WayScience · jenna-tomkinson · Jan 18, 2023 · Jan 17, 2023 · Jan 17, 2023 · Jan 18, 2023
diff --git a/4_processing_features/4.extract_sc_features.sh b/4_processing_features/4.extract_sc_features.sh
@@ -1,3 +1,6 @@
 #!/bin/bash
-jupyter nbconvert --to python extract_single_cell_features.ipynb
-python extract_single_cell_features.py
+jupyter nbconvert --to python *.ipynb
+
+python extract_sc_features_cp.py
+
+python extract_sc_features_dp.py
diff --git a/4_processing_features/4.processing_features.yml b/4_processing_features/4.processing_features.yml
@@ -14,4 +14,4 @@ dependencies:
   - conda-forge::numpy=1.22
   - conda-forge::scikit-learn
   - pip:
-    - git+https://github.com/cytomining/pycytominer@e43be528d3ca6d77d2b1a347fe8e4131dfc65bf0
+    - git+https://github.com/cytomining/pycytominer@afac3ea16818ad25f37318ecd5c5090c0eff5806
diff --git a/4_processing_features/README.md b/4_processing_features/README.md
@@ -1,17 +1,18 @@
 # 4. Processing Extracted Single Cell Features 
 
-In this module, we present our pipeline for processing outputted `.sqlite` file with single cell features from CellProfiler.
-The processed features are saved into compressed `.csv.gz` for use during statistical analysis.
+In this module, we present our pipeline for processing outputted `.sqlite` file with single cell features from CellProfiler (CP) and DeepProfiler (DP).
+
+The processed CP features are saved into compressed `.csv.gz` and DP features are saved as `.npz` files for use during statistical analysis.
 
 ## Pycytominer
 
-We use [Pycytominer](https://github.com/cytomining/pycytominer) to perform the aggregation, merging, and normalization of the NF1 single cell features.
+We use [Pycytominer](https://github.com/cytomining/pycytominer) to perform the merging, normalization, and feature selection of the NF1 single cell features.
 
 For more information regarding the functions that we used, please see [the documentation](https://pycytominer.readthedocs.io/en/latest/pycytominer.cyto_utils.html#pycytominer.cyto_utils.cells.SingleCells.merge_single_cells) from the Pycytominer team.
 
 ### Normalization
 
-CellProfiler features can display a variety of distributions across cells.
+CellProfiler and DeepProfiler features can display a variety of distributions across cells.
 To facilitate analysis, we standardize all features (z-score) to the same scale.
 
 ---
@@ -27,15 +28,17 @@ Make sure you are in the `4_processing_features` directory before performing the
 conda env create -f 4.processing_features.yml
 ```
 
-## Step 2: Normalize Single Cell Features
+## Step 2: Normalize and Feature Select Single Cell Features
 
 ### Step 2a: Set Up Paths
 
-Within the [extract_single_cell_features.ipynb](4_processing_features/extract_single_cell_features.ipynb) notebook, you can chnage the paths to reflect the local paths or names for your machine (***IF* you changed anything from the original pipeline**) for the various parameters (e.g. CellProfiler directory, output directory, path to sqlite file, etc.)
+Within the [extract_sc_features_cp.ipynb](4_processing_features/extract_sc_features_cp.ipynb) notebook, you can change the paths to reflect the local paths or names for your machine (***IF* you changed anything from the original pipeline**) for the various parameters (e.g. CellProfiler directory, output directory, path to sqlite file, etc.)
+
+As well, you can update the paths with the [extract_sc_features_dp.ipynb](4_processing_features/extract_sc_features_dp.ipynb) notebook if the paths to the project are different on your local machine.
 
 ### Step 2b: Run Extract Single Cell Features
 
-Using the code below, run the notebook to extract and normalize single cell features from CellProfiler.
+Using the code below, run the notebook to extract and normalize single cell features from CellProfiler and DeepProfiler.
 
 ```bash
 # Run this script in terminal

diff --git a/4_processing_features/data/nf1_sc_deepprofiler_cyto.csv.gz b/4_processing_features/data/nf1_sc_deepprofiler_cyto.csv.gz
diff --git a/4_processing_features/data/nf1_sc_deepprofiler_nuc.csv.gz b/4_processing_features/data/nf1_sc_deepprofiler_nuc.csv.gz
diff --git a/4_processing_features/data/nf1_sc_norm_deepprofiler_cyto.csv.gz b/4_processing_features/data/nf1_sc_norm_deepprofiler_cyto.csv.gz
diff --git a/4_processing_features/data/nf1_sc_norm_deepprofiler_nuc.csv.gz b/4_processing_features/data/nf1_sc_norm_deepprofiler_nuc.csv.gz
diff --git a/4_processing_features/data/nf1_sc_norm_fs_deepprofiler_cyto.csv.gz b/4_processing_features/data/nf1_sc_norm_fs_deepprofiler_cyto.csv.gz
diff --git a/4_processing_features/data/nf1_sc_norm_fs_deepprofiler_nuc.csv.gz b/4_processing_features/data/nf1_sc_norm_fs_deepprofiler_nuc.csv.gz
diff --git a/...atures/extract_single_cell_features.ipynb → ...ing_features/extract_sc_features_cp.ipynb b/...atures/extract_single_cell_features.ipynb → ...ing_features/extract_sc_features_cp.ipynb
diff --git a/..._features/extract_single_cell_features.py → ...essing_features/extract_sc_features_cp.py b/..._features/extract_single_cell_features.py → ...essing_features/extract_sc_features_cp.py