spacr 0.3.60__tar.gz → 0.3.62__tar.gz

{spacr-0.3.60/spacr.egg-info → spacr-0.3.62}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: spacr
-Version: 0.3.60
+Version: 0.3.62
 Summary: Spatial phenotype analysis of crisp screens (SpaCr)
 Home-page: https://github.com/EinarOlafsson/spacr
 Author: Einar Birnir Olafsson

spacr-0.3.62/notebooks/.ipynb_checkpoints/4_spacr_annotate-checkpoint.ipynb

@@ -0,0 +1,48 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d6a39408",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from spacr.gui_utils import annotate\n",
+    "\n",
+    "settings = {'src':'/nas_mnt/carruthers/Einar/tsg101_screen/TSG101SCREEN_20240826_140251/plate4', # (path) path to source folder (where origional images were stored)\n",
+    "            'image_type':'cell_png', # (Optional, string) string in the path of each image (used to filter images)\n",
+    "            'channels':['r', 'g', 'b'], # (list) - Channels to visualize ('r', 'g', and/or 'b')\n",
+    "            'img_size':200, # (integer) - Size of images on the screen (height and weight)\n",
+    "            'normalize_channels':['r','g','b'], # (list) - Channels to normalize\n",
+    "            'annotation_column':'test', # (string) - Column in the database containing/to contain annotations\n",
+    "            'normalize':False, # (bool) - Normalize images to percentiles\n",
+    "            'percentiles':(2,98), # (tuple) - Percentiles used for normalization\n",
+    "            'measurement':None, # (string or NoneType) - Measurement used to filter images\n",
+    "            'threshold':None} # (Integer or NoneType) - Threshold for measurement\n",
+    "\n",
+    "annotate(settings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

spacr-0.3.62/notebooks/1_spacr_generate_masks.ipynb

@@ -0,0 +1,72 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2c78f9de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from spacr.core import preprocess_generate_masks\n",
+    "%matplotlib inline\n",
+    "\n",
+    "settings = {'metadata_type':'cellvoyager', # (string) - type of fime name metadata (cellvoyager, cq1, Nikon)\n",
+    "            'custom_regex':None, # (regex) - Regular expression if filename metadata not in metadata_type \n",
+    "            'experiment':'ubiquitin', # (string) - Name of experiment\n",
+    "            'channels':[0,1,2,3], # (list) - list of integers representing available channels\n",
+    "            'cell_channel':3, # (integer or NoneType) - Cell image dimension \n",
+    "            'cell_background':100, # (integer) - Background value in cell images\n",
+    "            'cell_Signal_to_noise':10, # (integer) - Signal to noise ration for cell channel\n",
+    "            'cell_CP_prob':-1, # (integer) - Cellpose Cell probability\n",
+    "            'remove_background_cell':False, # (bool) - Set background to 0 for cell channel\n",
+    "            'nucleus_channel':0, # (Optional, integer or NoneType) - Nucleus image dimension \n",
+    "            'nucleus_background':500, # (Optional, integer) - Background value in nucleus images\n",
+    "            'nucleus_Signal_to_noise':2, # (Optional, integer) - Signal to noise ration for nucleus channel\n",
+    "            'nucleus_CP_prob':0, # (Optional, integer) - Cellpose Nucleus probability\n",
+    "            'remove_background_nucleus':False, # (Optional, bool) - Set background to 0 for nucleus channel\n",
+    "            'pathogen_model':None, # (Optional, path or NoneType) - Custom cellpose model path for pathogen detection\n",
+    "            'pathogen_channel':1, # (Optional, integer or NoneType) - Pathogen image dimension \n",
+    "            'pathogen_background':200, # (Optional, integer) - Background value in pathogen images\n",
+    "            'pathogen_Signal_to_noise':5, # (Optional, integer) - Signal to noise ration for pathogen channel\n",
+    "            'pathogen_CP_prob':-1, # (Optional, integer) - Cellpose pathogen probability\n",
+    "            'remove_background_pathogen':True, # (Optional, bool) - Set background to 0 for pathogen channel\n",
+    "            'magnification':40, # (integer) - Objective magnefication used to aquire images (40, 60, 100)\n",
+    "            'save':True, # (bool) - Save masks and object data to database\n",
+    "            'preprocess':True, # (bool) - Preprocess images\n",
+    "            'masks':True, # (bool) - Generate masks\n",
+    "            'batch_size':50, # (bool) - Number of images to be normalized together and loaded onto the GPU\n",
+    "            'filter':False, # (bool) - Filter objects based on size\n",
+    "            'merge_pathogens':True, # (bool) - Merge pathogens that share > 75% perimiter\n",
+    "            'plot':False, # (bool) - Plot normalized intensity and object images\n",
+    "            'adjust_cells':True, # (bool) - If cell, nucleus and pathogen: merge cells that share a pathogen\n",
+    "            'test_mode':False, # (bool) - Test settings in test mode before analyzing entire experiment\n",
+    "            'test_images':10, # (integer) - Number of images to analyze in test mode\n",
+    "            'random_test':True} # (bool) - Randomize images for test mode\n",
+    "\n",
+    "src = 'path' # (path) path to source folder (where origional images were stored)\n",
+    "preprocess_generate_masks(src, settings=settings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

