fix: config directory

config/README.md

@@ -0,0 +1,86 @@
+# Configuration instructions
+
+See below for an example config file with explanation of each option.
+
+```yaml
+# config/config.yaml
+
+# A list of datasets 
+sequencing_libraries:
+  - name: GSE13073
+    sample_sheet: sample-sheet.csv
+    trimmomatic: >-
+      "ILLUMINACLIP:TruSeq3-PE.fa:1:0:15:2
+       SLIDINGWINDOW:20:22
+       MAXINFO:20:0.6
+       LEADING:22
+       TRAILING:20
+       MINLEN:75"
+    star: >-
+      "--seedSearchStartLmax 30
+       --outFilterMismatchNoverReadLmax 0.04
+       --winAnchorMultimapNmax 40"
+    bamCoverage: "--binSize 50 --normalizeUsing None"
+
+#   - name: ...
+#     sample_sheet: ...
+#     trimmomatic: ...
+#     star: ...
+#     bamCoverage: ...
+
+# 
+globals:
+  # path to reads folder 
+  # NB: ./GSE13073 is expected to exist
+  reads_folder: .
+
+  # path to results folder
+  results_folder: results/
+
+  # path to qc
+  qc_folder: results/qc
+
+  # path to log
+  log_folder: results/log
+
+  # path to references
+  references_folder: results/references
+
+  # temp folder
+  tmp_folder: /tmp
+
+  # path to analysis
+  analysis_folder: results/analysis
+
+# genome informations
+genome:
+  # genome label
+  label: mm10
+
+  # annotation type
+  # can be ensembl, mgi, gencode
+  annotation_type: ensembl
+
+  # URL or path to genome sequence
+  fasta_url: <Genome fasta URL>
+
+  # URL or path to genome annotation file
+  gtf_url: <Genome annotation URL>
+
+  # URL to gtRNAdb zip file
+  gtrnadb_url: <GtRNADb bundle URL>
+
+# Differential expression analysis parameters
+deseq2:
+  # wd
+  working_directory: ../../..  
+
+  # DESeq2 test name, can be Wald or LRT
+  test: Wald
+
+  # name of the column from sample sheet with experimental variable
+  variable: genotype
+
+  # base level from variable column
+  reference_level: wt
+```

config/config.yaml

@@ -29,21 +29,21 @@ genome:
   annotation_type: other
 
   # URL for genome fasta file
-  fasta_url: https://s3.embl.de/boulard/GRCh38.p13.chr22.fa?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=LJ7ZKXIZLLMABJBTY2T0%2F20230713%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20230713T121255Z&X-Amz-Expires=604800&X-Amz-Security-Token=eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJhY2Nlc3NLZXkiOiJMSjdaS1hJWkxMTUFCSkJUWTJUMCIsImV4cCI6MTY4OTI1MTczMSwibGRhcFVzZXIiOiJjbj1GcmFuY2VzY28gVGFiYXJvLGNuPVVzZXJzLGRjPWVtYmwsZGM9b3JnIiwibGRhcFVzZXJuYW1lIjoidGFiYXJvIn0.eOb38Xy0mIPYpbPWETE73njY-knhF-JsgbdxmwcxeWAY9x7RkqhbBqi8V0VGGPQ1tHiQ4O1O2moNi5jT3DmA6Q&X-Amz-SignedHeaders=host&versionId=null&X-Amz-Signature=e7cf5df4cf63c169dcd87290c860b0f027757de363101590c77cdf0151fc58fe
+  fasta_url: https://s3.embl.de/boulard/GRCh38.p13.chr22.fa
 
   # URL for genome GTF file
-  gtf_url: https://s3.embl.de/boulard/gencode.v43.chr22.gtf?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=LJ7ZKXIZLLMABJBTY2T0%2F20230713%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20230713T121233Z&X-Amz-Expires=604800&X-Amz-Security-Token=eyJhbGciOiJIUzUxMiIsInR5cCI6IkpXVCJ9.eyJhY2Nlc3NLZXkiOiJMSjdaS1hJWkxMTUFCSkJUWTJUMCIsImV4cCI6MTY4OTI1MTczMSwibGRhcFVzZXIiOiJjbj1GcmFuY2VzY28gVGFiYXJvLGNuPVVzZXJzLGRjPWVtYmwsZGM9b3JnIiwibGRhcFVzZXJuYW1lIjoidGFiYXJvIn0.eOb38Xy0mIPYpbPWETE73njY-knhF-JsgbdxmwcxeWAY9x7RkqhbBqi8V0VGGPQ1tHiQ4O1O2moNi5jT3DmA6Q&X-Amz-SignedHeaders=host&versionId=null&X-Amz-Signature=c02e1f7dc3d1af80b3d4d215c67d6b4f194e49dbb17c7afb8193d6d5fdb9e9f0
+  gtf_url: https://s3.embl.de/boulard/gencode.v43.chr22.gtf
 
   # Get a RepeatMasker GTF file from UCSC genome browser
   rmsk_path: /home/francesco/Projects/snakemake-rnaseq/tests/test-datasets-rnaseq/references/rmsk.gtf.gz
 
-  # URL to Gene Ontology association file
-  gaf_url: http://current.geneontology.org/annotations/mgi.gaf.gz
-
   # URL to GtRNAdb files
   gtrnadb_url: http://gtrnadb.ucsc.edu/genomes/eukaryota/Hsapi38/hg38-tRNAs.tar.gz
   #gtrnadb_bed: ../../../data/references/tRNA/mm10-tRNAs.bed
 
 deseq2:
   working_directory: ../../..
-  notebook_path: ../../../src/Rmd/deseq2_viz.rmd
+  #notebook_path: ../../../src/Rmd/deseq2_viz.rmd
+  test: Wald
+  reference_level: wt
+  variable: genotype