Merge pull request #95 from nf-core/dev

Release 1.1.1

.github/PULL_REQUEST_TEMPLATE.md

@@ -15,7 +15,8 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/quan
 
 - [ ] This comment contains a description of changes (with reason).
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
-- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/quantms/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/quantms _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
+- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/quantms/tree/master/.github/CONTRIBUTING.md)
+- [ ] If necessary, also make a PR on the nf-core/quantms _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core lint`).
 - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).
 - [ ] Usage Documentation in `docs/usage.md` is updated.

.github/workflows/ci.yml

@@ -52,22 +52,14 @@ jobs:
         with:
           version: "${{ matrix.NXF_VER }}"
 
-      - name: Install mamba
+      - name: Install micromamba
         if: matrix.exec_profile == 'conda'
-        uses: conda-incubator/setup-miniconda@v2
-        with:
-          python-version: 3.9
-          mamba-version: "*"
-          channels: conda-forge,defaults
-
-      # - name: Install micromamba as mamba
-      #   if: matrix.exec_profile == 'conda'
-      #   run: |
-      #     wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba
-      #     mv bin/micromamba bin/mamba
-      #     echo "$(pwd)/bin" >> $GITHUB_PATH
-      #     echo "$(pwd)/mamba/bin" >> $GITHUB_PATH
-      #     ./bin/mamba shell init -s bash -p ./mamba
+        run: |
+          wget -qO- https://micromamba.snakepit.net/api/micromamba/linux-64/latest | tar -xvj bin/micromamba
+          echo "$(pwd)/bin" >> $GITHUB_PATH
+          echo "$(pwd)/micromamba/bin" >> $GITHUB_PATH
+          ./bin/micromamba shell init -s bash -p ./micromamba
+          echo $'channels:\n  - conda-forge\n  - bioconda\n  - defaults\nuse_lockfiles: false' >> ~/.mambarc
 
       - name: Run pipeline with test data
         if: matrix.exec_profile != 'conda'
@@ -82,7 +74,7 @@ jobs:
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile $TEST_PROFILE,$EXEC_PROFILE,mambaci --outdir ${TEST_PROFILE}_${EXEC_PROFILE}_results
+          nextflow run ${GITHUB_WORKSPACE} -profile $TEST_PROFILE,micromamba --outdir ${TEST_PROFILE}_${EXEC_PROFILE}_results
       - name: Gather failed logs
         if: failure() || cancelled()
         run: |

.nf-core.yml

@@ -4,3 +4,5 @@ lint:
     - conf/igenomes.config
     - conf/test_full.config
     - conf/test.config
+  files_unchanged:
+    - .github/PULL_REQUEST_TEMPLATE.md

CHANGELOG.md

@@ -3,6 +3,21 @@
 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).
 
+## [1.1.1] nfcore/quantms - [TBD] - Berlin-Bern
+
+### `Added`
+
+- [#92](https://github.com/nf-core/quantms/pull/92) Improved output docs for mzTab
+- [#91](https://github.com/nf-core/quantms/pull/91) Added dev profile for nightly versions of OpenMS tools
+
+### `Changed`
+
+- [#88](https://github.com/nf-core/quantms/pull/88) Updated Comet version to latest release (2023010)
+
+### `Fixed`
+
+- [#93](https://github.com/nf-core/quantms/pull/93) Fixed bug in docker vs. singularity container logic in some processes.
+
 ## [1.1.0] nfcore/quantms - [03/20/2023] - Berlin
 
 - Bugfixes and speed increases in the OpenMS tools due to version update to 2.9.1

README.md

@@ -1,6 +1,6 @@
 # ![nf-core/quantms](docs/images/nf-core-quantms_logo_light.png#gh-light-mode-only) ![nf-core/quantms](docs/images/nf-core-quantms_logo_dark.png#gh-dark-mode-only)
 
-[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/quantms/results)[![Cite with Zenodo](https://img.shields.io/badge/DOI-10.5281/zenodo.7754149-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7754149)
+[![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/quantms/results)[![Cite with Zenodo](https://img.shields.io/badge/DOI-10.5281/zenodo.7754148-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7754148)
 
 [![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.10.1-23aa62.svg)](https://www.nextflow.io/)
 [![run with conda](https://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
@@ -127,10 +127,7 @@ For further information or help, don't hesitate to get in touch on the [Slack `#
 
 ## Citations
 
-<!-- TODO nf-core: Add citation for pipeline after first release. Uncomment lines below and update Zenodo doi and badge at the top of this file. -->
-<!-- If you use  nf-core/quantms for your analysis, please cite it using the following doi: [10.5281/zenodo.XXXXXX](https://doi.org/10.5281/zenodo.XXXXXX) -->
-
-<!-- TODO nf-core: Add bibliography of tools and data used in your pipeline -->
+If you use nf-core/quantms for your analysis, please cite it using the following doi: [10.5281/zenodo.7754148](https://doi.org/10.5281/zenodo.7754148)
 
