adaptations for snakedeploy

.gitignore

@@ -157,7 +157,7 @@ cython_debug/
 # Built Visual Studio Code Extensions
 *.vsix
 
-workflow/data/reference/*
+workflow/{{reference_path}}/*
 workflow/data/samples/*
 !workflow/data/samples/readme_samples.md
 
@@ -167,3 +167,4 @@ workflow/results/*
 results/*
 .idea/
 config/config.yaml
+data/*

README.md

@@ -36,7 +36,8 @@ source activate wf
 **Samples:**
 
   - Put all sample names in a single column in [`samples.tsv`](/config/samples.tsv).
-  - Put all sample files in `workflow/data/samples/`
+  - Add the data folder to [`config.yaml`](config/config.yaml) where all files to be analysed are located
+    - standard path is set to `data/` 
   - assumed naming convention:
     - sampleName_R1.fastq.gz
     - sampleName_R2.fastq.gz

config/config.yaml

@@ -1,4 +1,8 @@
 # path or URL to sample sheet (TSV format, columns: sample)
 sample_file: config/samples.tsv
+# path to samples
+data_path : data
 # species of the samples and reference genome (dog, human, mouse)
-reference: ""
+# reference file expected to be named as such: species.fa
+reference: "human"
+reference_path: "workflow/results/reference"

workflow/Snakefile

@@ -3,12 +3,17 @@ from pathlib import Path
 
 
 ##### setup config #####
-configfile: "../config/config.yaml"
+configfile: "config/config.yaml"
 
 
-sample_file = Path.joinpath(Path(".."), Path(config["sample_file"]))
+#sample_file = Path.joinpath(Path(".."), Path(config["sample_file"]))
+sample_file = Path(config["sample_file"])
 samples = read_table(sample_file)["sample_name"].tolist()
 
+data_path = Path(config["data_path"])
+
+reference_path = Path(config["reference_path"])
+
 
 ##### load rules #####
 include: "rules/reference.smk"

workflow/rules/align.smk

@@ -1,10 +1,10 @@
 # mapping of the reads to the reference genome using Burrows-Wheeler Aligner
 rule bwa_mem:
     input:
-        amb="data/reference/{reference}.fa.amb",
-        ref="data/reference/{reference}.fa",
-        fastq_r1="data/samples/{sample}_R1.fastq.gz",
-        fastq_r2="data/samples/{sample}_R2.fastq.gz",
+        amb="{{reference_path}}/{reference}.fa.amb",
+        ref="{{reference_path}}/{reference}.fa",
+        fastq_r1="{{data_path}}/{sample}_R1.fastq.gz",
+        fastq_r2="{{data_path}}/{sample}_R2.fastq.gz",
     wildcard_constraints:
         reference="[A-Za-z0-9]+",
     output:
@@ -36,9 +36,9 @@ rule idx_bam:
 # creates index for the reference sequence in fasta format
 rule idx_fasta:
     input:
-        "data/reference/{reference}.fa",
+        "{{reference_path}}/{reference}.fa",
     output:
-        "data/reference/{reference}.fa.fai",
+        "{{reference_path}}/{reference}.fa.fai",
     conda:
         "../envs/samtools.yaml"
     log:

workflow/rules/consensus_sequence.smk

@@ -18,7 +18,7 @@ rule prepare_for_seq:
 # creates the consensus sequence
 rule vcf_to_fasta:
     input:
-        ref="data/reference/{reference}.fa",
+        ref="{{reference_path}}/{reference}.fa",
         vcf="results/sequences/{caller}/{reference}/{sample}.vcf.gz",
         index="results/sequences/{caller}/{reference}/{sample}.vcf.gz.tbi",
     output:

workflow/rules/reference.smk

@@ -1,7 +1,7 @@
 # downloading the mitochondrial reference genome for mouse, dog and human data
 rule get_ref:
     output:
-        "data/reference/{reference}.fa",
+        "{{reference_path}}/{reference}.fa",
     log:
         "logs/{reference}/get_ref.log",
     run:
@@ -22,13 +22,13 @@ rule get_ref:
 # creates the index for the reference genome
 rule bwa_idx:
     input:
-        "data/reference/{reference}.fa",
+        "{{reference_path}}/{reference}.fa",
     output:
-        "data/reference/{reference}.fa.amb",
-        "data/reference/{reference}.fa.ann",
-        "data/reference/{reference}.fa.bwt",
-        "data/reference/{reference}.fa.pac",
-        "data/reference/{reference}.fa.sa",
+        "{{reference_path}}/{reference}.fa.amb",
+        "{{reference_path}}/{reference}.fa.ann",
+        "{{reference_path}}/{reference}.fa.bwt",
+        "{{reference_path}}/{reference}.fa.pac",
+        "{{reference_path}}/{reference}.fa.sa",
     wildcard_constraints:
         reference="[A-Za-z0-9]+",
     conda:

workflow/rules/variants_bcftools.smk

@@ -6,8 +6,8 @@ rule call_variants:
     input:
         bam="results/mapped/{reference}/{sample}.bam",
         bamidx="results/mapped/{reference}/{sample}.bam.bai",
-        ref="data/reference/{reference}.fa",
-        index="data/reference/{reference}.fa.fai",
+        ref="{{reference_path}}/{reference}.fa",
+        index="{{reference_path}}/{reference}.fa.fai",
     output:
         "results/calls_bcftools/{reference}/{sample}.vcf",
     wildcard_constraints:
@@ -24,7 +24,7 @@ rule call_variants:
 rule normalize_variants:
     input:
         vcf="results/calls_bcftools/{reference}/{sample}.vcf.gz",
-        ref="data/reference/{reference}.fa",
+        ref="{{reference_path}}/{reference}.fa",
     output:
         "results/calls_bcftools/{reference}/norm_{sample}.vcf",
     conda:

workflow/rules/variants_mutserve.smk

@@ -10,8 +10,8 @@ rule mutserve:
     input:
         bam="results/mapped/{reference}/{sample}.bam",
         bamidx="results/mapped/{reference}/{sample}.bam.bai",
-        ref="data/reference/{reference}.fa",
-        index="data/reference/{reference}.fa.fai",
+        ref="{{reference_path}}/{reference}.fa",
+        index="{{reference_path}}/{reference}.fa.fai",
     output:
         "results/calls_mutserve/{reference}/{sample}.vcf",
     wildcard_constraints: