Refactor: extract calibration params to meta

.gitignore

@@ -17,4 +17,4 @@ null/
 .cursor/rules/codacy.mdc
 .codacy/
 .github/instructions/codacy.instructions.md
-docs/superpowers/
+docs/superpowers/

docs/usage.md

@@ -95,49 +95,50 @@ The pipeline passes parameters to DIA-NN at different steps. Some parameters com
 ### Parameter sources
 
 Parameters are resolved in this priority order:
+
 1. **SDRF metadata** (per-file, from `convert-diann` design file) — highest priority
 2. **Pipeline parameters** (`--param_name` on command line or params file)
 3. **Nextflow defaults** (`nextflow.config`) — lowest priority
 
 ### Pipeline steps
 
-| Step | Description |
-|------|-------------|
+| Step                            | Description                                                         |
+| ------------------------------- | ------------------------------------------------------------------- |
 | **INSILICO_LIBRARY_GENERATION** | Predicts a spectral library from FASTA using DIA-NN's deep learning |
-| **PRELIMINARY_ANALYSIS** | Per-file calibration and mass accuracy estimation (first pass) |
-| **ASSEMBLE_EMPIRICAL_LIBRARY** | Builds consensus empirical library from preliminary results |
-| **INDIVIDUAL_ANALYSIS** | Per-file quantification with the empirical library (second pass) |
-| **FINAL_QUANTIFICATION** | Aggregates all files into protein/peptide matrices |
+| **PRELIMINARY_ANALYSIS**        | Per-file calibration and mass accuracy estimation (first pass)      |
+| **ASSEMBLE_EMPIRICAL_LIBRARY**  | Builds consensus empirical library from preliminary results         |
+| **INDIVIDUAL_ANALYSIS**         | Per-file quantification with the empirical library (second pass)    |
+| **FINAL_QUANTIFICATION**        | Aggregates all files into protein/peptide matrices                  |
 
 ### Per-file parameters from SDRF
 
 These parameters are extracted per-file from the SDRF via `convert-diann` and stored in `diann_design.tsv`:
 
-| DIA-NN flag | SDRF column | Design column | Steps | Notes |
-|---|---|---|---|---|
-| `--mass-acc-ms1` | `comment[precursor mass tolerance]` | `PrecursorMassTolerance` | PRELIMINARY, INDIVIDUAL | Falls back to auto-detect if missing or not ppm |
-| `--mass-acc` | `comment[fragment mass tolerance]` | `FragmentMassTolerance` | PRELIMINARY, INDIVIDUAL | Falls back to auto-detect if missing or not ppm |
-| `--min-pr-mz` | `comment[ms1 scan range]` or `comment[ms min mz]` | `MS1MinMz` | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO |
-| `--max-pr-mz` | `comment[ms1 scan range]` or `comment[ms max mz]` | `MS1MaxMz` | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO |
-| `--min-fr-mz` | `comment[ms2 scan range]` or `comment[ms2 min mz]` | `MS2MinMz` | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO |
-| `--max-fr-mz` | `comment[ms2 scan range]` or `comment[ms2 max mz]` | `MS2MaxMz` | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO |
+| DIA-NN flag      | SDRF column                                        | Design column            | Steps                   | Notes                                           |
+| ---------------- | -------------------------------------------------- | ------------------------ | ----------------------- | ----------------------------------------------- |
+| `--mass-acc-ms1` | `comment[precursor mass tolerance]`                | `PrecursorMassTolerance` | PRELIMINARY, INDIVIDUAL | Falls back to auto-detect if missing or not ppm |
+| `--mass-acc`     | `comment[fragment mass tolerance]`                 | `FragmentMassTolerance`  | PRELIMINARY, INDIVIDUAL | Falls back to auto-detect if missing or not ppm |
+| `--min-pr-mz`    | `comment[ms1 scan range]` or `comment[ms min mz]`  | `MS1MinMz`               | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO  |
+| `--max-pr-mz`    | `comment[ms1 scan range]` or `comment[ms max mz]`  | `MS1MaxMz`               | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO  |
+| `--min-fr-mz`    | `comment[ms2 scan range]` or `comment[ms2 min mz]` | `MS2MinMz`               | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO  |
+| `--max-fr-mz`    | `comment[ms2 scan range]` or `comment[ms2 max mz]` | `MS2MaxMz`               | PRELIMINARY, INDIVIDUAL | Per-file for GPF; global broadest for INSILICO  |
 
 ### Global parameters from config
 
 These parameters apply globally across all files. They are set in `diann_config.cfg` (from SDRF) or as pipeline parameters:
 
