Biology subjects

Ballantyne, F.

Publications and source records attributed to Ballantyne, F..

8 recordsLinked to original sources

bioRxiv2026

Morphospatial profiling of cancer-associated fibroblasts reveals architectural subtypes of pancreatic ductal adenocarcinoma

Pancreatic ductal adenocarcinoma (PDAC) is a lethal malignancy with an urgent need for biomarkers to predict prognosis and guide treatment. Understanding the complex spatial biology of pancreatic cancer-associated fibroblasts (CAFs) and the broader architecture of the PDAC tumour microenvironment is central to this challenge. Using a multi-omics approach across multiple spatial resolutions in a large human PDAC cohort, we integrate geometry and shape to define discrete morphological CAF subtypes, expanding CAF phenotyping beyond conventional proteomics. We then reveal an architectural and molecular axis of PDAC at tissue level, suggestive of epithelial-stromal co-evolution, with translational implications and prioritisation of stromal targets. Finally, we recapitulate this axis by introducing four unique, internally validated architectural subtypes of PDAC, each characterised by a common microenvironment and CAF enrichment profile. These archetypes outperform conventional pathology in prognostication, and predict response to adjuvant chemotherapy. Collectively, this study establishes a novel morphological paradigm for spatial biology, illuminates the architectural landscape of PDAC, and provides a framework for spatial biomarker discovery to close the translational gap in this devastating disease.

cancer biology↗

bioRxiv2025

Self-supervised AI reveals a lethal discohesive phenotype in lung adenocarcinoma

Applications of artificial intelligence (AI) to histopathology are now common, but most require supervision which inherently limits their scope. By using self-supervised learning (SSL), we discover and quantify the full range of histopathological appearances in a disease, and associate them with clinicopathological ground truths such as prognosis. We used this approach to discover under-appreciated morphologies of lung adenocarcinoma (LUAD), using a highly characterised resected tumour cohort of over 4000 slides from over 1000 patients. By constructing an authoritative lexicon of recurrent LUAD appearances, we ab initio discovered several stromal morphologies strongly predictive of outcome. With multimodal data integration and external dataset validation, we propose that epithelial discohesion is lethal, but only in the context of immunologically cold stroma. Both these morphological features are independent of current prognostic schema. Crucially, we describe these features in the context of real-world diagnostic histopathology, giving them immediate clinical translatability. Statement of SignificanceHistopathology relies heavily on epithelial morphology, often neglecting the stroma. We use self-supervised AI to identify under-appreciated morphologies in LUAD linked to poor outcome and validate these observations in an external cohort, demonstrating the utility of self-supervised AI as a powerful biological discovery tool.

cancer biology↗

bioRxiv2025

Self-Supervised AI Reveals a Hidden Landscape of Prognostic Spatial Patterns in Multiplex Immunofluorescence Images

Modern spatial proteomic methods, such as multiplex immunofluorescence (mIF) imaging, offer a data-rich view of spatial biology in intact tissues. However, interpreting its complexity is a major bottleneck, limiting its potential for biological discovery and clinical translation. Current computational methods often rely on segmentation-based approaches that discard crucial morphological information and are limited to testing pre-defined hypotheses. Here, we introduce a self-supervised learning (SSL) framework that enables hypothesis-agnostic, context-aware discovery of biomarkers directly from mIF images. Our approach extracts rich feature representations that capture holistic architectural patterns, which integrate cellular morphology, marker interactions, and microenvironmental context without human supervision. Applying this framework to over 7,000 mIF tissue images from over 1,800 patients in two distinct cancer types, we demonstrate superior prognostic performance over conventional segmentation analyses. The method autonomously identified previously unknown and potentially clinically actionable biological patterns. In lung adenocarcinoma, these include a Ki67-mediated immune evasion phenotype, a sub-cellular pattern of GLB1 expression which aligns with low-grade EGFR-driven tumours, and distinct modes of tumour-immune interaction in PD-L1+ patients. We also find a regulatory T-cell-mediated immunosupressive environment promoting tumour budding in colorectal carcinoma. Our work establishes SSL as a powerful, scalable, and unbiased platform to decode tissue ecosystems while being fully explainable without pre-defined hypotheses. This paradigm shift transforms high-plex imaging from a hypothesistesting tool into a hypothesis-generating engine that can accelerate the discovery of next-generation spatial biomarkers.

cancer biology↗

bioRxiv2025

PixlMap: A generalisable pixel classifier for cellular phenotyping in multiplex immunofluorescence images

Multiplexed methods for the detection of protein expression generate extremely data-rich images of intact tissue sections. These images are invaluable for the quantification and analysis of complex biology and biomarker development. However, their interpretation presents a considerable analytical challenge. Cell segmentation from images is a key bottleneck and a major focus of research activity in artificial intelligence. Most current methods depend initially on the use of a nuclear counterstain to identify nuclear boundaries, which is a relatively straightforward task. The cellular boundary is then assigned either by expansion of the nuclear outline, or by the use of membrane or cytoplasm-specific stains to delineate cell boundaries, or by some combination of the two. The task is critical, as inaccurate segmentation leads to information loss and data contamination from neighbouring cells. Increasingly sophisticated methods are being developed to address these issues, but each has its own shortcomings. We present an alternative method which is inspired by the fact that the assignation of a cellular phenotype by eye does not depend upon the accurate identification of cell boundaries. We present an easy-to-use deep learning-based cellular phenotyping method which leverages this human capacity to assign phenotypes without segmenting the entire cell, and which can accurately phenotype cells based on nuclear segmentation alone. Using human ground truth annotations of entire cellular regions, we developed a classifier leveraging the U-Net architecture within a commercially available deep learning image analysis platform, but the principle is transferrable to any deep-learning framework. Crucially, training requires only a single example of each compartmental stain (nuclear/cytoplasmic/membranous). The resulting algorithm assigns class identities to cells with nuclear labelling alone, without the need for whole cell expansion. The method is highly novel, broadly generalisable, and comparable in accuracy to intensity-based phenotyping methods, bridging the gap between inaccurate cellular segmentation and accurate phenotype generation.

