bigbio · ypriverol · Apr 3, 2026 · Apr 3, 2026 · Apr 3, 2026 · Apr 3, 2026
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -27,15 +27,15 @@ jobs:
       TEST_PROFILE: ${{ matrix.test_profile }}
       EXEC_PROFILE: ${{ matrix.exec_profile }}
 
-    name: "CI [${{ matrix.test_profile }}] DIA-NN=1.8.1 NXF=${{ matrix.NXF_VER }}"
+    name: "CI [${{ matrix.test_profile }}] NXF=${{ matrix.NXF_VER }}"
     if: ${{ github.event_name != 'push' || (github.event_name == 'push' && github.repository == 'bigbio/quantmsdiann') }}
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         NXF_VER:
           - "25.04.0"
-        test_profile: ["test_dia", "test_dia_dotd"]
+        test_profile: ["test_dia", "test_dia_dotd", "test_dda"]
         exec_profile: ["docker"] # extended ci tests singularity.
 
     steps:
@@ -60,11 +60,24 @@ jobs:
           mkdir -p $NXF_SINGULARITY_CACHEDIR
           mkdir -p $NXF_SINGULARITY_LIBRARYDIR
 
+      - name: Log in to GitHub Container Registry
+        if: matrix.test_profile == 'test_dda'
+        env:
+          GHCR_TOKEN: ${{ secrets.GHCR_TOKEN }}
+          GHCR_USERNAME: ${{ secrets.GHCR_USERNAME }}
+        run: |
+          if [ -z "$GHCR_TOKEN" ] || [ -z "$GHCR_USERNAME" ]; then
+            echo "::warning::Skipping test_dda: GHCR credentials not available (expected for fork PRs)"
+            echo "SKIP_DDA=true" >> $GITHUB_ENV
+            exit 0
+          fi
+          echo "$GHCR_TOKEN" | docker login ghcr.io -u "$GHCR_USERNAME" --password-stdin
+
       - name: Disk space cleanup
         uses: jlumbroso/free-disk-space@v1.3.1
 
       - name: Run pipeline with test data in docker/singularity profile
-        if: github.event.pull_request.base.ref != 'master'
+        if: github.event.pull_request.base.ref != 'master' && env.SKIP_DDA != 'true'
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile $TEST_PROFILE,$EXEC_PROFILE,dev --outdir ${TEST_PROFILE}_${EXEC_PROFILE}_results
 

diff --git a/.github/workflows/extended_ci.yml b/.github/workflows/extended_ci.yml
@@ -114,7 +114,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        test_profile: ["test_latest_dia", "test_dia_quantums", "test_dia_parquet"]
+        test_profile:
+          ["test_latest_dia", "test_dia_quantums", "test_dia_parquet", "test_dda", "test_dia_skip_preanalysis"]
     env:
       NXF_ANSI_LOG: false
       CAPSULE_LOG: none

diff --git a/.gitignore b/.gitignore
@@ -21,3 +21,4 @@ null/
 .codacy/
 .github/instructions/codacy.instructions.md
 docs/superpowers/
+docs/plans/
diff --git a/AGENTS.md b/AGENTS.md
@@ -80,7 +80,7 @@ quantmsdiann/
 │   ├── pmultiqc/              # QC reporting
 │   ├── sdrf_parsing/          # SDRF parsing
 │   ├── samplesheet_check/     # Input validation
-│   └── utils/                 # tdf2mzml, decompress, mzml stats
+│   └── utils/                 # decompress, mzml stats
 ├── conf/
 │   ├── base.config            # Resource definitions
 │   ├── modules/               # Module-specific configs
@@ -97,7 +97,7 @@ quantmsdiann/
 The pipeline executes the following steps:
 
 1. **SDRF Validation & Parsing** - Validates input SDRF and extracts metadata
-2. **File Preparation** - Converts RAW/mzML/.d/.dia files (ThermoRawFileParser, tdf2mzml)
+2. **File Preparation** - Converts RAW/mzML/.d/.dia files (ThermoRawFileParser)
 3. **Generate Config** - Creates DIA-NN config from enzyme/modifications (`quantmsutilsc dianncfg`)
 4. **In-Silico Library Generation** - Predicts spectral library from FASTA (or uses provided library)
 5. **Preliminary Analysis** - Per-file calibration and mass accuracy determination

diff --git a/CITATIONS.md b/CITATIONS.md
@@ -1,6 +1,6 @@
 # bigbio/quantmsdiann: Citations
 
