[ONT] Remove KMC

tasks/utilities/data_export/task_broad_terra_tools.wdl

@@ -76,9 +76,6 @@ task export_taxon_tables {
     Float? nanoplot_r1_mean_q_clean
     Float? nanoplot_r1_median_q_clean
     Float? nanoplot_r1_est_coverage_clean
-    String? kmc_est_genome_length
-    File? kmc_kmer_stats
-    String? kmc_version
     String? rasusa_version
     File? tiptoft_plasmid_replicon_fastq
     String? tiptoft_plasmid_replicon_genes
@@ -490,9 +487,6 @@ task export_taxon_tables {
       "nanoplot_r1_mean_q_clean": "~{nanoplot_r1_mean_q_clean}",
       "nanoplot_r1_median_q_clean": "~{nanoplot_r1_median_q_clean}",
       "nanoplot_r1_est_coverage_clean": "~{nanoplot_r1_est_coverage_clean}",
-      "kmc_est_genome_length": "~{kmc_est_genome_length}",
-      "kmc_kmer_stats": "~{kmc_kmer_stats}",
-      "kmc_version": "~{kmc_version}",
       "rasusa_version": "~{rasusa_version}",
       "tiptoft_plasmid_replicon_fastq": "~{tiptoft_plasmid_replicon_fastq}",
       "tiptoft_plasmid_replicon_genes": "~{tiptoft_plasmid_replicon_genes}",

tests/workflows/theiaprok/test_wf_theiaprok_illumina_pe.yml

@@ -631,7 +631,7 @@
     - path: miniwdl_run/wdl/tasks/taxon_id/contamination/task_midas.wdl
       md5sum: 64caaaff5910ac0036e2659434500962
     - path: miniwdl_run/wdl/tasks/utilities/data_export/task_broad_terra_tools.wdl
-      md5sum: 14565031f96d01ee6480bb0f9d19551d
+      md5sum: 4d69a6539b68503af9f3f1c2787ff920
     - path: miniwdl_run/wdl/workflows/theiaprok/wf_theiaprok_illumina_pe.wdl
       md5sum: 6d9dd969e2144ca23f2a0e101e6b6966
     - path: miniwdl_run/wdl/workflows/utilities/wf_merlin_magic.wdl

tests/workflows/theiaprok/test_wf_theiaprok_illumina_se.yml

@@ -594,7 +594,7 @@
     - path: miniwdl_run/wdl/tasks/taxon_id/contamination/task_midas.wdl
       md5sum: 64caaaff5910ac0036e2659434500962
     - path: miniwdl_run/wdl/tasks/utilities/data_export/task_broad_terra_tools.wdl
-      md5sum: 14565031f96d01ee6480bb0f9d19551d
+      md5sum: 4d69a6539b68503af9f3f1c2787ff920
     - path: miniwdl_run/wdl/workflows/theiaprok/wf_theiaprok_illumina_se.wdl
       md5sum: 5aa25e4fad466f92c96a7c138aca0d20
     - path: miniwdl_run/wdl/workflows/utilities/wf_merlin_magic.wdl

workflows/theiacov/wf_theiacov_ont.wdl

@@ -12,7 +12,6 @@ import "../../tasks/species_typing/betacoronavirus/task_pangolin.wdl" as pangoli
 import "../../tasks/species_typing/lentivirus/task_quasitools.wdl" as quasitools
 import "../../tasks/task_versioning.wdl" as versioning
 import "../../tasks/taxon_id/task_nextclade.wdl" as nextclade_task
-import "../../workflows/utilities/wf_influenza_antiviral_substitutions.wdl" as flu_antiviral
 import "../utilities/wf_flu_track.wdl" as run_flu_track
 import "../utilities/wf_organism_parameters.wdl" as set_organism_defaults
 import "../utilities/wf_read_QC_trim_ont.wdl" as read_qc_trim_workflow
@@ -28,7 +27,7 @@ workflow theiacov_ont {
     # sequencing values
     String seq_method = "OXFORD_NANOPORE"
     File? primer_bed
-    # assembly parameters
+    # assembly parameters - sars-cov-2 specific
     Int normalise = 200
     Int max_length = 700
     Int min_length = 400
@@ -97,7 +96,7 @@ workflow theiacov_ont {
       input:
         read1 = read1,
         samplename = samplename,
-        genome_length = genome_length,
+        genome_length = organism_parameters.genome_length,
         min_length = min_length,
         max_length = max_length,
         run_prefix = run_prefix,

