Add per-sample search parameter support via samplesheet

.gitignore

@@ -7,3 +7,5 @@ testing/
 testing*
 *.pyc
 null/
+CLAUDE.md
+.claude/

.nf-core.yml

@@ -2,6 +2,7 @@ lint:
   files_unchanged:
     - .github/CONTRIBUTING.md
     - .vscode/settings.json
+  pipeline_if_empty_null: false
 nf_core_version: 3.5.1
 repository_type: pipeline
 template:

CHANGELOG.md

@@ -8,6 +8,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### `Added`
 
 - Added support for single run quantification [#438](https://github.com/nf-core/mhcquant/pull/438)
+- Added per-sample search parameter support via samplesheet with SearchPreset column and individual parameter overrides [#439](https://github.com/nf-core/mhcquant/pull/439)
 
 ### `Fixed`
 

assets/schema_input.json

@@ -13,14 +13,14 @@
                 "meta": ["id"]
             },
             "Sample": {
-                "type": "string",
-                "pattern": "^\\S+$",
+                "type": ["string", "integer"],
+                "anyOf": [{ "type": "string", "pattern": "^\\S+$" }, { "type": "integer" }],
                 "errorMessage": "Sample name must be provided and cannot contain spaces",
                 "meta": ["sample"]
             },
             "Condition": {
-                "type": "string",
-                "pattern": "^\\S+-?",
+                "type": ["string", "integer"],
+                "anyOf": [{ "type": "string", "pattern": "^\\S+-?" }, { "type": "integer" }],
                 "errorMessage": "Sample condition must be provided and cannot contain spaces",
                 "meta": ["condition"]
             },
@@ -37,6 +37,108 @@
                 "exists": true,
                 "pattern": "^\\S+\\.(fasta|fa|fas|fna|faa|ffn)$",
                 "errorMessage": "FASTA file cannot contain spaces and must have one of the extensions: fasta | fa | fas | fna | faa | ffn"
+            },
+            "SearchPreset": {
+                "type": "string",
+                "enum": [
+                    "lumos_class1",
+                    "lumos_class2",
+                    "qe_class1",
+                    "qe_class2",
+                    "timstof_class1",
+                    "timstof_class2",
+                    "xl_class1",
+                    "xl_class2"
+                ],
+                "errorMessage": "SearchPreset must be one of: lumos_class1, lumos_class2, qe_class1, qe_class2, timstof_class1, timstof_class2, xl_class1, xl_class2. Can be extended upon request.",
+                "meta": ["search_preset"]
+            },
+            "PeptideMinLength": {
+                "type": "integer",
+                "minimum": 1,
+                "errorMessage": "PeptideMinLength must be a positive integer",
+                "meta": ["peptide_min_length"]
+            },
+            "PeptideMaxLength": {
+                "type": "integer",
+                "minimum": 1,
+                "errorMessage": "PeptideMaxLength must be a positive integer",
+                "meta": ["peptide_max_length"]
+            },
+            "PrecursorMassRange": {
+                "type": "string",
+                "pattern": "^\\d+:\\d+$",
+                "errorMessage": "PrecursorMassRange must be in format 'min:max' (e.g., '800:2500')",
+                "meta": ["digest_mass_range"]
+            },
+            "PrecursorCharge": {
+                "type": "string",
+                "pattern": "^\\d+:\\d+$",
+                "errorMessage": "PrecursorCharge must be in format 'min:max' (e.g., '2:3')",
+                "meta": ["prec_charge"]
+            },
+            "PrecursorMassTolerance": {
+                "type": "integer",
+                "minimum": 0,
+                "errorMessage": "PrecursorMassTolerance must be a non-negative integer",
+                "meta": ["precursor_mass_tolerance"]
+            },
+            "FragmentMassTolerance": {
+                "type": "number",
+                "minimum": 0,
+                "errorMessage": "FragmentMassTolerance must be a non-negative number",
+                "meta": ["fragment_mass_tolerance"]
+            },
+            "FragmentBinOffset": {
+                "type": "number",
+                "minimum": 0,
+                "errorMessage": "FragmentBinOffset is recommended to be 0 for high res and 0.4 for low res devices.",
+                "meta": ["fragment_bin_offset"]
+            },
+            "MS2PIPModel": {
+                "type": "string",
+                "enum": [
+                    "Immuno-HCD",
+                    "timsTOF",
+                    "CIDch2",
+                    "HCD",
+                    "CID",
+                    "ITMS",
+                    "iTRAQ",
+                    "iTRAQphospho",
+                    "TMT",
+                    "HCDch2"
+                ],
+                "errorMessage": "MS2PIPModel must be a valid MS2PIP model name",
+                "meta": ["ms2pip_model"]
+            },
+            "ActivationMethod": {
+                "type": "string",
+                "enum": ["ALL", "CID", "HCD", "ETD", "ECD", "EThcD", "ETciD"],
+                "errorMessage": "ActivationMethod must be one of: ALL, CID, HCD, ETD, ECD, EThcD, ETciD",
+                "meta": ["activation_method"]
+            },
+            "Instrument": {
+                "type": "string",
+                "enum": ["high_res", "low_res"],
+                "errorMessage": "Instrument must be either 'high_res' or 'low_res'",
+                "meta": ["instrument"]
+            },
+            "NumberMods": {
+                "type": "integer",
+                "minimum": 0,
+                "errorMessage": "NumberMods must be a non-negative integer",
+                "meta": ["number_mods"]
+            },
+            "FixedMods": {
+                "type": "string",
+                "errorMessage": "FixedMods must be a comma-separated list of UNIMOD modification names",
+                "meta": ["fixed_mods"]
+            },
+            "VariableMods": {
+                "type": "string",
+                "errorMessage": "VariableMods must be a comma-separated list of UNIMOD modification names",
+                "meta": ["variable_mods"]
             }
         },
         "required": ["ID", "Sample", "Condition", "ReplicateFileName"]

