Live cell imaging has not been an active method of analysis during the drug discovery and development phase due to several limitations. This does not change the fact that it along with its time series data analysis describes an undergoing process better than a conventional study with fixed time points. In this project, I was a part of a team which are currently developing live cell morphological profiling assays which allows measuring cells’ morphology and perturbations caused on it due to toxicity by different treatments. Later, I attempted automating a group of robots to perform these assays automatically. I also developed a few software pipelines which generate quantitative data from live cell images, and performs analysis and data visualization on this quantitative time series data. Later, I implemented these methods on one of the experiment set and displayed importance of time series data by showing different trends displayed by different treatments for different morphology descriptors.

Microscopy imaging based techniques, such as the Cell Painting assay, could be used to generate images that visualize the Mechanism of Action (MoA) of a drug, which could be of great use in drug development. In order to extract information and predict the MoA of a new compound from these images we need powerful image analysis tools. The purpose with this project is to further develop a Deep Learning model to predict the MoA of different drugs from Cell Painting images using Convolutional Neural Networks (CNNs) and Conformal Prediction. The specific task was to compare the accuracy of different CNN architectures and to compare the efficiency of different nonconformity functions.  During the project the CNN architectures ResNet50, ResNet101 and DenseNet121 were compared as well as the nonconformity functions Inverse Probability, Margin and a combination of them both. No significant difference in accuracy between the CNNs and no difference in efficiency between the nonconformity functions was measured. The results showed that the model could predict the MoA of a compound with high accuracy when all compounds were used both in training, validation and test of the model, which validates the implementations. However, it is desirable for the model to be able to predict the MoA of a new compound if the model has been trained on other compounds with the same MoA. This could not be confirmed through this project and the model needs to be further investigated and tested with another dataset in order to be used for that purpose.

Purpose This project aims to explore the classification method of kinase inhibitors with five-channel cell painting image data based on the deep learning model. Methods A ResNet50 transfer learning model was used as the starting point to build the deep neural network (DNN) model, where different DNN parameters were selected to make the deep learning model more suitable for the cell painting data. Two different adaptive layers (adaptive average pooling 3D and convolution 2D) were added separately before the ResNet50 transfer learning model to adapt the five-layer cell painting image to the neural network. In addition, the skimage.transform.resize function was used to compress the five-layer cell painting image. Results The proposed deep learning model demonstrates the effectiveness in all three classification experiments. The proposed model performs particularly well in classifying among control, EGFR, PIKK and CDK kinase inhibitors families. It achieves an F1-score of 0.7764 on all four targets and has a 93\% accuracy rate in the PIKK kinase inhibitors family. The adaptive average pooling 3D layer successfully adapts the five-layer images to the model, resulting in an improved effect. The training time of the model is significantly reduced to one-fortieth by compressing the image size. Conclusion The proposed model achieved convincing effectiveness in classifying families, which showed progress in building the deep learning model to classify kinase inhibitors on five-channel cell painting data. This study also proved the feasibility of directly inputting five-channel cell painting images to DNN. In addition, the speed of the model increased sharply by compressing the image size without an obvious loss of data information.