added locidex merge

phac-nml · Mar 25, 2024 · bfc158b · bfc158b
1 parent 0a3df5a
commit bfc158b
Show file tree

Hide file tree

Showing 5 changed files with 83 additions and 75 deletions.
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -14,25 +14,12 @@
                 "unique": true,
                 "errorMessage": "Sample name must be provided and cannot contain spaces"
             },
-            "fastq_1": {
+            "profile": {
                 "type": "string",
-                "pattern": "^\\S+\\.f(ast)?q(\\.gz)?$",
-                "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have the extension: '.fq', '.fastq', '.fq.gz' or '.fastq.gz'"
-            },
-            "fastq_2": {
-                "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have the extension: '.fq', '.fastq', '.fq.gz' or '.fastq.gz'",
-                "anyOf": [
-                    {
-                        "type": "string",
-                        "pattern": "^\\S+\\.f(ast)?q(\\.gz)?$"
-                    },
-                    {
-                        "type": "string",
-                        "maxLength": 0
-                    }
-                ]
+                "pattern": "^\\S+\\.json(\\.gz)?$",
+                "errorMessage": "Json Profile"
             }
         },
-        "required": ["sample", "fastq_1"]
+        "required": ["sample", "profile"]
     }
 }
diff --git a/conf/modules.config b/conf/modules.config
@@ -16,6 +16,8 @@ process {
     assembly_directory_name = "assembly"
     summary_directory_name = "summary"
 
+    locidex_merge_directory_name = [params.outdir , "locidex", "merge"].join(File.separator)
+
     publishDir = [
         path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
         mode: params.publish_dir_mode,
@@ -54,6 +56,15 @@ process {
         ]
     }
 
+    withName: LOCIDEX_MERGE {
+        publishDir = [
+            path: locidex_merge_directory_name,
+            mode: params.publish_dir_mode,
+            pattern:  "*/*",
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: CUSTOM_DUMPSOFTWAREVERSIONS {
         publishDir = [
             path: { "${params.outdir}/pipeline_info" },

diff --git a/main.nf b/main.nf
@@ -17,29 +17,20 @@ nextflow.enable.dsl = 2
 
 include { validateParameters; paramsHelp; paramsSummaryLog; fromSamplesheet } from 'plugin/nf-validation'
 
-// Print help message if needed
-if (params.help) {
-    def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs)
-    def citation = '\n' + WorkflowMain.citation(workflow) + '\n'
-    def String command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker"
-    log.info logo + paramsHelp(command) + citation + NfcoreTemplate.dashedLine(params.monochrome_logs)
-    System.exit(0)
-}
-
 // Validate input parameters
 if (params.validate_params) {
     validateParameters()
 }
 
-WorkflowMain.initialise(workflow, params, log, args)
+
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     NAMED WORKFLOW FOR PIPELINE
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 */
 
-include { GAS_NOMENCLATURE } from './workflows/gasnomenclature'
+include { GAS_NOMENCLATURE } from './workflows/gas_nomenclature'
 
 //
 // WORKFLOW: Run main phac-nml/gasnomenclature analysis pipeline

diff --git a/modules/local/locidex/merge/main.nf b/modules/local/locidex/merge/main.nf
@@ -0,0 +1,28 @@
+// Merge missing loci
+
+process LOCIDEX_MERGE {
+    tag 'Merge Profiles'
+    label 'process_medium'
+
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+    'https://depot.galaxyproject.org/singularity/locidex:0.1.1--pyhdfd78af_0' :
+    'quay.io/biocontainers/locidex:0.1.1--pyhdfd78af_0' }"
+
+    input:
+    val input_values // [file(sample1), file(sample2), file(sample3), etc...]
+
+    output:
+    path("${combined_dir}/*.tsv"), emit: combined_profiles
+    path("${combined_dir}/*.json"), emit: report
+    path "versions.yml", emit: versions
+
+    script:
+    combined_dir = "merged"
+    """
+    locidex merge -i ${input_values.join(' ')} -o ${combined_dir}
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        locidex merge: \$(echo \$(locidex search -V 2>&1) | sed 's/^.*locidex //' )
+    END_VERSIONS
+    """
+}
diff --git a/workflows/gas_nomenclature.nf b/workflows/gas_nomenclature.nf
@@ -6,15 +6,6 @@
 
 include { paramsSummaryLog; paramsSummaryMap; fromSamplesheet  } from 'plugin/nf-validation'
 