workflows/theiaprok/wf_theiaprok_ont.wdl

@@ -273,9 +273,6 @@ workflow theiaprok_ont {
               nanoplot_r1_mean_q_clean = nanoplot_clean.mean_q,
               nanoplot_r1_median_q_clean = nanoplot_clean.median_q,
               nanoplot_r1_est_coverage_clean = nanoplot_clean.est_coverage,
-              kmc_est_genome_length = read_qc_trim.est_genome_length,
-              kmc_kmer_stats = read_qc_trim.kmc_kmer_stats,
-              kmc_version = read_qc_trim.kmc_version,
               rasusa_version = read_qc_trim.rasusa_version,
               tiptoft_plasmid_replicon_fastq = read_qc_trim.tiptoft_plasmid_replicon_fastq,
               tiptoft_plasmid_replicon_genes = read_qc_trim.tiptoft_plasmid_replicon_genes,
@@ -588,10 +585,6 @@ workflow theiaprok_ont {
     String? kraken2_report = read_qc_trim.kraken_report
     String? kraken2_database = read_qc_trim.kraken_database
     String? kraken_docker = read_qc_trim.kraken_docker
-    # Read QC - kmc outputs
-    Int? kmc_est_genome_length = read_qc_trim.est_genome_length
-    File? kmc_kmer_stats = read_qc_trim.kmc_kmer_stats
-    String? kmc_version = read_qc_trim.kmc_version
     # Read QC - rasusa outputs
     String? rasusa_version = read_qc_trim.rasusa_version
     # Read QC - tiptoft outputs

workflows/utilities/wf_read_QC_trim_ont.wdl

@@ -5,17 +5,20 @@ import "../../tasks/quality_control/read_filtering/task_artic_guppyplex.wdl" as
 import "../../tasks/quality_control/read_filtering/task_nanoq.wdl" as nanoq_task
 import "../../tasks/quality_control/read_filtering/task_ncbi_scrub.wdl" as ncbi_scrub
 import "../../tasks/taxon_id/contamination/task_kraken2.wdl" as kraken2
-import "../../tasks/utilities/task_kmc.wdl" as kmc_task
 import "../../tasks/utilities/task_rasusa.wdl" as rasusa_task
 
 workflow read_QC_trim_ont {
   meta {
-    description: "Runs basic QC on Oxford Nanopore (ONT) reads with (1) fastq_scan, (2) nanoplot, (3) kmc, (4) rasusa downsampling, (5) tiptoft plasmid detection, and (6) nanoq filtering"
+    description: "Runs basic QC on Oxford Nanopore (ONT) reads with (1) fastq_scan, (2) nanoplot, (3) rasusa downsampling, (4) tiptoft plasmid detection, and (5) nanoq filtering"
   }
   input {
     String samplename
     File read1
-    Int? genome_length
+
+    # kmc has been observed to be unreliable for genome length estimation, so we are now using a fixed value
+    # setting this to be 5Mb which is around .7Mb greater than the mean genome length of bacteria (based on https://github.com/CDCgov/phoenix/blob/717d19c19338373fc0f89eba30757fe5cfb3e18a/assets/databases/NCBI_Assembly_stats_20240124.txt)
+    # this default will not be used for TheiaCoV as that workflow series pass in the expected length based on the organism tag
+    Int genome_length = 5000000 
 
     String? workflow_series
 
@@ -96,22 +99,14 @@ workflow read_QC_trim_ont {
     } if ((call_kraken) && ! defined(kraken_db)) {
       String kraken_db_warning = "Kraken database not defined"
     }
-    # kmc for genome size estimation
-    call kmc_task.kmc {
-      input:
-        read1 = read1,
-        samplename = samplename
-    }
-
-    Int kmc_est_genome_length = if kmc.est_genome_length > 10000000 then 10000000 else kmc.est_genome_length
 
     # rasusa for random downsampling
     call rasusa_task.rasusa {
       input:
         read1 = read1,
         samplename = samplename,
         coverage = downsampling_coverage,
-        genome_length = select_first([genome_length, kmc_est_genome_length])
+        genome_length = genome_length
     }
     # tiptoft for plasmid detection
     call tiptoft_task.tiptoft {
@@ -145,12 +140,9 @@ workflow read_QC_trim_ont {
     File? kraken_report_dehosted = kraken2_recalculate_abundances_dehosted.kraken_report
     String kraken_database = select_first([kraken2_raw.database, kraken2_se.kraken2_database, kraken_db_warning, ""])
 
-    # theiaprok outputs
-    # kmc outputs
-    Int? est_genome_length = kmc_est_genome_length
-    File? kmc_kmer_stats = kmc.kmer_stats
-    String? kmc_version = kmc.kmc_version
-
+    # estimated genome length -- by default for TheiaProk this is 5Mb
+    Int est_genome_length = genome_length
+
     # nanoq outputs
     File read1_clean = select_first([nanoq.filtered_read1, read_filtering.read1_clean])
     String? nanoq_version = nanoq.version