pathology↗

bioRxiv2024

A histomorphological atlas of resected mesothelioma from 3446 whole-slide images discovered by self-supervised learning

1Mesothelioma is a highly lethal and poorly biologically understood disease which presents diagnostic challenges due to its morphological complexity. This study uses self-supervised AI (Artificial Intelligence) to map the histomorphological landscape of the disease. The resulting atlas consists of recurrent patterns identified from 3446 Hematoxylin and Eosin (H&E) stained images scanned from resected tumour slides. These patterns generate highly interpretable predictions, achieving state-of-the-art performance with 0.65 concordance index (c-index) for outcomes and 88% AUC in subtyping. Their clinical relevance is endorsed by comprehensive human pathological assessment. Furthermore, we characterise the molecular underpinnings of these diverse, meaningful, predictive patterns. Our approach both improves diagnosis and deepens our understanding of mesothelioma biology, highlighting the power of this self-learning method in clinical applications and scientific discovery.

pathology↗

bioRxiv2024

Spatial resolution of transcriptomic plasticity states underpinning lethal morphologies in lung adenocarcinoma

Adenocarcinoma of the lung (LUAD) is a common and highly lethal disease. Clinical grading of disease strongly predicts recurrence and survival after surgery and is determined by morphological assessment of histological growth patterns in resected tumours. The molecular basis of growth pattern is poorly understood at present, as are the mechanisms linking growth pattern to recurrence and death. Interestingly, the two archetypal lethal morphologies, solid and micropapillary patterns, are characterised by their biphasic appearance. Both have an epithelial fraction which is in direct stromal contact, and a fraction which is not. This morphological variance seems likely to represent plasticity, and to be causally linked to mechanisms of virulence. To investigate the gene expression changes related to growth pattern both intra- and intertumoral, we applied spatial transcriptomics (Nanostring GeoMx DSP) to tissue microarray specimens of primary resected human lung adenocarcinoma. Using a variety of region-of-interest (ROI) selection strategies, we sampled 160 pure epithelial ROIs across 7 distinct morphological features of LUAD from 51 patients. Analyses of gene expression reveal fundamental trajectories connecting growth patterns, and crucial modes of plasticity which underly high-risk morphologies. These modes suggest mechanisms for the origins of growth pattern and mechanisms of virulence. Our work highlights dramatic divergence in gene expression programmes between highly lethal but morphologically diverse modes of tumour growth. Furthermore, it provides an explanation for how microscopically localised hypoxia in the primary tumour helps to establish and maintain survival strategies which ultimately determine morphology-specific mechanisms of tumour metastasis, suggesting new therapeutic vulnerabilities.

cancer biology↗

bioRxiv2023

eIF4A1 is essential for reprogramming the translational landscape of Wnt-driven colorectal cancers

Dysregulated translation is a hallmark of cancer. Targeting the translational machinery represents a therapeutic avenue which is being actively explored. eIF4A inhibitors target both eIF4A1, which promotes translation as part of the eIF4F complex, and eIF4A2, which can repress translation via the CCR4-NOT complex. While high eIF4A1 expression is associated with poor patient outcome, the role of eIF4A2 in cancer remains unclear. Furthermore, the on-target toxicity of targeting specific eIF4A paralogues in healthy tissue is under-explored. We show that while loss of either paralogue is tolerated in the wild-type intestine, eIF4A1 is specifically required to support the translational demands of oncogenic Wnt signalling. Intestinal tumourigenesis is suppressed in colorectal cancer models following loss of eIF4A1 but accelerated following loss of eIF4A2, while eIF4A inhibition with eFT226 mimics loss of eIF4A1 in these models.

cancer biology↗

bioRxiv2023

The eIF4A2 negative regulator of mRNA translation promotes extracellular matrix deposition to accelerate hepatocellular carcinoma initiation

Increased protein synthesis supports growth of established tumours. However, how mRNA translation contributes to early tumorigenesis remains unclear. Here we show that following oncogene activation, hepatocytes enter a non-proliferative/senescent-like phase characterized by 5{beta}1 integrin-dependent deposition of fibronectin-rich extracellular matrix (ECM) niches. These niches then promote exit from oncogene-induced senescence to permit progression to proliferating hepatocellular carcinoma (HCC). Removal of eIF4A2, a negative regulator of mRNA translation, boosts the synthesis of membrane/secretory proteins which drives a compensatory increase in the turnover/degradation of membrane proteins including 5{beta}1 integrin. This increased membrane protein degradation, in turn, compromises generation of ECM-rich tumour initiation niches, senescence-exit and progression to proliferating HCC. Consistently, pharmacological inhibition of mRNA translation following eIF4A2 loss restores ECM deposition and reinstates HCC progression. Thus, although inhibition of protein synthesis may be an effective way to reduce tumour biomass and the growth of established tumours, our results highlight how agents which reduce mRNA translation, if administered during early tumorigenesis, may awaken senescent cells and promote tumour progression.

cancer biology↗