Biology subjects

Sorger, P. K.

Publications and source records attributed to Sorger, P. K..

At least 19 recordsLinked to original sources

bioRxiv2026

Genomic classification and immune profiling define mucosal melanoma

Mucosal melanoma is a rare, lethal melanoma subtype with distinct genetics and limited benefit from immunotherapy. To define features associated with mucosal melanoma clinical outcomes, we assembled a large, multimodally profiled cohort spanning primary and metastatic disease. Compared with cutaneous melanoma, primary mucosal melanoma showed greater genomic heterogeneity, ploidy and aneuploidy, and a more dedifferentiated, proliferative transcriptional state. Analysis of genomic sequencing of 339 patients with mucosal melanoma identified four mutually exclusive genomic subtypes: CDK4/MDM2/CCND1, SF3B1-mutated, TP53/ATRX, and mucosal melanoma Triple WT, associated with distinct anatomic sites but similar outcomes. In the tumor microenvironment, we observed reduced T cell infiltration and increased CD163+ tumor-associated macrophages in mucosal melanoma relative to cutaneous melanoma. In matched longitudinal samples, CD163+ tumor-associated macrophages increased with disease progression and immunotherapy resistance. CD163+ tumor-associated macrophages engaged non-regulatory T cells through GAL9-TIM-3 interactions, nominating TIM-3 blockade as a therapeutic strategy for mucosal melanoma. These findings define the distinct aggressive biology of mucosal melanoma and highlight potential therapeutic targets and mechanisms of immune resistance.

cancer biology↗

bioRxiv2026

Modeling development of tertiary lymphoid structures in pulmonary tuberculosis by 3D profiling and trajectory analysis

Tertiary lymphoid structures (TLSs) are sites of immune organization in peripheral tissues that arise from chronic inflammation. They play important roles in infection control and cancer but the mechanisms controlling their formation remain only partly understood. Here, we combine high-plex imaging, serial-section 3D reconstruction, and optimal transport trajectory modeling to reconstruct TLSs in human lungs infected with Mycobacterium tuberculosis. We find that the extended and irregular shape of TLSs is poorly captured by 2D histopathology or spatial profiling, making assessment of developmental stage (early, primary, or secondary) error prone. In contrast, modeling TLS development in 3D using optimal transport reveals two trajectories that differ in the timing and coordination of follicular dendritic cell association, germinal center consolidation, and position within the tissue. These findings highlight the value of volumetric analysis in understanding immune organization and provide new insights into TLS biology. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=98 SRC="FIGDIR/small/725201v2_ufig1.gif" ALT="Figure 1"> View larger version (32K): org.highwire.dtl.DTLVardef@11b4daorg.highwire.dtl.DTLVardef@7871feorg.highwire.dtl.DTLVardef@1840c2dorg.highwire.dtl.DTLVardef@3b6028_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LI3D reconstruction of TB-infected lung reveals TLSs to be extended, heterogeneous structures that are frequently misclassified in 2D C_LIO_LITLS maturation follows continuous trajectories rather than discrete histological stages C_LIO_LIOptimal transport modeling identifies distinct maturation paths with divergent follicular dynamics C_LIO_LIGerminal center organization and Tfh-FDC interactions emerge along maturation trajectories C_LIO_LITLS maturation states are shaped by spatially localized microenvironmental niches. C_LI

immunology↗

bioRxiv2026

Compositional and interpretable representation of histology using AI foundation models and sparse autoencoders

Light microscopy of tissue sections stained with hematoxylin and eosin (H&E) has been the foundation of histopathology for over 150 years and remains essential for diagnosis and research. The development of high-plex spatial profiling approaches able to measure protein and RNA expression at single-cell resolution augments but does not replace H&E imaging, even in research. Computational pathology (CPath) models based on deep learning promise to further increase the value of H&E imaging but interpreting these models in biological terms remains challenging. As a result, they are not widely used in spatial profiling studies. Here we describe a human-in-the-loop computational framework that leverages CPath foundation models (FMs) and sparse autoencoders (SAEs) to decompose FM embeddings and automatically identify diverse, human-interpretable histopathology features in H&E images. When FM-SAE modeling was applied to pulmonary diseases such as tuberculosis and lung cancer, human-machine interaction augmented and accelerated expert interpretation. Moreover, the resulting annotations provide a morphology-aware approach to integrating 2D and 3D mesoscale tissue architectures with molecular spatial profiling.

