Merge pull request #17 from snakemake-workflows/feat/allow-for-all-ca…

…ps-platform-spec

feat: allow for all caps platform spec

.github/workflows/main.yaml

@@ -55,4 +55,4 @@ jobs:
       with:
         directory: .test
         snakefile: workflow/Snakefile
-        args: "--configfile .test/config/config.yaml --report report.zip"
+        args: "--configfile .test/config/config.yaml --cores 2 --report report.zip"

workflow/rules/annotate.smk

@@ -26,9 +26,11 @@ rule cyrcular_annotate_graph:
         graph="results/calling/graphs/{group}.graph",
         gene_annotation="resources/gene_annotation.gff3.gz",
         regulatory_annotation="resources/regulatory_annotation.gff3.gz",
-        repeat_annotation=lambda wc: "resources/repeat_masker.fa.out.gz"
-        if config["reference"].get("repeat_masker_download_link", "")
-        else "",
+        repeat_annotation=lambda wc: (
+            "resources/repeat_masker.fa.out.gz"
+            if config["reference"].get("repeat_masker_download_link", "")
+            else ""
+        ),
     output:
         annotated="results/calling/graphs/{group}.annotated.graph",
     threads: 1
@@ -39,9 +41,11 @@ rule cyrcular_annotate_graph:
     conda:
         "../envs/cyrcular.yaml"
     params:
-        repeat_annotation=lambda wc, input: f"  --repeat-annotation {input.repeat_annotation} "
-        if config["reference"].get("repeat_masker_download_link", "")
-        else "",
+        repeat_annotation=lambda wc, input: (
+            f"  --repeat-annotation {input.repeat_annotation} "
+            if config["reference"].get("repeat_masker_download_link", "")
+            else ""
+        ),
     shell:
         "cyrcular graph annotate "
         "  --reference {input.reference} "

workflow/rules/common.smk

@@ -74,7 +74,7 @@ def get_all_input(wildcards):
 
 
 def pairhmm_mode(wildcards):
-    if samples.loc[wildcards.sample]["platform"] == "nanopore":
+    if samples.loc[wildcards.sample]["platform"].lower() == "nanopore":
         mode = "homopolymer"
     else:
         mode = "exact"
@@ -88,17 +88,23 @@ def get_group_candidates(wildcards):
     scenario = scenario_name(wildcards)
     if scenario == "nanopore_only":
         sample = list(
-            samples.query(f"group == '{group}' & platform == 'nanopore'")["sample_name"]
+            samples.query(f"group == '{group}' & platform.str.lower() == 'nanopore'")[
+                "sample_name"
+            ]
         )[0]
         return f"results/calling/candidate-calls/{sample}.{{scatteritem}}.bcf"
     elif scenario == "illumina_only":
         sample = list(
-            samples.query(f"group == '{group}' & platform == 'illumina'")["sample_name"]
+            samples.query(f"group == '{group}' & platform.str.lower() == 'illumina'")[
+                "sample_name"
+            ]
         )[0]
         return f"results/calling/candidate-calls/{sample}.{{scatteritem}}.bcf"
     elif scenario == "nanopore_with_illumina_support":
         sample = list(
-            samples.query(f"group == '{group}' & platform == 'nanopore'")["sample_name"]
+            samples.query(f"group == '{group}' & platform.str.lower() == 'nanopore'")[
+                "sample_name"
+            ]
         )[0]
         return f"results/calling/candidate-calls/{sample}.{{scatteritem}}.bcf"
     else:
@@ -128,17 +134,21 @@ def get_observations(wildcards):
 
     observations = []
 
-    has_nanopore = len(s.query("platform == 'nanopore'")["sample_name"]) > 0
-    has_illumina = len(s.query("platform == 'illumina'")["sample_name"]) > 0
+    has_nanopore = len(s.query("platform.str.lower() == 'nanopore'")["sample_name"]) > 0
+    has_illumina = len(s.query("platform.str.lower() == 'illumina'")["sample_name"]) > 0
 
     if has_nanopore:
-        for sample_nanopore in list(s.query("platform == 'nanopore'")["sample_name"]):
+        for sample_nanopore in list(
+            s.query("platform.str.lower() == 'nanopore'")["sample_name"]
+        ):
             observations.append(
                 f"results/calling/calls/observations/{sample_nanopore}.{{scatteritem}}.bcf"
             )
 
