Merge pull request #116 from daichengxin/dev

update meta.nf
bigbio · Mar 15, 2022 · 00cf5c9 · 00cf5c9
2 parents 6c436fe + 5c438b7
commit 00cf5c9
Show file tree

Hide file tree

Showing 6 changed files with 62 additions and 101 deletions.
diff --git a/modules/local/convert2msstats/main.nf b/modules/local/convert2msstats/main.nf
@@ -1,9 +1,9 @@
 process CONVERT2MSSTATS {
     label 'process_low'
 
-    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
+    conda (params.enable_conda ? "conda-forge::pandas_schema bioconda::sdrf-pipelines=0.0.21" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/python:3.8.3"
+        container "https://depot.galaxyproject.org/singularity/sdrf-pipelines:0.0.21--pyhdfd78af_0"
     } else {
         container "quay.io/biocontainers/sdrf-pipelines:0.0.21--pyhdfd78af_0"
     }

diff --git a/modules/local/convert2msstats/meta.yml b/modules/local/convert2msstats/meta.yml
@@ -1,45 +1,27 @@
-name: pmultiqc
-description: A library for proteomics QC report based on MultiQC framework.
+name: convert2msstats
+description: A module to convert DIA report files to MSstats
 keywords:
-    - MultiQC
-    - QC
-    - Proteomics
+    - DIA-NN
+    - conversion
+    - MSstats
 tools:
-    - pmultiqc:
+    - custom:
         description: |
-            A library for proteomics QC report based on MultiQC framework.
-        homepage: https://github.com/bigbio/pmultiqc/
-        documentation: https://github.com/bigbio/pmultiqc/
+            A custom module for DIA-NN report file conversion.
+        homepage: https://github.com/bigbio/quantms
+        documentation: https://github.com/bigbio/quantms/tree/readthedocs
 input:
-    - expdesign:
-        type: file
-        description: experimental design file in openms style
-    - mzmls:
-        type: dir
-        description:  mzML files directory
-    - quantms_results:
-        type: dir
-        description: the directory of quantms results including out.mzTab/out_msstats.csv
-    - raw_ids:
-        type: dir
-        description: idXML files directory
-output:
     - report:
         type: file
-        description: MultiQC report file
-        pattern: "multiqc_report.html"
-    - quantmsdb:
+        description: DIA-NN main report file
+    - exp_design:
         type: file
-        description: Sqlite3 database file stored protein psm and quantificaiton information
-        pattern: "*.db"
-    - data:
-        type: dir
-        description: MultiQC data dir
-        pattern: "multiqc_data"
-    - plots:
+        description:  An experimental design file including Sample and replicates column et al.
+output:
+    - out_msstats:
         type: file
-        description: Plots created by MultiQC
-        pattern: "*_data"
+        description: MSstats input file
+        pattern: "*.csv"
     - version:
         type: file
         description: File containing software version

diff --git a/modules/local/diann/meta.yml b/modules/local/diann/meta.yml
@@ -1,45 +1,38 @@
-name: pmultiqc
-description: A library for proteomics QC report based on MultiQC framework.
+name: diann
+description: A module for DIA library free analysis based on DIA-NN.
 keywords:
-    - MultiQC
-    - QC
-    - Proteomics
+    - DIA-NN
+    - library free
+    - DIA
 tools:
-    - pmultiqc:
+    - DIA-NN:
         description: |
-            A library for proteomics QC report based on MultiQC framework.
-        homepage: https://github.com/bigbio/pmultiqc/
-        documentation: https://github.com/bigbio/pmultiqc/
+            DIA-NN - a universal software for data-independent acquisition (DIA) proteomics data processing by Demichev.
+        homepage: https://github.com/vdemichev/DiaNN
+        documentation: https://github.com/vdemichev/DiaNN
 input:
-    - expdesign:
+    - fasta:
         type: file
-        description: experimental design file in openms style
-    - mzmls:
+        description: FASTA sequence databases
+    - mzMLs:
         type: dir
         description:  mzML files directory
-    - quantms_results:
+    - cfg:
         type: dir
-        description: the directory of quantms results including out.mzTab/out_msstats.csv
-    - raw_ids:
-        type: dir
-        description: idXML files directory
+        description: specifies a file to load options/commands from.
 output:
     - report:
         type: file
-        description: MultiQC report file
-        pattern: "multiqc_report.html"
-    - quantmsdb:
+        description: Main report file,a text table containing precursor and protein IDs, as well as plenty of associated information. Most column names are self-explanatory.
+        pattern: "report.tsv"
+    - report_stat:
         type: file
-        description: Sqlite3 database file stored protein psm and quantificaiton information
-        pattern: "*.db"
-    - data:
-        type: dir
-        description: MultiQC data dir
-        pattern: "multiqc_data"
-    - plots:
+        description: Contains a number of QC metrics which can be used for data filtering, e.g. to exclude failed runs, or as a readout for method optimization.
+        pattern: "report.stats.tsv"
+    - log:
         type: file
-        description: Plots created by MultiQC
-        pattern: "*_data"
+        description: DIA-NN log file
+        pattern: "report.log.txt"
     - version:
         type: file
         description: File containing software version

diff --git a/modules/local/generate_diann_cfg/main.nf b/modules/local/generate_diann_cfg/main.nf
@@ -3,17 +3,16 @@ process GENERATE_DIANN_CFG {
 
 
     //TODO What images include click or use sys.args rather than click
-    conda (params.enable_conda ? "conda-forge::python=3.8.3" : null)
+    conda (params.enable_conda ? "conda-forge::pandas_schema bioconda::sdrf-pipelines=0.0.21" : null)
     if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
-        container "https://depot.galaxyproject.org/singularity/python:3.8.3"
+        container "https://depot.galaxyproject.org/singularity/sdrf-pipelines:0.0.21--pyhdfd78af_0"
     } else {
         container "quay.io/biocontainers/sdrf-pipelines:0.0.21--pyhdfd78af_0"
     }
 
     input:
     val(meta)
     path(mzmls)
-    path(exp_design)
 
     output:
     path("*.mzML"), includeInputs: true, emit: mzmls_for_diann

diff --git a/modules/local/generate_diann_cfg/meta.yml b/modules/local/generate_diann_cfg/meta.yml
@@ -1,45 +1,32 @@
-name: pmultiqc
-description: A library for proteomics QC report based on MultiQC framework.
+name: generate_diann_cfg
+description: A module to generate DIA-NN configure file.
 keywords:
-    - MultiQC
-    - QC
-    - Proteomics
+    - configure
+    - DIA-NN
 tools:
-    - pmultiqc:
+    - custom:
         description: |
-            A library for proteomics QC report based on MultiQC framework.
-        homepage: https://github.com/bigbio/pmultiqc/
-        documentation: https://github.com/bigbio/pmultiqc/
+            A custom module for DIA-NN configure file.
+        homepage: https://github.com/bigbio/quantms
+        documentation: https://github.com/bigbio/quantms/tree/readthedocs
 input:
-    - expdesign:
-        type: file
-        description: experimental design file in openms style
+    - meta:
+        type: map
+        description: Groovy Map containing sample information
     - mzmls:
         type: dir
         description:  mzML files directory
-    - quantms_results:
-        type: dir
-        description: the directory of quantms results including out.mzTab/out_msstats.csv
-    - raw_ids:
-        type: dir
-        description: idXML files directory
-output:
-    - report:
+    - exp_design:
         type: file
-        description: MultiQC report file
-        pattern: "multiqc_report.html"
-    - quantmsdb:
-        type: file
-        description: Sqlite3 database file stored protein psm and quantificaiton information
-        pattern: "*.db"
-    - data:
+        description: An experimental design file including Sample and replicates column et al.
+output:
+    - mzmls_for_diann:
         type: dir
-        description: MultiQC data dir
-        pattern: "multiqc_data"
-    - plots:
+        description:  mzML files directory
+    - diann_cfg:
         type: file
-        description: Plots created by MultiQC
-        pattern: "*_data"
+        description: DIA-NN configure file
+        pattern: "*.cfg"
     - version:
         type: file
         description: File containing software version

diff --git a/workflows/dia.nf b/workflows/dia.nf
@@ -40,7 +40,7 @@ workflow DIA {
                                 }
                             .set { result }
 
-    DIANNCFG(result.meta.collect(), result.mzml.collect(), ch_expdesign)
+    DIANNCFG(result.meta.collect(), result.mzml.collect())
     ch_software_versions = ch_software_versions.mix(DIANNCFG.out.version.ifEmpty(null))
 
     DIANN(DIANNCFG.out.mzmls_for_diann.collect(), Channel.fromPath(params.database), DIANNCFG.out.diann_cfg)