Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

FISH_Processing_ER_fix #3

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

FISH_Processing_ER_fix #3

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
1b25b5d
updated mRNA to include clustered mRNA
ericron Jul 29, 2024
489a011
fixed nuc and cyto rna levels and added colums for clusters per cell
ericron Aug 2, 2024
24a68c1
Fixed spot size and psf mixup
ericron Aug 19, 2024
7241a10
added single cell viewer
ericron Aug 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions notebooks/FISH_pipeline.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,6 +183,7 @@
{
"cell_type": "code",
"execution_count": 5,
"id": "a061b473",
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -211,8 +212,8 @@
"diameter_nucleus=100 # Approximate nucleus size in pixels\n",
"diameter_cytosol=200 # Approximate cytosol size in pixels\n",
"\n",
"psf_z=350 # Theoretical size of the PSF emitted by a [rna] spot in the z plan, in nanometers\n",
"psf_yx=160 # Theoretical size of the PSF emitted by a [rna] spot in the yx plan, in nanometers\n",
"mRNA_radius_z=350 # Theoretical size of the mRNA_radius emitted by a [rna] spot in the z plan, in nanometers\n",
"mRNA_radius_yx=160 # Theoretical size of the mRNA_radius emitted by a [rna] spot in the yx plan, in nanometers\n",
"\n",
"voxel_size_z=500 # Microscope conversion px to nanometers in the z axis.\n",
"voxel_size_yx=160 # Microscope conversion px to nanometers in the xy axis.\n",
Expand All @@ -237,6 +238,7 @@
{
"cell_type": "code",
"execution_count": 7,
"id": "2a2a6ac1",
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -281,6 +283,7 @@
{
"cell_type": "code",
"execution_count": null,
"id": "72b35ad6",
"metadata": {},
"outputs": [],
"source": [
Expand Down Expand Up @@ -336,7 +339,7 @@
"source": [
"dataframe_FISH,_,_,_,output_identification_string = fa.PipelineFISH(local_data_dir, channels_with_cytosol, channels_with_nucleus, channels_with_FISH,diameter_nucleus, \n",
" diameter_cytosol, minimum_spots_cluster, masks_dir=masks_dir, voxel_size_z=voxel_size_z,\n",
" voxel_size_yx=voxel_size_yx ,psf_z=psf_z,psf_yx=psf_yx, show_plots=show_plots, \n",
" voxel_size_yx=voxel_size_yx ,mRNA_radius_z=mRNA_radius_z,mRNA_radius_yx=mRNA_radius_yx, show_plots=show_plots, \n",
" file_name_str=data_folder_path.name, \n",
" optimization_segmentation_method=optimization_segmentation_method,\n",
" save_all_images=save_all_images,\n",
Expand Down
56 changes: 46 additions & 10 deletions publications/Ron_2024/Data_Interpretation/DataManagement.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@


class DataManagement:
def __init__(self, file_path, Condition, DexConc, Replica, time_value,time_TPL_value,output_path,minimum_spots_cluster=4,mandatory_substring=None,connect_to_NAS=False,path_to_config_file=None,save_csv=True):
def __init__(self, file_path, Condition, DexConc, Replica, time_value,time_TPL_value,output_path,minimum_spots_cluster=2,mandatory_substring=None,connect_to_NAS=False,path_to_config_file=None,save_csv=True):
# This section downloads the zip file from NAS and extracts the dataframe or uses the dataframe from the local folder.
if connect_to_NAS == False:
self.file_path = file_path
Expand Down Expand Up @@ -67,8 +67,9 @@ def data_processor(self):
RNA_nuc_list = []
RNA_cyto_list = []
ts_size_list = []
nuc_cluster_list = []
cyto_cluster_list = []

# This code will loop through each cell and store the values in the lists above.
for i in range(number_cells):
nuc_area = np.asarray(dataframe.loc[
(dataframe['cell_id'] == i)
Expand Down Expand Up @@ -97,19 +98,49 @@ def data_processor(self):
(dataframe['is_cell_fragmented'] != -1)
].pseudo_cyto_int_ch_0.values[0])

# This is counting the number of spots in the nucleus that meet certain conditions and storing this in the nuc variable.
nuc = np.asarray(len(dataframe.loc[
# Count the number of RNA in the nucleus
nuc_spots = len(dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_nuc'] == True) &
(dataframe['is_cell_fragmented'] != -1)
].spot_id))
].spot_id)

