Prostate cancer classification workflow

This workflow segments tissue regions and classifies prostate cancer on H&E whole slide images, using AI. It consists of three steps:

1. low-resolution tissue segmentation to select areas for further processing;

2. high-resolution tissue segmentation to refine borders - it uses step 1 as input;

3. high-resolution normal/cancer classification - it uses step 1 as input.

Tissue segmentation workflow

This workflow performs tissue segmentation on H&E whole slide images using AI.

Fragment-based virtual screening with docking and pose scoring

Dock a compound library against a target protein with rDock and validate the poses generated against a reference fragment using SuCOS to compare the feature overlap. Poses are filtered by a user-specified SuCOS threshold.

A list of fragments should be specified which will be used to define the cavity for docking, using the 'Frankenstein ligand' technique. For more details, please see https://www.informaticsmatters.com/blog/2018/11/23/cavities-and-frankenstein-molecules.html ...