bioinformatics↗

bioRxiv2026

Volumetric Cyclic Immunofluorescence for 3D Spatial Profiling of Immune Structures in Human FFPE Tissue

Mapping how parenchymal, immune, and stromal cells interact with extended structures such as blood vessels and nerves is challenging using conventional thin-section tissue imaging. Volumetric methods such as light-sheet fluorescence microscopy (LSFM) are ideal in these cases and LSFM is widely used in animal models such as fish and mice. This is enabled by well-established clearing methods, genetically encoded reporters, and vascular dyes. However, LSFM is rarely utilized for human tissue, which is primarily available as formaldehyde-fixed paraffin embedded (FFPE) specimens. Here, we present an approach to volumetric cyclic immunofluorescence (v-CyCIF) that enables 40-plex or greater imaging of immune and other cell types in human specimens up to 1 mm thick. We demonstrate the use of v-CyCIF to study neuroimmune interactions and lymphoid structures in normal and cancer tissues. Following LSFM imaging, specimens can be re-embedded and sectioned to ~50 {micro}m thick for high-resolution confocal imaging of punctate structures and cell-cell junctions. v-CyCIF therefore provides a flexible framework for multi-scale 3D profiling of clinical specimens across imaging formats and resolutions.

cancer biology↗

bioRxiv2026

Polypharmacology of an Optimal Kinase Library

Despite decades of research, current understanding of the spectrum of targets bound by kinase inhibitors remains incomplete. This complicates mechanism of action studies, drug repurposing, and development of new therapies. Here, we describe kinome-wide profiling of an optimal kinase library (OKL) comprising 192 small molecules selected based on stage of clinical development, chemical diversity, and target coverage. Our results show that polypharmacology is widespread and independent of regulatory approval. The generally understood ("assigned") targets of approved molecules are not necessarily the most potently inhibited and off-targets include multiple understudied kinases. Moreover, median selectivity has not increased over time We illustrate how an OKL in combination with detailed kinome profiling can be used to identify potential toxicity targets, repurpose anti-inflammatory drugs for neurodegenerative and infectious diseases, and perform chemical genetic studies. Our studies also highlight how much remains to be discovered about the chemistry and biology of one of the largest classes of human therapeutics.

pharmacology and toxicology↗

bioRxiv2026

Harnessing Inflammatory Monocytes to Overcome Resistance to Anti-PD-1 Immunotherapy

BackgroundResistance to immune checkpoint inhibitors represents a major therapeutic challenge, as less than 50% of patients with melanoma achieve long-term response to immune checkpoint inhibitor therapy. One mechanism of acquired resistance involves somatic mutations, such as loss of beta-2 microglobulin (B2m), that enable tumor cells to evade T cell-mediated killing. MethodsThis study used single-cell RNA-seq, flow cytometry, and ex vivo functional assays to characterize tumor-infiltrating immune cells in antigen presentation-deficient tumors. Tumor-bearing mice were treated with anti-PD-1 or CD40 agonist antibodies and cell depletion or cytokine blocking antibodies to define mechanisms of action. Analysis of published human RNA-seq datasets was performed to dissect the contributions of inflammatory monocytes to patient outcomes. ResultsWe found an increase in immunosuppressive macrophages in B2m-null tumors. We hypothesized that repolarizing myeloid cells may restore control of tumor growth. Treatment with CD40 agonist antibody, which promotes differentiation of monocytes and macrophages towards a proinflammatory phenotype, reduced tumor growth and improved survival in B2m-null melanoma and colorectal cancer models. Unexpectedly, both CD8+ T cells and NK cells, but not CD4+ T cells, were required for the efficacy of CD40 agonist, even though CD8+ T cells cannot directly recognize antigen presentation-deficient tumor cells. Instead, these lymphocytes control tumor growth via secretion of IFN{gamma}, as depletion of IFN{gamma} inhibited the therapeutic effect of CD40 agonist. IFN{gamma} receptor (Ifngr1) expression was required on host cells, not tumor cells, for CD40 agonist-mediated tumor control. Single-cell analysis identified a distinct population of inflammatory monocytes that were enriched for an IFN{gamma} response signature in CD40 agonist-treated tumors, suggesting that these cells may be important for tumor control. Analysis of human bulk and single-cell RNA-seq datasets demonstrated that an inflammatory monocyte signature derived from our data was associated with improved patient outcomes and response to immune checkpoint inhibitors. ConclusionsThese data demonstrate that CD8+ T cells contribute to tumor control even in the absence of direct antigen presentation by tumor cells. More broadly, our work suggests that strategies to activate the effector functions of inflammatory monocytes may limit tumor growth and overcome acquired resistance to immune checkpoint inhibitors.

