CellSymphony: Deciphering the molecular and phenotypic orchestration of cells with single-cell pathomics

• URL: http://arxiv.org/abs/2508.10232v1
• Date: Wed, 13 Aug 2025 23:02:04 GMT
• Title: CellSymphony: Deciphering the molecular and phenotypic orchestration of cells with single-cell pathomics
• Authors: Paul H. Acosta, Pingjun Chen, Simon P. Castillo, Maria Esther Salvatierra, Yinyin Yuan, Xiaoxi Pan,
• Abstract summary: We introduce CellSymphony, a flexible framework that leverages foundation model-derived embeddings from both Xenium transcriptomic profiles and histology images at true single-cell resolution.<n>By learning joint representations that fuse spatial gene expression with morphological context, CellSymphony achieves accurate cell type annotation and uncovers distinct microenvironmental niches across three cancer types.
• Score: 1.5312292486898271
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Xenium, a new spatial transcriptomics platform, enables subcellular-resolution profiling of complex tumor tissues. Despite the rich morphological information in histology images, extracting robust cell-level features and integrating them with spatial transcriptomics data remains a critical challenge. We introduce CellSymphony, a flexible multimodal framework that leverages foundation model-derived embeddings from both Xenium transcriptomic profiles and histology images at true single-cell resolution. By learning joint representations that fuse spatial gene expression with morphological context, CellSymphony achieves accurate cell type annotation and uncovers distinct microenvironmental niches across three cancer types. This work highlights the potential of foundation models and multimodal fusion for deciphering the physiological and phenotypic orchestration of cells within complex tissue ecosystems.

Related papers

• Uncovering spatial tissue domains and cell types in spatial omics through cross-scale profiling of cellular and genomic interactions [26.7111709393529]
  We present CellScape, a deep learning framework designed to overcome limitations for high-performance spatial transcriptomics analysis.<n>CellScape models cellular interactions in tissue space and genomic relationships among cells, producing comprehensive representations.<n>This technique uncovers biologically informative patterns that improve spatial domain segmentation.
  arXiv  Detail & Related papers  (2026-02-13T06:22:43Z)
• Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow [80.00833033784079]
  Understanding of cellular microenvironment is essential for deciphering tissue development and disease data.<n>NicheFlow is a flow-based generative model that infers the temporal trajectory of cellular microenvironments across spatial slides.
  arXiv  Detail & Related papers  (2025-11-02T15:41:38Z)
• ITC-RWKV: Interactive Tissue-Cell Modeling with Recurrent Key-Value Aggregation for Histopathological Subtyping [2.99938892718088]
  We propose a dual-stream architecture that models the interplay between macroscale tissue features and aggregated cellular representations.<n>We introduce a bidirectional tissue-cell interaction module to enable mutual attention between localized cellular cues and their surrounding tissue environment.
  arXiv  Detail & Related papers  (2025-10-24T14:03:52Z)
• PAST: A multimodal single-cell foundation model for histopathology and spatial transcriptomics in cancer [26.795192024462963]
  PAST is a pan-cancer single-cell foundation model trained on 20 million paired histopathology images and single-cell transcriptomes.<n>It predicts single-cell gene expression, virtual molecular staining, and multimodal survival analysis directly from routine pathology slides.<n>Our work establishes a new paradigm for pathology foundation models, providing a versatile tool for high-resolution spatial omics, mechanistic discovery, and precision cancer research.
  arXiv  Detail & Related papers  (2025-07-08T21:51:25Z)
• SPATIA: Multimodal Model for Prediction and Generation of Spatial Cell Phenotypes [39.45743286683448]
  We introduce SPATIA, a multi-scale generative and predictive model for spatial transcriptomics.<n> SPATIA learns cell-level embeddings by fusing image-derived morphological tokens and transcriptomic vector tokens.<n>We benchmark SPATIA against 13 existing models across 12 individual tasks.
  arXiv  Detail & Related papers  (2025-07-07T06:54:02Z)
• HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data [13.66950862644406]
  We introduce HEIST, a hierarchical graph transformer-based model for spatial transcriptomics data.<n>HEIST is pre-trained on 22.3M cells from 124 tissues across 15 organs.<n>It effectively encodes the microenvironmental influences in cell embeddings, enabling the discovery of spatially-informed subpopulations.
  arXiv  Detail & Related papers  (2025-06-11T12:29:01Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [52.106879463828044]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• Segmentation-free integration of nuclei morphology and spatial transcriptomics for retinal images [1.2200074914789645]
  SEFI (SEgmentation-Free Integration) is a novel method for integrating morphological features of cell nuclei with spatial transcriptomics data.<n>We demonstrate SEFI on spatially resolved gene expression profiles of the developing retina, acquired using multiplexed single molecule Fluorescence In Situ Hybridization (smFISH)
  arXiv  Detail & Related papers  (2025-02-08T14:03:02Z)
• Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen [76.02070962797794]
  This work introduces CellFlow for Generation (CFGen), a flow-based conditional generative model that preserves the inherent discreteness of single-cell data.<n>CFGen generates whole-genome multi-modal single-cell data reliably, improving the recovery of crucial biological data characteristics.
  arXiv  Detail & Related papers  (2024-07-16T14:05:03Z)
• Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View [49.03501451546763]
  We identify the importance of implicit correspondences across biological contexts for exploiting domain-invariant pathological composition. We propose self-adaptive dynamic distillation to secure instance-aware trade-offs across different model constituents.
  arXiv  Detail & Related papers  (2024-07-14T04:41:16Z)
• Single-Cell Deep Clustering Method Assisted by Exogenous Gene Information: A Novel Approach to Identifying Cell Types [50.55583697209676]
  We develop an attention-enhanced graph autoencoder, which is designed to efficiently capture the topological features between cells. During the clustering process, we integrated both sets of information and reconstructed the features of both cells and genes to generate a discriminative representation. This research offers enhanced insights into the characteristics and distribution of cells, thereby laying the groundwork for early diagnosis and treatment of diseases.
  arXiv  Detail & Related papers  (2023-11-28T09:14:55Z)
• Tertiary Lymphoid Structures Generation through Graph-based Diffusion [54.37503714313661]
  In this work, we leverage state-of-the-art graph-based diffusion models to generate biologically meaningful cell-graphs. We show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content.
  arXiv  Detail & Related papers  (2023-10-10T14:37:17Z)
• Topology-Guided Multi-Class Cell Context Generation for Digital Pathology [28.43244574309888]
  We introduce several mathematical tools from spatial statistics and topological data analysis. We generate high quality multi-class cell layouts for the first time. We show that the topology-rich cell layouts can be used for data augmentation and improve the performance of downstream tasks such as cell classification.
  arXiv  Detail & Related papers  (2023-04-05T07:01:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.