Merge pull request #206 from DendrouLab/sarah_matplotlib

Small fixes

README.md

@@ -9,7 +9,7 @@ Panpipes allows reliable and customisable analysis and evaluation of individual
 
 **See our [documentation](https://panpipes-pipelines.readthedocs.io/en/latest/) and our [preprint](https://www.biorxiv.org/content/10.1101/2023.03.11.532085v2)**  
 
-These workflows make use of [cgat-core](https://github.com/cgat-developers/cgat-core):
+These workflows make use of [cgat-core](https://github.com/cgat-developers/cgat-core)
 
 Available workflows:
 

docs/install.md

@@ -16,7 +16,7 @@ conda config --add channels conda-forge
 conda config --set channel_priority strict
 # you should remove the strict priority afterwards!
 conda search r-base
-conda create --name pipeline_env python=3.9 r-base=4.3.0
+conda create --name pipeline_env python=3.10 r-base=4.3.0
 ```
 
 now we activate the environment
@@ -28,7 +28,7 @@ conda activate pipeline_env
 Let's first install the R packages
 
 ```bash
-conda install -c conda-forge r-tidyverse r-optparse r-ggforce r-ggraph r-xtable r-hdf5r r-clustree
+conda install -c conda-forge r-tidyverse r-optparse r-ggforce r-ggraph r-xtable r-hdf5r r-clustree r-cowplot
 ```
 
 Then we can install panpipes:

panpipes/panpipes/pipeline_preprocess.py

@@ -204,7 +204,7 @@ def prot_preprocess( log_file, scaled_file, ):
             if PARAMS['prot_solver'] == "default":
                 cmd += " --pca_solver arpack"
             else:
-                cmd += " --pca_solver %(pca_solver)s"
+                cmd += " --pca_solver %(prot_solver)s"
         cmd += """ 
         --run_pca True
         --n_pcs %(prot_n_pcs)s

panpipes/python_scripts/plot_features_scatter.py

@@ -41,15 +41,18 @@
 
 L.info(args)
 
-sc.settings.figdir  = "./scatters/"
+figdir = "./scatters/"
+if not os.path.exists(figdir):
+    os.mkdir(figdir)
+
+sc.settings.figdir  = figdir
 sc.set_figure_params(fontsize=12)
 
 
 mdata = mu.read(args.mdata_object)
 
 layers = read_yaml(args.layers_dict)
 
-
 df = pd.read_csv(args.scatters_csv)
 L.debug(df)
 

panpipes/python_scripts/run_scanpyQC_spatial.py

@@ -129,7 +129,7 @@
 percent_top = [x for x in percent_top if x <= spatial.n_vars]
 sc.pp.calculate_qc_metrics(spatial, qc_vars=qc_vars, percent_top=percent_top, inplace=True)
 
-if args.spatial_filetype == "vizgen":
+if (args.spatial_filetype == "vizgen") and ("blank_genes" in spatial.obsm):    
     spatial.obsm["blank_genes"].to_numpy().sum() / spatial.var["total_counts"].sum() * 100
 
 # Calculate cc scores 

pipeline_env.yaml

@@ -12,6 +12,7 @@ dependencies:
   - r-optparse
   - r-tidyverse
   - r-xtable
+  - r-cowplot
   - pip
   - pip:
     - pytest