-## [Pipeline](https://www.researchsquare.com/article/rs-3002027/v1)
+## [Pipeline](https://doi.org/10.1038/s41592-024-02343-1)
 
 > Dai C, Pfeuffer J, Wang H, Zheng P, Käll L, Sachsenberg T, Demichev V, Bai M, Kohlbacher O, Perez-Riverol Y. quantms: a cloud-based pipeline for quantitative proteomics enables the reanalysis of public proteomics data. Nat Methods. 2024 Jul 4. doi: 10.1038/s41592-024-02343-1. Epub ahead of print. PMID: 38965444.
 

diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 
 [![GitHub Actions CI Status](https://github.com/bigbio/quantmsdiann/actions/workflows/ci.yml/badge.svg)](https://github.com/bigbio/quantmsdiann/actions/workflows/ci.yml)
 [![GitHub Actions Linting Status](https://github.com/bigbio/quantmsdiann/actions/workflows/linting.yml/badge.svg)](https://github.com/bigbio/quantmsdiann/actions/workflows/linting.yml)
-[![Cite with Zenodo](https://zenodo.org/badge/DOI/10.5281/zenodo.15573386.svg)](https://doi.org/10.5281/zenodo.15573386)
+[![Cite with Zenodo](https://zenodo.org/badge/DOI/10.5281/zenodo.19437128.svg)](https://doi.org/10.5281/zenodo.19437128)
 [![nf-test](https://img.shields.io/badge/unit_tests-nf--test-337ab7.svg)](https://www.nf-test.com)
 
 [![Nextflow](https://img.shields.io/badge/version-%E2%89%A525.04.0-green?style=flat&logo=nextflow&logoColor=white&color=%230DC09D&link=https%3A%2F%2Fnextflow.io)](https://www.nextflow.io/)
@@ -25,7 +25,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
 The pipeline takes [SDRF](https://github.com/bigbio/proteomics-metadata-standard) metadata and mass spectrometry data files (`.raw`, `.mzML`, `.d`, `.dia`) as input and performs:
 
 1. **Input validation** — SDRF parsing and validation via [sdrf-pipelines](https://github.com/bigbio/sdrf-pipelines)
-2. **File preparation** — RAW to mzML conversion ([ThermoRawFileParser](https://github.com/compomics/ThermoRawFileParser)), indexing, Bruker `.d` handling ([tdf2mzml](https://github.com/bigbio/tdf2mzml))
+2. **File preparation** — RAW to mzML conversion ([ThermoRawFileParser](https://github.com/compomics/ThermoRawFileParser)), indexing
 3. **In-silico spectral library generation** — deep learning-based prediction, or use a user-provided library (`--diann_speclib`)
 4. **Preliminary analysis** — per-file calibration and mass accuracy estimation (parallelized)
 5. **Empirical library assembly** — consensus library from preliminary results with RT profiling
@@ -103,7 +103,7 @@ If you would like to contribute to this pipeline, please see the [contributing g
 
 If you use quantmsdiann in your research, please cite:
 
-> Dai et al. "quantms: a cloud-based pipeline for quantitative proteomics" (2024). DOI: [10.5281/zenodo.15573386](https://doi.org/10.5281/zenodo.15573386)
+> Dai et al. "quantms: a cloud-based pipeline for quantitative proteomics" (2024). DOI: [10.5281/zenodo.19437128](https://doi.org/10.5281/zenodo.19437128)
 
 An extensive list of references for the tools used by the pipeline can be found in the [CITATIONS.md](CITATIONS.md) file.
 

diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -11,7 +11,7 @@
             "source name": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Sample name must be provided and cannot contain spaces"
+                "errorMessage": "Source name must be provided and cannot contain spaces"
             },
             "comment[data file]": {
                 "type": "string",
@@ -22,7 +22,7 @@
             "assay name": {
                 "type": "string",
                 "pattern": "^\\S+$",
-                "errorMessage": "Assay name must be provided and cannot contain spaces",
+                "errorMessage": "Assay name must be provided and cannot contain whitespace",
                 "meta": ["assay"]
             }
         }

diff --git a/conf/diann_versions/v2_3_2.config b/conf/diann_versions/v2_3_2.config
@@ -0,0 +1,14 @@
+/*
+ * DIA-NN 2.3.2 container override (private ghcr.io)
+ * Latest release with DDA support and InfinDIA.
+ */
+params.diann_version = '2.3.2'
+
+process {
+    withLabel: diann {
+        container = 'ghcr.io/bigbio/diann:2.3.2'
+    }
+}
+
+singularity.enabled = false
+docker.enabled = true
diff --git a/conf/tests/test_dda.config b/conf/tests/test_dda.config
@@ -0,0 +1,53 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for testing DDA analysis (requires DIA-NN >= 2.3.2)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Tests DDA mode using the PXD022287 HeLa dataset with --diann_dda flag.
+    Uses ghcr.io/bigbio/diann:2.3.2.
+
+    Use as follows:
+        nextflow run bigbio/quantmsdiann -profile test_dda,docker [--outdir <OUTDIR>]
+
+------------------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '12.GB',
+        time: '48.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test profile for DDA analysis'
+    config_profile_description = 'DDA test using PXD022287 HeLa dataset with DIA-NN 2.3.2.'
+
+    outdir = './results_dda'
+
+    // Input data - PXD022287 HeLa DDA dataset
+    input = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata/diann_dda_ci/PXD022287.sdrf.tsv'
+    database = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata/diann_dda_ci/PXD022287_subset_human.fasta'
+
+    // DDA mode
+    diann_dda = true
+    diann_version = '2.3.2'
+
+    // Search parameters matching PXD022287 HeLa dataset
+    min_peptide_length = 7
+    max_peptide_length = 30
+    max_precursor_charge = 3
+    allowed_missed_cleavages = 1
+    diann_normalize = false
+    publish_dir_mode = 'symlink'
+    max_mods = 2
+}
+
+process {
+    withLabel: diann {
+        container = 'ghcr.io/bigbio/diann:2.3.2'
+    }
+}
+
+singularity.enabled = false
+docker.enabled = true
diff --git a/conf/tests/test_dia_skip_preanalysis.config b/conf/tests/test_dia_skip_preanalysis.config
@@ -0,0 +1,48 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Nextflow config file for testing skip_preliminary_analysis path
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Tests the pipeline with skip_preliminary_analysis=true, using default
+    mass accuracy parameters. Validates the untested code path in dia.nf.
+
+    Use as follows:
+        nextflow run bigbio/quantmsdiann -profile test_dia_skip_preanalysis,docker [--outdir <OUTDIR>]
+
+------------------------------------------------------------------------------------------------
+*/
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '12.GB',
+        time: '48.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test profile for skip preliminary analysis'
+    config_profile_description = 'Tests skip_preliminary_analysis path with default mass accuracy params.'
+
+    outdir = './results_skip_preanalysis'
+
+    // Input data - same as test_dia
+    input = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata/dia_ci/PXD026600.sdrf.tsv'
+    database = 'https://raw.githubusercontent.com/bigbio/quantms-test-datasets/quantms/testdata/dia_ci/REF_EColi_K12_UPS1_combined.fasta'
+    min_pr_mz = 350
+    max_pr_mz = 950
+    min_fr_mz = 500
+    max_fr_mz = 1500
+    min_peptide_length = 15
+    max_peptide_length = 30
+    max_precursor_charge = 3
+    allowed_missed_cleavages = 1
+    diann_normalize = false
+    publish_dir_mode = 'symlink'
+    max_mods = 2
+
+    // Skip preliminary analysis - use default mass accuracy params
+    skip_preliminary_analysis = true
+    mass_acc_ms2 = 15
+    mass_acc_ms1 = 15
+    scan_window = 8
+}