Merge pull request #15 from phac-nml/modify-parameters-iridanext-UI

Modify input parameters to integrate with IRIDA-Next UI
phac-nml · Jul 25, 2024 · 32adf64 · 32adf64
2 parents fcf87f2 + 23278eb
commit 32adf64
Show file tree

Hide file tree

Showing 8 changed files with 356 additions and 511 deletions.
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -15,6 +15,7 @@
             },
             "contigs": {
                 "type": "string",
+                "format": "file-path",
                 "pattern": "^\\S+\\.f(ast|n)?a\\.gz$",
                 "errorMessage": "FASTA file containing assembled contigs, cannot contain spaces and must have extension '.fa.gz' or '.fasta.gz'"
             },

diff --git a/conf/igenomes.config b/conf/igenomes.config
diff --git a/conf/modules.config b/conf/modules.config
@@ -44,12 +44,25 @@ process {
                                     'enterococcus_faecium', 'escherichia_coli', 'helicobacter_pylori']
 
         // Convert the species name to a Pointfinder database-style name:
-        def convert = {String species_name -> species_name.trim().toLowerCase().replaceAll(" ", "_")}
+        def species_code = "[sS]almonella|[cC]amplyobacter|[eE]nterococcus.faecalis|[eE]nterococcus.faecium|[eE]scherichia.coli|[hH]elicobacter.pylori"
+        def convert = {String species_name -> species_name.trim().toLowerCase().replaceAll(" ", "_").find(species_code)}
 
         // Create the command line arguments:
         def point_db_arg = {String database -> " --pointfinder-organism ${database} " }
         def plasmid_db_arg = {String database -> " --plasmidfinder-database-type ${database} " }
         def mlst_arg = {String scheme -> " --mlst-scheme ${scheme} " }
+        def minimum_contig_length_arg = {String min_length -> " --minimum-contig-length ${min_length} "}
+        def genome_size_lower_bound_arg = {String min_genome -> " --genome-size-lower-bound ${min_genome} "}
+        def genome_size_upper_bound_arg = {String max_genome -> " --genome-size-upper-bound ${max_genome} "}
+        def minimum_N50_value_arg = {String min_n50 -> " --minimum-N50-value ${min_n50} "}
+        def unacceptable_number_contigs_arg = {String min_length -> " --unacceptable-number-contigs ${min_length} "}
+        def pid_threshold_arg = {String min_pid -> " --pid-threshold ${min_pid} "}
+        def percent_length_overlap_plasmidfinder_arg = {String min_overlap -> " --percent-length-overlap-plasmidfinder ${min_overlap} "}
+        def percent_length_overlap_resfinder_arg = {String min_overlap -> " --percent-length-overlap-resfinder ${min_overlap} "}
+        def percent_length_overlap_pointfinder_arg = {String min_overlap -> " --percent-length-overlap-pointfinder ${min_overlap} "}
+        def no_exclude_genes_arg = " --no-exclude-genes"
+        def exclude_negatives_arg = " --exclude-negatives"
+        def exclude_resistance_phenotypes_arg = " --exclude-resistance-phenotypes"
 
         // Check to see if the database name is valid:
         def valid_point_db = {String database -> pointfinder_databases.contains(database)}
@@ -58,8 +71,8 @@ process {
         ext.args = {
             [
                 // Pointfinder database:
-                params.pointfinder_database && valid_point_db(params.pointfinder_database) ?
-                    point_db_arg(params.pointfinder_database) :
+                params.pointfinder_database && valid_point_db(convert(params.pointfinder_database)) ?
+                    point_db_arg(convert(params.pointfinder_database)) :
                         meta.species && valid_point_db(convert(meta.species)) ?
                             point_db_arg(convert(meta.species)) : "",
 
@@ -68,8 +81,48 @@ process {
                     ? plasmid_db_arg(params.plasmidfinder_database) : "",
 
