1.0.0 Cell Painting

Application Name

Cell Painting

Version

1.0.0

Documentation Version

16.10.2023 - 1

Input Image(s)

Multichannel Images; 5-8 channels; 8 Bit or 16 Bit

Input Parameter(s)

Regions of interest (optional)

Keywords

cell painting, cells, nuclei, cytoplasm, fluorescent, multichannel, in-vitro, microscopy, morphological profiling, high-throughput analysis

Short Description

This application automatically evaluates multi-well plate multichannel images that utilize five fluorescent dyes. The cells, nuclei and cytoplasm are segmented and quantified in each image.

References / Literature

For more information regarding Cell Painting please see:

https://www.nature.com/articles/nprot.2016.105/

Table of contents

IKOSA Prisma Cell Painting Assay

You can use this image analysis application or any of our other applications in your account on the IKOSA platform. If it is not in the list of available applications, please contact your organization's administrator or our team at support@kmlvision.com.

Application description

Cell Painting is the morphological profiling of cell populations to study the phenotypic or functional impacts of perturbations. This application automatically evaluates multi-well plate multichannel images that utilize five fluorescent dyes. The cells, nuclei and cytoplasms are segmented and quantified in each image.

This analysis can be performed on multichannel images containing five- to eight channels. The first five channels must be in a specific order (see Input data requirements section).

In the following sections, we provide the input data requirements that are necessary to obtain accurate image analysis results and a description of the output files.

Input data requirements

Input image(s)

Input for this application is the following image data:

Image type

Color channels

Color depth (per channel)

Size (px)

Resolution (μm/px)

Image type

Color channels

Color depth (per channel)

Size (px)

Resolution (μm/px)

Multichannel

 

Check image formats

Minimum of 5 and up to 8.

The first five channels must be in the following order:

  • Mito

  • AGP

  • RNA

  • ER

  • DNA

Further channels (up to 3) are supported and may be in any order.

 

8 Bit or 16 Bit

Standard images: max: 3,072 x 3,072

typically: 0.3-1.16

Image content

The captured high-content microscopy images provide information about various subcellular structures and compartments such as:

  • Mito (Mitochondria)

  • AGP (Cytoskeleton)

  • RNA (Ribonucleic acid)

  • ER (Endoplasmic reticulum)

  • DNA (Deoxyribonucleic acid)

Optionally, up to 3 further channels can be analyzed for the same field of view.


The Cell Painting input images represent usually crowded cells after specific chemical treatments, captured as a multichannel image with 5 fluorescent channels and 3 brightfield channels.

Important:

For all images, the following requirements apply:

  • The illumination must be constant throughout the image(s).

  • The sample must be in focus, i.e. no blurry regions in image(s).

  • The images must have a minimum of five channels in the following order:

    • Mito

    • AGP

    • RNA

    • ER

    • DNA

Input parameter(s)

No additional input parameters are required for this application.

As an optional parameter, a single or multiple regions of interest (ROIs) can be defined in which the analysis should be performed (‘inclusion ROIs’).

Description of output files and their content

Files

File format

Description

 

File format

Description

 

1

csv

results_01_cells.csv:

A csv file containing the analysis results for the segmented objects in each channel for the input image or all inclusion ROIs. Overall 1917 object features are extracted for each cellular compartment.

The extracted feature groups are:

  • Intensity (152)

  • Correlation (224)

  • Neighbors (14)

  • AreaShape (25)

  • Zernike (30)

  • Granularity (128)

  • RadialDistribution (96)

  • Texture (1248)

 

2

csv

results.csv:

A csv file containing the analysis results for the input image or all inclusion ROIs.

 

3

jpg

results_vis/<compartment_id>_<compartment_name>_vis.jpg (for multichannel image, no ROI), or

results_vis/<compartment_id>_<compartment_name>_<roi-id>.jpg (for multichannel image, ROI <roi-id>):

A visualization of the analysis result for a specific compartment (of a multichannel image) for either the whole image (if no inclusion ROIs selected for analysis) or each individual inclusion ROI.

Description for visualizations:

  • White contours: border lines of the segmented objects

  • Numbers: Identified cells and the corresponding nuclei, cytoplasms

Please note: If the objects' borders are within a 5-pixel distance from the image border, they will be excluded from segmentation and feature extraction, to prevent non-complete cell analysis.

Please note: The model operates under the assumption that the cells are mononuclear.

Cell segmentation output
Nucleus segmentation output
Cytoplasm segmentation output

Please note: The image quality might be reduced for the presentation in the technical docs.

For this application the dataset “CPG0000-JUMP-pilot” was used, available on https://registry.opendata.aws/cellpainting-gallery/.

 

4

json

annotation_results.json:

JSON file containing detected compartment objects (covered regions). The position is measured from the left upper corner (1,1) of the image.

 

5

json

roiMeta.json:

A json file containing all information regarding the ROIs defined for the analysis job to ensure reproducibility. The file is empty if no ROIs were defined for analysis.

 

6

jpg

rois_visualization.jpg:

An overview visualization to show locations of all analyzed ROIs for the 2D image of a multichannel image.

Please note: This file is only created if inclusion ROIs were defined for analysis.

 

7

json

jobResultBundleMeta.json:

A json file containing all information regarding the analysis job (application name and version, project, etc.) to ensure reproducibility.

Please note: This file is only included if bundled or merged analysis jobs are downloaded.

