3.0.1

.github/workflows/main.yaml

@@ -49,9 +49,9 @@ jobs:
         directory: .test
         snakefile: workflow/Snakefile
         args: "--use-conda --show-failed-logs --cores 2 --conda-cleanup-pkgs cache"
-    - name: Test report
-      uses: snakemake/[email protected]
-      with:
-        directory: .test
-        snakefile: workflow/Snakefile
-        args: "--use-conda --cores 2 --report report.zip"
+    # - name: Test report
+    #   uses: snakemake/[email protected]
+    #   with:
+    #     directory: .test
+    #     snakefile: workflow/Snakefile
+    #     args: "--use-conda --cores 2 --report report.zip"

CHANGELOG.md

@@ -1,3 +1,14 @@
+# 3.0.1
+
+## Features:
+
+* Genome schema validation update
+
+## Fixes:
+
+* Report testing removed as long as TBD issue is opened
+* Do not download un-necessary reference files anymore
+
 # 3.0.0
 
 Breaking change: Non canonical chromosomes removed by default

workflow/Snakefile

@@ -32,6 +32,8 @@ rule fair_bowtie2_mapping_target:
         "logs/fair_bowtie2_mapping_target.log",
     benchmark:
         "benchmark/fair_bowtie2_mapping_target.tsv"
+    params:
+        genomes=genomes.copy(),
     conda:
         "envs/python.yaml"
     script:

workflow/rules/common.smk

@@ -385,7 +385,6 @@ def get_fair_bowtie2_mapping_target(
         ],
         "bams": [],
         "bais": [],
-        "genomes": "reference/genomes/fair_genome_indexer.csv",
     }
     sample_iterator = zip(
         samples.sample_id,

workflow/schemas/genomes.schema.yaml

@@ -16,6 +16,50 @@ release:
   type: string
   description: Ensembl release tag
 
+dna_fasta:
+  type: string
+  description: Path to DNA genome sequences (fasta)
+
+dna_fai:
+  type: string
+  description: Path to DNA genome sequence index (fasta.fai)
+
+dna_dict:
+  type: string
+  description: Path to DNA genome sequence dictionary (dict)
+
+transcripts_fasta:
+  type: string
+  description: Path to DNA transcripts sequence (fasta)
+
+cdna_fasta:
+  type: string
+  description: Path to coding DNA genome sequences (fasta)
+
+gtf:
+  type: string
+  description: Path to genome annotation (gtf)
+
+id_to_gene:
+  type: string
+  description: Path to pyroe id_to_gene table (tsv)
+
+t2g:
+  type: string
+  description: Path to transcript_id to gene_id correspondancy (tsv)
+
+dbsnp:
+  type: string
+  description: Path to dbSNP known variants (vcf)
+
+dbsnp_tbi:
+  type: string
+  description: Path to dbSNP variant index table (vcf.tbi)
+
+blacklist:
+  type: string
+  description: Path to blacklisted regions for peak-calling (bed)
+
 required:
   - species
   - build

workflow/scripts/regenerate_genome.py

@@ -63,9 +63,7 @@ def replace_col(df: pandas.DataFrame, column: str, default: str) -> pandas.DataF
 
 
 # Main programm
-genomes: pandas.DataFrame = pandas.read_csv(
-    filepath_or_buffer=snakemake.input.genomes, sep=",", header=0, index_col=None
-)
+genomes: pandas.DataFrame = snakemake.params.genomes
 
 # Bowtie2 index
 genomes = replace_col(