Merge pull request #690 from maxplanck-ie/dev_ksikora2

Dev ksikora2
maxplanck-ie · Sep 11, 2020 · 4263be4 · 4263be4
2 parents fe82f85 + 3844371
commit 4263be4
Show file tree

Hide file tree

Showing 6 changed files with 23 additions and 11 deletions.
diff --git a/docs/content/News.rst b/docs/content/News.rst
@@ -1,6 +1,14 @@
 snakePipes News
 ===============
 
+
+snakePipes 2.x.y
+----------------
+
+* Genrich will now run if sampleSheet without replicates is provided.
+* Updated zenodo link to mouse genome GRCm38/mm10 .
+
+
 snakePipes 2.2.2
 ----------------
 
@@ -9,6 +17,7 @@ snakePipes 2.2.2
 * Fixed labels in deepTools commands.
 * Allele_info is now boolean.
 
+
 snakePipes 2.2.1
 ----------------
 
@@ -17,6 +26,7 @@ snakePipes 2.2.1
 * Added DAG test for allelic ChIPseq.
 * Fixed a bug with deepTools QC for allelic mRNAseq.
 
+
 snakePipes 2.2.0
 ----------------
 * Added Alevin mode in scRNA workflow

diff --git a/docs/content/setting_up.rst b/docs/content/setting_up.rst
@@ -34,7 +34,7 @@ The easiest way to install snakePipes is via our conda channel. The following co
 
 .. code:: bash
 
-    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.1.1
+    conda create -n snakePipes -c mpi-ie -c conda-forge -c bioconda snakePipes==2.2.2
 
 This way, the software used within snakePipes do not conflict with the software pre-installed on your terminal or in your python environment.
 
@@ -193,7 +193,7 @@ Download premade indices
 For the sake of convenience, we provide premade indices for the following organisms:
 
  - `Human (GRCh38, Gencode release 29) <https://zenodo.org/record/2650763>`__
- - `Mouse (GRCm38/mm10, Gencode release m19) <https://zenodo.org/record/3629114>`__
+ - `Mouse (GRCm38/mm10, Gencode release m19) <https://zenodo.org/record/4020455>`__
  - `Mouse (GRCm37/mm9, Gencode release 1) <https://zenodo.org/record/2650849>`__
  - `Fruit fly (dm6, Ensembl release 94) <https://zenodo.org/record/2650762>`__
 

diff --git a/snakePipes/common_functions.py b/snakePipes/common_functions.py
@@ -223,7 +223,7 @@ def check_replicates(sample_info_file):
 
     for k, v in d.items():
         if v < 2:
-            sys.stderr.write("ERROR: The {} group has no replicates!\n".format(k))
+            sys.stderr.write("WARNING: The {} group has no replicates!\n".format(k))
             return False
 
     return True

diff --git a/snakePipes/shared/rules/ChIP_peak_calling.snakefile b/snakePipes/shared/rules/ChIP_peak_calling.snakefile
@@ -157,7 +157,7 @@ if pairedEnd:
     rule Genrich_peaks:
         input:
             bams=lambda wildcards: expand(os.path.join("filtered_bam", "{sample}.namesorted.bam"), sample=genrichDict[wildcards.group]),
-            control = lambda wildcards: ["filtered_bam/"+get_control(x)+".namesorted.bam" for x in genrichDict[wildcards.group]]
+            control = lambda wildcards: ["filtered_bam/"+get_control(x)+".namesorted.bam" for x in genrichDict[wildcards.group]] if chip_samples_w_ctrl else []
         output:
             "Genrich/{group}.narrowPeak"
         log: "Genrich/logs/{group}.log"
@@ -174,7 +174,7 @@ else:
     rule Genrich_peaks:
         input:
             bams=lambda wildcards: expand(os.path.join("filtered_bam", "{sample}.namesorted.bam"), sample=genrichDict[wildcards.group]),
-            control = lambda wildcards: ["filtered_bam/"+get_control(x)+".namesorted.bam" for x in genrichDict[wildcards.group]]
+            control = lambda wildcards: ["filtered_bam/"+get_control(x)+".namesorted.bam" for x in genrichDict[wildcards.group] ] if chip_samples_w_ctrl else []
         output:
             "Genrich/{group}.narrowPeak"
         log: "Genrich/logs/{group}.log"

diff --git a/snakePipes/workflows/ChIP-seq/Snakefile b/snakePipes/workflows/ChIP-seq/Snakefile
@@ -57,7 +57,7 @@ else:
     include: os.path.join(maindir, "shared", "rules", "deepTools_ChIP_allelic.snakefile")
 
 # CSAW for differential binding (if sampleinfo specified)
-if sampleSheet:
+if sampleSheet and cf.check_replicates(sampleSheet):
     include: os.path.join(maindir, "shared", "rules", "CSAW.snakefile")
     include: os.path.join(maindir, "shared", "rules", "nearestGene.snakefile")
     include: os.path.join(maindir, "shared", "rules", "filterGTF.snakefile")
@@ -137,7 +137,7 @@ def run_deepTools_allelic():
     return(file_list)
 
 def run_CSAW():
-    if sampleSheet:
+    if sampleSheet and cf.check_replicates(sampleSheet):
         file_list=["CSAW_{}_{}/CSAW.session_info.txt".format(peakCaller, sample_name)]
         if not allele_info :
             file_list.append(["Annotation/genes.filtered.symbol","Annotation/genes.filtered.t2g","CSAW_{}_{}/CSAW.Stats_report.html".format(peakCaller, sample_name)])

diff --git a/snakePipes/workflows/ChIP-seq/internals.snakefile b/snakePipes/workflows/ChIP-seq/internals.snakefile
@@ -73,8 +73,9 @@ if not os.path.isfile(samples_config):
 if sampleSheet:
     cf.check_sample_info_header(sampleSheet)
     if not cf.check_replicates(sampleSheet):
-        print("\nWarning! CSAW cannot be invoked without replicates!\n")
-        sys.exit()
+        print("\nWarning! CSAW cannot be invoked without replicates and will not be run!\n")
+        if not peakCaller=="Genrich":
+            sys.exit()
 
 chip_dict = {}
 with open(samples_config, "r") as f:
@@ -181,9 +182,10 @@ def filter_dict(sampleSheet,input_dict):
     return(output_dict)
 
 if sampleSheet:
-    filtered_dict = filter_dict(sampleSheet,dict(zip(chip_samples_w_ctrl, [ get_control_name(x) for x in chip_samples_w_ctrl ])))
     genrichDict = cf.sampleSheetGroups(sampleSheet)
-    reordered_dict = {k: filtered_dict[k] for k in [item for sublist in genrichDict.values() for item in sublist]}
+    if chip_samples_w_ctrl:
+        filtered_dict = filter_dict(sampleSheet,dict(zip(chip_samples_w_ctrl, [ get_control_name(x) for x in chip_samples_w_ctrl ])))
+        reordered_dict = {k: filtered_dict[k] for k in [item for sublist in genrichDict.values() for item in sublist]}
 else:
     genrichDict = {"all_samples": chip_samples}