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
@@ -24,7 +24,7 @@ This is **non-negotiable**. All code must pass formatting and style checks befor
 
 - Built with Nextflow DSL2
 - DIA-NN for peptide/protein identification and quantification
-- Supports DIA-NN v1.8.1, v2.1.0, and v2.2.0 (latest)
+- Supports DIA-NN v1.8.1, v2.1.0, v2.2.0, v2.3.2, and v2.5.0 (latest)
 - QuantUMS quantification method (DIA-NN >= 1.9.2)
 - Parquet-native output with decoy reporting (DIA-NN >= 2.0)
 - MSstats-compatible output generation (via quantms-utils conversion, no MSstats analysis)
@@ -44,7 +44,7 @@ This is **non-negotiable**. All code must pass formatting and style checks befor
 - **nf-test**: Testing framework (config: `nf-test.config`)
 - **nf-core tools**: Pipeline standards and linting
 - **Containers**: Docker/Singularity/Apptainer/Podman (Conda deprecated)
-- **DIA-NN**: Primary search engine (versions 1.8.1 through 2.2.0)
+- **DIA-NN**: Primary search engine (versions 1.8.1 through 2.5.0)
 
 ### Key Configuration Files
 
@@ -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
@@ -109,13 +109,16 @@ The pipeline executes the following steps:
 
 ### DIA-NN Version-Specific Features
 
-| Feature                                     | Min Version | Parameter                    |
-| ------------------------------------------- | ----------- | ---------------------------- |
-| Core workflow, library-free, .quant caching | 1.8.1       | (default)                    |
-| QuantUMS quantification                     | 1.9.2       | `--quantums true`            |
-| Parquet output format                       | 2.0         | (automatic in 2.0+)          |
-| Decoy reporting                             | 2.0         | `--diann_report_decoys true` |
-| Native .raw on Linux                        | 2.1.0       | (automatic)                  |
+| Feature                                     | Min Version | Parameter              |
+| ------------------------------------------- | ----------- | ---------------------- |
+| Core workflow, library-free, .quant caching | 1.8.1       | (default)              |
+| QuantUMS quantification                     | 1.9.2       | `--quantums true`      |
+| Parquet output format                       | 2.0         | (automatic in 2.0+)    |
+| Decoy reporting                             | 2.0         | `--report_decoys true` |
+| Native .raw on Linux                        | 2.1.0       | (automatic)            |
+| DDA support                                 | 2.3.2       | `--dda true`           |
+| InfinDIA                                    | 2.3.0       | `--enable_infin_dia`   |
+| DL model fine-tuning & selection            | 2.5.0       | `--extra_args`         |
 
 ---
 
@@ -194,6 +197,8 @@ These apply on top of test profiles to override the DIA-NN container version:
 | `diann_v1_8_1` | `biocontainers/diann:v1.8.1_cv1` | none |
 | `diann_v2_1_0` | `ghcr.io/bigbio/diann:2.1.0`     | GHCR |
 | `diann_v2_2_0` | `ghcr.io/bigbio/diann:2.2.0`     | GHCR |
+| `diann_v2_3_2` | `ghcr.io/bigbio/diann:2.3.2`     | GHCR |
+| `diann_v2_5_0` | `ghcr.io/bigbio/diann:2.5.0`     | GHCR |
 
