Enable TBProfiler parameter changes (#246)

* updated VCF output file renaming in kSNP3 task (#207) * updated VCF output file renaming in kSNP3 task; also added 1 new File output and change the output names to be more descriptive * ksnp3 task:changed VCF file names to be predictable; split 2 ksnp3 options to 2 lines for readability; added new string output "ksnp3_vcf_ref_samplename" to capture sample within cluster to use for snp calling * added new string output to ksnp3 workflow "ksnp3_vcf_ref_samplename" * reduce unnecessary logging in MIDAS task (#210) * made untar/decompression of midas database quiet since it produces 41k lines of output. also made the 2 mv commands verbose (but it's only 2 lines!) * update CI * expose tbprofiler parameters as inputs in merlin * input spelling --------- Co-authored-by: Curtis Kapsak <[email protected]>
theiagen · Nov 13, 2023 · efafe25 · efafe25
1 parent c6fac1e
commit efafe25
Show file tree

Hide file tree

Showing 6 changed files with 36 additions and 12 deletions.
diff --git a/tasks/phylogenetic_inference/task_ksnp3.wdl b/tasks/phylogenetic_inference/task_ksnp3.wdl
@@ -53,7 +53,8 @@ task ksnp3 {
     -in ksnp3_input.tsv \
     -outdir ksnp3 \
     -k ~{kmer_size} \
-    -core -vcf \
+    -core \
+    -vcf \
     ~{'-SNPs_all ' + previous_ksnp3_snps} \
     ~{ksnp3_args}
 
@@ -71,7 +72,13 @@ task ksnp3 {
     echo "The core SNP matrix could not be produced" | tee SKIP_SNP_DIST # otherwise, skip
   fi
 
-  mv -v ksnp3/VCF.*.vcf ksnp3/~{cluster_name}_core.vcf
+  # capture sample name of genome used as reference
+  ls ksnp3/*.vcf | cut -d '.' -f 2 | tee KSNP3_VCF_REF_SAMPLENAME.txt
+
+  # rename the 2 vcf files by appending ~{cluster_name} and removing the ref genome name to make final filenames predictable
+  mv -v ksnp3/VCF.*.vcf ksnp3/~{cluster_name}_VCF.reference_genome.vcf
+  mv -v ksnp3/VCF.SNPsNotinRef.* ksnp3/~{cluster_name}_VCF_.SNPsNotinRef.tsv
+
   mv -v ksnp3/SNPs_all_matrix.fasta ksnp3/~{cluster_name}_pan_SNPs_matrix.fasta
   mv -v ksnp3/tree.parsimony.tre ksnp3/~{cluster_name}_pan_parsimony.nwk
 
@@ -84,9 +91,11 @@ task ksnp3 {
 
   >>>
   output {
-    File ksnp3_core_matrix = "ksnp3/${cluster_name}_core_SNPs_matrix.fasta"
-    File ksnp3_core_tree = "ksnp3/${cluster_name}_core.nwk"
-    File ksnp3_core_vcf = "ksnp3/${cluster_name}_core.vcf"
+    File ksnp3_core_matrix = "ksnp3/~{cluster_name}_core_SNPs_matrix.fasta"
+    File ksnp3_core_tree = "ksnp3/~{cluster_name}_core.nwk"
+    File ksnp3_vcf_ref_genome = "ksnp3/~{cluster_name}_VCF.reference_genome.vcf"
+    File ksnp3_vcf_snps_not_in_ref = "ksnp3/~{cluster_name}_VCF_.SNPsNotinRef.tsv"
+    String ksnp3_vcf_ref_samplename = read_string("KSNP3_VCF_REF_SAMPLENAME.txt")
     File ksnp3_pan_matrix = "ksnp3/~{cluster_name}_pan_SNPs_matrix.fasta"
     File ksnp3_pan_parsimony_tree = "ksnp3/~{cluster_name}_pan_parsimony.nwk"
     File? ksnp3_ml_tree = "ksnp3/~{cluster_name}_ML.nwk"

diff --git a/tasks/taxon_id/task_midas.wdl b/tasks/taxon_id/task_midas.wdl
@@ -16,14 +16,15 @@ task midas {
 
     # Decompress the Midas database
     mkdir db
-    tar -C ./db/ -xzvf ~{midas_db}  
+    echo "Decompressing Midas database. Please be patient, this may take a few minutes."
+    tar -C ./db/ -xzf ~{midas_db}  
 
     # Run Midas
     run_midas.py species ~{samplename} -1 ~{read1} ~{'-2 ' + read2} -d db/midas_db_v1.2/ -t ~{cpu} 
 
     # rename output files
-    mv ~{samplename}/species/species_profile.txt ~{samplename}/species/~{samplename}_species_profile.tsv
-    mv ~{samplename}/species/log.txt ~{samplename}/species/~{samplename}_log.txt
+    mv -v ~{samplename}/species/species_profile.txt ~{samplename}/species/~{samplename}_species_profile.tsv
+    mv -v ~{samplename}/species/log.txt ~{samplename}/species/~{samplename}_log.txt
 
