NF_MAAgilent1ch: address #99

Author: cyouh95

Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/main.nf

@@ -97,13 +97,11 @@ workflow {
     ch_software_versions = Channel.value(nf_version)
     AGILE1CH.out.versions | map{ it -> it.text } | mix(ch_software_versions) | set{ch_software_versions}
     VV_AGILE1CH.out.versions | map{ it -> it.text } | mix(ch_software_versions) | set{ch_software_versions}
-    ch_software_versions | unique 
-                         | collectFile(
-                            newLine: true, 
-                            sort: true,
-                            cache: false
-                            )
-                         | GENERATE_SOFTWARE_TABLE
+
+    GENERATE_SOFTWARE_TABLE(
+      ch_software_versions | unique | collectFile(newLine: true, sort: true, cache: false),
+      ch_runsheet | splitCsv(header: true, quote: '"') | first | map{ row -> row['Array Data File Name'] }
+    )
 
     emit:
       meta = ch_meta 

Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/modules/GENERATE_SOFTWARE_TABLE/main.nf

@@ -5,12 +5,13 @@ process GENERATE_SOFTWARE_TABLE {
 
   input:
     path("software_versions.yaml")
+    val(filename)
 
   output:
     path("software_versions_GLmicroarray.md")
 
   script:
     """
-    SoftwareYamlToMarkdownTable.py software_versions.yaml
+    SoftwareYamlToMarkdownTable.py software_versions.yaml \"$filename\"
     """
 }

Microarray/Agilent_1-channel/Workflow_Documentation/NF_MAAgilent1ch/workflow_code/modules/GENERATE_SOFTWARE_TABLE/resources/usr/bin/SoftwareYamlToMarkdownTable.py

@@ -41,14 +41,19 @@
 
 @click.command()
 @click.argument("input_yaml", type=click.Path(exists=True))
-def yamlToMarkdown(input_yaml: Path):
+@click.argument("filename")
+def yamlToMarkdown(input_yaml: Path, filename: str):
     """ Using a software versions """
     with open(input_yaml, "r") as f:
         data = yaml.safe_load(f)
 
     data.extend(ASSUMED_SOFTWARE)
     df = pd.DataFrame(data)
 
+    # If data files are not compressed, won't use R.utils to unzip them during processing
+    if not filename.endswith('.gz'):
+        AGILENT_SOFTWARE_DPPD.remove('r.utils')
+
     # Filter to direct software used (i.e. exclude dependencies of the software)
     df = df.loc[df["name"].str.lower().isin(AGILENT_SOFTWARE_DPPD)]