Thrilled to share our newest publication!
Leveraging the JUMP-CP consortium’s vast dataset, we described and compared multiple Deep Learning approaches for analyzing HCS data, particularly from U2OS cells and employing the CellPainting protocol.
We show strengths and weaknesses of both supervised and self-supervised learning techniques as well as transferability of such models to other datasets. Our findings demonstrate the potential for broader, cost-effective application in drug discovery, offering strategic insights for HCS data analysis.
This publication was made possible through our collaboration with Janssen Pharmaceutica and Jagiellonian University.
Abstract
Biomedical imaging techniques such as high content screening (HCS) are valuable for drug discovery, but high costs limit their use to pharmaceutical companies. To address this issue, The JUMP-CP consortium released a massive open image dataset of chemical and genetic perturbations, providing a valuable resource for deep learning research. In this work, we aim to utilize the JUMP-CP dataset to develop a universal representation model for HCS data, mainly data generated using U2OS cells and CellPainting protocol, using supervised and self-supervised learning approaches. We propose an evaluation protocol that assesses their performance on mode of action and property prediction tasks using a popular phenotypic screening dataset. Results show that the self-supervised approach that uses data from multiple consortium partners provides representation that is more robust to batch effects whilst simultaneously achieving performance on par with standard approaches. Together with other conclusions, it provides recommendations on the training strategy of a representation model for HCS images.
Read the full article here
