Merge pull request #133 from CCBR/refactor-go-enrich

feat: add parameter to make long-running rules optional

.test/config_lint.yaml

@@ -11,10 +11,12 @@ samplemanifest: "/opt2/.test/samples.test_lintr.tsv"
 # User parameters
 #####################################################################################
 # run sample contrasts
-run_contrasts: "Y" # Y or N
+run_contrasts: true
 contrasts: "/opt2/.test/contrasts.test.tsv"  # run_contrasts needs to be "Y"
-contrasts_fdr_cutoff: "0.05"
-contrasts_lfc_cutoff: "0.59" # FC of 1.5
+contrasts_fdr_cutoff: 0.05
+contrasts_lfc_cutoff: 0.59 # FC of 1.5
+run_go_enrichment: true
+run_rose: true
 
 # reference
 genome: "hg38"    # currently supports hg38, hg19 and mm10. Custom genome can be added with appropriate additions to "reference" section below.

CHANGELOG.md

@@ -7,7 +7,11 @@
     - Fixes FDR cutoff misassigned to log2FC cutoff.
     - Fixes `no_dedup` variable names in library normalization scripts.
 - Containerize rules that require R (`deseq`, `go_enrichment`, and `spikein_assessment`) to fix installation issues with common R library path. (#129, @kelly-sovacool)
-    The `Rlib_dir` and `Rpkg_config` config options have been removed as they are no longer needed.
+    - The `Rlib_dir` and `Rpkg_config` config options have been removed as they are no longer needed.
+- New parameters in the config file to make certain rules optional: (#133, @kelly-sovacool)
+    - GO enrichment is controlled by `run_go_enrichment` (default: `false`)
+    - rose is controlled by `run_rose` (default: `false`)
+
 
 ## CARLISLE v2.5.0
 - Refactors R packages to a common source location (#118, @slsevilla)

config/config.yaml

@@ -17,10 +17,14 @@ samplemanifest: "WORKDIR/config/samples.tsv"
 # User parameters
 #####################################################################################
 # run sample contrasts
-run_contrasts: "Y" # Y or N
-contrasts: "WORKDIR/config/contrasts.tsv"  # run_contrasts needs to be "Y"
-contrasts_fdr_cutoff: "0.05"
-contrasts_lfc_cutoff: "0.59" # FC of 1.5
+run_contrasts: true # true or false, no quotes
+contrasts: "WORKDIR/config/contrasts.tsv"  # run_contrasts needs to be `true`
+contrasts_fdr_cutoff: 0.05
+contrasts_lfc_cutoff: 0.59 # FC of 1.5
+
+# these steps are long-running. use `true` if you would like to run them
+run_go_enrichment: false 
+run_rose: false
 
 # reference
 genome: "hg38"    # currently supports hg38, hg19 and mm10. Custom genome can be added with appropriate additions to "reference" section below.

docs/user-guide/output.md

@@ -10,9 +10,9 @@ The following directories are created under the WORKDIR/results directory:
         - contrasts: this directory includes the contrasts for each line listed in the contrast manifest
         - peak_caller: this directory includes all peak calls from each peak_caller (SEACR, MACS2, GOPEAKS) for each sample
             - annotation
-                - go_enrichment: this directory includes gene set enrichment pathway predictions
+                - go_enrichment: this directory includes gene set enrichment pathway predictions when `run_go_enrichment` is set to `true` in the config file.
                 - homer: this directory includes the annotation output from HOMER
-                - rose: this directory includes the annotation output from ROSE
+                - rose: this directory includes the annotation output from ROSE when `run_rose` is set to `true` in the config file.
 - qc: this directory includes MULTIQC reports and spike-in control reports (when applicable)
 
 ```

docs/user-guide/preparing-files.md

@@ -30,7 +30,7 @@ The pipeline allows for the use of a species specific spike-in control, or the u
 
 For example for ecoli spike-in:
 ```
-run_contrasts: "Y"
+run_contrasts: true
 norm_method: "spikein"
 spikein_genome: "ecoli"
 spikein_reference:
@@ -41,7 +41,7 @@ spikein_reference:
 