immunology↗

bioRxiv2026

Ribosome-associated quality control of aberrant protein production during amino acid limitation

Amino acids can become limiting for protein synthesis through depletion of charged tRNAs, leading to ribosome stalling and disruption of translation elongation at specific codons. To assess whether this is a mechanism by which amino acid availability can directly influence gene expression, we designed a reporter library to measure translation disruption across all sense codons in the context of amino acid limitations. We found that arginine limitation consistently impairs translation at the arginine codon AGA, resulting in synthesis of proteins from endogenous transcripts. In contrast, GCN2 pathway activation suppresses translation disruption following depletion of most other amino acids. Genome-wide screens revealed that the ribosome quality control trigger (RQC-T) and RQC pathways, which resolve ribosome collisions on defective mRNAs, catalyze ribosome splitting and premature fall-off in response to arginine depletion. Additionally, the E3 ubiquitin ligase RNF14, recently shown to clear ribosome A-site obstructions, promotes translation disruption through both ribosome fall-off and frameshifting during arginine limitation. Together, these data show that the RQC machinery is engaged by tRNA-limited ribosomes and identify a new role for RNF14 as a regulator of translation upon arginine limitation.

genetics↗

bioRxiv2026

In vivo evidence for bleb-induced survival signaling in metastatic melanoma

Bleb signaling is a cellular process in which pressure-driven plasma membrane protrusions generate localized micron-scale membrane curvature that recruits cytosolic septin complexes, assembling signaling hubs that promote cell survival1. Our prior work showed that this morphology-encoded signaling pathway is necessary to sustain anchorage-independent survival of BRAF and NRAS mutant melanoma cells in vitro. However, whether bleb-induced signaling occurs in vivo and contributes to cancer progression is unclear. Here, we develop complementary in vivo and ex vivo assays spanning human patient samples and mouse xenograft models to mechanistically interrogate bleb signaling directly in physiologic contexts. We observe that bleb-associated septin hubs are exclusively formed in poorly adherent amoeboid tumor cells at the invasive margin, within malignant effusions, and at distant metastatic sites, while well-adhered cells in the tumor interior show no signs of septin hub formation. Accordingly, pharmacological pathway disruption specifically kills disseminated tumor cells within these low-adhesion microenvironments while having no appreciable effect on adhered cells in the tumor interior, resulting in reduced metastatic burden and delayed disease recurrence in vivo. This work confirms septin-mediated bleb signaling as a previously unrecognized vulnerability of disseminated cancer cells and demonstrates that this morphology-encoded pathway operates in vivo to support disease progression, preserving cancer cell viability under conditions in which cell survival signals from the environment are muted. These findings suggest novel opportunities to target survival signaling in micrometastatic disseminated cancer cells. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=150 SRC="FIGDIR/small/697601v1_ufig1.gif" ALT="Figure 1"> View larger version (61K): org.highwire.dtl.DTLVardef@1770384org.highwire.dtl.DTLVardef@87e567org.highwire.dtl.DTLVardef@1e5d6b2org.highwire.dtl.DTLVardef@724c5f_HPS_FORMAT_FIGEXP M_FIG C_FIG

cancer biology↗

bioRxiv2025

Mechanisms of tumor persistence in metastatic melanoma following successful immunotherapy

Tumor dormancy is thought to enable cancer recurrence, but the settings and mechanisms of dormancy in patients are poorly characterized. Both immunogenic tumor mass dormancy, involving continued tumor cell proliferation and balanced immune-mediated cell death, and cell-level quiescence have been observed in preclinical models. Here, we demonstrate the existence of mass dormancy rather than quiescence in long-term stable residual lesions in melanoma patients treated with immune checkpoint inhibitors (ICI). In a large stable lesion subjected to detailed spatial profiling, the proportion of proliferating tumor cells is similar to that in site-matched tumors from patients progressing after ICI. Residual stable lesions from other patients, judged to contain only scar tissue upon clinical pathology review, also contained nests of dividing tumor cells surrounded by active immune cells. These findings demonstrate the presence of viable tumor cells and mass dormancy in persistent stable lesions, a finding with implications for disease monitoring and management.

cancer biology↗

bioRxiv2025

Integrative single-cell and spatial mapping of oxidative stress response uncovers GCLC+ mesenchymal tumor cell state linked with favorable outcomes in triple negative breast cancer