spacr-0.3.62/notebooks/2_spacr_generate_mesurments_crop_images.ipynb

@@ -0,0 +1,61 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8fddf2d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from spacr.measure import measure_crop\n",
+    "%matplotlib inline\n",
+    "\n",
+    "settings = {'src':'path', # (path) path to source folder (ens in /merged)\n",
+    "            'channels':[0,1,2,3],# (list) - list of integers representing available channels\n",
+    "            'cell_mask_dim':4, # (integer or NoneType) - Cell mask dimension \n",
+    "            'cell_min_size':2000, # (integer) - minimum size in px2 of cell objects\n",
+    "            'nucleus_mask_dim':5, # (integer or NoneType) - Nucleus mask dimension \n",
+    "            'nucleus_min_size':1000, # (integer) - minimum size in px2 of nuclei objects\n",
+    "            'pathogen_mask_dim':6, # (integer or NoneType) - Pathogen mask dimension \n",
+    "            'pathogen_min_size':400, # (integer) - minimum size in px2 of pathogen objects\n",
+    "            'cytoplasm_min_size':0, # (integer) - minimum size in px2 of cutoplasm (cell-(nucleus+pathogen)) objects\n",
+    "            'save_png':True, # (bool) - save objects as PNGs\n",
+    "            'crop_mode':['cell'], # (list) - Object(s) to be cropped into images ('cell', 'nuclei', 'pathogen')\n",
+    "            'use_bounding_box':False, # (bool) - Use bounding box for cropped images instead of object area\n",
+    "            'png_size':[[224,224]], # (list of lists) - size of single object pngs\n",
+    "            'normalize':False, # (bool or list) - normalize PNGs to percentiles\n",
+    "            'png_dims':[0,1,2], # (list) - Dimensions to include in PNG images\n",
+    "            'normalize_by':'png', # (string) - If normalize, normalize to fov (field of view) or png \n",
+    "            'save_measurements':True, # (bool) - Save measurements\n",
+    "            'plot':False, # (bool) - plot images during analazys\n",
+    "            'plot_filtration':False, # () - Plot filtration steps\n",
+    "            'uninfected':False, # () - Include uninfected\n",
+    "            'test_mode':False, # (bool) - Activate Test mode\n",
+    "            'test_nr':10} # (integer) - Number of images to analyze in test mode\n",
+    "\n",
+    "measure_crop(settings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

