A current challenge in bioimaging for immunology and immunotherapy research lies in analyzing multimodal and multidimensional data that capture dynamic interactions between diverse cell populations. Here, we introduce Celldetective, an open-source Python-based software designed for high-performance, end-to-end analysis of image-based in vitro immune and immunotherapy assays. Purpose-built for multicondition, 2D multichannel time-lapse microscopy of mixed cell populations, Celldetective is optimized for the needs of immunology assays. The software seamlessly integrates AI-based segmentation, Bayesian tracking, and automated single-cell event detection, all within an intuitive graphical interface that supports interactive visualization, annotation, and training capabilities. We demonstrate its utility with original data on immune effector cell interactions with an activating surface, mediated by bispecific antibodies, and further showcase its potential for analyzing extensive sets of pairwise interactions in antibody-dependent cell cytotoxicity events..

https://doi.org/10.7554/eLife.105302.1

_{A. An end-to-end GUI pipeline for studying interactions between target and effector cell pairs (from left to right). After loading an experiment project that mimics a multiwell plate structure, the user can apply preprocessing steps to the 2D time lapse microscopy images before segmentation. Target and effector cells are then segmented, tracked, and measured independently. Events are detected from the resulting time series, and the co-culture images are distilled into tables of single-cell measurements. The neighborhood module links cells in spatial proximity, and the cell-pair signal analysis framework facilitates the investigation of interactions between cell pairs. Eye and brush icons indicate steps where visual control and corrections are possible, with an appropriate viewer. B.Schematic (top) and snapshot (bottom) of a spreading assay imaged by time-lapse RICM. C Intensity time series for a cell performing a contact and spreading sequence. D Schematics side-view of target/NK cells co-culture assay for bispecific ADCC (top) and representative multimodal composite images, obtained at two different time points, with target nuclei labelled in blue, dying cells in red and NK cells in green (bottom). Corresponding colors are also used in the schematics. Decomposition of partly overlapping fluorescence channels and benchmark of segmentation DL models}

In recent years, immunotherapy has brought about a paradigm shift in the treatment of cancer, making it possible to stimulate and re-arm the immune system against the disease. One strategy already used against certain cancers involves injecting molecular engaging agents (e.g. bispecific monoclonal antibodies) capable of recruiting immune cells such as lymphocytes to directly attack the targeted tumour cells. These bispecific molecules act as a molecular bridge between activating receptors on immune cells and tumour antigens exposed by the target cells. Despite the potential of these new agents, the ability to predict their efficacy remains limited, as it depends on both the patient and the details of the agents molecular structure. Patrick Chames and his team (CRCM) have for several years been developing bispecific antibodies constructed from camelid monodomain antibodies, known as nanobodies.

the authors tested in-vitro a range of 6 original bispecific antibodies combining several nanobodies, and recruiting Natural Killer cells from 15 healthy donors to different target tumour cell lines. They systematically measured the quantity of target cells killed for varying concentrations of engaging molecules, taking into account biophysical parameters such as antibody affinity and receptor density. These data showed that it was possible to largely decouple the role of donor cells from the molecular details of the engager to predict the effective engager dose. They also proposed a simple formula for quantitatively predicting this effective dose in vitro.

DOI: 10.1021/acsnano.4c08541

Original bispecific engager molecules are being tested to recruit immune cells from healthy donors to kill tumour cells. Donor and molecule parameters are decoupled and the multi-scale model predicts the optimal dose required to kill in vitro (Credit: L. Limozin).

We are pleased to announce the publication of a review authored by Pierre Bongrand in the International Journal of Molecular Sciences. This review examines the growing integration of artificial intelligence into everyday biomedical research and practice, questioning whether this represents a true scientific revolution or a temporary hubris of its potential.

The paper explores:

• Insights based on a review of past scientific progress, with an emphasis on immunology, it is concluded that current “omic” data contain useful information that is not adequately interpreted by currently available theoretical processing methods.
• A brief description of currently available artificial intelligence tools is presented, with a discussion of expected potential and pitfalls.
• Applications of AI in the biomedical field, are described with an emphasis on the biomedical domain.

It is concluded that it is already warranted to apply artificial intelligence to routine biomedical practice, but it is essential to develop validation procedures.

https://doi.org/10.3390/ijms252413371.