-| DIA-NN flag | Pipeline parameter | Default | Steps | Notes |
-|---|---|---|---|---|
-| `--cut` | (from SDRF enzyme) | — | ALL | Enzyme cut rule, derived from `comment[cleavage agent details]` |
-| `--fixed-mod` | (from SDRF) | — | ALL | Fixed modifications from `comment[modification parameters]` |
-| `--var-mod` | (from SDRF) | — | ALL | Variable modifications from `comment[modification parameters]` |
-| `--monitor-mod` | `--enable_mod_localization` + `--mod_localization` | `false` / `Phospho (S),Phospho (T),Phospho (Y)` | PRELIMINARY, ASSEMBLE, INDIVIDUAL, FINAL | PTM site localization scoring (DIA-NN 1.8.x only) |
-| `--window` | `--scan_window` | `8` | PRELIMINARY, ASSEMBLE, INDIVIDUAL | Scan window; auto-detected when `--scan_window_automatic=true` |
-| `--quick-mass-acc` | `--quick_mass_acc` | `true` | PRELIMINARY | Fast mass accuracy calibration |
-| `--min-corr 2 --corr-diff 1 --time-corr-only` | `--performance_mode` | `true` | PRELIMINARY | High-speed, low-RAM mode |
-| `--pg-level` | `--pg_level` | `2` | INDIVIDUAL, FINAL | Protein grouping level |
-| `--species-genes` | `--species_genes` | `false` | FINAL | Use species-specific gene names |
-| `--no-norm` | `--diann_normalize` | `true` | FINAL | Disable normalization when `false` |
+| DIA-NN flag                                   | Pipeline parameter                                 | Default                                         | Steps                                    | Notes                                                           |
+| --------------------------------------------- | -------------------------------------------------- | ----------------------------------------------- | ---------------------------------------- | --------------------------------------------------------------- |
+| `--cut`                                       | (from SDRF enzyme)                                 | —                                               | ALL                                      | Enzyme cut rule, derived from `comment[cleavage agent details]` |
+| `--fixed-mod`                                 | (from SDRF)                                        | —                                               | ALL                                      | Fixed modifications from `comment[modification parameters]`     |
+| `--var-mod`                                   | (from SDRF)                                        | —                                               | ALL                                      | Variable modifications from `comment[modification parameters]`  |
+| `--monitor-mod`                               | `--enable_mod_localization` + `--mod_localization` | `false` / `Phospho (S),Phospho (T),Phospho (Y)` | PRELIMINARY, ASSEMBLE, INDIVIDUAL, FINAL | PTM site localization scoring (DIA-NN 1.8.x only)               |
+| `--window`                                    | `--scan_window`                                    | `8`                                             | PRELIMINARY, ASSEMBLE, INDIVIDUAL        | Scan window; auto-detected when `--scan_window_automatic=true`  |
+| `--quick-mass-acc`                            | `--quick_mass_acc`                                 | `true`                                          | PRELIMINARY                              | Fast mass accuracy calibration                                  |
+| `--min-corr 2 --corr-diff 1 --time-corr-only` | `--performance_mode`                               | `true`                                          | PRELIMINARY                              | High-speed, low-RAM mode                                        |
+| `--pg-level`                                  | `--pg_level`                                       | `2`                                             | INDIVIDUAL, FINAL                        | Protein grouping level                                          |
+| `--species-genes`                             | `--species_genes`                                  | `false`                                         | FINAL                                    | Use species-specific gene names                                 |
+| `--no-norm`                                   | `--diann_normalize`                                | `true`                                          | FINAL                                    | Disable normalization when `false`                              |
 
 ### PTM site localization (`--monitor-mod`)
 
@@ -161,19 +162,20 @@ nextflow run bigbio/quantmsdiann \
 ```
 
 The parameter accepts two formats:
+
 - **Modification names** (quantms-compatible): `Phospho (S),Phospho (T),Phospho (Y)` — site info in parentheses is stripped, the base name is mapped to UniMod
 - **UniMod accessions** (direct): `UniMod:21,UniMod:1`
 
 Supported modification name mappings:
 
-| Name | UniMod ID | Example |
-|---|---|---|
-| Phospho | `UniMod:21` | `Phospho (S),Phospho (T),Phospho (Y)` |
-| GlyGly | `UniMod:121` | `GlyGly (K)` |
-| Acetyl | `UniMod:1` | `Acetyl (Protein N-term)` |
-| Oxidation | `UniMod:35` | `Oxidation (M)` |
-| Deamidated | `UniMod:7` | `Deamidated (N),Deamidated (Q)` |
-| Methylation | `UniMod:34` | `Methylation (K),Methylation (R)` |
+| Name        | UniMod ID    | Example                               |
+| ----------- | ------------ | ------------------------------------- |
+| Phospho     | `UniMod:21`  | `Phospho (S),Phospho (T),Phospho (Y)` |
+| GlyGly      | `UniMod:121` | `GlyGly (K)`                          |
+| Acetyl      | `UniMod:1`   | `Acetyl (Protein N-term)`             |
+| Oxidation   | `UniMod:35`  | `Oxidation (M)`                       |
+| Deamidated  | `UniMod:7`   | `Deamidated (N),Deamidated (Q)`       |
+| Methylation | `UniMod:34`  | `Methylation (K),Methylation (R)`     |
 
 ## Optional outputs
 
@@ -269,6 +271,7 @@ nextflow run main.nf \
 ```
 
