Researchers: Rocio Mercado (CHT), Ola Spjuth (UU), Ashkan Panahi (CTH), Prashant Singh (UU) and Brinton Seashore-Ludlow (KI)

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 TIMED project 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 DDLS and 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.

Contact main PIs:
Rocio Mercado, rocio.mercado@chalmers.se
Ola Spjuth, ola.spjuth@uu.se

Researchers: Thomas Schön (UU), Johan Elf (UU) and Magda Bienko (KI)

Background: How can AI help us understand the structure of DNA and its function, the very organization of life? The DNA sequence has for a long time been viewed as linear, but since the molecule is compactly folded to fit in the cells, the complex 3D organization likely affects how the information is read. DNA is arranged in chromosomes in the cells, ready to be activated when needed. The relationship between chromosome structure and function is a topic of major interest.

The project proposes that the complex organization of DNA and its relation to the constantly moving 3D-structured chromosomes are affecting the regulation and expression of genes and ultimately protein production. The project aims to draw up a map of how DNA is organized inside an Escherichia coli (E. Coli) cell and how the organization of DNA changes from the birth of the cell until it divides.

Research questions: To improve our fundamental understanding of the design principles of chromosomes, it is essential to first grasp the most basic principles, starting with prokaryotes—before adding layers of eukaryotic complexity (chromatin, chromosome numbers, cell-cell communication).

By identifying the rules of chromosomal organization in a less complex, prokaryotic system such as E. coli, we aim to define the basic building blocks that will allow for optimal design of synthetic chromosomes.

Objective 1: Generating a large set of single-cell bacterial 3D genome structures with partial dynamic information. We apply three orthogonal single-cell approaches to generate the first-of-its-kind database of 3D genome organization and dynamics adopted by the model prokaryote organism, Escherichia coli.

Objective 2: Developing machine learning solutions capable of uncovering the rules that govern the dynamics of the bacterial chromosome structure. This bridging effort will combine learning-based spatiotemporal modeling to integrate the data from the three complementary types of data-rich single-cell experiments in WP1 into a 4D model of the bacterial chromosome.

Aim: The main goal is to decipher the fundamental rules that:

a) drive the structural dynamics of bacterial chromosomes in space and time, and

b) determine the regulatory effects of spatial gene positioning.

Synergy and team: The Bienko and Elf groups have ample experience working with big data, already using AI and statistical learning tools to curate and analyze. The effort described in this project is too far-reaching for a standard solution, and the input from Schön’s group is crucial for us to reach the ambitious goals. Schön has a long history of the interplay between basic science and applied problems from the real world.

Contact main PIs:
Thomas Schön, thomas.schon@it.uu.se
Johan Elf, johan.elf@icm.uu.se

Researchers: Claes Lundström (LiU), Mattias Rantalainen (KI), Sophia Zackrisson (LU) and Dave Zachariah (UU)

Background: Cancer is a leading cause of death globally with increasing incidence, breast cancer being the most common cancer in women. Breast cancer is a heterogeneous disease, which is reflected in high variability in outcomes even within well-established subtypes of the disease.

Different aspects of this complexity can be glimpsed from different data modalities including mammograms (radiology) and histopathology slides, molecular information from RNA sequencing, and clinical data from health registries.

In clinical practice, these data are acquired at different stages of the patient’s journey and often manually analyzed and considered in isolation when making clinical decisions. It is beyond human capabilities to integrate the full extent of information and arrive at a detailed and comprehensive view of the entire patient journey.

This project will develop both methodology and AI-models for individual data types (radiology, pathology, molecular, clinical), and models that fuse multiple data types and consider the longitudinal dimension of the patient journey.

The goal is to advance precision diagnostics and decision support for breast cancer treatment.

Research questions: The project focuses on precision diagnostics solutions that offer either prognostic or treatment response predictions.

In addition, the project focuses on rational clinical decision-making that integrates a multitude of parameters, including both routine clinical information and AI-based predictions to provide certified conclusions using causal inference and conformal prediction, and provide an intuitive interface to support decision-making in multidisciplinary teams.

Aim: The overarching aim is to make strategic scientific advances in data-driven multimodal methods to enable true precision diagnostics throughout the breast cancer pathway. The main aims are:

• Development and validation of single- and multi-modal AI-based precision diagnostic models to reduce costs and increase equality in access to advanced diagnostics.

• Focused methodology development in AI-based computer vision, multi-modal AI-based modelling, and data-driven clinical decision-making under uncertainty.

• Development and implementation of data models and infrastructure for multi-modal AI-driven diagnostic research, facilitating transition between research and healthcare.

• Establish the world’s largest multi-site and multi-modal (radiology and pathology images, RNAseq molecular profiling, clinical data) breast cancer study (N >10,000).

Synergy and Team: The project, AID4BC, consists of partners at four sites, with at least two investigators at each site. This is likely the only constellation globally having access to large (>10,000 patients) matched multimodal data across radiology, pathology and molecular profiling and clinical data.

The project has the capacity to perform fully independent validation studies, and to implement prospective validation studies. AID4BC partners have previous experience of developing regulatory-approved medical devices for clinical use, opening clear routes toward clinical translation.

Karolinska Institutet: Provides expertise in predictive medicine and AI-based precision diagnostics, computational and clinical pathology, and cancer epidemiology. KI also contributes large population-representative cohort studies.

Researchers: Main PI, Senior lecturer and Docent Mattias Rantalainen, Prof. Johan Hartman, Dr. Bojing Liu

Lund University: Provides unique data, along with expertise in generating and analyzing molecular data, AI for radiology, pathology and precision-medicine.

Researchers: Prof. Sophia Zackrisson, Associate Prof. Predrag Bakic, Associate Prof. Magnus Dustler.

Uppsala University: Provides expertise in statistical machine methods focusing on causal foundations for internal and externally valid decision-making, as well as efficient learning of multi-modal AI models for large-scale data.

Researchers: Associate Prof. Dave Zachariah, Associate senior lecturer/ Assistant Prof. Jens Sjölund

Linköping University: Offers strong expertise in tackling healthcare adoption challenges for data-driven precision diagnostics. The team brings deep understanding in machine learning and AI-related visualization and access to infrastructure at CMIV.

Researchers: Adj. Prof. Claes Lundström, Associate Prof. Daniel Jönsson

Collaboration with industry and other organizations

Companies Sectra and Stratipath are integral parts of the project. Lund University’s industrial partners include Siemens, ScreenPoint (Transpara), and Collective Mind Radiology. Through the national Analytical Image Diagnostic Arena (AIDA) the project gains a strong connection to Swedish industry and healthcare, as well as with SciLifeLab. Through the innovation environment Swedish AI Precision Pathology (SwAIPP), strong collaboration is established with healthcare, patient organizations and industry.

Impact

AID4BC will have a major impact on several aspects of both the scientific and clinical fronts of breast cancer but will also push the frontiers of AI-based precision diagnostics and causal machine learning methodologies.

In addition to an increase in the understanding of breast cancer and novel biomarkers related to outcome and therapy response, it will drive future breast cancer research and contribute towards transforming clinical diagnosis and management of the disease.

AI-based analyses and decision support hold the promise to reduce costs substantially for precision diagnostics and increase equality in access, ultimately contributing to better outcome for all patients.

The project anticipates multiple high impact publications, with outputs from the project forming the basis for future studies, trials, and translational activities with industry partners.

Contact main PIs:
Claes Lundström, claes.lundstrom@liu.se
Mattias Rantalainen, mattias.rantalainen@ki.se