 process junctions_nanosplicer{
   container = "${container_url}"
   label "small_mem_mono_cpus"
   tag "identification de variants d'épissage"
-  if (params.junctions_out != "") {
-    publishDir "results/${params.junctions_out}", mode: 'copy'
+  if (params.nanosplicer_out != "") {
+    publishDir "results/${params.nanosplicer_out}", mode: 'copy'
   }
 
   input:
@@ -17,10 +17,11 @@ process junctions_nanosplicer{
   output:
     path("Rplots.pdf")
     path("JWR_check_parsed.csv")
+    path("*.jpg")
     path("identified_SPvariants.csv"), emit: identified_SPvariants
 
   script:
     """
-    Rscript Junctions_NanoSplicer.R -c txt -j csv
+    Rscript /Junctions_NanoSplicer.R -c ${txt} -j ${csv}
     """
 }
\ No newline at end of file

src/nf_modules/rna_count/main.nf

 version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
 
 params.rna_count_out = ""
 process rna_count{
@@ -17,9 +17,10 @@ process rna_count{
   output:
     path("*.csv")
     path("*.pdf")
+    path("*.jpg")
 
   script:
     """
-    Rscript HBV_RNAs_count.R -s spvariants -c classification
+    Rscript /HBV_RNAs_count.R -s ${spvariants} -c ${classification}
     """
 }

src/nf_modules/start_positions/main.nf

 version = "1.0"
-container_url = "xgrand/r-scripts:${version}"
+container_url = "xgrand/r-bolero:${version}"
 
-params.start_position_counts_out = ""
+params.start_position_counts_out =""
 process start_position_individuals{
   container = "${container_url}"
   label "small_mem_mono_cpus"
@@ -9,17 +9,17 @@ process start_position_individuals{
   if (params.start_position_counts_out != "") {
     publishDir "results/${params.start_position_counts_out}", mode: 'copy'
   }
-
   input:
     path(start_position_counts)
 
   output:
     path("Rplots.pdf")
+    path("*.jpg")
     path("Count_reads_per_promoter.tsv")
     path("classification_of_reads_per_RNA.txt"), emit: classification_of_reads
 
   script:
     """
-    Rscript start_positions.R -i start_position_counts
+    Rscript /Start_positions.R -i ${start_position_counts}
     """
 }
\ No newline at end of file