 

Please note:

  • In the case where inclusion ROIs are partially outside of the image, the ROIs are cropped to the areas that lie inside the image.

  • In the case where inclusion ROIs are completely outside of the image, no analysis is performed. However, they are still listed in corresponding results files.

  • A <roi-id> is generated automatically by the application corresponding to the creation date of a ROI. The location of an ROI within an image with its specific <roi-id> can be seen in the file “rois_visualization.jpg.” ROIs that are completely outside of the image are not shown in this file.

  • All visualizations are downscaled to 25 megapixels (MP), if the original image or inclusion ROI is larger than 25 MP.

Content

results_01_cells.csv

Single csv-file

Column NO.

Column name

Description

Column NO.

Column name

Description

1

roi_id

<roi-id> starting from “ROI-01”. Empty, if no inclusion ROI is specified and the whole image was analyzed.

2

roi_name

Custom text to identify the ROI. Empty, if no inclusion ROI is specified and the whole image was analyzed.

3

roi_size [Px^2]

Size of the ROI that was analyzed in pixels^2. The size of the whole image is given if no inclusion ROI is specified and the whole image was analyzed.

4

object_id

Identifier number of the individual compartments.

4 - 156
1922 - 2073
3839 - 3990

Cells_Intensity_<feature>
Nuclei_Intensity_<feature>
Cytoplasms_Intensity_<feature>

Intensity feature measurements for identified objects.

157 - 380
2074 - 2297
3991 - 4214

Cells_Correlation_<feature>
Nuclei_Correlation_<feature>
Cytoplasms_Correlation_<feature>

Correlation between intensities in different channels within identified objects.

381 - 394
2298 - 2311
4215 - 4228

Cells_Neighbors_<feature>
Nuclei_Neighbors_<feature>
Cytoplasms_Neighbors_<feature>

Properties about the relationships of the neighboring objects.

395 - 419
2312 - 2336
4229 - 4253

Cells_AreaShape_<feature>
Nuclei_AreaShape_<feature>
Cytoplasms_AreaShape_<feature>

Area and shape features of the identified objects.

420 - 449
2337 - 2366
4254 - 4283

Cells_AreaShape_Zernike_<feature>
Nuclei_AreaShape_Zernike_<feature>
Cytoplasms_AreaShape_Zernike_<feature>

Distribution of intensities across the identified objects.

450 - 577
2367 - 2494
4284 - 4411

Cells_Granularity_<feature>
Nuclei_Granularity_<feature>
Cytoplasms_Granularity_<feature>

Spectra of size measurements of the textures within the identified objects.

578 - 673
2495 - 2590
4412 - 4507

Cells_RadialDistribution_<feature>
Nuclei_RadialDistribution_<feature>
Cytoplasms_RadialDistribution_<feature>

Spatial distribution of intensities within each identified object.

674 - 1921
2591 - 3838
4508 - 5755

Cells_Texture_<feature>
Nuclei_Texture_<feature>
Cytoplasms_Texture_<feature>

Degree and nature of textures within identified objects to quantify their roughness and smoothness.

Please note: AreaShape parameter values are calculated using https://scikit-image.org/. and the feature measurements are based on the CellProfiler software documentation.

results.csv

Single csv-file

Column NO.

Column name

Examples

Value range

Description

Column NO.

Column name

Examples

Value range

Description

1

roi_id

ROI-03

ROI-01 - 

<roi-id> starting from “ROI-01”. Empty, if no inclusion ROI is specified and the whole image was analyzed.

2

roi_name

“central”

text

Custom text to identify the ROI. Empty, if no inclusion ROI is specified and the whole image was analyzed.

3

roi_size [Px^2]

1212212

1 -

Size of the ROI that was analyzed in pixels^2. The size of the whole image is given if no inclusion ROI is specified and the whole image was analyzed.

4

bit_depth [bit]

8

8 or 16

Number of bits used to represent the value of each pixel of the image.

5

number_of_channels

6

5 - 8

The count of the distinct data layers to represent the uploaded image.

6

Cells_total_area [Px^2]

1011878

0 - #of pixels in image

Total area with adherent cells in Pixel^2, includes cell-covered area and free/floating cells).

7

Cells_total_area [%]

68.6

0 - 100

Ratio of total area with adherent cells to the total area of the image.

8

Cells_total_num_of_objects

5

0 -

The total number of the complete cells on the analyzed image.

9
18
27

Cells_Overall_mean_intensity
Nuclei_Overall_mean_intensity
Cytoplasms_Overall_mean_intensity

37.9136

0 - 65535

The overall mean intensity for the compartments.

10 - 17
19 - 26
28 - 35

Cells_<channel>_mean_intensity
Nuclei_<channel>_mean_intensity
Cytoplasms_<channel>_mean_intensity

10.0729816

0 - 65535

The mean channel intensity for each compartment.

Please note: If one or more ROIs were specified, the results in a specific row refer to the ROI specified in the corresponding columns, otherwise (empty ROI columns) the results refer to the whole image.

Error information

More information about errors can be found in the Application Error Documentation.

Contact

If you have any questions about this app, as well as suggestions or ideas for new ones, email us at support@kmlvision.com.

Feel free to book a 30-minute meeting to speak with us about IKOSA and the apps!

https://calendly.com/kmlvision/book-the-ikosa-platform-demo

Copyright 2016-2021 KML Vision GmbH. IKOSA® is a registered EU trademark.