iTRADE: image-based TRAnsfer learning for Drug Effects

iTRADE: image-based TRAnsfer learning for Drug Effects

This dataset supports Berker et al. (2022) IEEE Trans Med Imaging, https://doi.org/10.1109/TMI.2022.3205554.

It comprises microscopy images, layout information and metabolic readouts for a total of 18 acquisitions: 1 control experiment (CE) and 17 drug screens (DS).

.
├── Images
├── Layouts
├── MeanOfStack
├── Metabolic
└── README.md

4 directories, 1 file

Images: microscopy images

In total, the dataset contains 1 × 420 + 17 × 1848 = 31836 TIFF images (2123194264 bytes) in 18 folders.

Images
├── BT-40_V2_DS1
├── BT-40_V3_DS1
├── BT-40_V3_DS2
├── HD-MB03_V1_DS1
├── HD-MB03_V1_DS2
├── HD-MB03_V2_DS1
├── HD-MB03_V2_DS2
├── INF_R_1021_relapse1_V1_DS2
├── INF_R_1025_primary_V2_DS1
├── INF_R_1123_primary_V1_DS1
├── INF_R_153_CE
├── INF_R_153_V2_DS1
├── INF_R_153_V3_DS1
├── NCI-H3122_V2_DS1
├── SJ-GBM2_V2_DS1
├── SMS-KCNR_V1_DS1
├── SMS-KCNR_V2_DS1
└── SMS-KCNR_V2_DS2

18 directories, 0 files

Control experiment

The INF_R_153_CE folder contains images for a control experiment using the INFR153 cell line subjected to DMSO in 7 × 14 = 98 wells and staurosporine (STS) in 8 × 14 = 112 wells on a single 384-well plate (ignoring border wells). Each well is represented by 2 images (maximum intensity projection, proj, and mid-z image, midz), respectively. In total, this folder contains (7 + 8) × 14 × 2 = 420 images (26 megabytes).

Images/INF_R_153_CE
├── [ 60K] INF_R_153_CE_P1_B05_midz_224x224.tif
├── [ 58K] INF_R_153_CE_P1_B05_proj_224x224.tif
┆ ...
├── [ 62K] INF_R_153_CE_P1_O23_midz_224x224.tif
└── [ 59K] INF_R_153_CE_P1_O23_proj_224x224.tif

0 directories, 420 files

Drug screens

Other folders, such as BT-40_V2_DS1, are named for screen identifiers, which consist of a sample identifier (name of cell line, INF_R_153|BT-40|HD-MB03|NCI-H3122|SJ-GBM2|SMS-KCNR, or INFORM pseudonym of primary patient-derived sample, INF_R_[0-9]{3,}_(primary|relapse[0-9])) followed by _V[0-9]_DS[0-9] indicating the biological (V) and the technical (DS) replicate. For the three patient-derived samples included (INF_R_[0-9]{4}), V1 signifies fresh viable tissue shipped immediately after biopsy while V2 indicates a cell culture shipped after establishment.

Each drug-screen folder contains images for a single drug screen consisting of 3 plates per screen, 14 × 22 = 308 wells per plate (namely, a 384-well plate ignoring all border wells), and 2 images per well. In total, each folder contains 3 × 14 × 22 × 2 = 1848 images (112 to 146 megabytes).

Images/BT-40_V2_DS1
├── [ 62K] BT-40_V2_DS1_P1_B02_midz_224x224.tif
├── [ 58K] BT-40_V2_DS1_P1_B02_proj_224x224.tif
┆ ...
├── [ 60K] BT-40_V2_DS1_P3_O23_midz_224x224.tif
└── [ 54K] BT-40_V2_DS1_P3_O23_proj_224x224.tif

0 directories, 1848 files

Images/BT-40_V3_DS1
├── [ 64K] BT-40_V3_DS1_P1_B02_midz_224x224.tif
├── [ 61K] BT-40_V3_DS1_P1_B02_proj_224x224.tif
┆ ...
├── [ 63K] BT-40_V3_DS1_P3_O23_midz_224x224.tif
└── [ 62K] BT-40_V3_DS1_P3_O23_proj_224x224.tif

0 directories, 1848 files

...

