Background
Traditional omics techniques offer static snapshots of cellular processes, limiting the understanding of dynamic biological systems. Live-cell imaging allows observation of cell behavior over time but there is a lack of large-scale, publicly available datasets and robust analytical models. The project Time-Resolved Imaging and Multi-Channel Evaluation of Cellular Dynamics (TIMED) addresses this gap by combining advanced live-cell imaging with artificial intelligence (AI) to investigate cellular dynamics, particularly in the context of cancer.
Research Questions
TIMED aims to develop a robust framework for collecting, processing, and analyzing complex time-resolved cellular imaging data. Key research questions include: how to implement efficient iterative experimental designs; manage the combinatorial explosion of experiments with multiple perturbagens; apply AI to de novo compound design for cellular reprogramming; and applying the developed methods to identify novel treatments for ovarian cancer through analysis of dynamic cellular responses.
Aim
The primary aim is to establish a novel framework for studying cellular dynamics through advanced imaging and AI. Specific objectives include: generating and publishing large-scale time-series image datasets; developing AI-driven experimental design strategies; using ovarian cancer as a model system; building predictive and generative AI models; and validating findings using patient-derived materials.
Research Program
TIMED consists of five interconnected work packages:
• WP1: New theory for designing and optimising dynamic cell experiments (Lead: Panahi).
• WP2: Large-scale temporal multi-channel cell perturbation experiments (Lead: Spjuth).
• WP3: Robust scalable Bayesian ML for dynamic data (Lead: Singh).
• WP4: Deep generative modeling (Lead: Mercado).
• WP5: Real-life validation using primary patient material (Lead: Seashore-Ludlow).
Synergy & Team
TIMED exemplifies the collaboration between the SciLifeLab and Wallenberg National Program for Data-Driven Life Science (DDLS) and the Wallenberg AI, Autonomous Systems and Software Program (WASP), bringing together complementary expertise across artificial intelligence, and data-driven life science.
The team includes Rocío Mercado (WASP) and Ola Spjuth (DDLS) as main PIs, contributing expertise in generative AI, computational modeling, bioinformatics, and high-content imaging. They are joined by Ashkan Panahi, Prashant Singh, and Brinton Seashore-Ludlow, whose combined strengths in optimization, Bayesian machine learning, and translational cancer research form a cohesive foundation across disciplines. The project is further supported by SciLifeLab and industrial partners such as AstraZeneca.
Cover photo by: National Cancer Institute on Unsplash