PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 7, 2026Cancer Research0 citationsOpen Access

CellFuse enables Multi-modal Integration of Single-cell and Spatial Proteomics Data for Systems-level Analysis in Cancer

View Full Paper
AKAbhishek KoladiyaInstitute for Stem Cell Biology and Regenerative MedicineZGZinaida GoodCancer Prevention Institute of CaliforniaSVSricharan Reddy. VarraInstitute for Stem Cell Biology and Regenerative Medicine

Key Points

  • To develop a framework that integrates single-cell and spatial proteomics data for cancer analysis.
  • Developed CellFuse, a deep learning-based integration framework.
  • Utilized supervised contrastive learning to create a shared embedding space.
  • Applied the framework to analyze datasets from peripheral blood, bone marrow, and lymphoma.
  • CellFuse outperformed existing integration approaches in identifying relevant cell populations.
  • Successfully captured interactions in solid tumors between malignant, stromal, and immune cells.
  • Reconstructed spatially resolved microenvironments correlated with treatment response.

Abstract

Analysis of tumors using single-cell and spatial modalities is critical to advance our understanding of cancer. The growth of technologies that enable these studies provides an increasing number of single cell datasets. Integrating such data across studies will increase the impact of individual studies and speed cancer research. Most existing integration approaches are tailored to transcriptomic data and assume large sets of shared features, an assumption that fails for lower-dimensional proteomic measurements. Here, we developed CellFuse, a deep learning-based integration framework that unifies antibody-based proteomic datasets including high-dimensional cytometry, CITE-seq, and spatial proteomics data. Leveraging supervised contrastive learning, CellFuse learned a shared embedding space that enabled accurate cross-modality cell type prediction and robust label transfer across tumor samples and experimental conditions. Applied to datasets spanning peripheral blood, bone marrow, and lymphoma, CellFuse consistently outperformed existing approaches in recovering clinically relevant populations, including rare malignant and immune subsets. In solid tumors, it reconstructed spatially resolved microenvironments, capturing interactions between malignant, stromal, and immune cells that correlated with treatment response. By enabling scalable, modality-agnostic integration, CellFuse provides a powerful tool to uncover prognostic cell states and delineate the architecture of the tumor-immune ecosystem with translational relevance, driving cancer discoveries.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Koladiya et al. (2026) studied this question.

synapsesocial.com/papers/69fbe3ca164b5133a91a30adhttps://doi.org/10.1158/0008-5472.can-25-3699
Ask AI
Helpful
Bookmark
Share
View Full Paper