Inhibiting oxidative stress response (OSR) proteins has been suggested as a therapeutic strategy in triple negative breast cancer (TNBC). However, the cell type specificity and spatial distribution of OSR genes and proteins, such as GCLC and NQO1, is unknown. Using single cell and spatial transcriptomics datasets we found that OSR genes were highly expressed in TNBC tumor cells, which localized in spatial clusters. Multiplex immunofluorescence imaging of 345 TNBC samples from 186 patients demonstrated that OSR proteins GCLC and NQO1 exhibit distinct expression profiles across tumor, immune, and stromal cell populations and are elevated in inflamed histological regions. Tumor cell OSR protein expression was associated with the composition of the adjacent cellular neighborhood. Furthermore, we identified GCLC and vimentin positive (GCLC+VIM+) mesenchymal-like tumor cells, residing near immune cells and exhibiting increased proliferation and decreased anastasis signatures, suggesting sensitivity to chemotherapy. Across a panel of thirteen TNBC cell lines, GCLC expression was positively correlated with sensitivity to cisplatin. Cox regression analysis revealed that patients with higher proportions of GCLC+VIM+ tumor cells had a longer overall survival. Collectively, our results demonstrate that individual OSR proteins are expressed in distinct microenvironments and tumor cell states, potentially contributing to patient outcomes.

cancer biology↗

bioRxiv2025

Regulatory T cells inhibit CD8+ TRM-like cells during the early stages of tumor immune escape

How the immune system surveys nascent tumors and how this surveillance is subverted remain poorly understood. Using high-plex cyclic immunofluorescence and 3D imaging, we identified regulatory T (Treg) cells that co-localize with tissue-resident memory (TRM)-like T cells in early-stage human melanoma. In an autochthonous Braf/PTEN melanoma model expressing a defined tumor antigen, the initial CD8+ T cell infiltrate adopts a CD103+CD101+ TRM-like fate, establishing active immunosurveillance within nascent lesions. TRM-like cells dominate early tumors, occupy a stable epidermal niche, express effector molecules, and initiate T cell recruitment. However, Treg cells adopt a parallel tissue-resident phenotype, co-localizing with TRM-like cells and restraining both cytotoxic and sentinel functions. Tumor-site-specific Treg depletion reactivated TRM-like cells, drove robust T cell recruitment, expanded tumor-specific responses, and limited tumor growth. These findings reveal how early immunosurveillance is established through tissue-resident programs and identify Treg co-option of this response as a critical mechanism of tumor immune evasion. One Sentence SummaryNascent melanoma imprints a tissue-resident program on the initial CD8+ T cell infiltrate, which is suppressed by regulatory T cells as a critical checkpoint in immune evasion.

immunology↗

bioRxiv2025

Multiomic profiling of a unique in-transit melanoma cohort identifies melanoma differentiation as predictor of tumor progression and therapy response

Melanoma patients with in-transit metastasis (ITM), a stage of disease where melanoma has metastasized to sites in between the primary lesion and draining lymph node, vary significantly in their clinical outcomes, but the biology driving differential outcomes in ITM is poorly understood. To elucidate the mechanisms of differential outcomes, we utilized multimodal molecular profiling (WES, RNA-seq, highly multiplexed immunofluorescence, spatial transcriptomics) in 1) evolutionary analysis of longitudinal tumor samples and 2) identifying prognostic tumor intrinsic and microenvironmental features in a unique cohort of patients with unresectable ITM. Among other findings, we observed a persistent dedifferentiated AXL/NGFR clonal lineage pre-existing and following immune checkpoint blockade in in-transit and distant metastases. Concordantly, we found that low pigmentation and high T cell exhaustion signatures were independently associated with distant progression. Our findings highlight tumor cell state and immune dysfunction as key predictors and potential biomarkers of metastatic risk in ITM. STATEMENT OF SIGNIFICANCEWhat drives distant progression in melanoma is unclear. Analyzing tumor and immune features in a rare in-transit melanoma patient cohort, we identify biological signals highlighting how immune and tumor states observable in pre-distant metastasis melanomas shape long-term outcomes, and nominate potential prognostic biomarkers.

cancer biology↗

bioRxiv2025

Spatially organized lymphocytic microenvironments in high grade primary prostate tumors