 An extensive list of references for the tools used by the pipeline can be found in the [`CITATIONS.md`](CITATIONS.md) file.
 

conf/dev.config

@@ -2,11 +2,11 @@
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     Nextflow config file for running with nightly dev. containers (mainly for OpenMS)
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-    Only overwrites the container. E.g. uses the OpenMS nightly executable and thirdparty
-    containers. TODO Currently does nothing, we need to set it up.
+    Only overwrites the used containers and conda packages. E.g., uses the OpenMS nightly
+    executable and thirdparty containers.
 
     Use as follows:
-        nextflow run nf-core/quantms -profile test,<docker/singularity> [--outdir <OUTDIR>]
+        nextflow run nf-core/quantms -profile dev,<docker/singularity> [--outdir <OUTDIR>]
 
 -------------------------------------------------------------------------------------------
 */
@@ -15,3 +15,10 @@ params {
     config_profile_name = 'Development profile'
     config_profile_description = 'To use nightly development containers'
 }
+
+withLabel: openms {
+    conda = "openms::openms"
+    container = "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'ghcr.io/openms/openms-executables-sif:latest' :
+        'ghcr.io/openms/openms-executables:latest' }"
+}

docs/output.md

@@ -135,6 +135,51 @@ The mzTab is exported for all three workflows DDA-LFQ, DDA-ISO and DIA-LFQ. It i
 ready for submission to [PRIDE](https://www.ebi.ac.uk/pride/). It contains both identifications (only those responsible for a quantification),
 quantities and some metadata about both the experiment and the quantification.
 
+mzTab is a multi-section TSV file where the first column is a section identifier:
+
+- MTD: Metadata
+- PRH: Protein header line
+- PRT: Protein entry line
+- PEH: Peptide header line
+- PEP: Peptide entry line
+- PSH: Peptide-spectrum match header
+- PSM: Peptide-spectrum match entry line
+
+Some explanations for optional ("opt\_") columns:
+
+PRT section:
+
+- opt_global_Posterior_Probability_score: As opposed to the best_search_engine_score columns (which usually represent an FDR [consult the MTD section]) this specifies the posterior probability for a protein or protein group as calculated by protein inference.
+- opt_global_nr_found_peptides: The number of found peptides for the protein (group). By default this counts unmodified peptide sequences (TODO double-check)
+- opt_global_cv_PRIDE:0000303_decoy_hit: If this was a real target hit or a decoy entry added artificially to the protein database.
+- opt_global_result_type:
+  - single_protein: A protein that is uniquely distinguishable from others. Note: this could be a subsumable protein.
+  - indistinguishable_protein_group: A group of proteins that share exactly the same set of observed peptides.
+  - protein_details: A dummy entry for every protein belonging to either of the two classes above. In case of an indistinguishable group, it would otherwise not be possible to report unique sequence coverage information about each member of the group. Do not use these entries for quantitative information or scoring as they will be "null/empty". They shall only be used to extract auxiliary information if required.
+
+PEP section:
+
+- opt_global_cv_MS:1000889_peptidoform_sequence: The sequence of the best explanation of this feature/spectrum but with modifications.
+- opt_global_feature_id: A unique ID assigned by internal algorithms. E.g., for looking up additional information in the PSM section or other output files like consensusXML
+- opt_global_SpecEValue_score: Spectral E-Value for the best match for this peptide (from the MSGF search engine)
+- opt_global_q-value(\_score): Experiment-wide q-value of the best match. The exact interpretation depends on the FDR/q-value settings of the pipeline.
+- opt_global_cv_MS:1002217_decoy_peptide: If the peptide from the best match was a target peptide from the digest of the input protein database, or an annotated or generated decoy.
+- opt_global_mass_to_charge_study_variable[n]: The m/z of the precursor (isobaric) or the feature (LFQ) in study_variable (= usually sample) n.
+- opt_global_retention_time_study_variable[n]: The retention time in seconds of the precursor (isobaric) or the feature (LFQ) in study_variable (= usually sample) n.
+
+PSM section:
+
+- opt_global_FFId_category: Currently always "internal".
+- opt_global_feature_id: A unique ID assigned by internal algorithms. E.g., for looking up additional information in the PEP section or other output files like consensusXML.
+- opt_global_map_index: May be ignored. Should be a one-to-one correspondence between "ms_run" in which this PSM was found and the value in this column + 1.
+- opt_global_spectrum_reference: May be ignored. Should be a one-to-one correspondence between the second part of the spectra_ref column and this column.
+- opt_global_cv_MS:1000889_peptidoform_sequence: The sequence for this match including modifications.
+- opt_global_SpecEValue_score: Spectral E-Value for this match (from the MSGF search engine)
+- opt_global_q-value(\_score): Experiment-wide q-value. The exact interpretation depends on the FDR/q-value settings of the pipeline.
+- opt_global_cv_MS:1002217_decoy_peptide: If the peptide from this match was a target peptide from the digest of the input protein database, or an annotated or generated decoy.
+
+Note that columns with scores heavily depend on the chosen search engines and rescoring tools and are better looked up in the documentation of the underlying tool.
+
 #### MSstats-processed mzTab
 
