Merge pull request #260 from broadinstitute/ct-guess-instrument-model

guess instrument model in demux; pass to output
broadinstitute · May 1, 2021 · e1b71c2 · e1b71c2
2 parents c1d835f + 4916e8e
commit e1b71c2
Show file tree

Hide file tree

Showing 6 changed files with 33 additions and 14 deletions.
diff --git a/pipes/WDL/tasks/tasks_demux.wdl b/pipes/WDL/tasks/tasks_demux.wdl
@@ -292,6 +292,8 @@ task illumina_demux {
 
     illumina.py guess_barcodes --expected_assigned_fraction=0 barcodes.txt metrics.txt barcodes_outliers.txt
 
+    illumina.py flowcell_metadata --inDir $FLOWCELL_DIR flowcellMetadataFile.tsv
+
     mkdir -p unmatched
     mv Unmatched.bam unmatched/
 
@@ -352,6 +354,10 @@ task illumina_demux {
     Int         max_ram_gb               = ceil(read_float("MEM_BYTES")/1000000000)
     Int         runtime_sec              = ceil(read_float("UPTIME_SEC"))
     Int         cpu_load_15min           = ceil(read_float("LOAD_15M"))
+
+    String      instrument_model         = read_json("~{out_base}-runinfo.json")["sequencer_model"]
+    String      flowcell_lane_count      = read_json("~{out_base}-runinfo.json")["lane_count"]
+
     String      viralngs_version         = read_string("VERSION")
 
     Map[String,Map[String,String]] meta_by_sample        = read_json('meta_by_sample.json')

diff --git a/pipes/WDL/workflows/demux_deplete.wdl b/pipes/WDL/workflows/demux_deplete.wdl
@@ -20,7 +20,7 @@ workflow demux_deplete {
         File?        biosample_map
         Int          min_reads_per_bam = 100
 
-        String?      instrument_model
+        String?      instrument_model_user_specified
         String?      sra_title
 
         File         spikein_db
@@ -113,8 +113,9 @@ workflow demux_deplete {
                 library_metadata      = samplesheet_rename_ids.new_sheet,
                 platform              = "ILLUMINA",
                 paired                = (illumina_demux.run_info[0]['indexes'] == '2'),
+
                 out_name              = "sra_metadata-~{illumina_demux.run_info[0]['run_id']}.tsv",
-                instrument_model      = select_first([instrument_model]),
+                instrument_model      = select_first(flatten([[instrument_model_user_specified],[illumina_demux.run_info[0]['sequencer_model']]])),
                 title                 = select_first([sra_title])
         }
     }
@@ -161,6 +162,8 @@ workflow demux_deplete {
         File        multiqc_report_cleaned                   = multiqc_cleaned.multiqc_report
         File        spikein_counts                           = spike_summary.count_summary
         
+        String      instrument_model_inferred                = select_first(flatten([[instrument_model_user_specified],[illumina_demux.run_info[0]['sequencer_model']]]))
+
         String             run_date                          = illumina_demux.run_info[0]['run_start_date']
         Map[String,String] run_info                          = illumina_demux.run_info[0]
         File               run_info_json                     = illumina_demux.run_info_json[0]

diff --git a/pipes/WDL/workflows/demux_metag.wdl b/pipes/WDL/workflows/demux_metag.wdl
@@ -14,6 +14,7 @@ workflow demux_metag {
         Array[File]? bmtaggerDbs  # .tar.gz, .tgz, .tar.bz2, .tar.lz4, .fasta, or .fasta.gz
         Array[File]? blastDbs  # .tar.gz, .tgz, .tar.bz2, .tar.lz4, .fasta, or .fasta.gz
         Array[File]? bwaDbs
+        String?      instrument_model_user_specified
 
         File kraken2_db_tgz
         File krona_taxonomy_db_kraken2_tgz
@@ -111,10 +112,12 @@ workflow demux_metag {
         Array[Int]  read_counts_depleted            = deplete.depletion_read_count_post
         Array[Int]  read_counts_dedup               = rmdup_ubam.dedup_read_count_post
         Array[Int]  read_counts_prespades_subsample = spades.subsample_read_count
+
 
         File        demux_metrics                   = illumina_demux.metrics
         File        demux_commonBarcodes            = illumina_demux.commonBarcodes
         File        demux_outlierBarcodes           = illumina_demux.outlierBarcodes
+        String      instrument_model_inferred       = select_first(flatten([[instrument_model_user_specified],[illumina_demux.run_info['sequencer_model']]]))
 