 This config (`conf/tests/test_dia_local.config`) overrides:
+
 - `SDRF_PARSING` → `local/sdrf-pipelines:dev`
 - `SAMPLESHEET_CHECK` → `local/quantms-utils:dev`
 - `DIANN_MSSTATS` → `local/quantms-utils:dev`

modules/local/diann/assemble_empirical_library/main.nf

@@ -19,6 +19,7 @@ process ASSEMBLE_EMPIRICAL_LIBRARY {
     path "empirical_library.*", emit: empirical_library
     path "assemble_empirical_library.log", emit: log
     path "versions.yml", emit: versions
+    path "diann_calibrated_params.csv", emit: calibrated_params
 
     when:
     task.ext.when == null || task.ext.when
@@ -83,6 +84,14 @@ process ASSEMBLE_EMPIRICAL_LIBRARY {
 
     cp report.log.txt assemble_empirical_library.log
 
+    val_mass_acc_ms2=\$(grep "Averaged recommended settings" assemble_empirical_library.log | cut -d ' ' -f 11 | tr -cd "[0-9.]")
+    val_mass_acc_ms1=\$(grep "Averaged recommended settings" assemble_empirical_library.log | cut -d ' ' -f 15 | tr -cd "[0-9.]")
+    val_scan_window=\$(grep "Averaged recommended settings" assemble_empirical_library.log | cut -d ' ' -f 19 | tr -cd "[0-9.]")
+    if [ -z "\$val_mass_acc_ms2" ]; then val_mass_acc_ms2="0"; fi
+    if [ -z "\$val_mass_acc_ms1" ]; then val_mass_acc_ms1="0"; fi
+    if [ -z "\$val_scan_window" ]; then val_scan_window="0"; fi
+    echo "\${val_mass_acc_ms2},\${val_mass_acc_ms1},\${val_scan_window}" > diann_calibrated_params.csv
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         DIA-NN: \$(diann 2>&1 | grep "DIA-NN" | grep -oP "\\d+\\.\\d+(\\.\\w+)*(\\.[\\d]+)?")

modules/local/diann/assemble_empirical_library/meta.yml

@@ -35,5 +35,9 @@ output:
       type: file
       description: File containing software version
       pattern: "versions.yml"
+  - calibrated_params:
+      type: file
+      description: A file containing mass_acc_ms2, mass_acc_ms1, and scan_window extracted from the DIA-NN log.
+      pattern: "diann_calibrated_params.csv"
 authors:
   - "@daichengxin"

modules/local/diann/diann_msstats/main.nf

@@ -3,8 +3,8 @@ process DIANN_MSSTATS {
     label 'process_medium'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.27--pyh106432d_0' :
-        'biocontainers/quantms-utils:0.0.27--pyh106432d_0' }"
+        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.28--pyh106432d_0' :
+        'biocontainers/quantms-utils:0.0.28--pyh106432d_0' }"
 
     input:
     path(report)

modules/local/diann/generate_cfg/main.nf

@@ -3,8 +3,8 @@ process GENERATE_CFG {
     label 'process_tiny'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.27--pyh106432d_0' :
-        'biocontainers/quantms-utils:0.0.27--pyh106432d_0' }"
+        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.28--pyh106432d_0' :
+        'biocontainers/quantms-utils:0.0.28--pyh106432d_0' }"
 
     input:
     val(meta)

modules/local/diann/individual_analysis/main.nf

@@ -8,7 +8,7 @@ process INDIVIDUAL_ANALYSIS {
         'docker.io/biocontainers/diann:v1.8.1_cv1' }"
 
     input:
-    tuple val(meta), path(ms_file), path(fasta), path(diann_log), path(library)
+    tuple val(meta), path(ms_file), path(fasta), path(library)
     path(diann_config)
 