-def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs)
-def citation = '\n' + WorkflowMain.citation(workflow) + '\n'
-def summary_params = paramsSummaryMap(workflow)
-
-// Print parameter summary log to screen
-log.info logo + paramsSummaryLog(workflow) + citation
-
-WorkflowIridanextexample.initialise(params, log)
-
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     CONFIG FILES
@@ -30,7 +21,7 @@ WorkflowIridanextexample.initialise(params, log)
 //
 // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules
 //
-include { INPUT_CHECK          } from '../subworkflows/local/input_check'
+
 include { GENERATE_SAMPLE_JSON } from '../modules/local/generatesamplejson/main'
 include { SIMPLIFY_IRIDA_JSON  } from '../modules/local/simplifyiridajson/main'
 include { IRIDA_NEXT_OUTPUT    } from '../modules/local/iridanextoutput/main'
@@ -47,6 +38,7 @@ include { GENERATE_SUMMARY     } from '../modules/local/generatesummary/main'
 // MODULE: Installed directly from nf-core/modules
 //
 include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main'
+include { LOCIDEX_MERGE } from "../modules/local/locidex/merge/main"
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -60,45 +52,44 @@ workflow GAS_NOMENCLATURE {
 
     // Create a new channel of metadata from a sample sheet
     // NB: `input` corresponds to `params.input` and associated sample sheet schema
-    input = Channel.fromSamplesheet("input")
-        // Map the inputs so that they conform to the nf-core-expected "reads" format.
-        // Either [meta, [fastq_1]] or [meta, [fastq_1, fastq_2]] if fastq_2 exists
-        .map { meta, fastq_1, fastq_2 ->
-                fastq_2 ? tuple(meta, [ file(fastq_1), file(fastq_2) ]) :
-                tuple(meta, [ file(fastq_1) ])}
-
-    ASSEMBLY_STUB (
-        input
-    )
-    ch_versions = ch_versions.mix(ASSEMBLY_STUB.out.versions)
+    input = Channel.fromSamplesheet("input").map { meta, profile -> tuple(meta, file(profile))};
+    profiles = input.map{
+        it -> it[1]
+    }.collect()
+    LOCIDEX_MERGE(profiles)
+
+    //ASSEMBLY_STUB (
+    //    input
+    //)
+    //ch_versions = ch_versions.mix(ASSEMBLY_STUB.out.versions)
 
     // A channel of tuples of ({meta}, [read[0], read[1]], assembly)
-    ch_tuple_read_assembly = input.join(ASSEMBLY_STUB.out.assembly)
-
-    GENERATE_SAMPLE_JSON (
-        ch_tuple_read_assembly
-    )
-    ch_versions = ch_versions.mix(GENERATE_SAMPLE_JSON.out.versions)
-
-    GENERATE_SUMMARY (
-        ch_tuple_read_assembly.collect{ [it] }
-    )
-    ch_versions = ch_versions.mix(GENERATE_SUMMARY.out.versions)
-
-    SIMPLIFY_IRIDA_JSON (
-        GENERATE_SAMPLE_JSON.out.json
-    )
-    ch_versions = ch_versions.mix(SIMPLIFY_IRIDA_JSON.out.versions)
-    ch_simplified_jsons = SIMPLIFY_IRIDA_JSON.out.simple_json.map { meta, data -> data }.collect() // Collect JSONs
-
-    IRIDA_NEXT_OUTPUT (
-        samples_data=ch_simplified_jsons
-    )
-    ch_versions = ch_versions.mix(IRIDA_NEXT_OUTPUT.out.versions)
-
-    CUSTOM_DUMPSOFTWAREVERSIONS (
-        ch_versions.unique().collectFile(name: 'collated_versions.yml')
-    )
+    //ch_tuple_read_assembly = input.join(ASSEMBLY_STUB.out.assembly)
+
+    //GENERATE_SAMPLE_JSON (
+    //    ch_tuple_read_assembly
+    //)
+    //ch_versions = ch_versions.mix(GENERATE_SAMPLE_JSON.out.versions)
+
+    //GENERATE_SUMMARY (
+    //    ch_tuple_read_assembly.collect{ [it] }
+    //)
+    //ch_versions = ch_versions.mix(GENERATE_SUMMARY.out.versions)
+
+    //SIMPLIFY_IRIDA_JSON (
+    //    GENERATE_SAMPLE_JSON.out.json
+    //)
+    //ch_versions = ch_versions.mix(SIMPLIFY_IRIDA_JSON.out.versions)
+    //ch_simplified_jsons = SIMPLIFY_IRIDA_JSON.out.simple_json.map { meta, data -> data }.collect() // Collect JSONs
+
+    //IRIDA_NEXT_OUTPUT (
+    //    samples_data=ch_simplified_jsons
+    //)
+    //ch_versions = ch_versions.mix(IRIDA_NEXT_OUTPUT.out.versions)
+
+    //CUSTOM_DUMPSOFTWAREVERSIONS (
+    //    ch_versions.unique().collectFile(name: 'collated_versions.yml')
+    //)
 }