         File        multiqc_report_raw              = multiqc_raw.multiqc_report
         File        multiqc_report_cleaned          = multiqc_cleaned.multiqc_report

diff --git a/pipes/WDL/workflows/demux_only.wdl b/pipes/WDL/workflows/demux_only.wdl
@@ -10,6 +10,10 @@ workflow demux_only {
         email:  "[email protected]"
     }
 
+    input {
+        String? instrument_model_user_specified
+    }
+
     call tasks_demux.illumina_demux
 
     call reports.MultiQC {
@@ -18,11 +22,12 @@ workflow demux_only {
     }
 
     output {
-        Array[File] raw_reads_unaligned_bams = illumina_demux.raw_reads_unaligned_bams
-        File        demux_metrics            = illumina_demux.metrics
-        File        demux_commonBarcodes     = illumina_demux.commonBarcodes
-        File        demux_outlierBarcodes    = illumina_demux.outlierBarcodes
-        File        multiqc_report_raw       = MultiQC.multiqc_report
-        String      demux_viral_core_version = illumina_demux.viralngs_version
+        Array[File] raw_reads_unaligned_bams  = illumina_demux.raw_reads_unaligned_bams
+        File        demux_metrics             = illumina_demux.metrics
+        File        demux_commonBarcodes      = illumina_demux.commonBarcodes
+        File        demux_outlierBarcodes     = illumina_demux.outlierBarcodes
+        File        multiqc_report_raw        = MultiQC.multiqc_report
+        String      instrument_model_inferred = select_first(flatten([[instrument_model_user_specified],[illumina_demux.run_info['sequencer_model']]]))
+        String      demux_viral_core_version  = illumina_demux.viralngs_version
     }
 }
diff --git a/pipes/WDL/workflows/demux_plus.wdl b/pipes/WDL/workflows/demux_plus.wdl
@@ -20,6 +20,7 @@ workflow demux_plus {
         Array[File]? bmtaggerDbs  # .tar.gz, .tgz, .tar.bz2, .tar.lz4, .fasta, or .fasta.gz
         Array[File]? blastDbs  # .tar.gz, .tgz, .tar.bz2, .tar.lz4, .fasta, or .fasta.gz
         Array[File]? bwaDbs
+        String?      instrument_model_user_specified
     }
 
     call demux.illumina_demux as illumina_demux
@@ -85,6 +86,7 @@ workflow demux_plus {
         File        demux_metrics                     = illumina_demux.metrics
         File        demux_commonBarcodes              = illumina_demux.commonBarcodes
         File        demux_outlierBarcodes             = illumina_demux.outlierBarcodes
+        String      instrument_model_inferred         = select_first(flatten([[instrument_model_user_specified],[illumina_demux.run_info['sequencer_model']]]))
 
         File        multiqc_report_raw                = multiqc_raw.multiqc_report
         File        multiqc_report_cleaned            = multiqc_cleaned.multiqc_report

diff --git a/pipes/WDL/workflows/sarscov2_illumina_full.wdl b/pipes/WDL/workflows/sarscov2_illumina_full.wdl
@@ -42,7 +42,7 @@ workflow sarscov2_illumina_full {
         String        amplicon_bed_prefix
 
         Array[File]   biosample_attributes
-        String        instrument_model
+        String?       instrument_model
         String        sra_title
 
         Int           min_genome_bases = 24000
@@ -77,10 +77,10 @@ workflow sarscov2_illumina_full {
     ### demux, deplete, SRA submission prep, fastqc/multiqc
     call demux_deplete.demux_deplete {
         input:
-            flowcell_tgz     = flowcell_tgz,
-            biosample_map    = biosample_merge.out_tsv,
-            instrument_model = instrument_model,
-            sra_title        = sra_title
+            flowcell_tgz                    = flowcell_tgz,
+            biosample_map                   = biosample_merge.out_tsv,
+            instrument_model_user_specified = instrument_model,
+            sra_title                       = sra_title
     }
     String  flowcell_id = demux_deplete.run_id
 
@@ -134,7 +134,7 @@ workflow sarscov2_illumina_full {
 
             File passing_assemblies     = rename_fasta_header.renamed_fasta
             String passing_assembly_ids = orig_name
-            Array[String] assembly_cmt  = [orig_name, "Broad viral-ngs v. " + demux_deplete.demux_viral_core_version, assemble_refbased.assembly_mean_coverage, instrument_model]
+            Array[String] assembly_cmt  = [orig_name, "Broad viral-ngs v. " + demux_deplete.demux_viral_core_version, assemble_refbased.assembly_mean_coverage, demux_deplete.instrument_model_inferred]
 
             # lineage assignment
             call sarscov2_lineages.sarscov2_lineages {