Yidong Chen | PubMed Health

PubMed2026

shinyDeepGxP: a user-friendly R shiny app for predicting surface protein abundance from scRNA-seq expression using deep learning in blood cells.

MOTIVATION: Understanding accurate immune cell heterogeneity and function in single-cell datasets requires access to protein-level information, which is often unavailable due to experimental limitations. RESULTS: We present shinyDeepGxP, an interactive web application featuring our deep learning model, DeepGxP, for predicting surface protein abundance from single-cell RNA-sequencing (scRNA-seq) data. This platform makes DeepGxP accessible to researchers without programming skills. Users can upload scRNA-seq count matrices and use "Predict Protein" to predict the abundance of 224 biologically relevant surface proteins. shinyDeepGxP provides visualizations to help identify distinct cell populations based on predicted protein profiles. Moreover, users can choose "Explore Model" to reveal key RNA predictors and their associated biological pathways for each protein. Overall, shinyDeepGxP is a user-friendly, freely available web tool that provides protein-level detail for RNA-only single-cell datasets, enabling multimodal discovery without additional experiments. AVAILABILITY AND IMPLEMENTATION: shinyDeepGxP can be launched on https://shiny.crc.pitt.edu/deepgxp/.

Journal Article↗

PubMed2026

Antibody-Mediated Targeting of Secretory Protein SCUBE3 Suppresses Cancer Progression by Inhibiting Oncogenic Signaling and Inducing Antitumor Immunity.

UNLABELLED: Approaches targeting factors that simultaneously promote tumor growth and progression, induce therapy resistance, and inhibit antitumor immunity offer clear benefits over therapies targeting only one of these tumor-promoting processes. Through comprehensive loss-of-function genomic screening, we identified SCUBE3 as a pivotal factor that supports survival and therapy resistance and also orchestrates an immunosuppressive tumor microenvironment. Secretory SCUBE3 supported oncogenic activity through interactions with key oncogenic cell surface receptor proteins, including EGFR, mutant CALR, and TGFβRI/II. These interactions activated the transcription factors FOXR2 and c-Myc, promoting cancer cell proliferation and therapy resistance by enhancing DNA damage repair. Additionally, the SCUBE3-FOXR2 axis created an immunosuppressive tumor microenvironment by facilitating recruitment of the DNMT1 epigenetic repressor complex to the transcription regulator IRF1, thereby inhibiting the expression of MHC-I and MHC-II genes. A first-in-class neutralizing antibody targeting SCUBE3, which was developed using a sophisticated antibody discovery platform and engineered with specific mutations in the heavy chain for enhanced specificity and efficacy, demonstrated profound therapeutic potential across various cancer types in preclinical models, including patient-derived breast and ovarian cancer xenografts. This discovery marks an advancement toward developing a targeted therapy for cancers characterized by hyperactive SCUBE3-associated signaling pathways. SIGNIFICANCE: Targeting SCUBE3 with a neutralizing antibody inhibits tumor growth and metastasis by blocking oncogenic signaling through FOXR2 and c-Myc and by circumventing immunosuppression, providing a promising pan-cancer treatment approach.

Humans↗