 ### CI Workflows
 

diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,6 +3,62 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [2.0.0] bigbio/quantmsdiann — Rome - 2026-04-13
+
+### `Added`
+
+- DDA analysis mode support (requires DIA-NN >= 2.3.2), auto-detected from SDRF or set via `--dda`
+- DIA-NN 2.3.2 version profile (`-profile diann_v2_3_2`) with InfinDIA and DDA support
+- Scoring mode parameter (`--scoring_mode`): `generic` (default), `proteoforms` (proteogenomics/variant detection, >= 2.0), `peptidoforms` (PTM analysis)
+- FDR controls: `--precursor_qvalue`, `--matrix_qvalue`, `--matrix_spec_q` replacing the misleadingly named `protein_level_fdr_cutoff`
+- Channel normalization flags: `--channel_run_norm`, `--channel_spec_norm` for multiplexing workflows (plexDIA/SILAC)
+- InfinDIA support: `--enable_infin_dia`, `--pre_select` for ultra-large search spaces (DIA-NN >= 2.3.0)
+- Fragment-level export: `--export_quant` for parquet fragment data (DIA-NN >= 2.0)
+- MS1 PTM quantification: `--site_ms1_quant` (DIA-NN >= 2.0)
+- Skip preliminary analysis: `--skip_preliminary_analysis` to use a provided spectral library directly
+- Centralized blocked-flags registry (`lib/BlockedFlags.groovy`) replacing duplicated per-module logic
+- Version guards for all DIA-NN version-dependent features with clear error messages
+- `VersionUtils.groovy` for semantic version comparison (replaces fragile string comparisons)
+- Log capture via `tee` fallback in all DIA-NN modules for robust log handling across versions
+- CI: `test_dda` and `test_dia_skip_preanalysis` test profiles
+
+### `Changed`
+
+- Removed `diann_` prefix from all user-facing parameters (e.g., `--diann_report_decoys` → `--report_decoys`, `--diann_normalize` → `--normalize`)
+- Removed `diann_no_peptidoforms` parameter (superseded by `--scoring_mode`)
+- Separated FINAL_QUANTIFICATION report output into parquet and TSV channels (DIA-NN >= 1.9 produces parquet)
+- Matrix/stats outputs in FINAL_QUANTIFICATION now `optional: true` for DIA-NN 2.x compatibility
+- Decoupled container engine from DIA-NN version configs (engine selected via `-profile`, not version config)
+- Removed hardcoded DIA-NN container from `pride_codon_slurm.config`
+- Updated Zenodo DOI to 10.5281/zenodo.19437128
+
+### `Removed`
+
+- `tdf2mzml` module and all references (Bruker .d files handled natively by DIA-NN >= 2.0)
+- `protein_level_fdr_cutoff` parameter (replaced by `precursor_qvalue`)
+- `diann_no_peptidoforms` parameter (replaced by `scoring_mode`)
+
+### `Fixed`
+
+- DIA-NN log file handling for versions >= 2.x that don't produce `*.log.txt` files
+- `DIANN_MSSTATS` receiving both parquet and TSV when both exist (now only one format reaches downstream)
+- Missing blocked flags: `--no-prot-inf` in ASSEMBLE/INDIVIDUAL/FINAL, `--channel-run-norm`/`--channel-spec-norm` in FINAL, `--var-mod`/`--fixed-mod`/`--channels` in INSILICO
+- Unnecessary `.first()` warning on `ch_sdrf` value channel
+- `--out` added to in-silico library generation to produce a log file with DIA-NN 2.3.2
+
+### `Dependencies`
+
+| Dependency            | Version   |
+| --------------------- | --------- |
+| `nextflow`            | >=25.04.0 |
+| `dia-nn`              | 1.8.1+    |
+| `thermorawfileparser` | 2.0.0.dev |
+| `sdrf-pipelines`      | 0.1.2     |
+| `pmultiqc`            | 0.0.44    |
+| `quantms-utils`       | 0.0.29    |
+
+---
+
 ## [1.0.0] bigbio/quantmsdiann - 2026-04-03
 
 Initial release of the standalone DIA-NN quantitative proteomics pipeline, refactored from [bigbio/quantms](https://github.com/bigbio/quantms).

diff --git a/CITATION.cff b/CITATION.cff
@@ -0,0 +1,44 @@
+cff-version: 1.2.0
+title: "quantmsdiann"
+message: "If you use quantmsdiann, please cite the quantms paper."
+type: software
+license: MIT
+repository-code: https://github.com/bigbio/quantmsdiann
+url: https://quantmsdiann.quantms.org
+keywords:
+  - proteomics
+  - mass-spectrometry
+  - dia
+  - data-independent-acquisition
+  - dia-nn
+  - nextflow
+preferred-citation:
+  type: article
+  title: "quantms: a cloud-based pipeline for quantitative proteomics enables the reanalysis of public proteomics data"
+  journal: "Nature Methods"
+  year: 2024
+  volume: "21"
+  start: 1603
+  end: 1607
+  doi: "10.1038/s41592-024-02343-1"
+  authors:
+    - family-names: Dai
+      given-names: Chengxin
+    - family-names: Pfeuffer
+      given-names: Julianus
+    - family-names: Wang
+      given-names: Hong
+    - family-names: Zheng
+      given-names: Ping
+    - family-names: Kall
+      given-names: Lukas
+    - family-names: Sachsenberg
+      given-names: Timo
+    - family-names: Demichev
+      given-names: Vadim
+    - family-names: Bai
+      given-names: Mingze
+    - family-names: Kohlbacher
+      given-names: Oliver
+    - family-names: Perez-Riverol
+      given-names: Yasset
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/)
@@ -25,8 +25,8 @@ 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))
-3. **In-silico spectral library generation** — deep learning-based prediction, or use a user-provided library (`--diann_speclib`)
+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 (`--speclib`)
 4. **Preliminary analysis** — per-file calibration and mass accuracy estimation (parallelized)
 5. **Empirical library assembly** — consensus library from preliminary results with RT profiling
 6. **Individual analysis** — per-file search with the empirical library (parallelized)
@@ -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_1_0.config b/conf/diann_versions/v2_1_0.config
@@ -10,5 +10,4 @@ process {
     }
 }
 
-singularity.enabled = false
-docker.enabled = true
+// Container engine is selected via -profile (docker/singularity), not here
diff --git a/conf/diann_versions/v2_2_0.config b/conf/diann_versions/v2_2_0.config
@@ -10,5 +10,4 @@ process {
     }
 }
 
-singularity.enabled = false
-docker.enabled = true
+// Container engine is selected via -profile (docker/singularity), not here
diff --git a/conf/diann_versions/v2_3_2.config b/conf/diann_versions/v2_3_2.config
@@ -0,0 +1,13 @@
+/*
+ * 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'
+    }
+}
+
+// Container engine is selected via -profile (docker/singularity), not here
diff --git a/conf/diann_versions/v2_5_0.config b/conf/diann_versions/v2_5_0.config
@@ -0,0 +1,14 @@
+/*
+ * DIA-NN 2.5.0 container override (private ghcr.io)
+ * Major protein ID improvements (+70%), DL model selection flags,
+ * new --aa-eq flag for amino acid equivalence.
+ */
+params.diann_version = '2.5.0'
+
+process {
+    withLabel: diann {
+        container = 'ghcr.io/bigbio/diann:2.5.0'
+    }
+}
+
+// Container engine is selected via -profile (docker/singularity), not here
diff --git a/conf/modules/dia.config b/conf/modules/dia.config
@@ -2,7 +2,7 @@
 ========================================================================================
     DIA-NN module options — all DIA pipeline steps
 ========================================================================================
-    Passes params.diann_extra_args to each DIA-NN step via ext.args.
+    Passes params.extra_args (formerly params.diann_extra_args) to each DIA-NN step via ext.args.
     Blocked-flag validation is performed in each module's script block,
     so it applies regardless of whether ext.args is overridden by the user.
 ----------------------------------------------------------------------------------------
@@ -11,22 +11,22 @@
 process {
 
     withName: ".*:DIA:INSILICO_LIBRARY_GENERATION" {
-        ext.args   = { params.diann_extra_args ?: '' }
+        ext.args   = { params.extra_args ?: '' }
     }
 
     withName: ".*:DIA:PRELIMINARY_ANALYSIS" {
-        ext.args   = { params.diann_extra_args ?: '' }
+        ext.args   = { params.extra_args ?: '' }
     }
 
     withName: ".*:DIA:ASSEMBLE_EMPIRICAL_LIBRARY" {
-        ext.args   = { params.diann_extra_args ?: '' }
+        ext.args   = { params.extra_args ?: '' }
     }
 
     withName: ".*:DIA:INDIVIDUAL_ANALYSIS" {
-        ext.args   = { params.diann_extra_args ?: '' }
+        ext.args   = { params.extra_args ?: '' }
     }
 
     withName: ".*:DIA:FINAL_QUANTIFICATION" {
-        ext.args   = { params.diann_extra_args ?: '' }
+        ext.args   = { params.extra_args ?: '' }
     }
 }
diff --git a/conf/pride_codon_slurm.config b/conf/pride_codon_slurm.config
@@ -42,9 +42,8 @@ process {
         cpus   = {Math.min((ms_files as List).size() < 200 ? 12 * task.attempt : 24 * task.attempt, 48)}
     }
 
-    withLabel: diann {
-        container = '/hps/nobackup/juan/pride/reanalysis/singularity/ghcr.io-bigbio-diann-1.9.2.sif'
-    }
+    // DIA-NN container: use -c conf/diann_versions/v<X>.config or
+    // --diann_container to select the version. No default hardcoded here.
 }
 
 executor {