Benedikt update

DE_pipeline.snake

@@ -64,7 +64,7 @@ def get_inputs_all():
 	#functional annotation
 	inputs.append(pph.expand_path(step = "goseq", extension = "go.rds",   if_set = dict(goseq=True) ))
 	inputs.append(pph.expand_path(step = "goseq", extension = "kegg.rds", if_set = dict(goseq=True) ))
-	inputs.append(pph.file_path(step = "annotation", extension = "rds", contrast="all"))
+	#inputs.append(pph.file_path(step = "annotation", extension = "rds", contrast="all"))
 	inputs.append(pph.file_path(step = "export_raw_counts", extension = "xlsx", contrast = "all"))
 	inputs.append(pph.expand_path(step = "cluster_profiler", extension = "rds", if_set = dict(cluster_profiler=dict(run=True)) ))
   # XXX uncomment the following line to run tmod_pca

README.md

@@ -48,27 +48,27 @@ Quick-Start
 After cloning this git repository:
 
 ```
-git clone [email protected]:CUBI/Pipelines/sea-snap.git
+git clone [email protected]:CUBI/Pipelines/seasnap-pipeline.git
 ```
 
 all required tools and packages can be installed via conda.
 
-Currently there are two separate conda environments, one for the mapping+sc
+Currently there are two separate conda environments, one for the mapping
 pipeline and one for the DE pipeline
 
-Download and install them into new environments called `sea_snap_mapping_sc`
+Download and install them into new environments called `sea_snap_mapping`
 and `sea_snap_de`:
 
 ```
-conda env create -f conda_env_mapping_sc.yaml
+conda env create -f conda_env_mapping.yaml
 conda env create -f conda_env_de.yaml
 ```
 
-The files `conda_env_mapping_sc.yaml` and `conda_env_de.yaml` are located in the main directory of the git repository.
+The files `conda_env_mapping.yaml` and `conda_env_de.yaml` are located in the main directory of the git repository.
 Each time before using SeA-SnaP, activate the environment with:
 
 ```
-conda activate sea_snap_mapping_sc
+conda activate sea_snap_mapping
 ```
 
 or 
@@ -103,7 +103,6 @@ The next steps depend on, whether you want to run:
 
 - [**`The mapping pipeline`**](documentation/run_mapping.md)
 - [**`The DE pipeline`**](documentation/run_DE.md)
-- [**`The sc pipeline`**](documentation/run_sc.md)
 
 The results of an analysis can also be [`exported`](documentation/export.md) to a new folder structure, e.g. to upload them to SODAR.
 

TODO.md

@@ -2,5 +2,8 @@ The roadmap ahead:
 
 1) merging Eric's branches and the ATAC_seq branch
 2) making sure sea-snap runs smoothly with newer versions of snakemake (it
-doesn't currently)
-3) making the step from drmaa to cluster profiles.
+doesn't currently) --> DONE for mapping pipeline if snakemake version = 7.19.1
+3) making the step from drmaa to cluster profiles --> mostly DONE for mapping pipeline 
+4) optimizing resource requirements in `mapping_pipeline.snake` (check `mem` vs `mem_per_cpu`) and adding them to `DE_pipeline.snake`
+5) allowing sample-specific indices for bwa / salmon / kallisto?
+6) adapting the `conda_env.yaml` files

cluster_config.json

@@ -5,7 +5,7 @@
 
         "run_command_sge": "--drmaa=\" -cwd -V -l h_vmem={cluster.h_vmem}M -l h_rt={cluster.h_rt} -pe smp {cluster.pe} -j yes -o {cluster.output} -e {cluster.errors}\"",
 
-        "run_command_slurm": "--drmaa=\" --mem-per-cpu={cluster.h_vmem} -t {cluster.h_rt} -c {cluster.pe} -p medium -o {cluster.output} -e {cluster.errors}\""
+        "run_command_slurm": "--drmaa=\" --mem-per-cpu={cluster.h_vmem} -t {cluster.h_rt} -c {cluster.pe} -p medium -o {cluster.output} -e {cluster.output}\""
     },
 
     "__default__":
@@ -35,7 +35,7 @@
 
     "salmon":
     {
-        "h_vmem": "4000",
+         "h_vmem": "4000",
         "h_rt": "40:00:00",
         "pe": "8"
     },
@@ -110,20 +110,6 @@
         "pe": "4"
     },
 
-    "cellranger_count":
-    {
-        "h_vmem": "4000",
-        "h_rt": "40:00:00",
-        "pe": "1"
-    },
-
-    "velocyto_run":
-    {
-        "h_vmem": "20000",
-        "h_rt": "40:00:00",
-        "pe": "8"
-    },
-
     "cluster_profiler":
     {   "h_vmem": "20000",
         "h_rt": "10:00:00",