 For example for drosophila spike-in:
 ```
-run_contrasts: "Y"
+run_contrasts: true
 norm_method: "spikein"
 spikein_genome: "drosophila"
 spikein_reference:

workflow/Snakefile

@@ -97,7 +97,7 @@ def run_qc(wildcards):
 
 def run_contrasts(wildcards):
     files=[]
-    if config["run_contrasts"] == "Y":
+    if config["run_contrasts"]:
         files.append(join(RESULTSDIR,"replicate_sample.tsv"))
 
         # inputs for matrix
@@ -146,20 +146,21 @@ def get_motifs(wildcards):
 
 def get_rose(wildcards):
     files=[]
-    if ("macs2_narrow" in PEAKTYPE) or ("macs2_broad" in PEAKTYPE):
-        anno_m=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="macs2",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_M,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_M,s_dist=S_DISTANCE),
-        files.extend(anno_m)
-    if ("gopeaks_narrow" in PEAKTYPE) or ("gopeaks_broad" in PEAKTYPE):
-        anno_g=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="gopeaks",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_SG,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_G,s_dist=S_DISTANCE),
-        files.extend(anno_g)
-    if ("seacr_stringent" in PEAKTYPE) or ("seacr_relaxed" in PEAKTYPE):
-        anno_s=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="seacr",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_SG,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_S,s_dist=S_DISTANCE),
-        files.extend(anno_s)
+    if config['run_rose']:
+        if ("macs2_narrow" in PEAKTYPE) or ("macs2_broad" in PEAKTYPE):
+            anno_m=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="macs2",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_M,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_M,s_dist=S_DISTANCE),
+            files.extend(anno_m)
+        if ("gopeaks_narrow" in PEAKTYPE) or ("gopeaks_broad" in PEAKTYPE):
+            anno_g=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="gopeaks",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_SG,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_G,s_dist=S_DISTANCE),
+            files.extend(anno_g)
+        if ("seacr_stringent" in PEAKTYPE) or ("seacr_relaxed" in PEAKTYPE):
+            anno_s=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","rose","{treatment_control_list}.{dupstatus}.{peak_caller_type}.{s_dist}","{treatment_control_list}_AllStitched.table.super.summits.bed"),peak_caller="seacr",qthresholds=QTRESHOLDS,treatment_control_list=TREATMENT_LIST_SG,dupstatus=DUPSTATUS,peak_caller_type=PEAKTYPE_S,s_dist=S_DISTANCE),
+            files.extend(anno_s)
     return files
 
 def get_enrichment(wildcards):
     files=[]
-    if config["run_contrasts"] == "Y":
+    if config["run_contrasts"] and config['run_go_enrichment']:
         if (GENOME == "hg19") or (GENOME == "hg38"):
             if ("macs2_narrow" in PEAKTYPE) or ("macs2_broad" in PEAKTYPE):
                 t=expand(join(RESULTSDIR,"peaks","{qthresholds}","{peak_caller}","annotation","go_enrichment","{contrast_list}.{dupstatus}.txt"),peak_caller="macs2",qthresholds=QTRESHOLDS,contrast_list=CONTRAST_LIST,dupstatus=DUPSTATUS)

workflow/rules/annotations.smk

@@ -256,7 +256,7 @@ rule rose:
             echo "Less than 5 usable peaks detected (N=${{num_of_peaks}})" > {output.super_summit}
         fi
     """
-if config["run_contrasts"] == "Y":
+if config["run_contrasts"]:
     rule create_contrast_peakcaller_files:
         """
         Reads in all of the output from Rules create_contrast_data_files which match the same peaktype and merges them together

workflow/rules/init.smk

@@ -185,7 +185,7 @@ QTRESHOLDS=config["quality_thresholds"]
 QTRESHOLDS=list(map(lambda x:x.strip(),QTRESHOLDS.split(",")))
 
 # set contrast settings
-if config["run_contrasts"] == "Y":
+if config["run_contrasts"]:
     print("#"*100)
     print("# Checking constrasts to run...")
     contrasts_table = config["contrasts"]