Merge pull request #100 from sanjaynagi/local-snpeffdb-support-18-06-24

add local db support for snpeff and update config names
sanjaynagi · Jun 27, 2024 · 69fe338 · 69fe338
2 parents 715ca49 + 89d648c
commit 69fe338
Show file tree

Hide file tree

Showing 18 changed files with 387 additions and 378 deletions.
diff --git a/.test/config/config_paired_end.yaml b/.test/config/config_paired_end.yaml
@@ -1,9 +1,10 @@
 metadata: config/samples.tsv
+pipeline: cpu
 
 # Dataset name
 dataset: 'Test-GithubActionsCI'
 
-jupyter-book:
+results-jupyterbook:
       activate: True
 
 fastq: 
@@ -18,8 +19,9 @@ reference:
         "resources/reference/Anopheles-gambiae-PEST_TRANSCRIPTS_AgamP4.12-X.fa.gz"
   gff:
         "resources/reference/Anopheles-gambiae-PEST_BASEFEATURES_AgamP4.12-X.gff3"
-  snpeffdb:
-        "Anopheles_gambiae"
+  snpeff:
+      customdb: True
+      dbname: Anopheles_gambiae 
   genes2transcripts:
         "resources/Gene2TranscriptMap.tsv"
 
@@ -35,7 +37,7 @@ contrasts:
 QualityControl:
       fastp-trim:
             activate: True
-      mosdepth:
+      coverage:
             activate: True
       multiqc:
             activate: True 
@@ -45,7 +47,7 @@ DifferentialExpression:                       # Activate differential expression
       gene-level:
             activate: True
       isoform-level:
-            activate: True 
+            activate: False 
 
       progressiveGenes:
             activate: True
@@ -60,7 +62,6 @@ DifferentialExpression:                       # Activate differential expression
 
 VariantAnalysis:
       activate: True
-      caller: freebayes #haplotypecaller # Options: haplotypecaller, freebayes
       ploidy: 10
       chunks: 9 # Number of chunks to split the genome into when parallelising freebayes
 # Number of chunks to split the genome into when parallelising freebayes
@@ -69,15 +70,15 @@ VariantAnalysis:
             activate: True
             missingness: 0.4
 
-      summaryStatistics:
+      geneticDiversity:
             activate: True
             missingness: 0.4
 
       selection:
             activate: True
             missingness: 0.5
             # Do we want to run pbs (Needs three conditions, two more closely related and a slight outgroup)
-            pbs:
+            population-branch-statistic:
                   activate: False
                   contrasts: ['PiriTia_ContTia_Kisumu']
 

diff --git a/.test/config/config_single_end.yaml b/.test/config/config_single_end.yaml
@@ -1,9 +1,10 @@
 metadata: config/samples.tsv
+pipeline: cpu
 
 # Dataset name
 dataset: 'Test-GithubActionsCI'
 
-jupyter-book:
+results-jupyterbook:
       activate: True
 
 fastq: 
@@ -20,8 +21,9 @@ reference:
         "resources/reference/Anopheles-gambiae-PEST_TRANSCRIPTS_AgamP4.12-X.fa.gz"
   gff:
         "resources/reference/Anopheles-gambiae-PEST_BASEFEATURES_AgamP4.12-X.gff3"
-  snpeffdb:
-        "Anopheles_gambiae"
+  snpeff:
+      customdb: False
+      dbname: Anopheles_gambiae 
   genes2transcripts:
         "resources/Gene2TranscriptMap.tsv"
 
@@ -38,7 +40,7 @@ contrasts:
 QualityControl:
       fastp-trim:
             activate: True
-      mosdepth:
+      coverage:
             activate: True
       multiqc:
             activate: True 
@@ -65,7 +67,6 @@ DifferentialExpression:                       # Activate differential expression
 
 VariantAnalysis:
       activate: True
-      caller: freebayes
       ploidy: 10
       chunks: 9 # Number of chunks to split the genome into when parallelising freebayes
 # Number of chunks to split the genome into when parallelising freebayes
@@ -74,15 +75,15 @@ VariantAnalysis:
             activate: True
             missingness: 0.4
 
