Merge pull request #15 from NorwegianVeterinaryInstitute/dev

Completed changes for draft assembly track

README.md

@@ -1 +1,20 @@
-# Assemblage
+# Assemblage
+
+Assemblage is a nextflow pipeline used for generating assemblies.
+Documentation can be found [here](https://github.com/NorwegianVeterinaryInstitute/Assemblage/wiki).
+The pipeline is currently under construction, but the plan is to generate the following tracks:
+
+### Draft genome assembly
+This track generates assemblies using the normal Illumina paired-end reads.
+
+Status: Complete
+
+### Hybrid genome assembly
+This track generates assemblies based on both Illumina and Nanopore reads, using hybrid assembly.
+
+Status: Under construction
+
+### Optimized genome assembly
+This track is using the long-read-first assembly method, compares that to a hybrid assembly, and merges all plasmid sequences by the use of trycycler.
+
+Status: Not yet started

assets/data/reads/samplesheet.csv

@@ -0,0 +1,4 @@
+sample,R1,R2,np
+sample1,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample1_R1.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample1_R2.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/nanopore/sample1.fastq.gz
+sample2,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample2_R1.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample2_R2.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/nanopore/sample2.fastq.gz
+sample3,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample3_R1.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/illumina/sample3_R2.fastq.gz,https://raw.githubusercontent.com/NorwegianVeterinaryInstitute/Assemblage/master/assets/data/reads/nanopore/sample3.fastq.gz

