add vsearch and script for plotting quality files

bin/plot_quality_profile.R

@@ -0,0 +1,31 @@
+#!/usr/bin/env Rscript
+suppressPackageStartupMessages(library(dada2))
+suppressPackageStartupMessages(library(tidyverse))
+suppressPackageStartupMessages(library(optparse))
+
+option_list = list(
+    make_option(c("-i","--id"),
+        type="character", 
+        help="ID of sample"),
+    make_option(c("-f", "--file_pattern"),
+        type="character",
+        default = "fastq.gz",
+        help="File pattern [default \"%default\"]"),
+    make_option(c("--session"),
+        action = "store_true", 
+        help="Generate nf-core compliant YAML file w/ version information",
+        ),
+    make_option(c("--yaml"),
+        default = "versions.yml", 
+        help="YAML file name (see --session)")
+)
+
+opt <- parse_args(OptionParser(option_list=option_list))
+
+fns <- list.files(pattern=opt$file_pattern, full.names=TRUE)
+
+pl <- plotQualityProfile(fns)
+ggsave(paste0(opt$id,".qualities.pdf"), plot=pl, device="pdf")
+
+# we may revisit the quality scores and other info in this plot for other purposes
+saveRDS(pl, paste0(opt$id,".qualities.RDS"))

modules/local/vsearch_eestats.nf

@@ -0,0 +1,67 @@
+// TODO: at the moment I'm checking on the feasibility of using 
+//       these for additional QC plots, esp on cum expected errors;
+//       at the moment they are a bit of a data dump
+
+process VSEARCH_EESTATS {
+    tag "$meta.id"
+    label 'process_low'
+
+    container "quay.io/biocontainers/vsearch:2.27.0--h6a68c12_1"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    path("${meta.id}.{R1,R2}.stats"), emit: stats
+    path("${meta.id}.{R1,R2}.eestats"), emit: eestats
+    path("${meta.id}.{R1,R2}.eestats2"), emit: eestats2
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if (meta.single_end) {
+        """
+        vsearch --fastq_stats ${reads[0]} \
+            --log ${meta.id}.R1.stats
+
+        vsearch --fastq_eestats ${reads[0]} \
+            --output ${meta.id}.R1.eestats
+
+        vsearch --fastq_eestats2 ${reads[0]} \
+            --ee_cutoffs "0.5,1.0,2.0,4.0,8.0" \
+            --output ${meta.id}.R1.eestats2
+        """
+    } else {
+        """
+        vsearch --fastq_stats ${reads[0]} \
+            --log ${meta.id}.R1.stats
+
+        vsearch --fastq_stats ${reads[1]} \
+            --log ${meta.id}.R2.stats            
+
+        vsearch --fastq_eestats ${reads[0]} \
+            --output ${meta.id}.R1.eestats
+
+        vsearch --fastq_eestats ${reads[1]} \
+            --output ${meta.id}.R2.eestats
+
+        vsearch --fastq_eestats2 ${reads[0]}  \
+            --ee_cutoffs "0.5,1.0,2.0,4.0,8.0" \
+            --output ${meta.id}.R1.eestats2
+
+        vsearch --fastq_eestats2 ${reads[1]} \
+            --ee_cutoffs "0.5,1.0,2.0,4.0,8.0" \
+            --output ${meta.id}.R2.eestats2
+        """
+    }
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.PDF
+    """
+}

workflows/tada.nf

@@ -6,18 +6,17 @@
 
 include { FASTQC                 } from '../modules/nf-core/fastqc/main'
 include { MULTIQC                } from '../modules/nf-core/multiqc/main'
-include { PLOTQUALITYPROFILE     } from '../modules/local/plotqualityprofile'
+include { PLOT_QUALITY_PROFILE   } from '../modules/local/plotqualityprofile'
+include { VSEARCH_EESTATS        } from '../modules/local/vsearch_eestats'
 
 include { FILTER_AND_TRIM        } from '../subworkflows/local/filter_and_trim'
 include { DADA2_DENOISE          } from '../subworkflows/local/dada2_denoise'
 
-// // TODO: move to a subworkflow and implement pooled vs per-sample + optional priors
-// include { LEARNERRORS            } from '../modules/local/learnerrors'
-// include { DADAINFER              } from '../modules/local/dadainfer'
-// include { POOLEDSEQTABLE         } from '../modules/local/pooledseqtable'
-// include { REMOVECHIMERAS         } from '../modules/local/removechimeras'
-// include { RENAMEASVS             } from '../modules/local/renameasvs'
-include { ASSIGNTAXASPECIES      } from '../modules/local/assigntaxaspecies'
+// TODO: may want to move into a subworkflow since we will likely implement a 
+//       few additional methods (q2-feature-classifier, IDTAXA, etc)
+include { ASSIGN_TAXA_SPECIES    } from '../modules/local/assigntaxaspecies'
+
+// TODO: Move into phylogenetic subworkflow
 include { DECIPHER               } from '../modules/local/decipher'
 include { PHANGORN               } from '../modules/local/phangorn'
 include { FASTTREE               } from '../modules/local/fasttree'
@@ -109,7 +108,11 @@ workflow TADA {
 
     // TODO: we may want to allow aggregation of the read files for larger projects;
     // current version is per read per sample
-    PLOTQUALITYPROFILE (
+    PLOT_QUALITY_PROFILE (
+        ch_samplesheet
+    )
+
+    VSEARCH_EESTATS (
         ch_samplesheet
     )
 
@@ -164,7 +167,6 @@ workflow TADA {
     )
 
     ch_tree = Channel.empty()
-    ch_tool = Channel.empty()
 
     // this seems like the sort of thing a function map 
     // would be useful for...
@@ -188,7 +190,6 @@ workflow TADA {
     )
 
     // QC
-
     READ_TRACKING(
         FILTER_AND_TRIM.out.trimmed_report,
         DADA2_DENOISE.out.seqtable_renamed,