spacr-0.3.62/notebooks/3a_spacr_machine_learning.ipynb

@@ -0,0 +1,110 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9e030e83",
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [],
+   "source": [
+    "# Description: Train a ML model to classigy cells based on measurement data\n",
+    "from spacr.ml import generate_ml_scores\n",
+    "%matplotlib inline\n",
+    "\n",
+    "settings = {'src':'path', # (path) path to source folder (where origional images were stored)\n",
+    "            'model_type_ml':'xgboost', # (string) - Type of model ( 'random_forest', 'xgboost', 'gradient_boosting')\n",
+    "            'heatmap_feature':'predictions', # (string) - column to display in heatmaps\n",
+    "            'grouping':'mean', # (string) - Grouping for heatmap\n",
+    "            'min_max':'allq', # (string) - Quantiles to normalize heatmap to (all, allq)\n",
+    "            'cmap':'viridis', # (string) - Heatmap cmap\n",
+    "            'n_estimators':100, # (integer) - Number of estimators for model\n",
+    "            'test_size':0.2, # (float) - Fraction of images used for the test set\n",
+    "            'location_column':'column_name', # (string) - Column containing negative/ positive controll metadata information.\n",
+    "            'positive_control':'c2', # (string) - Value for positive control in location column\n",
+    "            'negative_control':'c1', # (string) - Value for negative control in location column\n",
+    "            'exclude':None, # (string, NoneType) - Rows to exclude in location_column\n",
+    "            'nuclei_limit':1, # (integer) - Maximum number of nuclei for each cell\n",
+    "            'pathogen_limit':3, # (integer) - Maximum number of pathogens per cell\n",
+    "            'n_repeats':10, # (integer) - Number of repeats for permutation importance.\n",
+    "            'top_features':30, # (integer) - Number of top features to plot based on permutation importance, feature importance and shap.\n",
+    "            'channel_of_interest':1, # (integer) - \n",
+    "            'minimum_cell_count':25, # (integer) - Minimum number of cells per well\n",
+    "            'remove_low_variance_features':True, # (bool) - Remove columns with low variance.\n",
+    "            'remove_highly_correlated_features':True, # (bool) - Remove highly correlated features.\n",
+    "            'verbose':False, # (bool) - Display verbose output\n",
+    "            'n_jobs':10} # (integer) - Number of threads\n",
+    "\n",
+    "results = generate_ml_scores(settings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e316cb19",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "# Description: Fit a regression model to estimate the effect size of gRNAs on cell scores.\n",
+    "from spacr.ml import perform_regression\n",
+    "import pandas as pd\n",
+    "%matplotlib inline\n",
+    "\n",
+    "settings = {'count_data':'path', # (path) path or list of paths to sequencing count data\n",
+    "            'score_data':'path', # (path) path or list of paths to score data\n",
+    "            'score_column':'column', # () - column with cell scores\n",
+    "            'metadata_files':['path.csv','path.csv'], # (list) pahts to gene metadata \n",
+    "            'positive_control':'gene', # (string) - gene to highlight in volcano plot\n",
+    "            'negative_control':'gene', # (string) - gene to highlight in volcano plot\n",
+    "            'min_n':3, # () - \n",
+    "            'fraction_threshold':None, # (Optional, float or NoneType) - Minimum threshold for gene fraction, if None automatically calculated\n",
+    "            'target_unique_count':5, # () - Number of expected unique gRNAs per well\n",
+    "            'tolerance':0.02, # (float) - Tollerance for cells per well limit\n",
+    "            'log_x':False, # () - gRNA Fraction plot X axis log\n",
+    "            'log_y':False, # () - gRNA Fraction plot Y axis log\n",
+    "            'x_lim':None, # () - Volcano X axis limit\n",
+    "            'control_wells':['c1','c2','c3'], # (list) - Metadata to exclude from regression model\n",
+    "            'filter_column':'column', # (str) - Column containing control metadata to remove\n",
+    "            'dependent_variable': 'column', # (string) - Dependent variable for regression\n",
+    "            'threshold_method':'var', # (string) - effect size thresold type (std or var)\n",
+    "            'threshold_multiplier':4, # (integer) - effect size threshold multiplyer \n",
+    "            'transform':'log', # (string) - Transform dependent variable\n",
+    "            'agg_type':'mean', # (string) - aggregation for dependent variable\n",
+    "            'min_cell_count':None, # (integer) - Minimum number of cells per well\n",
+    "            'regression_type':'ols', # (string) - Type of regression (ols, glm, mixed, ridge, lasso).\n",
+    "            'random_row_column_effects':False, # (bool) - Remove plate , row and column random effects.\n",
+    "            'y_lims':[[0,9], [12, 16]], # (list of lists) limits for broken y axis\n",
+    "            'plate':None, # (string or NoneType) - strinf to replace plate column values with\n",
+    "            'cov_type':None, # (string) - covariance type for ols regression\n",
+    "            'volcano':'gene', # (string) - mode for significant resuls (gene, grna, all)\n",
+    "            'alpha':0.8} # (float) - alpha for hinge and lasso regression\n",
+    "\n",
+    "coef_df = perform_regression(settings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

spacr-0.3.60/notebooks/spacr_computer_vision.ipynb → spacr-0.3.62/notebooks/3b_spacr_computer_vision.ipynb