     output:
@@ -44,19 +44,39 @@ process INDIVIDUAL_ANALYSIS {
         }
     }
 
-    scan_window = params.scan_window
-
-    if (params.mass_acc_automatic | params.scan_window_automatic) {
-        mass_acc_ms2 = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 11 | tr -cd \"[0-9]\")"
-        scan_window = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 19 | tr -cd \"[0-9]\")"
-        mass_acc_ms1 = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 15 | tr -cd \"[0-9]\")"
-    } else if (meta['precursormasstoleranceunit'].toLowerCase().endsWith('ppm') && meta['fragmentmasstoleranceunit'].toLowerCase().endsWith('ppm')) {
+    if (params.mass_acc_automatic || params.scan_window_automatic) {
+        if (meta.mass_acc_ms2 != "0" && meta.mass_acc_ms2 != null) {
+            mass_acc_ms2 = meta.mass_acc_ms2
+            mass_acc_ms1 = meta.mass_acc_ms1
+            scan_window  = meta.scan_window
+        }
+        else if (meta['fragmentmasstolerance']) {
+            mass_acc_ms2 = meta['fragmentmasstolerance']
+            mass_acc_ms1 = meta['precursormasstolerance']
+            scan_window  = params.scan_window
+        }
+        else {
+            mass_acc_ms2 = params.mass_acc_ms2
+            mass_acc_ms1 = params.mass_acc_ms1
+            scan_window  = params.scan_window
+        }
+    } else if (meta['precursormasstoleranceunit']?.toLowerCase()?.endsWith('ppm') && meta['fragmentmasstoleranceunit']?.toLowerCase()?.endsWith('ppm')) {
         mass_acc_ms1 = meta["precursormasstolerance"]
         mass_acc_ms2 = meta["fragmentmasstolerance"]
     } else {
-        mass_acc_ms2 = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 11 | tr -cd \"[0-9]\")"
-        scan_window = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 19 | tr -cd \"[0-9]\")"
-        mass_acc_ms1 = "\$(cat ${diann_log} | grep \"Averaged recommended settings\" | cut -d ' ' -f 15 | tr -cd \"[0-9]\")"
+        if (meta.mass_acc_ms2 != "0" && meta.mass_acc_ms2 != null) {
+            mass_acc_ms2 = meta.mass_acc_ms2
+            mass_acc_ms1 = meta.mass_acc_ms1
+            scan_window  = meta.scan_window
+        } else if (meta['fragmentmasstolerance']) {
+            mass_acc_ms2 = meta['fragmentmasstolerance']
+            mass_acc_ms1 = meta['precursormasstolerance']
+            scan_window  = params.scan_window
+        } else {
+            mass_acc_ms2 = params.mass_acc_ms2
+            mass_acc_ms1 = params.mass_acc_ms1
+            scan_window  = params.scan_window
+        }
     }
 
     diann_no_peptidoforms = params.diann_no_peptidoforms ? "--no-peptidoforms" : ""

modules/local/diann/individual_analysis/meta.yml

@@ -10,10 +10,6 @@ tools:
       homepage: https://github.com/vdemichev/DiaNN
       documentation: https://github.com/vdemichev/DiaNN
 input:
-  - diann_log:
-      type: file
-      description: DIA-NN log file
-      pattern: "assemble_empirical_library.log"
   - empirical_library:
       type: file
       description: An empirical spectral library from the .quant files.

modules/local/pmultiqc/main.nf

@@ -2,8 +2,8 @@ process PMULTIQC {
     label 'process_high'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/pmultiqc:0.0.42--pyhdfd78af_0' :
-        'biocontainers/pmultiqc:0.0.42--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/pmultiqc:0.0.43--pyhdfd78af_0' :
+        'biocontainers/pmultiqc:0.0.43--pyhdfd78af_0' }"
 
     input:
     path 'results/*'

modules/local/samplesheet_check/main.nf

@@ -4,8 +4,8 @@ process SAMPLESHEET_CHECK {
     label 'process_tiny'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.27--pyh106432d_0' :
-        'biocontainers/quantms-utils:0.0.27--pyh106432d_0' }"
+        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.28--pyh106432d_0' :
+        'biocontainers/quantms-utils:0.0.28--pyh106432d_0' }"
 
     input:
     path input_file

modules/local/utils/mzml_statistics/main.nf

@@ -4,8 +4,8 @@ process MZML_STATISTICS {
     label 'process_single'
 
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.27--pyh106432d_0' :
-        'biocontainers/quantms-utils:0.0.27--pyh106432d_0' }"
+        'https://depot.galaxyproject.org/singularity/quantms-utils:0.0.28--pyh106432d_0' :
+        'biocontainers/quantms-utils:0.0.28--pyh106432d_0' }"
 
     input:
     tuple val(meta), path(ms_file)

nextflow.config

@@ -85,6 +85,10 @@ params {
     random_preanalysis_seed      = 42
     empirical_assembly_ms_n      = 200
 
+    // DIA-NN: INDIVIDUAL_ANALYSIS
+    mass_acc_ms2    = 15
+    mass_acc_ms1    = 15
+
     // DIA-NN: FINAL_QUANTIFICATION — summarization & output
     pg_level                = 2
     species_genes           = false