Biology subjects

Bussi, Y.

Publications and source records attributed to Bussi, Y..

7 recordsLinked to original sources

bioRxiv2026

Single-section multiplexed imaging enables comprehensive lung cancer diagnosis

Accurate and timely diagnosis is essential for effective lung cancer treatment. However, contemporary workflows rely on sequential immunohistochemistry of small biopsy specimens, which can exhaust tissue, limit biomarker assessment, and delay treatment decisions. Here, we demonstrate that multiplexed imaging addresses these limitations by enabling comprehensive lung cancer diagnosis from a single tissue section. We developed and validated a clinically informed multiplexed antibody panel that integrates tumor classification, predictive biomarker assessment, and immune profiling. In diagnostic biopsies, multiplexed imaging achieved 96% concordance with standard pathology, while enabling accurate automated PD-L1 scoring and rapid detection of clinically approved and emerging actionable targets. Simultaneously measuring dozens of proteins improves standard pathology by incorporating complex multi-protein biomarkers, supporting quantitative computational analysis to streamline diagnosis, and generating spatial data for translational research. By reducing turnaround time and preserving scarce tissue, this workflow has the potential to accelerate treatment decisions, improve patient outcomes and bridge clinical care with translational discovery.

cancer biology↗

bioRxiv2025

CellTune: An integrative software for accurate cell classification in spatial proteomics

Spatial proteomics measures multiple proteins in situ, capturing tissue complexity. However, cell classification in densely packed tissues remains challenging due to the lack of efficient classification algorithms, annotation tools, and high-quality labeled datasets to benchmark computational methods. We introduce CellTune, an integrated software for analysis of large spatial proteomics datasets, which streamlines precise cell classification through an optimized human-in-the-loop active learning workflow. It advances core capabilities across within a unified, intuitive, and code-free interface. To evaluate CellTune, we created CellTuneDepot, a resource of 40k manually-annotated cells and 3.5 million high-quality labeled cells across 60 cell types. CellTune outperforms alternative methods, achieving accuracy comparable to human performance while enabling increased classification resolution and discovery of novel cell types. Together, CellTune and CellTuneDepot provide researchers with a tool for state-of-the-art classification accuracy and resolution at scale to drive biological insights.

bioinformatics↗

bioRxiv2024

Generalized cell phenotyping for spatial proteomics with language-informed vision models

We present DeepCell Types, a novel approach to cell phenotyping for spatial proteomics that addresses the challenge of generalization across diverse datasets with varying marker panels collected across different platforms. Our approach utilizes a transformer with channel-wise attention to create a language-informed vision model; this models semantic understanding of the underlying marker panel enables it to learn from and adapt to heterogeneous datasets. Leveraging a curated, diverse dataset named Expanded TissueNet with cell type labels spanning the literature and the NIH Human BioMolecular Atlas Program (HuBMAP) consortium, our model demonstrates robust performance across various cell types, tissues, and imaging modalities. Comprehensive benchmarking shows that our method outperforms existing approaches on cell-type prediction and, from the same model, predicts marker positivity competitively with a dedicated specialist; it further matches manual expert gating and adapts to new data with modest fine-tuning, well past what baselines reach when trained from scratch. This work equips the spatial proteomics community with a single, continuously improvable phenotyping model that generalizes to new marker panels and can be fine-tuned efficiently when needed. We release both DeepCell Types and Expanded TissueNet as open-source resources.

bioinformatics↗

bioRxiv2024

A spatial atlas of human gastro-intestinal acute GVHD reveals epithelial and immune dynamics underlying disease pathophysiology