 If MSstats was enabled, the pipeline additionally exports an mzTab file where the quantities are replaced with the normalized and imputed ones from

modules/local/openms/proteinquantifier/main.nf

@@ -3,10 +3,9 @@ process PROTEINQUANTIFIER {
     label 'process_medium'
 
     conda "bioconda::openms=2.9.1"
-    container "${ workflow.containerEngine == 'docker' && !task.ext.singularity_pull_docker_container ?
-        'quay.io/biocontainers/openms:2.9.1--h135471a_0' :
-        'https://depot.galaxyproject.org/singularity/openms:2.9.1--h135471a_0'
-        }"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/openms:2.9.1--h135471a_0' :
+        'quay.io/biocontainers/openms:2.9.1--h135471a_0' }"
 
     input:
     path epi_filt_resolve

modules/local/openms/proteomicslfq/main.nf

@@ -3,10 +3,9 @@ process PROTEOMICSLFQ {
     label 'process_high'
 
     conda "bioconda::openms=2.9.1"
-    container "${ workflow.containerEngine == 'docker' && !task.ext.singularity_pull_docker_container ?
-        'quay.io/biocontainers/openms:2.9.1--h135471a_0' :
-        'https://depot.galaxyproject.org/singularity/openms:2.9.1--h135471a_0'
-        }"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/openms:2.9.1--h135471a_0' :
+        'quay.io/biocontainers/openms:2.9.1--h135471a_0' }"
 
     input:
     path(mzmls)

modules/local/openms/thirdparty/luciphoradapter/main.nf

@@ -4,8 +4,8 @@ process LUCIPHORADAPTER {
 
     conda "bioconda::openms-thirdparty=2.9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_0' :
-        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_1' :
+        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_1' }"
 
     input:
     tuple val(meta), path(mzml_file), path(id_file)

modules/local/openms/thirdparty/percolator/main.nf

@@ -4,8 +4,8 @@ process PERCOLATOR {
 
     conda "bioconda::openms-thirdparty=2.9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_0' :
-        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_1' :
+        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_1' }"
 
     input:
     tuple val(meta), path(id_file)

modules/local/openms/thirdparty/searchenginecomet/main.nf

@@ -4,8 +4,8 @@ process SEARCHENGINECOMET {
 
     conda "bioconda::openms-thirdparty=2.9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_0' :
-        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_1' :
+        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_1' }"
 
     input:
     tuple val(meta), file(mzml_file), file(database)

modules/local/openms/thirdparty/searchenginemsgf/main.nf

@@ -4,8 +4,8 @@ process SEARCHENGINEMSGF {
 
     conda "bioconda::openms-thirdparty=2.9.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_0' :
-        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/openms-thirdparty:2.9.1--h9ee0642_1' :
+        'quay.io/biocontainers/openms-thirdparty:2.9.1--h9ee0642_1' }"
 
     input:
     tuple val(meta),  file(mzml_file), file(database)

nextflow.config

@@ -243,9 +243,9 @@ profiles {
         conda.enabled          = true
         docker.enabled         = false
         singularity.enabled    = false
-        conda.createTimeout = '1 h'
-        conda.useMamba = true
-        process.executor = 'lsf'
+        conda.createTimeout    = '1 h'
+        conda.useMamba         = true
+        process.executor       = 'lsf'
     }
     conda {
         conda.enabled          = true
@@ -256,6 +256,16 @@ profiles {
         charliecloud.enabled   = false
         conda.useMamba    = true
     }
+    micromamba {
+        conda.enabled          = true
+        conda.useMicromamba    = true
+        conda.createTimeout    = '1 h'
+        docker.enabled         = false
+        singularity.enabled    = false
+        podman.enabled         = false
+        shifter.enabled        = false
+        charliecloud.enabled   = false
+    }
     mamba {
         conda.enabled          = true
         conda.useMamba         = true
@@ -366,8 +376,8 @@ manifest {
     description     = """Quantitative Mass Spectrometry nf-core workflow"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=22.10.1'
-    version         = '1.1.0'
-    doi             = ''
+    version         = '1.1.1'
+    doi             = '10.5281/zenodo.7754148'
 }
 
 // Load modules.config for DSL2 module specific options