WIP: process_cog_uk workflow now runs

Author: Rachel Colquhoun

environment.yml

@@ -20,6 +20,7 @@ dependencies:
   - r-base=3.5.1
   - r-networkd3
   - jclusterfunk
+  - benjamincjackson::gofasta=v0.0.3
   - pip:
       - git+https://github.com/COG-UK/phylo-reports.git
       - git+https://github.com/cov-lineages/pangolin.git

modules/align_and_variant_call_cog_uk.nf

@@ -17,7 +17,7 @@ process uk_minimap2_to_reference {
     cpus 1
 
     input:
-    file uk_fasta
+    path uk_fasta
 
     output:
     path "uk_alignment.sam"
@@ -39,7 +39,7 @@ process uk_get_variants {
     cpus 1
 
     input:
-    file uk_sam
+    path uk_sam
 
     output:
     path "uk.variants.csv"
@@ -64,7 +64,7 @@ process uk_get_indels {
     publishDir "${publish_dir}/metadata/", pattern: "*.csv", mode: 'copy'
 
     input:
-    file uk_sam
+    path uk_sam
 
     output:
     path "uk.insertions.csv", emit: uk_insertions
@@ -91,7 +91,7 @@ process uk_alignment {
     cpus 1
 
     input:
-    file uk_sam
+    path uk_sam
 
     output:
     path "uk_alignment.fasta"
@@ -115,7 +115,7 @@ process uk_mask_alignment {
     */
 
     input:
-    file uk_alignment
+    path uk_alignment
 
     output:
     path "${uk_alignment.baseName}.masked.fa"
@@ -139,7 +139,7 @@ process uk_get_snps {
     */
 
     input:
-    file uk_alignment
+    path uk_alignment
 
     output:
     path "uk.snps.csv"
@@ -159,8 +159,8 @@ process uk_type_AAs_and_dels {
     */
 
     input:
-    file uk_alignment
-    file uk_metadata
+    path uk_alignment
+    path uk_metadata
 
     output:
     path "${uk_metadata.baseName}.typed.csv"
@@ -189,8 +189,8 @@ process publish_full_aligned_cog_data {
 
 
     input:
-    file uk_alignment
-    file uk_metadata
+    path uk_alignment
+    path uk_metadata
 
     output:
     path "${uk_alignment.baseName}.matched.fa"

modules/deduplicate_cog_uk.nf

@@ -13,8 +13,8 @@ process uk_annotate_with_unmapped_genome_completeness {
     */
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_metadata.baseName}.annotated.csv"
@@ -54,8 +54,8 @@ process uk_remove_duplicates_COGID_by_proportionN {
     */
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_fasta.baseName}.deduplicated_by_cogid.fa", emit: uk_fasta_updated
@@ -120,8 +120,8 @@ process uk_remove_duplicates_biosamplesourceid_by_date {
     */
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_fasta.baseName}.deduplicated_by_biosamplesourceid.fa", emit: uk_fasta_updated
@@ -193,8 +193,8 @@ process uk_remove_duplicates_rootbiosample_by_gaps {
     publishDir "${params.publish_dir}/alignments/", pattern: "*.fa", mode: 'copy', saveAs: {"cog_${params.date}_all.fasta"}
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_fasta.baseName}.deduplicated_by_rootbiosample.fa", emit: uk_fasta_updated

modules/filter_and_trim_cog_uk.nf

@@ -15,8 +15,8 @@ process uk_filter_low_coverage_sequences {
     */
 
     input:
-    file uk_alignment
-    file uk_metadata
+    path uk_alignment
+    path uk_metadata
 
     output:
     path "${uk_alignment.baseName}.low_covg_filtered.fasta", emit: uk_fasta_updated
@@ -68,7 +68,7 @@ process uk_trim_alignment {
     */
 
