identified sticking point for sample names not being passed to the ir…

…idanext config

conf/irida_next.config

@@ -11,7 +11,7 @@ iridanext {
         overwrite = true
         validate = false
         files {
-            idkey = "sample"
+            idkey = "irida_id"
             global = [
                 "**/FinalReports/Aggregated/Json/final_report.json",
                 "**/FinalReports/Aggregated/Tables/final_report.tsv"

main.nf

@@ -112,6 +112,7 @@ workflow MIKROKONDO {
         ch_versions = ch_versions.mix(REPORT_AGGREGATE.out.versions)
 
 
+        // TODO need to add logic to merge this channel with a previous one to get its INX id
         updated_samples = REPORT_AGGREGATE.out.flat_samples.flatten().map{
                     sample ->
                         def name_trim = sample.getName()

modules/local/report.nf

@@ -47,6 +47,10 @@ process REPORT{
             sample_data[meta_data.sample]["meta"] = [:]
         }
 
+
+        // TODO add a condition around this to only be appened if iridanext is enabled
+        update_map_values(sample_data, meta_data, "irida_id")
+
         update_map_values(sample_data, meta_data, "metagenomic")
         update_map_values(sample_data, meta_data, "assembly")
         update_map_values(sample_data, meta_data, "hybrid")

nextflow.config

@@ -7,6 +7,7 @@
 */
 
 
+
 // Global default params, used in configs
 params {
     // Input options
@@ -43,7 +44,7 @@ params {
     show_hidden_params = false
     validationS3PathCheck = true
     validationShowHiddenParams = false
-    validationSchemaIgnoreParams = 'rasusa,locidex_summary,allele_scheme_selected,top_hit_method,abricate,locidex,assembly_status,bakta,bandage,checkm,chopper,contigs_too_short,coreutils,coverage_calc_fields,ectyper,fastp,fastqc,filtered_reads,flye,kat,kleborate,kraken,kraken_bin,kraken_species,lissero,mash,mash_meta,medaka,minimap2,mlst,mobsuite_recon,opt_platforms,pilon,pilon_iterative,pointfinder_db_tag,python3,QCReport,QCReport-fields,QCReportFields,quast,racon,raw_reads,report_aggregate,r_contaminants,samtools,seqkit,seqtk,seqtk_size,shigeifinder,sistr,spades,spatyper,staramr,subtyping_report,top_hit_species,unicycler'
+    validationSchemaIgnoreParams = '__in_iridanext,rasusa,locidex_summary,allele_scheme_selected,top_hit_method,abricate,locidex,assembly_status,bakta,bandage,checkm,chopper,contigs_too_short,coreutils,coverage_calc_fields,ectyper,fastp,fastqc,filtered_reads,flye,kat,kleborate,kraken,kraken_bin,kraken_species,lissero,mash,mash_meta,medaka,minimap2,mlst,mobsuite_recon,opt_platforms,pilon,pilon_iterative,pointfinder_db_tag,python3,QCReport,QCReport-fields,QCReportFields,quast,racon,raw_reads,report_aggregate,r_contaminants,samtools,seqkit,seqtk,seqtk_size,shigeifinder,sistr,spades,spatyper,staramr,subtyping_report,top_hit_species,unicycler'
     validationFailUnrecognisedParams = false // for the qcreport fields
 