     if has_illumina:
-        for sample_illumina in list(s.query("platform == 'illumina'")["sample_name"]):
+        for sample_illumina in list(
+            s.query("platform.str.lower() == 'illumina'")["sample_name"]
+        ):
             observations.append(
                 f"results/calling/calls/observations/{sample_illumina}.{{scatteritem}}.bcf"
             )
@@ -150,17 +160,17 @@ def scenario_name(wildcards):
     s = samples.query(f"group == '{wildcards.group}'")
     num_samples_in_group = len(s)
     if num_samples_in_group == 1:
-        if "illumina" in set(s["platform"]):
+        if "illumina" in set(s["platform"].str.lower()):
             return "illumina_only"
-        elif "nanopore" in set(s["platform"]):
+        elif "nanopore" in set(s["platform"].str.lower()):
             return "nanopore_only"
         else:
-            platforms = ", ".join(set(s["platform"]))
+            platforms = ", ".join(set(s["platform"].str.lower()))
             raise ValueError(
                 f"Single sample scenario not defined for platforms {platforms}"
             )
     elif num_samples_in_group == 2:
-        if len(set(s["platform"]) - {"illumina", "nanopore"}) == 0:
+        if len(set(s["platform"].str.lower()) - {"illumina", "nanopore"}) == 0:
             return "nanopore_with_illumina_support"
         else:
             raise ValueError(
@@ -191,9 +201,9 @@ def get_scenario(wildcards):
 
 
 def get_minimap2_mapping_params(wildcards):
-    if samples.loc[wildcards.sample]["platform"] == "nanopore":
+    if samples.loc[wildcards.sample]["platform"].lower() == "nanopore":
         return "-x map-ont"
-    elif samples.loc[wildcards.sample]["platform"] == "illumina":
+    elif samples.loc[wildcards.sample]["platform"].lower() == "illumina":
         return "-x sr"
     else:
         return ""

workflow/rules/map.smk

@@ -11,7 +11,7 @@ rule minimap2_bam:
     params:
         extra=get_minimap2_mapping_params,  # optional
         sorting="coordinate",  # optional: Enable sorting. Possible values: 'none', 'queryname' or 'coordinate'
-        sort_extra=lambda wc, threads: f"-@ {min(threads, 4)}",  # optional: extra arguments for samtools/picard
+        sort_extra=lambda wc, threads: f"-@ {min(threads , 4)}",  # optional: extra arguments for samtools/picard
     threads: workflow.cores // 2
     wrapper:
         "v1.25.0/bio/minimap2/aligner"
@@ -27,9 +27,11 @@ rule merge_fastqs:
     wildcard_constraints:
         read="single|R1|R2",
     params:
-        cmd=lambda wc: "pigz -dc"
-        if (any(map(lambda f: f.endswith(".gz"), get_fastqs(wc))))
-        else "cat",
+        cmd=lambda wc: (
+            "pigz -dc"
+            if (any(map(lambda f: f.endswith(".gz"), get_fastqs(wc))))
+            else "cat"
+        ),
     conda:
         "../envs/pigz.yaml"
     shell:

workflow/rules/ref.smk

@@ -45,8 +45,6 @@ rule minimap2_index:
         ),
     log:
         "logs/minimap2_index/genome.log",
-    benchmark:
-        "benchmarks/minimap2_index/genome.txt"
     params:
         extra="",  # optional additional args
     cache: True
@@ -65,8 +63,6 @@ rule download_regulatory_annotation:
         "logs/download_regulatory_annotation.log",
     params:
         release=config["reference"].get("release", "107"),
-    benchmark:
-        "benchmarks/download_regulatory_annotation.txt"
     cache: "omit-software"  # save space and time with between workflow caching (see docs)
     conda:
         "../envs/wget.yaml"
@@ -81,8 +77,6 @@ rule download_repeatmasker_annotation:
         "logs/download_repeatmasker_annotation.log",
     params:
         download_link=config["reference"].get("repeat_masker_download_link", ""),
-    benchmark:
-        "benchmarks/download_repeatmasker_annotation.txt"
     cache: "omit-software"  # save space and time with between workflow caching (see docs)
     conda:
         "../envs/wget.yaml"

workflow/schemas/samples.schema.yaml

@@ -14,7 +14,9 @@ properties:
     type: string
     enum:
       - "illumina"
+      - "ILLUMINA"
       - "nanopore"
+      - "NANOPORE"
     description: sequencing platform