wrapping things up

assets/test.csv

@@ -0,0 +1,2 @@
+taxa,segment,assembly,length
+Influenza_A,HA,,1950

bin/assign-remainder.R

@@ -1,4 +1,8 @@
 #!/usr/bin/env Rscript
+version <- "1.0"
+
+# assign-remainder.R
+# Author: Jared Johnson, [email protected]
 
 library(tidyverse)
 
@@ -10,6 +14,12 @@ remainder_list_path <- args[3]
 taxa_name <- args[4]
 segment_name <- args[5]
 
+#---- VERSION ----#
+if(reps_path == "version"){
+  cat(version, sep = "\n")
+  quit(status=0)
+}
+
 # set output file name
 file.name <- paste(taxa_name,segment_name,"assigned",sep="-")
 

bin/assign-remainder.sh

@@ -31,4 +31,4 @@ mash sketch -p $threads -o reps -i reps.fa
 mash sketch -p $threads -o remainder -i ${remainder}
 
 mash dist -p $threads reps.msh remainder.msh | awk -v OFS=',' -v t=${threshold} '$3 < t {print $1,$2,$3}' > remainder-mash.csv
-cat ${remainder} | grep '>' | tr -d '>' > remainder-list.csv
+cat ${remainder} | grep '>' | tr -d '>' > remainder-list.csv

bin/summary.R

@@ -10,6 +10,7 @@ summary_file <- args[1]
 fastani_ava_file <- args[2]
 fastani_seeds_file <- args[3]
 seeds_file <- args[4]
+timestamp <- args[5]
 
 #---- VERSION ----#
 if(summary_file == "version"){
@@ -23,7 +24,7 @@ library(tidyverse)
 #---- FUNCTIONS ----#
 basename_fa <- function(path){
     result <- basename(path) %>%
-      str_remove_all(pattern = ".fa$")
+      str_remove_all(pattern = ".fa.gz$")
     return(result)
 
 }
@@ -98,6 +99,10 @@ fastani_ava <- fastani_ava %>%
   filter(query != ref) %>%
   group_by(query, taxa, segment) %>%
   summarise(min_ani = round(min(ani), digits = 1), max_ani = round(max(ani), digits = 1)) %>%
+  mutate(min_ani = case_when(min_ani < 80 ~ '< 80',
+                             TRUE ~ as.character(min_ani)),
+         max_ani = case_when(max_ani < 80 ~ '< 80',
+                             TRUE ~ as.character(max_ani))) %>%
   rename(seq = query) %>%
   ungroup() %>%
   select(-taxa, -segment)
@@ -107,7 +112,7 @@ fastani_ava <- fastani_ava %>%
 clusters %>%
   full_join(fastani_ava, by = "seq") %>%
   select(seq,taxa,segment,cluster,n,condensed,length,min_ani,max_ani) %>%
-  write.csv(file = paste0(format(Sys.Date(), "%s"),"-epitome.csv"), quote = F, row.names = F)
+  write.csv(file = paste0(timestamp,"-summary.csv"), quote = F, row.names = F)
 
 ## WITH SEEDS
 if(file.exists(fastani_seeds_file) & file.exists(seeds_file)){
@@ -129,5 +134,5 @@ if(file.exists(fastani_seeds_file) & file.exists(seeds_file)){
     full_join(clusters, by = "seq") %>%
     left_join(seeds, by = "ref") %>%
     select(seq,taxa,segment,cluster,n,length,min_ani,max_ani, seed, seed_ani) %>%
-    write.csv(file = paste0(format(Sys.Date(), "%s"),"-epitome.csv"), quote = F, row.names = F)
+    write.csv(file = paste0(timestamp,"-summary.csv"), quote = F, row.names = F)
 }

conf/base.config

@@ -37,15 +37,20 @@ process {
         time   = { check_max( 4.h   * task.attempt, 'time'    ) }
     }
     withLabel:process_medium {
-        cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
+        cpus   = { check_max( 4     * task.attempt, 'cpus'    ) }
         memory = { check_max( 8.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 8.h   * task.attempt, 'time'    ) }
     }
     withLabel:process_high {
-        cpus   = { check_max( 10    * task.attempt, 'cpus'    ) }
+        cpus   = { check_max( 8    * task.attempt, 'cpus'    ) }
         memory = { check_max( 16.GB * task.attempt, 'memory'  ) }
         time   = { check_max( 16.h  * task.attempt, 'time'    ) }
     }
+    withLabel:process_very_high {
+        cpus   = { check_max( 16    * task.attempt, 'cpus'    ) }
+        memory = { check_max( 32.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 16.h  * task.attempt, 'time'    ) }
+    }
     withLabel:process_long {
         time   = { check_max( 20.h  * task.attempt, 'time'    ) }
     }

conf/modules.config

@@ -17,8 +17,15 @@ process {
         mode: params.publish_dir_mode,
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
-
+    withName: TIMESTAMP {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
+        publishDir = [
+            path: { "${params.outdir}/" },
+            pattern: "none"
+        ]
+    }
     withName: INPUT_QC {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/qc" },
             pattern: "*.csv"
@@ -49,21 +56,25 @@ process {
         ]
     }
     withName: CLUSTER {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/clusters" }
         ]
     }
     withName: CLUSTER_LOOSEENDS {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/clusters" }
         ]
     }
     withName: ASSIGN_REMAINDER {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/clusters" }
         ]
     }  
     withName: BIND_CLUSTERS {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/clusters" }
         ]
@@ -87,12 +98,14 @@ process {
         ]
     }
     withName: CONSENSUS {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/consensus" },
             pattern: "none"
         ]
     }
     withName: CONDENSE {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/${taxa}/${segment}/consensus" },
             pattern: "*.fa"
@@ -113,10 +126,17 @@ process {
         ]
     }
     withName: SUMMARY {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
         publishDir = [
             path: { "${params.outdir}/summary" }
         ]
     }
+    withName: EXPORT {
+        container = 'docker.io/jdj0303/epitome-base:1.0'
+        publishDir = [
+            path: { "${params.outdir}/" }
+        ]
+    }
     withName: CUSTOM_DUMPSOFTWAREVERSIONS {
         publishDir = [
             path: { "${params.outdir}/pipeline_info" },

conf/test.config

@@ -20,10 +20,7 @@ params {
     max_time   = '6.h'
 
     // Input data
-    // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets
-    // TODO nf-core: Give any required params for the test so that command line flags are not needed
-    input  = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv'
-
-    // Genome references
-    genome = 'R64-1-1'
+    input  = ''
+    // 
+    max_cluster = 500
 }