The spatial arrangement of immune cells in the tumor microenvironment (TME) varies widely, from dispersed to clustered and tumor excluded to infiltrating. Multiplexed spatial profiling is an effective means of characterizing tumor-infiltrating lymphocytes (TILs) and immune complexes such as tertiary lymphoid structures (TLS) in the TME. However, few approaches have been described for objectively parametrizing patterns of immune organization and assessing their association with biological or clinical variables. This makes it difficult to evaluate whether a set of tumors is relatively immunologically cold or hot. Here we describe an intuitive set of statistical tools (available in the R package, tlsR) for characterizing lymphocyte patterns in the TME of solid cancers. We apply tlsR to primary prostate cancer (PCa), which is often described as immunologically cold. Using a cohort of 29 radical prostatectomy specimens stratified into low Gleason-grade (LGG; n=15) and high Gleason-grades (HGG; n =14) we show that HGG PCa is significantly more infiltrated than LGG PCa with lymphocytes organized into B cell or T cell enriched immune clusters (BICs and TICs). A subset of these ICs have the B and T cell zonation and follicular dendritic cells characteristic of a bona fide TLS. HGGs are also enriched with ICs containing precursor exhausted T cells (Tpex) and proliferating B cells and their tumor compartments harbor granzyme-B+ cytotoxic T cells in contact with cancer cells. Thus, far from being cold, a subset of HGG PCa has features associated with active immune surveillance, a finding with implications for emerging PCa immunotherapies.

cancer biology↗

bioRxiv2025

SEAL: Spatially-resolved Embedding Analysis with Linked Imaging Data

Dimensionality reduction techniques help analysts make sense of complex, high-dimensional spatial datasets, such as multiplexed tissue imaging, satellite imagery, and astronomical observations, by projecting data attributes into a two-dimensional space. However, these techniques typically abstract away crucial spatial, positional, and morphological contexts, complicating interpretation and limiting insights. To address these limitations, we present SEAL, an interactive visual analytics system designed to bridge the gap between abstract 2D embeddings and their rich spatial imaging context. SEAL introduces a novel hybrid-embedding visualization that preserves image and morphological information while integrating critical high-dimensional feature data. By adapting set visualization methods, SEAL allows analysts to identify, visualize, and compare selections--defined manually or algorithmically--in both the embedding and original spatial views, facilitating a deeper understanding of the spatial arrangement and morphological characteristics of entities of interest. To elucidate differences between selected sets of items, SEAL employs a scalable surrogate model to calculate feature importance scores, identifying the most influential features governing the position of objects within embeddings. These importance scores are visually summarized across selections, with mathematical set operations enabling detailed comparative analyses. We demonstrate SEALs effectiveness and versatility through three case studies: colorectal cancer tissue analysis with a pharmacologist, melanoma investigation with a cell biologist, and exploration of sky survey data with an astronomer. These studies underscore the importance of integrating image context into embedding spaces when interpreting complex imaging datasets. Implemented as a standalone tool while also integrating seamlessly with computational notebooks, SEAL provides an interactive platform for spatially informed exploration of high-dimensional datasets, significantly enhancing interpretability and insight generation.

bioinformatics↗

bioRxiv2025

Morphology-Aware Profiling of Highly Multiplexed Tissue Images using Variational Autoencoders

Spatial proteomics (highly multiplexed tissue imaging) provides unprecedented insight into the types, states, and spatial organization of cells within preserved tissue environments. To enable single-cell analysis, high-plex images are typically segmented using algorithms that assign marker signals to individual cells. However, conventional segmentation is often imprecise and susceptible to signal spillover between adjacent cells, interfering with accurate cell type identification. Segmentation-based methods also fail to capture the morphological detail that histopathologists rely on for disease diagnosis and staging. Here, we present a method that combines unsupervised, pixel-level machine learning using autoencoders with traditional segmentation to generate single-cell data that captures information on protein abundance, morphology, and local neighborhood in a manner analogous to human experts while overcoming signal spillover. We demonstrate the generality of this approach by applying it to CyCIF, Lunaphore COMET, and CODEX data, and show that it can learn histological features across multiple spatial scales.

pathology↗

bioRxiv2025

Spatial determinants of tumor cell dedifferentiation and plasticity in primary cutaneous melanoma

Localized cutaneous melanoma can be cured by excision but success critically depends on early detection and risk assessment of primary lesions. However, their initiation, progression, and immunology remain poorly understood, partly due to high intra- and inter-tumor heterogeneity. We studied this heterogeneity using spatial profiling in over 300 histological domains, each representing a single progression stage, and found that 200-600 cell neighborhoods from a single melanoma can be as different in RNA and protein expression as neighborhoods from different tumors. These differences are not stochastic, however, and disease progression can be mapped at the neighborhood level onto a cell state landscape defined by the activity of the melanocyte master regulator MITF and genes associated with a dedifferentiated neural crest phenotype. Position in this landscape is influenced by proximity to immune cells, perivascular environments, and other tissue features, but no single association is absolute, giving rise to complex spatial patterns.

cancer biology↗

bioRxiv2025

Multiomic analysis identifies suppressive myeloid cell populations in human TB granulomas.