@@ -9,7 +9,7 @@
    },
    "outputs": [],
    "source": [
-    "# use this cell to generate train and test folders: datasets/train/nc and pc and datasets/test/nc and pc\n",
+    "# Description: use this cell to generate train and test folders: datasets/train/nc and pc and datasets/test/nc and pc\n",
     "from spacr.io import generate_training_dataset\n",
     "\n",
     "settings = {'src':'path', # (path) path to source folder (where origional images were stored)\n",
@@ -37,7 +37,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# train a torch model\n",
+    "# Description: train a torch model\n",
     "from spacr.deep_spacr import train_test_model\n",
     "\n",
     "settings = {'src':'path', # (path) path to source folder (ends with datasets/training)\n",
@@ -81,7 +81,7 @@
    },
    "outputs": [],
    "source": [
-    "# generate a tar dataset\n",
+    "# Description: generate a tar dataset\n",
     "\n",
     "from spacr.io import generate_dataset\n",
     "\n",
@@ -100,7 +100,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# apply a model to a tar dataset\n",
+    "# Description: apply a model to a tar dataset\n",
     "\n",
     "from spacr.deep_spacr import apply_model_to_tar\n",
     "\n",
@@ -120,10 +120,46 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "28debecd",
+   "id": "9916c814",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "# Description: Fit a regression model to estimate the effect size of gRNAs on cell scores.\n",
+    "from spacr.ml import perform_regression\n",
+    "import pandas as pd\n",
+    "%matplotlib inline\n",
+    "\n",
+    "settings = {'count_data':'path', # (path) path or list of paths to sequencing count data\n",
+    "            'score_data':'path', # (path) path or list of paths to score data\n",
+    "            'score_column':'column', # () - column with cell scores\n",
+    "            'metadata_files':['path.csv','path.csv'], # (list) pahts to gene metadata \n",
+    "            'positive_control':'gene', # (string) - gene to highlight in volcano plot\n",
+    "            'negative_control':'gene', # (string) - gene to highlight in volcano plot\n",
+    "            'min_n':3, # () - \n",
+    "            'fraction_threshold':None, # (Optional, float or NoneType) - Minimum threshold for gene fraction, if None automatically calculated\n",
+    "            'target_unique_count':5, # () - Number of expected unique gRNAs per well\n",
+    "            'tolerance':0.02, # (float) - Tollerance for cells per well limit\n",
+    "            'log_x':False, # () - gRNA Fraction plot X axis log\n",
+    "            'log_y':False, # () - gRNA Fraction plot Y axis log\n",
+    "            'x_lim':None, # () - Volcano X axis limit\n",
+    "            'control_wells':['c1','c2','c3'], # (list) - Metadata to exclude from regression model\n",
+    "            'filter_column':'column', # (str) - Column containing control metadata to remove\n",
+    "            'dependent_variable': 'column', # (string) - Dependent variable for regression\n",
+    "            'threshold_method':'var', # (string) - effect size thresold type (std or var)\n",
+    "            'threshold_multiplier':4, # (integer) - effect size threshold multiplyer \n",
+    "            'transform':'log', # (string) - Transform dependent variable\n",
+    "            'agg_type':'mean', # (string) - aggregation for dependent variable\n",
+    "            'min_cell_count':None, # (integer) - Minimum number of cells per well\n",
+    "            'regression_type':'ols', # (string) - Type of regression (ols, glm, mixed, ridge, lasso).\n",
+    "            'random_row_column_effects':False, # (bool) - Remove plate , row and column random effects.\n",
+    "            'y_lims':[[0,9], [12, 16]], # (list of lists) limits for broken y axis\n",
+    "            'plate':None, # (string or NoneType) - strinf to replace plate column values with\n",
+    "            'cov_type':None, # (string) - covariance type for ols regression\n",
+    "            'volcano':'gene', # (string) - mode for significant resuls (gene, grna, all)\n",
+    "            'alpha':0.8} # (float) - alpha for hinge and lasso regression\n",
+    "\n",
+    "coef_df = perform_regression(settings)"
+   ]
   }
  ],
  "metadata": {

spacr-0.3.62/notebooks/4_spacr_annotate.ipynb

@@ -0,0 +1,48 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d6a39408",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from spacr.gui_utils import annotate\n",
+    "\n",
+    "settings = {'src':'/nas_mnt/carruthers/Einar/tsg101_screen/TSG101SCREEN_20240826_140251/plate4', # (path) path to source folder (where origional images were stored)\n",
+    "            'image_type':'cell_png', # (Optional, string) string in the path of each image (used to filter images)\n",
+    "            'channels':['r', 'g', 'b'], # (list) - Channels to visualize ('r', 'g', and/or 'b')\n",
+    "            'img_size':200, # (integer) - Size of images on the screen (height and weight)\n",
+    "            'normalize_channels':['r','g','b'], # (list) - Channels to normalize\n",
+    "            'annotation_column':'test', # (string) - Column in the database containing/to contain annotations\n",
+    "            'normalize':False, # (bool) - Normalize images to percentiles\n",
+    "            'percentiles':(2,98), # (tuple) - Percentiles used for normalization\n",
+    "            'measurement':None, # (string or NoneType) - Measurement used to filter images\n",
+    "            'threshold':None} # (Integer or NoneType) - Threshold for measurement\n",
+    "\n",
+    "annotate(settings)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "spacr",
+   "language": "python",
+   "name": "spacr"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.19"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}