Image files

Image file names of the form $ScreenID_P[123]_[B-O][0-9]{2}_(midz|proj)_[0-9]+x[0-9]+.tif include the plate number (1, 2, 3), the well coordinates (B02 to O23), the image type (midz|proj) and the size of the square images (224x224).

Images are stored in Tagged Image File Format (TIFF), using a 16-bit integer in little-endian encoding for each pixel value. Files have been read from original TIFF image files and downscaled using the Keras-Preprocessing (v1.1.2) load_img function, and resaved (from plain image arrays without any metadata) using the opencv-python (v4.5.5.62) imwrite function using Adobe Deflate as a compression algorithm.

Layouts: layout information

Layouts
├── Drugs.csv
├── Layout_CE.csv
└── Layout_DS.csv

0 directories, 3 files

Two text files, Layout_CE.csv and Layout_DS.csv, describe the layout of control experiments (CE) and drug screens (DS), respectively. Note that Layout_DS.csv has been generated from the imaging layout file published with the iTReX web app (available at https://itrex.kitz-heidelberg.de/), which can be downloaded from GitHub or iTReX. See itrade.util.layouts.convert_itrex_ds_layout() for details.

A third text file, Drugs.csv, maps drug names as used in the iTReX-based Layout_DS.csv to drug names, abbreviations and drug (sub-)classes used throughout the manuscript. This file is used only by plots.R.

All layout information is stored in long-table format. Text files are stored as Comma-Separated Values (CSV) with UTF-8 character encoding and Unix-style (LF) line endings.

MeanOfStack: mean-of-stack measurements

For each drug screen represented by a folder named after the screen identifier, mean-of-stack computations produced from the full-resolution (2048x2048 pixels) are stored in matrix format using one text file per plate, named SID_P[123]_$Barcode.txt, e.g., BT-40_V2_DS1_P1_H104-03N1A98.txt. Text files are stored as Tab-Separated Values (TSV) with UTF-8 character encoding and Unix-style (LF) line endings. This folder comprises a total of 17 × 3 = 51 text files.

MeanOfStack
├── BT-40_V2_DS1
│ ├── BT-40_V2_DS1_P1_H104-03N1A98.txt
│ ├── BT-40_V2_DS1_P2_H104-03N2A98.txt
│ └── BT-40_V2_DS1_P3_H104-03N3A98.txt
├── BT-40_V3_DS1
│ ├── BT-40_V3_DS1_P1_H104-03N1D07.txt
│ ├── BT-40_V3_DS1_P2_H104-03N2D07.txt
│ └── BT-40_V3_DS1_P3_H104-03N3D07.txt
┆ ...
└── SMS-KCNR_V2_DS2
├── SMS-KCNR_V2_DS2_P1_H104-03N1D02.txt
├── SMS-KCNR_V2_DS2_P2_H104-03N2D02.txt
└── SMS-KCNR_V2_DS2_P3_H104-03N3D02.txt

17 directories, 51 files

Metabolic: metabolic readouts

Similar to mean-of-stack computations, metabolic readouts are included for each drug screen. Folder and file names and file formats are identical to the MeanOfStack folder.

Metabolic
├── BT-40_V2_DS1
│ ├── BT-40_V2_DS1_P1_H104-03N1A98.txt
│ ├── BT-40_V2_DS1_P2_H104-03N2A98.txt
│ └── BT-40_V2_DS1_P3_H104-03N3A98.txt
├── BT-40_V3_DS1
│ ├── BT-40_V3_DS1_P1_H104-03N1D07.txt
│ ├── BT-40_V3_DS1_P2_H104-03N2D07.txt
│ └── BT-40_V3_DS1_P3_H104-03N3D07.txt
┆ ...
└── SMS-KCNR_V2_DS2
├── SMS-KCNR_V2_DS2_P1_H104-03N1D02.txt
├── SMS-KCNR_V2_DS2_P2_H104-03N2D02.txt
└── SMS-KCNR_V2_DS2_P3_H104-03N3D02.txt

17 directories, 51 files