     # Run a python block to parse output file for terra data tables
     # pandas is available in default docker image for python2 but not python3

diff --git a/tests/workflows/theiaprok/test_wf_theiaprok_illumina_pe.yml b/tests/workflows/theiaprok/test_wf_theiaprok_illumina_pe.yml
@@ -630,7 +630,7 @@
     - path: miniwdl_run/wdl/tasks/taxon_id/task_kraken2.wdl
       md5sum: a1f287e6e6feaf2d7d3c74a70e3b5a28
     - path: miniwdl_run/wdl/tasks/taxon_id/task_midas.wdl
-      md5sum: 024971d1439dff7d59c0a26a824bd2c6
+      md5sum: faacd87946ee3fbdf70f3a15b79ce547
     - path: miniwdl_run/wdl/tasks/utilities/task_broad_terra_tools.wdl
       md5sum: 43ef050bde1fb8755f38e697a1794918
     - path: miniwdl_run/wdl/workflows/theiaprok/wf_theiaprok_illumina_pe.wdl

diff --git a/tests/workflows/theiaprok/test_wf_theiaprok_illumina_se.yml b/tests/workflows/theiaprok/test_wf_theiaprok_illumina_se.yml
@@ -598,7 +598,7 @@
     - path: miniwdl_run/wdl/tasks/taxon_id/task_kraken2.wdl
       md5sum: a1f287e6e6feaf2d7d3c74a70e3b5a28
     - path: miniwdl_run/wdl/tasks/taxon_id/task_midas.wdl
-      md5sum: 024971d1439dff7d59c0a26a824bd2c6
+      md5sum: faacd87946ee3fbdf70f3a15b79ce547
     - path: miniwdl_run/wdl/tasks/utilities/task_broad_terra_tools.wdl
       md5sum: 43ef050bde1fb8755f38e697a1794918
     - path: miniwdl_run/wdl/workflows/theiaprok/wf_theiaprok_illumina_se.wdl

diff --git a/workflows/phylogenetics/wf_ksnp3.wdl b/workflows/phylogenetics/wf_ksnp3.wdl
@@ -67,7 +67,9 @@ workflow ksnp3_workflow {
     String ksnp3_docker = ksnp3_task.ksnp3_docker_image
     # ksnp3_outputs
     String ksnp3_snp_dists_version = pan_snp_dists.snp_dists_version
-    File ksnp3_core_vcf = ksnp3_task.ksnp3_core_vcf
+    File ksnp3_vcf_ref_genome = ksnp3_task.ksnp3_vcf_ref_genome
+    File ksnp3_vcf_snps_not_in_ref = ksnp3_task.ksnp3_vcf_snps_not_in_ref
+    String ksnp3_vcf_ref_samplename = ksnp3_task.ksnp3_vcf_ref_samplename
     String ksnp3_core_snp_matrix_status = ksnp3_task.skip_core_snp_dists
     File ksnp3_snps = ksnp3_task.ksnp3_snps_all
     # ordered matrixes and reordered trees

diff --git a/workflows/utilities/wf_merlin_magic.wdl b/workflows/utilities/wf_merlin_magic.wdl
@@ -62,6 +62,12 @@ workflow merlin_magic {
     Boolean call_shigeifinder_reads_input = false
     Boolean assembly_only = false
     Boolean theiaeuk = false
+    String? tbp_mapper
+    String? tbp_caller
+    Int? tbp_min_depth
+    Float? tbp_min_af
+    Float? tbp_min_af_pred
+    Int? tbp_cov_frac_threshold
     Boolean tbprofiler_run_custom_db = false
     File tbprofiler_custom_db = "gs://theiagen-public-files/terra/theiaprok-files/tbdb_varpipe_combined_nodups.tar.gz"
     Boolean tbprofiler_additional_outputs = false
@@ -252,7 +258,13 @@ workflow merlin_magic {
           samplename = samplename,
           tbprofiler_run_custom_db = tbprofiler_run_custom_db,
           tbprofiler_custom_db = tbprofiler_custom_db,
-          ont_data = ont_data
+          ont_data = ont_data,
+          mapper = tbp_mapper,
+          caller = tbp_caller,
+          min_depth = tbp_min_depth,
+          min_af = tbp_min_af,
+          min_af_pred = tbp_min_af_pred,
+          cov_frac_threshold = tbp_cov_frac_threshold
       }
       if (tbprofiler_additional_outputs) {
         call tbp_parser_task.tbp_parser {