Tuberculosis (TB) remains a major global health challenge, particularly in the context of multidrug-resistant (MDR) Mycobacterium tuberculosis (Mtb). Host-directed therapies (HDTs) have been proposed as adjunctive therapy to enhance immune control of infection. Recently, one such HDT, pharmacologic modulation of myeloid-derived suppressor cells (MDSCs), has been proposed to treat MDR-TB. While MDSCs have been well characterized in cancer, their role in TB pathogenesis remains unclear. To investigate whether MDSCs or other myeloid suppressor populations contribute to TB granuloma microenvironments (GME), we performed spatial transcriptional profiling and single-cell immunophenotyping on eighty-four granulomas in lung specimens from three individuals with active disease. Granulomas were histologically classified based on H&E staining, and transcriptional signatures were compared across regions of interest (ROIs) at different states of granuloma maturation. Our analysis revealed that immune suppression within granuloma was not primarily driven by classical MDSCs but rather by multiple myeloid cell subsets, including dendritic cells expressing indoleamine 2,3 dioxygenase-1 expressing (IDO1+ DCs). IDO1+ DCs were the most frequently observed suppressive myeloid cells, particularly in cellular regions, and their spatial proximity to activated T cells suggested localized immunosuppression. Importantly, granulomas at different stages contained distinct proportions of suppressor myeloid cells, with necrotic and cellular regions showing different myeloid phenotypes that may influence granuloma progression. Gene set enrichment analysis (GSEA) further indicated that elevated IDO1 expression was associated with a complex immune response that balanced suppressive signaling, immune activation, and cellular metabolism. These findings suggest that classical MDSCs, as defined in tumor microenvironments, likely play a minor role in TB, whereas IDO1+ DCs may be key regulators of immune suppression in granulomas influencing local Mtb control in infected lung. A deeper understanding of the role of IDO1+ suppressive myeloid cells in TB granulomas is essential to assessing their potential as therapeutic targets in TB treatment.

pathology↗

bioRxiv2025

Dynamic Modeling of Cell Cycle Arrest Through Integrated Single-Cell and Mathematical Modelling Approaches

Highly multiplexed imaging assays allow simultaneous quantification of multiple protein and phosphorylation markers, providing a static snapshots of cell types and states. Pseudo-time techniques can transform these static snapshots of unsynchronized cells into dynamic trajectories, enabling the study of dynamic processes such as development trajectories and the cell cycle. Such ordering also enables training of mathematical models on these data, but technical challenges have hitherto made it difficult to integrate multiple experimental conditions, limiting the predictive power and insights these models can generate. In this work, we propose data processing and model training approaches for integrating multiplexed, multi-condition immunofluorescence data with mathematical modelling. We devise training strategies that are applicable to datasets where cells exhibit oscillatory as well as arrested dynamics and use them to train a cell cycle model on a dataset of MCF-10A mammary epithelial exposed to cell-cycle arresting small molecules. We validate the model by investigating predicted growth factor sensitivities and responses to inhibitors of cells at different initial conditions. We anticipate that our framework will generalise to other highly multiplexed measurement techniques such as mass-cytometry, rendering larger bodies of data accessible to dynamic modelling and paving the way to deeper biological insights. Author SummaryAdvanced imaging techniques allow us to see detailed pictures of different proteins and cell changes. By using computational algorithms, we turn these static pictures into dynamic sequences to understand processes like the cell cycle better. However, combining data from different experiments is difficult and limits how well our models can predict outcomes. This study introduces new ways to process data and train models to handle complex data from various conditions. The approach is tested by using data from untreated and treated cells to create a model of the cell cycle. This model was then checked for accuracy by seeing how well it could predict how cells respond to growth factors and drugs from different starting points. In the future, this method could be used with other data types, allowing for more detailed and accurate models of cellular behavior.

systems biology↗