diff --git a/Plate_2_data/4.processing_features/0.merge_sc_plate2.ipynb b/Plate_2_data/4.processing_features/0.merge_sc_plate2.ipynb index da3b186..b728583 100644 --- a/Plate_2_data/4.processing_features/0.merge_sc_plate2.ipynb +++ b/Plate_2_data/4.processing_features/0.merge_sc_plate2.ipynb @@ -58,7 +58,7 @@ "source": [ "# set directory for sqlite files\n", "sqlite_dir = pathlib.Path(\n", - " \"/scratch/alpine/mlippincott@xsede.org/sqlite_files\"\n", + " \"/projects/mlippincott@xsede.org/\"\n", ").resolve(strict=True)\n", "\n", "# dictionary with info for the sqlite file from each run\n", diff --git a/Plate_2_data/4.processing_features/2.combine_sc_runs_plate2.ipynb b/Plate_2_data/4.processing_features/2.combine_sc_runs_plate2.ipynb index e03515c..72e5957 100644 --- a/Plate_2_data/4.processing_features/2.combine_sc_runs_plate2.ipynb +++ b/Plate_2_data/4.processing_features/2.combine_sc_runs_plate2.ipynb @@ -60,13 +60,13 @@ "outputs": [], "source": [ "# set paths to each individual run file after annotation\n", - "first_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_1.parquet\")\n", - "second_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_2.parquet\")\n", - "third_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_3.parquet\")\n", - "fourth_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_4.parquet\")\n", - "fifth_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_5.parquet\")\n", - "sixth_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_6.parquet\")\n", - "seventh_run_sc_path = pathlib.Path(f\"{annotated_dir}/PBMC_batch_7.parquet\")" + "first_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_1_sc.parquet\")\n", + "second_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_2_sc.parquet\")\n", + "third_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_3_sc.parquet\")\n", + "fourth_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_4_sc.parquet\")\n", + "fifth_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_5_sc.parquet\")\n", + "sixth_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_6_sc.parquet\")\n", + "seventh_run_sc_path = pathlib.Path(f\"{annotated_dir}/batch_7_sc.parquet\")" ] }, { diff --git a/Plate_2_data/4.processing_features/4.feature_select_sc_plate2.ipynb b/Plate_2_data/4.processing_features/4.feature_select_sc_plate2.ipynb index da64da4..b7a83d5 100644 --- a/Plate_2_data/4.processing_features/4.feature_select_sc_plate2.ipynb +++ b/Plate_2_data/4.processing_features/4.feature_select_sc_plate2.ipynb @@ -46,17 +46,17 @@ "outputs": [], "source": [ "# directory where normalized parquet file is located\n", - "data_dir = pathlib.Path(\"./data/\")\n", + "data_dir = pathlib.Path(\"./data/normalized_data\")\n", "\n", "# directory where the feature selected parquet file is saved to\n", "output_dir = pathlib.Path(\"./data/feature_selected_data\")\n", "output_dir.mkdir(exist_ok=True)\n", "\n", "# define input path\n", - "normalized_file_path = str(pathlib.Path(f\"{data_dir}/SHSY5Y_sc_norm.parquet\"))\n", + "normalized_file_path = str(pathlib.Path(f\"{data_dir}/PBMC_sc_norm.parquet\"))\n", "\n", "# define ouput path\n", - "feature_select_output_file = str(pathlib.Path(f\"{output_dir}/SHSY5Y_sc_norm_fs.parquet\"))" + "feature_select_output_file = str(pathlib.Path(f\"{output_dir}/PBMC_sc_norm_fs.parquet\"))" ] }, { diff --git a/Plate_2_data/4.processing_features/5.extract_image_features.ipynb b/Plate_2_data/4.processing_features/5.extract_image_features.ipynb index c0c8954..6782787 100644 --- a/Plate_2_data/4.processing_features/5.extract_image_features.ipynb +++ b/Plate_2_data/4.processing_features/5.extract_image_features.ipynb @@ -63,7 +63,7 @@ "\n", "# set directory for sqlite files\n", "sqlite_dir = pathlib.Path(\n", - " \"/scratch/alpine/mlippincott@xsede.org/sqlite_files\"\n", + " \"/projects/mlippincott@xsede.org/\"\n", ").resolve(strict=True)\n", "\n", "# dictionary with info for the sqlite file from each run\n", diff --git a/Plate_2_data/4.processing_features/processing_features_plate2.sh b/Plate_2_data/4.processing_features/processing_features_plate2.sh index c2bc7d0..bc55cf0 100644 --- a/Plate_2_data/4.processing_features/processing_features_plate2.sh +++ b/Plate_2_data/4.processing_features/processing_features_plate2.sh @@ -4,10 +4,10 @@ #SBATCH --nodes=1 #SBATCH --ntasks=1 -#SBATCH --mem=500G +#SBATCH --mem=600G #SBATCH --partition=amem #SBATCH --qos=mem -#SBATCH --time=25:00:00 +#SBATCH --time=48:00:00 #SBATCH --output=sample-%j.out module purge @@ -34,5 +34,5 @@ python scripts/3.normalize_sc_plate2.py echo "Feature selecting plate 2 data" python scripts/4.feature_select_sc_plate2.py echo "Extracting image features from plate 2 data" -python scripts/5.extract_image_features +python scripts/5.extract_image_features.py echo "Processing of plate 2 data complete"