Fig. 4
From: Attention-based deep learning for accurate cell image analysis
Feature landscape of single cell features and multiple cell features. (a) The feature landscape of multiple cell features images using the X-Profiler model, each point represents a batch of 100 cell-slice images. (b) The feature landscape of single cell features using the X-Profiler model, each point represents a single cell-slice image. (c) The feature landscape of multiple cell features using DeepProfiler, each point represents average value of 100 single cell-slice images’ feature which were random seleted. (d) The feature landscape of single cell features using the DeepProfiler, each point represents a single cell-slice image and images were random seleted. (e) The feature landscape of multiple cell features using the CellProfiler model, each point represents average value of 100 single cell-slice images’ feature which were random seleted. (f) The feature landscape of single cell features images using the CellProfiler model, each point represents a single cell-slice image and images were random seleted. (g) The single cell-slice images of four compounds. For the four compounds (Bedaquiline, belzutifan, carvedilol and daclatasvir), each compound has one row and three columns of images. Images were taken with a 20x water objective. Scale bars = 50 mm (h) The box plot of MMP and ROS intensity of belzutifan, carvedilol, daclatasvir and betrixaban. ROS: reactive oxygen species. MMP: mitochondrial membrane potential.