     // SKIP options

tests/main.nf.test

@@ -100,6 +100,132 @@ nextflow_pipeline {
         }
     }
 
+        test("Should run without failure unzipped IRIDANext id") {
+        tag "succeed_assembly_inx_id"
+
+        when {
+            params {
+                input = "https://raw.githubusercontent.com/phac-nml/mikrokondo/refs/heads/dev/tests/data/samplesheets/samplesheet-small-assembly-inx.csv"
+                outdir = "results"
+                platform = "illumina"
+
+                mash_sketch = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy-staph-ecoli.msh"
+                mh_min_kmer = 1
+
+                dehosting_idx = "https://github.com/phac-nml/mikrokondo/raw/dev/tests/data/databases/campy.mmi"
+                kraken2_db = "$baseDir/tests/data/kraken2/test"
+
+                min_reads = 100
+                skip_allele_calling = true
+
+                QCReport {
+                    fallthrough {
+                        search = "No organism specific QC data available."
+                        raw_average_quality = 30
+                        min_n50 = null
+                        max_n50 = null
+                        min_nr_contigs = null
+                        max_nr_contigs = null
+                        fixed_genome_size = 1000
+                        min_length = null
+                        max_length = null
+                        max_checkm_contamination = 3.0
+                        min_average_coverage = 30
+                    }
+                }
+
+
+                skip_bakta = true
+                skip_staramr = false
+                skip_mobrecon = false
+                skip_checkm = false
+                skip_raw_read_metrics = false
+                skip_polishing = false
+
+                max_memory = "2.GB"
+                max_cpus = 1
+            }
+        }
+
+        then {
+
+            assert workflow.success
+            assert path("$launchDir/results").exists()
+
+            // parse output json file
+            def json = path("$launchDir/results/FinalReports/Aggregated/Json/final_report.json").json
+
+            assert json.short.short.RawReadSummary.R1."total_bp".equals(118750)
+            assert json.short.short.RawReadSummary.R1."total_reads".equals(475)
+            assert json.short.short.RawReadSummary.R1."read_qual_mean".equals(40.0)
+            assert json.short.short.RawReadSummary.R1."mean_sequence_length".equals(250.0)
+
+            assert json.short.short.FastP.summary.sequencing.equals("paired end (250 cycles + 250 cycles)")
+            assert json.short.short.FastP.summary.before_filtering.total_reads.equals(950)
+            assert json.short.short.FastP.filtering_result.passed_filter_reads.equals(950)
+            assert json.short.short.FastP.filtering_result.low_quality_reads.equals(0)
+            assert json.short.short.FastP.insert_size.peak.equals(347)
+
+            //assert json.short.meta.metagenomic.equals(false)  // Currently, this is "null".
+            assert json.short.meta.assembly.equals(false)
+            assert json.short.meta.hybrid.equals(false)
+            assert json.short.meta.single_end.equals(false)
+            assert json.short.meta.merge.equals(false)
+            assert json.short.meta.downsampled.equals(false)
+
+            assert json.short.short.AssemblyCompleted.equals(true)
+            assert json.short.short.QUAST."0"."Total length (>= 0 bp)".equals("4949")
+            assert json.short.short.QUAST."0"."Largest contig".equals("4949")
+            assert json.short.short.QUAST."0"."GC (%)".equals("52.96")
+            assert json.short.short.QUAST."0"."Avg. coverage depth".equals("47")
+
+            // Below two values should be empty
+            assert json.short.short.StarAMR."0"."Genotype".equals("None")
+            assert json.short.short.StarAMR."0"."Predicted Phenotype".equals("Susceptible")
+            assert json.short.short.StarAMR."0"."Genome Length".equals("4949")
+
+            assert json.short.short.CheckM."0"."# genomes".equals("5656")
+            assert json.short.short.CheckM."0"."# markers".equals("56")
+            assert json.short.short.CheckM."0"."# marker sets".equals("24")
+            assert json.short.short.CheckM."0".Contamination.equals("0.00")
+
+            assert json.short.short.SevenGeneMLSTReport[0].filename.equals("short.filtered.fasta.gz")
+
+            assert json.short.short.Abricate."0".RESISTANCE.equals("NoData")  // All Abricate results for this are "NoData".
+
+            def assembly_path = "$launchDir/results/Assembly/FinalAssembly/short/short.final.filtered.assembly.fasta.gz"
+            assert path(assembly_path).exists()
+
+            // parse assembly file
+            def assembly_header = path(assembly_path).linesGzip[0]
+            assert assembly_header.startsWith(">NODE_1_length_4949_cov_23.917254")  // _pilon_pilon_pilon gets appended
+
+            // compare IRIDA Next JSON output
+            def iridanext_json = path("$launchDir/results/iridanext.output.json").json
+            def iridanext_global = iridanext_json.files.global
+            def iridanext_samples = iridanext_json.files.samples
+            def iridanext_metadata = iridanext_json.metadata.samples
+
+            // output files
+            assert iridanext_global.findAll { it.path == "FinalReports/Aggregated/Json/final_report.json" }.size() == 1
+            assert iridanext_global.findAll { it.path == "FinalReports/Aggregated/Tables/final_report.tsv" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Assembly/FinalAssembly/short/short.final.filtered.assembly.fasta.gz" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Assembly/Quality/QUAST/short/short.transposed_short.quast.quality.tsv" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Assembly/Quality/SeqKitStats/short.seqkit.stats.summary.tsv" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Assembly/PostProcessing/Speciation/MashScreen/short.mash.screen.taxa.screen.screen" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Reads/Quality/Trimmed/MashScreen/short.mash.screen.reads.screen.screen" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Reads/Quality/Trimmed/FastP/short.fastp.summary.json" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "Reads/Quality/RawReadQuality/short.read.scan.summary.json" }.size() == 1
+            assert iridanext_samples.INX.findAll { it.path == "FinalReports/FlattenedReports/short.flat_sample.json.gz" }.size() == 1
+
+            // output metadata
+            assert iridanext_metadata.INX."QC Status" == "PASSED"
+
+        }
+
+    }
+
+
     test("Should run without failure.") {
         tag "succeed_assembly"