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 +37,12 @@
                 "exists": true,
                 "pattern": "^\\S+\\.(fasta|fa|fas|fna|faa|ffn)$",
                 "errorMessage": "FASTA file cannot contain spaces and must have one of the extensions: fasta | fa | fas | fna | faa | ffn"
+            },
+            "SearchPreset": {
+                "type": "string",
+                "pattern": "^[a-zA-Z0-9_]+$",
+                "errorMessage": "SearchPreset must contain only alphanumeric characters and underscores",
+                "meta": ["search_preset"]
             }
         },
         "required": ["ID", "Sample", "Condition", "ReplicateFileName"]

assets/schema_search_presets.json

@@ -0,0 +1,125 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/mhcquant/master/assets/schema_search_presets.json",
+    "title": "nf-core/mhcquant pipeline - params.search_presets schema",
+    "description": "Schema for the search parameter presets file provided with params.search_presets",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "PresetName": {
+                "type": "string",
+                "pattern": "^[a-zA-Z0-9_]+$",
+                "errorMessage": "PresetName must contain only alphanumeric characters and underscores",
+                "meta": ["preset_name"]
+            },
+            "PeptideMinLength": {
+                "type": "integer",
+                "minimum": 1,
+                "errorMessage": "PeptideMinLength must be a positive integer",
+                "meta": ["peptide_min_length"]
+            },
+            "PeptideMaxLength": {
+                "type": "integer",
+                "minimum": 1,
+                "errorMessage": "PeptideMaxLength must be a positive integer",
+                "meta": ["peptide_max_length"]
+            },
+            "PrecursorMassRange": {
+                "type": "string",
+                "pattern": "^\\d+:\\d+$",
+                "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": "number",
+                "minimum": 0,
+                "errorMessage": "PrecursorMassTolerance must be a non-negative number",
+                "meta": ["precursor_mass_tolerance"]
+            },
+            "PrecursorErrorUnit": {
+                "type": "string",
+                "enum": ["ppm", "Da"],
+                "errorMessage": "PrecursorErrorUnit must be either 'ppm' or 'Da'",
+                "meta": ["precursor_error_units"]
+            },
+            "FragmentMassTolerance": {
+                "type": "number",
+                "minimum": 0,
+                "errorMessage": "FragmentMassTolerance must be a non-negative number",
+                "meta": ["fragment_mass_tolerance"]
+            },
+            "FragmentBinOffset": {
+                "type": "number",
+                "minimum": 0,
+                "errorMessage": "FragmentBinOffset must be a non-negative number",
+                "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": [
+            "PresetName",
+            "PeptideMinLength",
+            "PeptideMaxLength",
+            "PrecursorMassRange",
+            "PrecursorCharge",
+            "PrecursorMassTolerance",
+            "FragmentMassTolerance",
+            "FragmentBinOffset",
+            "MS2PIPModel",
+            "ActivationMethod",
+            "Instrument",
+            "NumberMods"
+        ]
+    }
+}

assets/search_presets.tsv

@@ -0,0 +1,11 @@
+PresetName	PeptideMinLength	PeptideMaxLength	PrecursorMassRange	PrecursorCharge	PrecursorMassTolerance	PrecursorErrorUnit	FragmentMassTolerance	FragmentBinOffset	MS2PIPModel	ActivationMethod	Instrument	NumberMods	FixedMods	VariableMods
+lumos_class1	8	14	800:2500	2:3	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	3	 	Oxidation (M)
+lumos_class2	8	30	800:5000	2:5	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	5	 	Oxidation (M)
+qe_class1	8	14	800:2500	2:3	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	3	 	Oxidation (M)
+qe_class2	8	30	800:5000	2:5	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	5	 	Oxidation (M)
+timstof_class1	8	14	800:2500	1:4	20	ppm	0.01	0.0	timsTOF	CID	high_res	3	 	Oxidation (M)
+timstof_class2	8	30	800:5000	1:5	20	ppm	0.01	0.0	timsTOF	CID	high_res	5	 	Oxidation (M)
+astral_class1	8	14	800:2500	2:3	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	3	 	Oxidation (M)
+astral_class2	8	30	800:5000	2:5	5	ppm	0.01	0.0	Immuno-HCD	HCD	high_res	5	 	Oxidation (M)
+xl_class1	8	14	800:2500	2:3	5	ppm	0.50025	0.4	CIDch2	CID	low_res	3	 	Oxidation (M)
+xl_class2	8	30	800:5000	2:5	5	ppm	0.50025	0.4	CIDch2	CID	low_res	5	 	Oxidation (M)

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}",
-            "-precursor_error_units ${params.precursor_error_units}",
-            "-fragment_mass_tolerance ${params.fragment_mass_tolerance}",
-            "-fragment_bin_offset ${params.fragment_bin_offset}",
+            "-activation_method ${meta.activation_method}",
+            "-precursor_mass_tolerance ${meta.precursor_mass_tolerance}",
+            "-precursor_error_units ${meta.precursor_error_units}",
+            "-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}",
+            "-fixed_modifications ${meta.fixed_mods.trim() ? meta.fixed_mods.tokenize(',').collect { "'${it.trim()}'" }.join(' ') : ''}",
+            meta.variable_mods.trim() ? "-variable_modifications ${meta.variable_mods.tokenize(',').collect { "'${it.trim()}'" }.join(' ')}" : "",
             "-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,

conf/test_search_presets.config

@@ -0,0 +1,29 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for running tests with search parameter presets
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Defines input files and everything required to run a test with different
+    search parameter presets specified per sample in the samplesheet.
+
+    Use as follows:
+        nextflow run main.nf -profile test_search_presets,<docker/singularity> --outdir <OUTDIR>
+
+----------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '6.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test search presets profile'
+    config_profile_description = 'Minimal test dataset with search parameter presets'
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/mhcquant/testdata/sample_sheet_presets.tsv'
+    fasta = params.pipelines_testdata_base_path + 'mhcquant/testdata/UP000005640_9606.fasta'
+}