assets/r_env.yml

@@ -0,0 +1,223 @@
+name: alppaca_report
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - _r-mutex=1.0.1=anacondar_1
+  - binutils_impl_linux-64=2.36.1=h193b22a_2
+  - binutils_linux-64=2.36=hf3e587d_10
+  - bioconductor-ggtree=3.2.0=r41hdfd78af_0
+  - bioconductor-treeio=1.18.0=r41hdfd78af_0
+  - bwidget=1.9.14=ha770c72_1
+  - bzip2=1.0.8=h7f98852_4
+  - c-ares=1.18.1=h7f98852_0
+  - ca-certificates=2022.12.7=ha878542_0
+  - cairo=1.16.0=ha12eb4b_1010
+  - curl=7.85.0=h2283fc2_0
+  - expat=2.4.9=h27087fc_0
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=hab24e00_0
+  - fontconfig=2.14.0=hc2a2eb6_1
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - freetype=2.12.1=hca18f0e_0
+  - fribidi=1.0.10=h36c2ea0_0
+  - gcc_impl_linux-64=9.5.0=h6c5bc03_16
+  - gcc_linux-64=9.5.0=h4258300_10
+  - gettext=0.19.8.1=h27087fc_1009
+  - gfortran_impl_linux-64=9.5.0=h3c9b8b6_16
+  - gfortran_linux-64=9.5.0=hdb51d14_10
+  - graphite2=1.3.13=h58526e2_1001
+  - gsl=2.7=he838d99_0
+  - gxx_impl_linux-64=9.5.0=h6c5bc03_16
+  - gxx_linux-64=9.5.0=h43f449f_10
+  - harfbuzz=4.2.0=h40b6f09_0
+  - icu=69.1=h9c3ff4c_0
+  - jpeg=9e=h166bdaf_2
+  - kernel-headers_linux-64=2.6.32=he073ed8_15
+  - keyutils=1.6.1=h166bdaf_0
+  - krb5=1.19.3=h08a2579_0
+  - ld_impl_linux-64=2.36.1=hea4e1c9_2
+  - lerc=4.0.0=h27087fc_0
+  - libblas=3.9.0=16_linux64_openblas
+  - libcblas=3.9.0=16_linux64_openblas
+  - libcurl=7.85.0=h2283fc2_0
+  - libdeflate=1.14=h166bdaf_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libev=4.33=h516909a_1
+  - libffi=3.4.2=h7f98852_5
+  - libgcc-devel_linux-64=9.5.0=h367e8d2_16
+  - libgcc-ng=12.1.0=h8d9b700_16
+  - libgfortran-ng=12.1.0=h69a702a_16
+  - libgfortran5=12.1.0=hdcd56e2_16
+  - libglib=2.74.0=h7a41b64_0
+  - libgomp=12.1.0=h8d9b700_16
+  - libiconv=1.17=h166bdaf_0
+  - liblapack=3.9.0=16_linux64_openblas
+  - libnghttp2=1.47.0=hff17c54_1
+  - libopenblas=0.3.21=pthreads_h78a6416_3
+  - libpng=1.6.38=h753d276_0
+  - libsanitizer=9.5.0=hf86b28c_16
+  - libssh2=1.10.0=hf14f497_3
+  - libstdcxx-devel_linux-64=9.5.0=h367e8d2_16
+  - libstdcxx-ng=12.1.0=ha89aaad_16
+  - libtiff=4.4.0=h55922b4_4
+  - libuuid=2.32.1=h7f98852_1000
+  - libwebp-base=1.2.4=h166bdaf_0
+  - libxcb=1.13=h7f98852_1004
+  - libxml2=2.9.12=h885dcf4_1
+  - libzlib=1.2.12=h166bdaf_4
+  - make=4.3=hd18ef5c_1
+  - ncurses=6.2=h58526e2_4
+  - openssl=3.0.8=h0b41bf4_0
+  - pandoc=2.19.2=ha770c72_0
+  - pango=1.50.7=hbd2fdc8_0
+  - pcre2=10.37=hc3806b6_1