# This is counting the number of spots in the nucleus that meet certain conditions and storing this in the nuc variable.
cyto = np.asarray(len(dataframe.loc[
nuc_cluster_rna = dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_nuc'] == True) &
(dataframe['is_cell_fragmented'] != -1)
].cluster_size.sum()

nuc = np.asarray(nuc_spots + nuc_cluster_rna - 1)

number_nuc_cluster = len(dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_cluster'] == True) &
(dataframe['is_nuc'] == True) &
(dataframe['is_cell_fragmented'] != -1)
].spot_id)

# Count the number of RNA in the cytoplasm
cyto_spots = len(dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_nuc'] == False) &
(dataframe['is_cell_fragmented'] != -1)
].spot_id))
].spot_id)

cyto_cluster_rna = dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_nuc'] == False) &
(dataframe['is_cell_fragmented'] != -1)
].cluster_size.sum()

cyto = np.asarray(cyto_spots + cyto_cluster_rna - 1)

cyto_cluster_number = len(dataframe.loc[
(dataframe['cell_id'] == i) &
(dataframe['is_cluster'] == True) &
(dataframe['is_nuc'] == False) &
(dataframe['is_cell_fragmented'] != -1)
].spot_id)

####### This is counting all transcription sites for DUSP1 that are larger than "minimum_spots_cluster".
ts_size = dataframe.loc[
Expand Down Expand Up @@ -141,6 +172,9 @@ def data_processor(self):
RNA_nuc_list.append(nuc)
RNA_cyto_list.append(cyto)
ts_size_list.append(ts_size_array)
nuc_cluster_list.append(number_nuc_cluster)
cyto_cluster_list.append(cyto_cluster_number)


# Create a pandas DataFrame from the list of ts_int values
df_ts_size_per_cell = pd.DataFrame(ts_size_list)
Expand All @@ -160,8 +194,10 @@ def data_processor(self):
'Cyto_GR_avg_int': GR_avg_cyto_intensity_list,
'Nuc_DUSP1_avg_int': DUSP1_avg_nuc_intensity_list, # Only relevant for condition == DUSP1_timesweep and DUSP1_TPL. NaNs for GR_timesweep.
'Cyto_DUSP1_avg_int': DUSP1_avg_cyto_intensity_list, # Only relevant for condition == DUSP1_timesweep and DUSP1_TPL. NaNs for GR_timesweep.
'RNA_DUSP1_nuc': RNA_nuc_list, # RNA_GR_cyto do we need also for DUSP1?
'RNA_DUSP1_cyto': RNA_cyto_list # RNA_GR_cyto do we need also for DUSP1?
'RNA_DUSP1_nuc': RNA_nuc_list,
'RNA_DUSP1_cyto': RNA_cyto_list,
'Nuc_cluster_number': nuc_cluster_list,
'Cyto_cluster_number': cyto_cluster_list
}
# Create a pandas DataFrame from the dictionary
df_data = pd.DataFrame(data)
Expand Down
6 changes: 3 additions & 3 deletions publications/Ron_2024/Data_Interpretation/Notebok_Data_Interpretation.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,7 +103,7 @@
"metadata": {},
"outputs": [],
"source": [
"def summarize_dataframes(list_dirs, Condition, time_list, DexConc_list, time_TPL_value_list=None, Replica='A', minimum_spots_cluster=5, mandatory_substring='nuc_100__cyto_200__psfz_350__psfyx_160', connect_to_NAS=True,save_csv=True):\n",
"def summarize_dataframes(list_dirs, Condition, time_list, DexConc_list, time_TPL_value_list=None, Replica='A', minimum_spots_cluster=2, mandatory_substring='nuc_100__cyto_200__psfz_350__psfyx_160', connect_to_NAS=True,save_csv=True):\n",
" \"\"\"\n",
" Summarizes the dataframes from multiple directories into a single concatenated dataframe.\n",
"\n",
Expand All @@ -114,7 +114,7 @@
" - DexConc_list (list): List of DexConc values.\n",
" - time_TPL_value_list (list, optional): List of time_TPL values. Defaults to None.\n",
" - Replica (str, optional): Replica value. Defaults to 'A'.\n",
" - minimum_spots_cluster (int, optional): Minimum number of spots in a cluster. Defaults to 5.\n",
" - minimum_spots_cluster (int, optional): Minimum number of spots in a cluster. Defaults to 2.\n",
" - mandatory_substring (str, optional): Mandatory substring in the file path. Defaults to 'nuc_100__cyto_200__psfz_350__psfyx_160'.\n",
" - connect_to_NAS (bool, optional): Flag to connect to NAS. Defaults to True.\n",
" - save_csv (bool, optional): Flag to save the concatenated dataframe as a CSV file. Defaults to True.\n",
Expand Down Expand Up @@ -738,7 +738,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.12"
"version": "3.8.15"
}
},
"nbformat": 4,
Expand Down
Loading