conf/modules.config

@@ -94,20 +94,20 @@ process {
         ext.args    = { [
             (params.default_params_file_comet != " ") ? "-default_params_file ${params.default_params_file_comet}" : "",
             "-pin_out ${mzml.baseName}_pin.tsv",
-            "-instrument ${params.instrument}",
+            "-instrument ${meta.instrument}",
             "-spectrum_batch_size ${params.spectrum_batch_size}",
-            "-activation_method ${params.activation_method}",
-            "-precursor_mass_tolerance ${params.precursor_mass_tolerance}",
+            "-activation_method ${meta.activation_method}",
+            "-precursor_mass_tolerance ${meta.precursor_mass_tolerance}",
             "-precursor_error_units ${params.precursor_error_units}",
-            "-fragment_mass_tolerance ${params.fragment_mass_tolerance}",
-            "-fragment_bin_offset ${params.fragment_bin_offset}",
+            "-fragment_mass_tolerance ${meta.fragment_mass_tolerance}",
+            "-fragment_bin_offset ${meta.fragment_bin_offset}",
             "-num_hits ${params.num_hits}",
-            "-digest_mass_range ${params.digest_mass_range}",
-            "-max_variable_mods_in_peptide ${params.number_mods}",
+            "-digest_mass_range ${meta.digest_mass_range}",
+            "-max_variable_mods_in_peptide ${meta.number_mods}",
             "-missed_cleavages 0",
-            "-precursor_charge ${params.prec_charge}",
-            "-fixed_modifications ${params.fixed_mods.tokenize(',').collect {"'${it}'"}.join(" ")}",
-            "-variable_modifications ${params.variable_mods.tokenize(',').collect {"'${it}'"}.join(" ")}",
+            "-precursor_charge ${meta.prec_charge}",
+            meta.fixed_mods.trim() ? "-fixed_modifications '${meta.fixed_mods.trim()}'" : "",
+            meta.variable_mods.trim() ? "-variable_modifications '${meta.variable_mods.trim()}'" : "",
             "-enzyme '${params.enzyme}'",
             "-use_X_ions ${params.use_x_ions}",
             "-use_Z_ions ${params.use_z_ions}",
@@ -156,12 +156,12 @@ process {
 