+  - pixman=0.40.0=h36c2ea0_0
+  - pthread-stubs=0.4=h36c2ea0_1001
+  - r-ape=5.6_2=r41h43535f1_0
+  - r-aplot=0.1.8=r41hc72bb7e_0
+  - r-askpass=1.1=r41h06615bd_3
+  - r-assertthat=0.2.1=r41hc72bb7e_3
+  - r-backports=1.4.1=r41h06615bd_1
+  - r-base=4.1.2=h2553ce4_1
+  - r-base64enc=0.1_3=r41h06615bd_1005
+  - r-bit=4.0.4=r41h06615bd_1
+  - r-bit64=4.0.5=r41h06615bd_1
+  - r-brio=1.1.3=r41h06615bd_1
+  - r-bslib=0.4.0=r41hc72bb7e_1
+  - r-cachem=1.0.6=r41h06615bd_1
+  - r-callr=3.7.2=r41hc72bb7e_1
+  - r-cli=3.4.1=r41h7525677_1
+  - r-clipr=0.8.0=r41hc72bb7e_1
+  - r-colorspace=2.0_3=r41h06615bd_1
+  - r-cpp11=0.4.2=r41hc72bb7e_1
+  - r-crayon=1.5.2=r41hc72bb7e_1
+  - r-crosstalk=1.2.0=r41hc72bb7e_1
+  - r-curl=4.3.3=r41h06615bd_1
+  - r-data.table=1.14.2=r41h06615bd_1
+  - r-desc=1.4.2=r41hc72bb7e_1
+  - r-diffobj=0.3.5=r41h06615bd_1
+  - r-digest=0.6.29=r41h7525677_1
+  - r-distributional=0.3.1=r41hc72bb7e_1
+  - r-dplyr=1.0.10=r41h7525677_1
+  - r-ellipsis=0.3.2=r41h06615bd_1
+  - r-evaluate=0.17=r41hc72bb7e_1
+  - r-fansi=1.0.3=r41h06615bd_1
+  - r-farver=2.1.1=r41h7525677_1
+  - r-fastmap=1.1.0=r41h7525677_1
+  - r-formattable=0.2.1=r41ha770c72_1
+  - r-fs=1.5.2=r41h7525677_2
+  - r-gdtools=0.2.4=r41h287fb7f_1
+  - r-generics=0.1.3=r41hc72bb7e_1
+  - r-ggdist=3.2.1=r41hc72bb7e_0
+  - r-ggfun=0.0.7=r41hc72bb7e_0
+  - r-ggplot2=3.4.1=r41hc72bb7e_0
+  - r-ggplotify=0.1.0=r41hc72bb7e_0
+  - r-glue=1.6.2=r41h06615bd_1
+  - r-gridextra=2.3=r41hc72bb7e_1004
+  - r-gridgraphics=0.5_1=r41hc72bb7e_1
+  - r-gtable=0.3.1=r41hc72bb7e_1
+  - r-hdinterval=0.2.4=r41hc72bb7e_0
+  - r-hexbin=1.28.2=r41h8da6f51_1
+  - r-highr=0.9=r41hc72bb7e_1
+  - r-hms=1.1.2=r41hc72bb7e_1
+  - r-htmltools=0.5.3=r41h7525677_1
+  - r-htmlwidgets=1.5.4=r41hc72bb7e_1
+  - r-httr=1.4.4=r41hc72bb7e_1
+  - r-isoband=0.2.6=r41h7525677_1
+  - r-jquerylib=0.1.4=r41hc72bb7e_1
+  - r-jsonlite=1.8.2=r41h06615bd_1
+  - r-kableextra=1.3.4=r41hc72bb7e_1
+  - r-knitr=1.40=r41hc72bb7e_1
+  - r-labeling=0.4.2=r41hc72bb7e_2
+  - r-later=1.2.0=r41h7525677_1
+  - r-lattice=0.20_45=r41h06615bd_1
+  - r-lazyeval=0.2.2=r41h06615bd_3
+  - r-lifecycle=1.0.3=r41hc72bb7e_1
+  - r-magrittr=2.0.3=r41h06615bd_1
+  - r-mass=7.3_58.1=r41h06615bd_1
+  - r-matrix=1.4_1=r41h5f7b363_1
+  - r-memoise=2.0.1=r41hc72bb7e_1
+  - r-mgcv=1.8_40=r41h0154571_0
+  - r-mime=0.12=r41h06615bd_1
+  - r-munsell=0.5.0=r41hc72bb7e_1005
+  - r-nlme=3.1_159=r41h8da6f51_1
+  - r-numderiv=2016.8_1.1=r41hc72bb7e_4