     input:
-    file uk_alignment
+    path uk_alignment
 
     output:
     path "${uk_alignment.baseName}.trimmed.fa"
@@ -108,8 +108,8 @@ process publish_filtered_aligned_cog_data {
     publishDir "${publish_dir}/alignments/", pattern: "*.csv", mode: 'copy', saveAs: {"cog_${params.date}_metadata.fasta"}
 
     input:
-    file uk_alignment
-    file uk_metadata
+    path uk_alignment
+    path uk_metadata
 
     output:
     path "${uk_alignment.baseName}.matched.fa"

modules/pangolin_cog_uk.nf

@@ -16,8 +16,8 @@ process extract_sequences_for_pangolin {
     */
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_fasta.baseName}.for_pangolin.fasta", emit: pangolin_fasta
@@ -86,7 +86,7 @@ process uk_pangolin {
     */
 
     input:
-    file uk_fasta
+    path uk_fasta
 
     output:
     path "pangolin/lineage_report.csv"
@@ -107,8 +107,8 @@ process uk_add_new_pangolin_lineages_to_metadata {
     */
 
     input:
-    file uk_metadata
-    file pangolin_csv
+    path uk_metadata
+    path pangolin_csv
 
     output:
     path "${uk_metadata.baseName}.with_pangolin.csv"
@@ -155,7 +155,7 @@ workflow pangolin_cog_uk {
         uk_pangolin(extract_sequences_for_pangolin.out.pangolin_fasta)
         uk_add_new_pangolin_lineages_to_metadata(extract_sequences_for_pangolin.out.metadata_with_previous, uk_pangolin.out)
     emit:
-        uk_add_new_pangolin_lineages_to_metadata.out
+        metadata = uk_add_new_pangolin_lineages_to_metadata.out
 }
 
 

modules/preprocess_cog_uk.nf

@@ -13,10 +13,10 @@ process uk_strip_header_digits {
     */
 
     input:
-    file uk_fasta
+    path uk_fasta
 
     output:
-    file "${uk_fasta.baseName}.header_stripped.fasta"
+    path "${uk_fasta.baseName}.header_stripped.fasta"
 
     script:
     """
@@ -43,12 +43,12 @@ process uk_add_columns_to_metadata {
     */
 
     input:
-    file uk_metadata
-    file uk_accessions
-    file uk_updated_dates
+    path uk_metadata
+    path uk_accessions
+    path uk_updated_dates
 
     output:
-    file "${uk_metadata.baseName}.updated.csv"
+    path "${uk_metadata.baseName}.updated.csv"
 
     script:
     """
@@ -69,9 +69,9 @@ process uk_filter_omitted_sequences {
     * @params uk_omissions
     */
     input:
-    file uk_fasta
-    file uk_metadata
-    file uk_omissions
+    path uk_fasta
+    path uk_metadata
+    path uk_omissions
 
     output:
     path "${uk_fasta.baseName}.omit_filtered.fa", emit: fasta
@@ -125,8 +125,8 @@ process uk_filter_on_sample_date {
     */
 
     input:
-    file uk_fasta
-    file uk_metadata
+    path uk_fasta
+    path uk_metadata
 
     output:
     path "${uk_fasta.baseName}.date_filtered.fa", emit: fasta

workflows/process_cog_uk.nf

@@ -23,11 +23,11 @@ workflow process_cog_uk {
 }
 
 workflow {
-    uk_fasta = file(params.uk_fasta)
-    uk_metadata = file(params.uk_metadata)
-    uk_accessions = file(params.uk_accessions)
+    ch_uk_fasta = Channel.fromPath(params.uk_fasta)
+    ch_uk_metadata = Channel.fromPath(params.uk_metadata)
+    ch_uk_accessions = Channel.fromPath(params.uk_accessions)
 
-    process_cog_uk(uk_fasta,
-                   uk_metadata,
-                   uk_accessions)
+    process_cog_uk(ch_uk_fasta,
+                   ch_uk_metadata,
+                   ch_uk_accessions)
 }