Acute graft-versus-host disease (aGVHD) is a significant complication of allogeneic hematopoietic stem cell transplantation (aHSCT), driven by alloreactive donor T cells in the gut. However, the roles of additional donor and host cells in this process are not fully understood. We conducted multiplexed imaging on 59 biopsies from patients with gastrointestinal GVHD and 10 healthy controls, revealing key pathological changes, including fibrosis, crypt alterations, loss of Paneth cells, accumulation of endocrine cells, and disrupted immune organization, particularly a reduction in IgA-secreting plasma cells. Interestingly, CD8T cells were enriched only in a subset of patients, while others exhibited non-canonical enrichments of macrophages and neutrophils. Post-transplantation time significantly influenced immune composition, with host cells dominating plasma and T cell compartments long after transplantation. This spatial atlas of healthy duodenum and GVHD uncovers non-canonical immune dynamics, offering insights into disease pathophysiology and potential clinical applications in GVHD and other inflammatory bowel diseases.

immunology↗

bioRxiv2024

Data-modeling the interplay between single cell shape, single cell protein expression, and tissue state

Changes in cell shape are fundamentally involved in signaling, intracellular organization, function, and intercellular interactions within tissues, in health and disease. Investigating the interplay between cell shape and protein expression was limited, until recently, by the number of proteins that can be imaged simultaneously or by population averaging. We combined spatial multiplexed single cell imaging and machine learning to systematically investigate the intricate relationships between cell shape and protein expression in the context of heterogeneous human cells in their native state in human tissue samples in situ. Our analysis established a universal bi-directional link between the cells shape and its protein expression across different cell types, diseases, and disease states in human tissues, enabling new applications. Machine learning interpretability showed that the contribution of shape features to a prediction can potentially infer new protein functions. Unbiased screening of the links between all pairs consisting of one protein and one cell type identified a subpopulation of large p53-positive tumor cells across two cancers. Ultimately, inclusion of single cell shape properties enhanced Graph Neural Network disease state prediction. Our results open the door to unraveling the intricate connections between protein expression at the single cell level, cell shape, tissue organization, and tissue state in a physiological context.

cell biology↗

bioRxiv2023

Escalating High-dimensional Imaging using Combinatorial Channel Multiplexing and Deep Learning

Understanding tissue structure and function requires tools that quantify the expression of multiple proteins at single-cell resolution while preserving spatial information. Current imaging technologies use a separate channel for each individual protein, inherently limiting their throughput and scalability. Here, we present CombPlex (COMBinatorial multiPLEXing), a combinatorial staining platform coupled with an algorithmic framework to exponentially increase the number of proteins that can be measured from C up to 2c - 1. In CombPlex, every protein can be imaged in several channels, and every channel contains agglomerated images of several proteins. These combinatorically-compressed images are then decompressed to individual protein-images using deep learning. We achieve accurate reconstruction when compressing the stains of twenty-two proteins to five imaging channels and demonstrate that the approach works in both fluorescence microscopy and in mass-based imaging. Combinatorial staining coupled with deep-learning decompression can escalate the number of proteins measured using any imaging modality, without the need for specialized instrumentation. Coupling CombPlex with instruments for high-dimensional imaging could pave the way to image hundreds of proteins at single-cell resolution in intact tissue sections.

systems biology↗

bioRxiv2022

CellSighter - A neural network to classify cells in highly multiplexed images

Multiplexed imaging enables measurement of multiple proteins in situ, offering an unprecedented opportunity to chart various cell types and states in tissues. However, cell classification, the task of identifying the type of individual cells, remains challenging, labor-intensive, and limiting to throughput. Here, we present CellSighter, a deep-learning based pipeline to accelerate cell classification in multiplexed images. Given a small training set of expert-labeled images, CellSighter outputs the label probabilities for all cells in new images. CellSighter achieves over 80% accuracy for major cell types across imaging platforms, which approaches inter-observer concordance. Ablation studies and simulations show that CellSighter is able to generalize its training data and learn features of protein expression levels, as well as spatial features such as subcellular expression patterns. CellSighters design reduces overfitting, and it can be trained with only thousands or even hundreds of labeled examples. CellSighter also outputs a prediction confidence, allowing downstream experts control over the results. Altogether, CellSighter drastically reduces hands-on time for cell classification in multiplexed images, while improving accuracy and consistency across datasets.

systems biology↗