+  - r-openssl=2.0.3=r41h1f3e0c5_1
+  - r-patchwork=1.1.2=r41hc72bb7e_0
+  - r-pillar=1.8.1=r41hc72bb7e_1
+  - r-pkgconfig=2.0.3=r41hc72bb7e_2
+  - r-pkgload=1.3.0=r41hc72bb7e_1
+  - r-plotly=4.10.0=r41hc72bb7e_0
+  - r-praise=1.0.0=r41hc72bb7e_1006
+  - r-prettyunits=1.1.1=r41hc72bb7e_2
+  - r-processx=3.7.0=r41h06615bd_1
+  - r-progress=1.2.2=r41hc72bb7e_3
+  - r-promises=1.2.0.1=r41h7525677_1
+  - r-ps=1.7.1=r41h06615bd_1
+  - r-purrr=0.3.5=r41h06615bd_1
+  - r-quadprog=1.5_8=r41hd009a43_4
+  - r-r6=2.5.1=r41hc72bb7e_1
+  - r-rappdirs=0.3.3=r41h06615bd_1
+  - r-rcolorbrewer=1.1_3=r41h785f33e_1
+  - r-rcpp=1.0.9=r41h7525677_2
+  - r-readr=2.1.2=r41h03ef668_0
+  - r-rematch2=2.1.2=r41hc72bb7e_2
+  - r-rlang=1.0.6=r41h7525677_1
+  - r-rmarkdown=2.17=r41hc72bb7e_1
+  - r-rprojroot=2.0.3=r41hc72bb7e_1
+  - r-rstudioapi=0.14=r41hc72bb7e_1
+  - r-rvest=1.0.3=r41hc72bb7e_1
+  - r-sass=0.4.2=r41h7525677_1
+  - r-scales=1.2.1=r41hc72bb7e_1
+  - r-selectr=0.4_2=r41hc72bb7e_2
+  - r-stringi=1.7.6=r41h337692f_1
+  - r-stringr=1.4.0=r41hc72bb7e_2
+  - r-svglite=2.1.0=r41h7525677_1
+  - r-sys=3.4=r41h06615bd_1
+  - r-systemfonts=1.0.4=r41h0ff29ef_1
+  - r-testthat=3.1.5=r41h7525677_1
+  - r-tibble=3.1.8=r41h06615bd_1
+  - r-tidyr=1.2.1=r41h7525677_1
+  - r-tidyselect=1.1.2=r41hc72bb7e_1
+  - r-tidytree=0.4.1=r41hc72bb7e_0
+  - r-tinytex=0.42=r41hc72bb7e_1
+  - r-tzdb=0.3.0=r41h7525677_1
+  - r-utf8=1.2.2=r41h06615bd_1
+  - r-vctrs=0.5.2=r41h38f115c_0
+  - r-viridis=0.6.2=r41hc72bb7e_0
+  - r-viridislite=0.4.1=r41hc72bb7e_1
+  - r-vroom=1.6.0=r41h7525677_1
+  - r-waldo=0.4.0=r41hc72bb7e_1
+  - r-webshot=0.5.4=r41hc72bb7e_1
+  - r-withr=2.5.0=r41hc72bb7e_1
+  - r-xfun=0.33=r41h7525677_1
+  - r-xml2=1.3.3=r41h03ef668_0
+  - r-yaml=2.3.5=r41h06615bd_1
+  - r-yulab.utils=0.0.5=r41hc72bb7e_1
+  - readline=8.1=h46c0cb4_0
+  - sed=4.8=he412f7d_0
+  - sysroot_linux-64=2.12=he073ed8_15
+  - tk=8.6.12=h27826a3_0
+  - tktable=2.10=hb7b940f_3
+  - xorg-kbproto=1.0.7=h7f98852_1002
+  - xorg-libice=1.0.10=h7f98852_0
+  - xorg-libsm=1.2.3=hd9c2040_1000
+  - xorg-libx11=1.7.2=h7f98852_0
+  - xorg-libxau=1.0.9=h7f98852_0
+  - xorg-libxdmcp=1.1.3=h7f98852_0
+  - xorg-libxext=1.3.4=h7f98852_1
+  - xorg-libxrender=0.9.10=h7f98852_1003
+  - xorg-libxt=1.2.1=h7f98852_2
+  - xorg-renderproto=0.11.1=h7f98852_1002
+  - xorg-xextproto=7.3.0=h7f98852_1002
+  - xorg-xproto=7.0.31=h7f98852_1007
+  - xz=5.2.6=h166bdaf_0
+  - zlib=1.2.12=h166bdaf_4
+  - zstd=1.5.2=h6239696_4