                 // MLST scheme:
-                params.mlst_scheme
-                    ? mlst_arg(params.mlst_scheme) : ""
+                params.mlst_scheme && (params.mlst_scheme != "Automatic")
+                    ? mlst_arg(params.mlst_scheme) : "",
+
+                // Additional parameters
+                params.minimum_contig_length
+                    ? minimum_contig_length_arg(params.minimum_contig_length.toString()) : "",
+
+                params.genome_size_lower_bound
+                    ? genome_size_lower_bound_arg(params.genome_size_lower_bound.toString()) : "",
+
+                params.genome_size_upper_bound
+                    ? genome_size_upper_bound_arg(params.genome_size_upper_bound.toString()) : "",
+
+                params.minimum_N50_value
+                    ? minimum_N50_value_arg(params.minimum_N50_value.toString()) : "",
+
+                params.minimum_contig_length
+                    ? minimum_contig_length_arg(params.minimum_contig_length.toString()) : "",
+
+                params.unacceptable_number_contigs
+                    ? unacceptable_number_contigs_arg(params.unacceptable_number_contigs.toString()) : "",
+
+                params.pid_threshold
+                    ? pid_threshold_arg(params.pid_threshold.toString()) : "",
+
+                params.percent_length_overlap_plasmidfinder
+                    ? percent_length_overlap_plasmidfinder_arg(params.percent_length_overlap_plasmidfinder.toString()) : "",
+
+                params.percent_length_overlap_resfinder
+                    ? percent_length_overlap_resfinder_arg(params.percent_length_overlap_resfinder.toString()) : "",
+
+                params.percent_length_overlap_pointfinder
+                    ? percent_length_overlap_pointfinder_arg(params.percent_length_overlap_pointfinder.toString()) : "",
+
+                params.no_exclude_genes
+                    ? no_exclude_genes_arg : "",
+
+                params.exclude_negatives
+                    ? exclude_negatives_arg : "",
+
+                params.exclude_resistance_phenotypes
+                    ? exclude_resistance_phenotypes_arg : ""
             ].join(" ")
         }
     }

diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy
@@ -49,15 +49,5 @@ class WorkflowMain {
             Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'")
         }
     }
-    //
-    // Get attribute from genome config file e.g. fasta
-    //
-    public static Object getGenomeAttribute(params, attribute) {
-        if (params.genomes && params.genome && params.genomes.containsKey(params.genome)) {
-            if (params.genomes[ params.genome ].containsKey(attribute)) {
-                return params.genomes[ params.genome ][ attribute ]
-            }
-        }
-        return null
-    }
+
 }
diff --git a/lib/WorkflowStaramr.groovy b/lib/WorkflowStaramr.groovy
@@ -12,7 +12,6 @@ class WorkflowStaramr {
     //
     public static void initialise(params, log) {
 
-        genomeExistsError(params, log)
     }
 
     public static String toolCitationText(params) {
@@ -65,17 +64,5 @@ class WorkflowStaramr {
         return description_html
     }
 
-    //
-    // Exit pipeline if incorrect --genome key provided
-    //
-    private static void genomeExistsError(params, log) {
-        if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) {
-            def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" +
-                "  Genome '${params.genome}' not found in any config files provided to the pipeline.\n" +
-                "  Currently, the available genome keys are:\n" +
-                "  ${params.genomes.keySet().join(", ")}\n" +
-                "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~"
-            Nextflow.error(error_string)
-        }
-    }
+
 }
diff --git a/nextflow.config b/nextflow.config
@@ -12,10 +12,6 @@ params {
     // TODO nf-core: Specify your pipeline's command line flags
     // Input options
     input                      = null
-    // References
-    genome                     = null
-    igenomes_base              = 's3://ngi-igenomes/igenomes'
-    igenomes_ignore            = false
 
     // Boilerplate options
     outdir                     = null
@@ -50,10 +46,26 @@ params {
     validationShowHiddenParams       = false
     validate_params                  = true
 
-    //StarAMR options
-    pointfinder_database             = null
-    plasmidfinder_database           = null
-    mlst_scheme                      = null
+    // StarAMR options
+
+    // Databases
+    pointfinder_database             = "Automatic Selection"
+    plasmidfinder_database           = "All"
+    mlst_scheme                      = "Automatic"
+
+    // Additional CLI arguments
+    genome_size_lower_bound              = 4000000
+    genome_size_upper_bound              = 6000000
+    minimum_N50_value                    = 10000
+    minimum_contig_length                = 300
+    unacceptable_number_contigs          = 1000
+    pid_threshold                        = 98
+    percent_length_overlap_plasmidfinder = 60
+    percent_length_overlap_resfinder     = 60
+    percent_length_overlap_pointfinder   = 95
+    no_exclude_genes                     = false
+    exclude_negatives                    = false
+    exclude_resistance_phenotypes        = false
 
 }
 
@@ -183,12 +195,6 @@ plugins {
 }
 
 
-// Load igenomes.config if required
-if (!params.igenomes_ignore) {
-    includeConfig 'conf/igenomes.config'
-} else {
-    params.genomes = [:]
-}
 // Export these variables to prevent local Python/R libraries from conflicting with those in the container
 // The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container.
 // See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable.