bigbio · ypriverol · May 7, 2026 · May 3, 2026 · May 5, 2026 · May 6, 2026
diff --git a/modules/bigbio/pridepy/environment.yml b/modules/bigbio/pridepy/environment.yml
@@ -3,4 +3,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::pridepy=0.0.14
+  - bioconda::pridepy=0.0.15
diff --git a/modules/bigbio/pridepy/main.nf b/modules/bigbio/pridepy/main.nf
@@ -5,8 +5,8 @@ process PRIDEPY_DOWNLOAD {
 
     conda "${moduleDir}/environment.yml"
     container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
-        ? 'https://depot.galaxyproject.org/singularity/pridepy:0.0.14--pyhdfd78af_0'
-        : 'biocontainers/pridepy:0.0.14--pyhdfd78af_0'}"
+        ? 'https://depot.galaxyproject.org/singularity/pridepy:0.0.15--pyhdfd78af_0'
+        : 'biocontainers/pridepy:0.0.15--pyhdfd78af_0'}"
 
     input:
     val(meta)
@@ -39,7 +39,7 @@ process PRIDEPY_DOWNLOAD {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        pridepy: 0.0.14
+        pridepy: 0.0.15
     END_VERSIONS
     """
 }
diff --git a/modules/bigbio/pridepy/tests/main.nf.test.snap b/modules/bigbio/pridepy/tests/main.nf.test.snap
@@ -10,7 +10,7 @@
                 ]
             ],
             [
-                "versions.yml:md5,c27ccb04c91f92f188b7f4cf2d54ed49"
+                "versions.yml:md5,19782821de060ab1588d5d4274bdacf0"
             ]
         ],
         "timestamp": "2026-04-28T18:15:37.876014654",
@@ -38,7 +38,7 @@
                 ]
             ],
             [
-                "versions.yml:md5,c27ccb04c91f92f188b7f4cf2d54ed49"
+                "versions.yml:md5,19782821de060ab1588d5d4274bdacf0"
             ]
         ],
         "timestamp": "2026-04-28T18:15:43.996367071",

diff --git a/modules/bigbio/qpx/environment.yml b/modules/bigbio/qpx/environment.yml
@@ -0,0 +1,7 @@
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - pip:
+      - qpx
diff --git a/modules/bigbio/qpx/main.nf b/modules/bigbio/qpx/main.nf
@@ -0,0 +1,81 @@
+process QPX_EXPORT {
+    tag "qpx_export"
+    label 'process_medium'
+    label 'error_retry'
+
+    conda "${moduleDir}/environment.yml"
+    container "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container
+        ? 'https://depot.galaxyproject.org/singularity/qpx:1.0.2--pyhdfd78af_1'
+        : 'biocontainers/qpx:1.0.2--pyhdfd78af_1'}"
+
+    input:
+    path(diann_report)
+    path(pg_matrix)
+    path(sdrf)
+    path(diann_log)
+    val(project_accession)
+
+    output:
+    path "qpx_output/" , emit: qpx_dataset
+    path "*.h5mu"      , emit: mudata
+    path "versions.yml", emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args    = task.ext.args ?: ''
+    def prefix  = project_accession ?: 'diann'
+    def pg_arg  = pg_matrix ? "--pg-matrix-path ${pg_matrix}" : ''
+    def log_arg = diann_log ? "--diann-log ${diann_log}" : ''
+    def acc_arg = project_accession ? "--project-accession ${project_accession}" : ''
+    def qvalue  = params.matrix_qvalue ?: 0.05
+    """
+    set -o pipefail
+    qpxc convert diann \\
+        --report-path ${diann_report} \\
+        --sdrf-file ${sdrf} \\
+        ${pg_arg} \\
+        ${log_arg} \\
+        ${acc_arg} \\
+        --output-folder qpx_output \\
+        --output-prefix ${prefix} \\
+        --qvalue-threshold ${qvalue} \\
+        --standardized-intensities \\
+        --duckdb-threads ${task.cpus} \\
+        --duckdb-max-memory ${task.memory ? task.memory.toGiga() : 4}GB \\
+        --compression zstd \\
+        ${args}
+
+    python - <<'PY'
+from qpx.dataset import Dataset
+from qpx.mudata import build_mudata
+
+ds = Dataset("qpx_output")
+mdata = build_mudata(ds)
+mdata.write("${prefix}.h5mu")
+ds.close()
+print(f"MuData: {mdata.n_obs} obs x {mdata.n_vars} vars -> ${prefix}.h5mu")
+PY
+
+cat <<-END_VERSIONS > versions.yml
+"${task.process}":
+    qpx: \$(qpxc --version 2>&1 | sed 's/^qpx //')
+    mudata: \$(python -c 'import mudata; print(mudata.__version__)')
+END_VERSIONS
+    """
+
+    stub:
+    def prefix = project_accession ?: 'diann'
+    """
+    mkdir -p qpx_output
+    touch qpx_output/stub.parquet
+    touch ${prefix}.h5mu
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        qpx: stub
+        mudata: stub
+    END_VERSIONS
+    """
+}
diff --git a/modules/bigbio/qpx/meta.yml b/modules/bigbio/qpx/meta.yml
@@ -0,0 +1,65 @@
+name: qpx_export
+description: Convert DIA-NN quantification outputs to QPX Parquet dataset and MuData (.h5mu)
+keywords:
+  - proteomics
+  - quantification
+  - parquet
+  - mudata
+  - dia-nn
+  - qpx
+tools:
+  - qpx:
+      description: |
+        QPX (Quantitative Proteomics eXchange) converts tool-specific quantification
+        outputs into a standardised Parquet dataset and optionally a MuData (.h5mu) file
+        for downstream analysis in Python (scanpy / muon).
+      homepage: https://github.com/bigbio/qpx
+      documentation: https://github.com/bigbio/qpx
+      tool_dev_url: https://github.com/bigbio/qpx
+      licence:
+        - "Apache-2.0"
+      identifier: ""
+input:
+  - diann_report:
+      type: file
+      description: DIA-NN main report (TSV or Parquet)
+      pattern: "*.{tsv,parquet}"
+  - pg_matrix:
+      type: file
+      description: DIA-NN protein-group matrix
+      pattern: "*.{tsv,parquet}"
+  - sdrf:
+      type: file
+      description: SDRF sample metadata file
+      pattern: "*.sdrf.tsv"
+  - diann_log:
+      type: file
+      description: DIA-NN summary log for version detection
+      pattern: "*.log"
-  - diann_log:
-      type: file
-      description: DIA-NN summary log for version detection
-      pattern: "*.log"
+  - diann_log:
+      type: file
+      description: DIA-NN summary log for version detection
+      pattern: "*.log*"
-  - diann_log:
-      type: file
-      description: DIA-NN summary log for version detection
-      pattern: "*.log"
+  - diann_log:
+      type: file
+      description: DIA-NN summary log for version detection
+      pattern: "*.log*"
+  - project_accession:
+      type: string
+      description: PRIDE project accession (e.g. PXD026600) used as output prefix
+output:
+  qpx_dataset:
+    - "qpx_output/":
+        type: directory
+        description: QPX Parquet dataset directory
+        pattern: "qpx_output/"
+  mudata:
+    - "*.h5mu":
+        type: file
+        description: MuData file containing the quantification data
+        pattern: "*.h5mu"
+  versions:
+    - versions.yml:
+        type: file
+        description: File containing software versions
+        pattern: "versions.yml"
+        ontologies:
+          - edam: http://edamontology.org/format_3750
+authors:
+  - "@ypriverol"
+  - "@Shen-YuFei"
+maintainers:
+  - "@ypriverol"
+  - "@Shen-YuFei"
diff --git a/modules/bigbio/qpx/tests/main.nf.test b/modules/bigbio/qpx/tests/main.nf.test
@@ -0,0 +1,88 @@
+nextflow_process {
+
+    name "Test Process QPX_EXPORT"
+    script "../main.nf"
+    process "QPX_EXPORT"
+    tag "modules"
+    tag "modules_bigbio"
+    tag "modules_qpx"
+    tag "qpx"
+
+    config "./nextflow.config"
+
+    test("Should convert DIA-NN output to QPX Parquet + MuData") {
+
+        when {
+            def zipUrl = (params.test_data?.proteomics?.qpx?.diann_results) ?: "https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/pmultiqc/example-projects/PXD063291.zip"
+            def zipFile = file("test_qpx.zip")
+            zipFile.withOutputStream { out ->
+                out << new URL(zipUrl).openStream()
+            }
+            def resultsDir = file("test_qpx_data")
+            resultsDir.mkdirs()
+            new java.util.zip.ZipFile(zipFile).withCloseable { zip ->
+                zip.entries().each { entry ->
+                    if (!entry.isDirectory()) {
+                        def extractFile = new File(resultsDir, entry.name)
+                        extractFile.parentFile.mkdirs()
+                        extractFile.withOutputStream { out ->
+                            out << zip.getInputStream(entry)
+                        }
+                    }
+                }
+            }
-            zipFile.withOutputStream { out ->
-                out << new URL(zipUrl).openStream()
-            }
-            def resultsDir = file("test_qpx_data")
-            resultsDir.mkdirs()
-            new java.util.zip.ZipFile(zipFile).withCloseable { zip ->
-                zip.entries().each { entry ->
-                    if (!entry.isDirectory()) {
-                        def extractFile = new File(resultsDir, entry.name)
-                        extractFile.parentFile.mkdirs()
-                        extractFile.withOutputStream { out ->
-                            out << zip.getInputStream(entry)
-                        }
-                    }
-                }
-            }
+            def connection = new URL(zipUrl).openConnection()
+            connection.setConnectTimeout(30_000)
+            connection.setReadTimeout(120_000)
+            connection.inputStream.withCloseable { input ->
+                zipFile.withOutputStream { out -> out << input }
+            }
+            def resultsDir = file("test_qpx_data")
+            resultsDir.mkdirs()
+            new java.util.zip.ZipFile(zipFile).withCloseable { zip ->
+                def canonicalRoot = resultsDir.canonicalFile
+                zip.entries().each { entry ->
+                    if (!entry.isDirectory()) {
+                        def extractFile = new File(resultsDir, entry.name).canonicalFile
+                        if (!extractFile.path.startsWith(canonicalRoot.path + File.separator)) {
+                            throw new SecurityException("Blocked zip entry outside target dir: ${entry.name}")
+                        }
+                        extractFile.parentFile.mkdirs()
+                        zip.getInputStream(entry).withCloseable { input ->
+                            extractFile.withOutputStream { out -> out << input }
+                        }
+                    }
+                }
+            }
-            zipFile.withOutputStream { out ->
-                out << new URL(zipUrl).openStream()
-            }
-            def resultsDir = file("test_qpx_data")
-            resultsDir.mkdirs()
-            new java.util.zip.ZipFile(zipFile).withCloseable { zip ->
-                zip.entries().each { entry ->
-                    if (!entry.isDirectory()) {
-                        def extractFile = new File(resultsDir, entry.name)
-                        extractFile.parentFile.mkdirs()
-                        extractFile.withOutputStream { out ->
-                            out << zip.getInputStream(entry)
-                        }
-                    }
-                }
-            }
+            def connection = new URL(zipUrl).openConnection()
+            connection.setConnectTimeout(30_000)
+            connection.setReadTimeout(120_000)
+            connection.inputStream.withCloseable { input ->
+                zipFile.withOutputStream { out -> out << input }
+            }
+            def resultsDir = file("test_qpx_data")
+            resultsDir.mkdirs()
+            new java.util.zip.ZipFile(zipFile).withCloseable { zip ->
+                def canonicalRoot = resultsDir.canonicalFile
+                zip.entries().each { entry ->
+                    if (!entry.isDirectory()) {
+                        def extractFile = new File(resultsDir, entry.name).canonicalFile
+                        if (!extractFile.path.startsWith(canonicalRoot.path + File.separator)) {
+                            throw new SecurityException("Blocked zip entry outside target dir: ${entry.name}")
+                        }
+                        extractFile.parentFile.mkdirs()
+                        zip.getInputStream(entry).withCloseable { input ->
+                            extractFile.withOutputStream { out -> out << input }
+                        }
+                    }
+                }
+            }
+            zipFile.delete()
+
+            process {
+                """
+                input[0] = file('${resultsDir.getAbsolutePath()}/PXD063291/DiaNN/report.tsv')
+                input[1] = file('${resultsDir.getAbsolutePath()}/PXD063291/DiaNN/report.pg_matrix.tsv')
+                input[2] = file('${resultsDir.getAbsolutePath()}/PXD063291/PXD063291.sdrf.tsv')
+                input[3] = file('${resultsDir.getAbsolutePath()}/PXD063291/DiaNN/report.log.txt')
+                input[4] = "PXD063291"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert process.out.qpx_dataset.size() == 1 },
+                { assert process.out.mudata.size() == 1 },
+                { assert process.out.mudata[0].toString().endsWith('.h5mu') },
+                { assert snapshot(process.out.versions).match("versions") }
+            )
+        }
+
+        cleanup {
+            file("test_qpx_data").deleteDir()
+        }
+    }
+
+    test("Should run stub mode") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = file("stub_report.tsv", checkIfExists: false)
+                input[1] = file("stub_pg_matrix.tsv", checkIfExists: false)
+                input[2] = file("stub_sample.sdrf.tsv", checkIfExists: false)
+                input[3] = file("stub_diann.log", checkIfExists: false)
+                input[4] = "PXD026600"
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assert process.out.qpx_dataset.size() == 1
+            assert process.out.mudata.size() == 1
+            assert snapshot(
+                process.out.mudata,
+                process.out.versions
+            ).match("stub")
+        }
+    }
+}
diff --git a/modules/bigbio/qpx/tests/main.nf.test.snap b/modules/bigbio/qpx/tests/main.nf.test.snap
@@ -0,0 +1,17 @@
+{
+    "stub": {
+        "content": [
+            [
+                "PXD026600.h5mu:md5,d41d8cd98f00b204e9800998ecf8427e"
+            ],
+            [
+                "versions.yml:md5,cc457dc644e23b74317eaa02eedda495"
+            ]
+        ],
+        "timestamp": "2026-05-05T18:36:46.564300378",
+        "meta": {
+            "nf-test": "0.9.5",
+            "nextflow": "26.04.0"
+        }
+    }
+}
diff --git a/modules/bigbio/qpx/tests/nextflow.config b/modules/bigbio/qpx/tests/nextflow.config
@@ -0,0 +1,10 @@
+process {
+    withName: 'QPX_EXPORT' {
+        ext.args = ''
+    }
+}
+
+params {
+    qpx_version       = 'dev'
+    matrix_qvalue      = 0.05
+}
diff --git a/tests/config/test_data.config b/tests/config/test_data.config
@@ -23,6 +23,10 @@ params {
                 mzml = "https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/quantms-ci-github/onsite/1.mzML"
                 idxml = "https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/quantms-ci-github/onsite/1_consensus_fdr_filter_pep.idXML"
             }
+            qpx {
+                // DIA-NN results for QPX export testing (reuses pmultiqc DIANN example)
+                diann_results = "https://ftp.pride.ebi.ac.uk/pub/databases/pride/resources/proteomes/pmultiqc/example-projects/PXD063291.zip"
+            }
         }
     }
 }