bin/gen_report.R

@@ -3,7 +3,6 @@
 args <- commandArgs(trailingOnly = TRUE)
 workflow <- args[1]
 genome_size <- args[2]
-species_name <- args[3]
 
 # Generate rmarkdown report for the relevant track
 if (workflow == "draft") {
@@ -13,8 +12,7 @@ if (workflow == "draft") {
         quast_report = "transposed_report.tsv",
         kraken_report = "kraken_reports.txt",
         coverage_report = "coverage_reports.txt",
-        genome_size_val = genome_size,
-        species_name = species_name
+        genome_size_val = genome_size
       )
     )
 }

bin/generate_input.R

@@ -3,6 +3,8 @@
 args <- commandArgs(trailingOnly = TRUE)
 
 option <- args[1]
+r1 <- args[4]
+r2 <- args[5]
 
 if (option == "illumina") {
     path <- args[2]
@@ -19,8 +21,8 @@ if (option == "illumina") {
 
     filenames <- unique(sub(pattern, "", files))
     df <- data.frame(sample = filenames)
-    forward <- grep("_R1_", files_path, value = TRUE)
-    reverse <- grep("_R2_", files_path, value = TRUE)
+    forward <- grep(r1, files_path, value = TRUE)
+    reverse <- grep(r2, files_path, value = TRUE)
 
     df$R1 <- forward
     df$R2 <- reverse

bin/report_draft_assembly.Rmd

@@ -17,8 +17,6 @@ params:
     value: x
   genome_size_val:
     value: x
-  species_name:
-    value: x
 ---
 
 ```{r, message=FALSE, warning=FALSE}

conf/modules.config

@@ -91,7 +91,7 @@ process {
                 ]
         }
 
-	withName: 'UNICYCLER' {
+	withName: 'UNICYCLER|UNICYCLER_HYBRID' {
 		ext.args = {
 			[ params.unicycler_args ? "${params.unicycler_args}" : '',
 			"--verbosity 2",

modules/KRAKEN.nf

@@ -1,18 +1,18 @@
 process KRAKEN {
-	conda (params.enable_conda ? 'bioconda::kraken2=2.1.2' : null)
-	container 'quay.io/biocontainers/kraken2:2.1.2--pl5321h4ac6f70_4'
+	conda (params.enable_conda ? 'bioconda::kraken2=2.1.3' : null)
+	container 'quay.io/biocontainers/kraken2:2.1.3--pl5321hdcf5f25_1'
 
 	label 'process_high_memory'
 
         input:
-        tuple val(datasetID), path(R1), path(R2)
+        tuple val(datasetID), path(R1), path(R2), path(db)
 
         output:
         file("*")
 	path "*kr2.report", emit: report_ch
 
         script:
         """
-	kraken2 --db $params.kraken_db --paired $R1 $R2 --threads $task.cpus --output ${datasetID}.kr2.out --report ${datasetID}.kr2.report --use-names
+	kraken2 --db $db --paired $R1 $R2 --threads $task.cpus --output ${datasetID}.kr2.out --report ${datasetID}.kr2.report --use-names
         """
 }

modules/MERGE.nf

@@ -19,6 +19,8 @@ process MERGE_COV_REPORTS {
         conda (params.enable_conda ? './assets/r_env.yml' : null)
         container 'evezeyl/r_assemblage:latest'
 
+	label 'process_high_memory'
+
         input:
         path(reports)
 

modules/REPORT.nf

@@ -15,6 +15,6 @@ process REPORT_DRAFT {
         script:
         """
         cp $baseDir/bin/report_draft_assembly.Rmd .
-        Rscript $baseDir/bin/gen_report.R "draft" $params.genome_size $params.species_name
+        Rscript $baseDir/bin/gen_report.R "draft" $params.genome_size
         """
 }

workflows/DRAFT_ASSEMBLY.nf

@@ -17,13 +17,20 @@ workflow DRAFT_ASSEMBLY {
 	Channel
             .fromPath(params.input, checkIfExists: true)
             .splitCsv(header:true, sep:",")
-            .map { tuple(it.id, file(it.R1, checkIfExists: true), file(it.R2, checkIfExists: true)) }
+            .map { tuple(it.sample, file(it.R1, checkIfExists: true), file(it.R2, checkIfExists: true)) }
             .set { input_ch }
 
+	Channel
+	    .fromPath(params.kraken_db, checkIfExists: true)
+	    .set { db_ch }
+
+	input_ch.combine(db_ch)
+	    .set { kraken2_input_ch }
+
 	// QC
         FASTQC(input_ch)
         MULTIQC_PRE(FASTQC.out.fastqc_reports.collect())
-        KRAKEN(input_ch)
+        KRAKEN(kraken2_input_ch)
 	MERGE_KRAKEN_REPORTS(KRAKEN.out.report_ch.collect())
         TRIM(input_ch)
 	RASUSA(TRIM.out.trim_reads)