     withName: 'OPENMS_IDFILTER_Q_VALUE' {
         ext.prefix  = {"${meta.id}_pout_filtered"}
-        ext.args    = [
+        ext.args    = { [
             "-remove_decoys",
-            "-precursor:length '${params.peptide_min_length}:${params.peptide_max_length}'",
+            "-precursor:length '${meta.peptide_min_length}:${meta.peptide_max_length}'",
             "-delete_unreferenced_peptide_hits",
             (params.fdr_threshold == '0.01') ? "-score:peptide 0.05" : "-score:peptide " + params.fdr_threshold
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir  = [
             path: {"${params.outdir}/intermediate_results/rescoring"},
             mode: params.publish_dir_mode,
@@ -172,12 +172,12 @@ process {
     withName: 'OPENMS_IDFILTER_Q_VALUE_GLOBAL' {
         label = 'process_high_memory'
         ext.prefix  = {"${meta.id}_pout_filtered"}
-        ext.args    = [
+        ext.args    = { [
             "-remove_decoys",
-            "-precursor:length '${params.peptide_min_length}:${params.peptide_max_length}'",
+            "-precursor:length '${meta.peptide_min_length}:${meta.peptide_max_length}'",
             "-delete_unreferenced_peptide_hits",
             (params.fdr_threshold == '0.01') ? "-score:peptide 0.05" : "-score:peptide " + params.fdr_threshold
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir  = [
             enabled: false
         ]
@@ -186,12 +186,12 @@ process {
     withName: 'OPENMS_IDFILTER_GLOBAL' {
         label = 'process_medium'
         ext.prefix  = {"${meta.id}_pout_filtered"}
-        ext.args    = [
+        ext.args    = { [
             "-remove_decoys",
-            "-precursor:length '${params.peptide_min_length}:${params.peptide_max_length}'",
+            "-precursor:length '${meta.peptide_min_length}:${meta.peptide_max_length}'",
             "-delete_unreferenced_peptide_hits",
             (params.fdr_threshold == '0.01') ? "-score:peptide 0.05" : "-score:peptide " + params.fdr_threshold
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir  = [
             path: {"${params.outdir}/intermediate_results/rescoring"},
             mode: params.publish_dir_mode,
@@ -348,23 +348,23 @@ process {
 
     withName: 'OPENMS_IDMASSACCURACY' {
         ext.prefix  = {"${meta.spectra}"}
-        ext.args    = [
+        ext.args    = { [
             (params.precursor_error_units == 'ppm') ? "-precursor_error_ppm": "",
-            "-fragment_mass_tolerance ${params.fragment_mass_tolerance}"
-        ].join(' ').trim()
+            "-fragment_mass_tolerance ${meta.fragment_mass_tolerance}"
+        ].join(' ').trim() }
         publishDir  = [
             enabled: false
         ]
     }
 
     withName: 'MS2RESCORE' {
-        ext.args   = [
-            "--ms2_tolerance ${2 * params.fragment_mass_tolerance}",
-            "--ms2pip_model ${params.ms2pip_model}",
+        ext.args   = { [
+            "--ms2_tolerance ${2 * (meta.fragment_mass_tolerance as double)}",
+            "--ms2pip_model ${meta.ms2pip_model}",
             "--ms2pip_model_dir ${params.ms2pip_model_dir}",
             "--rescoring_engine ${params.rescoring_engine}",
             params.feature_generators.trim() ? "--feature_generators ${params.feature_generators}" : ''
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir = [
             [path: "${params.outdir}/intermediate_results/rescoring",
                 mode: params.publish_dir_mode,
@@ -395,15 +395,16 @@ process {
 
     withName: 'OPENMS_PERCOLATORADAPTER_GLOBAL' {
         label = 'process_high_mem_high_cpu'
-        ext.args    = [
+        ext.args    = { [
             "-seed 4711",
             "-trainFDR 0.05",
             "-testFDR 0.05",
             "-enzyme no_enzyme",
             "-subset_max_train ${params.subset_max_train}",
             "-post_processing_tdc",
+            "-weights ${meta.id}_percolator_feature_weights.tsv",
             (params.fdr_level != 'psm_level_fdrs') ? "-" + params.fdr_level : ""
-        ].join(' ').trim()
+        ].join(' ').trim() }
         publishDir  = [
             enabled: false
         ]
@@ -526,11 +527,11 @@ process {
 
     if (params.annotate_ions) {
         withName: 'PYOPENMS_IONANNOTATOR' {
-            ext.args   = [
-                    "--precursor_charge ${params.prec_charge}",
-                    "--fragment_mass_tolerance ${params.fragment_mass_tolerance}",
+            ext.args   = { [
+                    "--precursor_charge ${meta.prec_charge}",
+                    "--fragment_mass_tolerance ${meta.fragment_mass_tolerance}",
                     "--remove_precursor_peak ${params.remove_precursor_peak}"
-                ].join(' ').trim()
+                ].join(' ').trim() }
                 publishDir  = [
                     path: {"${params.outdir}/intermediate_results/ion_annotations"},
                     mode: params.publish_dir_mode,