-      summaryStatistics:
+      geneticDiversity:
             activate: True
             missingness: 0.4
 
       selection:
             activate: True
             missingness: 0.5
             # Do we want to run pbs (Needs three conditions, two more closely related and a slight outgroup)
-            pbs:
+            population-branch-statistic:
                   activate: False
                   contrasts: 
                         - 'PiriTia_ContTia_Kisumu'

diff --git a/config/exampleconfig.yaml b/config/exampleconfig.yaml
@@ -1,5 +1,5 @@
 # RNA-Seq-Pop
-
+pipeline: parabricks  #parabricks or cpu
 metadata: config/samples.tsv                    # samplesheet metadata file
 
 dataset: 'Ag_Bouake'                            # Dataset name: Can be anything, will be used to name some main output files
@@ -27,10 +27,11 @@ reference:
         "resources/reference/Anopheles-gambiae-PEST_TRANSCRIPTS_AgamP4.12.fa"     # Path to transcriptome reference FASTA file
   gff:
         "resources/reference/Anopheles-gambiae-PEST_BASEFEATURES_AgamP4.12.gff3"  # Path to GFF annotation file
-  snpeffdb:
-        "Anopheles_gambiae"                                                       # SNPeff database name
+  snpeff:
+      customdb: False
+      dbname: Anopheles_gambiae                                                        # SNPeff database name
   genes2transcripts:                                                                
-        "resources/exampleGene2TranscriptMap.tsv"                                 # gene names file with gene and transcript names
+        resources/exampleGene2TranscriptMap.tsv                                 # gene names file with gene and transcript names
 
 # Chromosome names for the appropriate species.
 # Please ensure that these correspond exactly to the reference fasta/gff files. Extra unwanted chromosomes (unplaced contigs) can be ignored. 
@@ -48,7 +49,7 @@ contrasts:
 QualityControl:
       fastp-trim:
             activate: False
-      mosdepth:
+      coverage:
             activate: True
       multiqc:
             activate: True 
@@ -75,23 +76,22 @@ DifferentialExpression:
 
 VariantAnalysis:
       activate: True
-      caller: freebayes
       ploidy: 10                          # Ploidy level for freebayes to call at (Generally we are using pooled samples).For diploid organisms, this should be 2 * number of individuals in each pool
       chunks: 9                           # Number of chunks to split each chromosome into when parallelising freebayes. 9 or less is recommended. 
 
       pca:                                # Run PCA on the genotype data
             activate: True
             missingness: 1 
 
-      summaryStatistics:                  # Estimate Population Genetic Summary Statistics such as Dxy, Pi
+      geneticDiversity:                  # Estimate Population Genetic Summary Statistics such as Dxy, Pi
             activate: True
             missingness: 1
 
       selection:                          # Calculate Fst and PBS per gene and in windows
             activate: True
             missingness: 1
 
-            pbs:
+            population-branch-statistic:
                   activate: True          # Activate Population Branch Statistic analysis (Needs three conditions, two closely related and an outgroup) for resistance, do survivors_unexposed_susceptible
                   contrasts: 
                         - 'gambiaePM_gambiaeCont_Kisumu'
@@ -114,7 +114,6 @@ VariantAnalysis:
             #      - "2Ru"
 
 
-
 miscellaneous:
       VariantsOfInterest:                                
             activate: True                             

diff --git a/workflow/Snakefile b/workflow/Snakefile
@@ -23,14 +23,14 @@ welcome(version="v2.0.2")
 
 include: "rules/qc.smk"
 include: "rules/diffexp.smk"
-include: "rules/alignment.smk"
-include: "rules/variantCalling.smk"
-include: "rules/filterAnnotate.smk"
+include: "rules/utilities.smk"
+include: "rules/hisat2-freebayes.smk"
+include: "rules/snpEff.smk"
 include: "rules/variantAnalysis.smk"
 include: "rules/jupyter-book.smk"
 
-if config['VariantAnalysis']['caller'] == 'haplotypecaller':
-    include: "rules/parabricks-gpu.smk"
+if config['pipeline'] == 'parabricks':
+    include: "rules/star-haplotypecaller.smk"
 
 rule all:
     input:

diff --git a/workflow/notebooks/windowed-selection.ipynb b/workflow/notebooks/windowed-selection.ipynb
@@ -109,7 +109,7 @@
     "comparisons = comparisons.contrast.str.split(\"_\", expand=True)\n",
     "comparisons.columns = ['sus', 'res']\n",
     "comparisons = [list(row) for i,row in comparisons.iterrows()]\n",
-    "pbscomps = config_params[\"VariantAnalysis\"]['selection']['pbs']['contrasts']\n",
+    "pbscomps = config_params[\"VariantAnalysis\"]['selection']['population-branch-statistic']['contrasts']\n",
     "\n",
     "for i, contig in enumerate(contigs):\n",
     "\n",

diff --git a/workflow/rules/alignment.smk b/workflow/rules/alignment.smk