Biology subjects

Groeneveld, C.

Publications and source records attributed to Groeneveld, C..

2 recordsLinked to original sources

bioRxiv2025

Deep Learning Bridges Histology and Transcriptomics to Predict Molecular Subtypes and Outcomes in Muscle-Invasive Bladder Cancer

Muscle-Invasive Bladder Cancer (MIBC) is a heterogeneous disease with distinct molecular subtypes influencing prognosis and therapeutic response. However, molecular profiling through RNA sequencing remains costly, time-consuming and complicated by intratumoral heterogeneity. We developed a Deep Learning (DL) approach to infer molecular subtypes from routine histopathological slides and to evaluate its prognostic value in patients treated with neoadjuvant chemotherapy (NAC). We developed an DL-model predicting the expression of 848 subtype-associated genes from histological images of transurethral resection of bladder tumor, enabling spatial molecular subtyping at tile level. The model was trained on 297 NAC-treated patients from the VESPER clinical trial and evaluated on three independent cohorts (COBLAnCE, n=224; Saint-Louis, n=30 and TCGA, n=315), covering diverse staining protocols and scanner types. Spatial transcriptomics from six VESPER patients confirmed the spatial consistency of the inferred expression profiles. Our approach achieved a ROC AUC of 0.94 for molecular subtype prediction, with 95% of genes significantly predicted, demonstrating its ability to capture transcriptomic dysregulations from histological morphology. Predicted expression maps revealed spatially coherent patterns and intratumoral molecular heterogeneity. Importantly, tumors predicted with basal/squamous features (pure or mixed), were associated with significantly worse progression-free and overall survival after NAC (log-rank p=0.014 and 0.037, respectively). This DL-based framework enables accurate and spatially resolved inference of gene expression and molecular subtypes in MIBC without sequencing. These findings could improve patient stratification in clinical practice and support the design of more targeted clinical trials. Further validation in larger cohorts is needed before routine clinical implementation.

cancer biology↗

bioRxiv2025

fastCNV: Fast and accurate copy number variation prediction from High-Definition Spatial Transcriptomics and scRNA-Seq Data

BackgroundPredicting DNA copy number variations (CNVs) from spatial transcriptomics (ST), including Visium HD, or single-cell RNA-sequencing (scRNA-seq) data helps to distinguish malignant from non-malignant cells and to characterize the clonal architecture of tumor cells. Though there are existing methods of CNV analysis, they are often limited by slow speed, high memory consumption, lower accuracy in the absence of a reference for diploid cells, lower sensitivity at low read counts, and no support for clonal tree construction. ResultsTo overcome these issues, we developed the R package fastCNV for detecting CNVs from ST, including Visium HD, or scRNA-seq data. FastCNV pools diploid references across samples and, within each sample, aggregates similar spots or cells with few reads into meta spots or cells. It automatically builds a clonality tree, and runs several times faster than other methods while using less memory. To measure the accuracy of fastCNV, we used 117 cancer cell line samples with both scRNA-seq and bulk whole-exome sequencing (WES) data. FastCNV identified CNVs highly correlated to those calculated from WES data (median correlation above 0.75), showing a significant improvement as compared to other methods such as inferCNV. Notably, fastCNV enables, for the first time, the analysis of CNVs from the Visium HD spatial transcriptomics technology. Applied to Visium HD breast cancer ST data, fastCNV identifies tumor subclones tightly related to different histologies, linking specific genetic aberrations to tumor progression. ConclusionsFastCNV is a significant improvement on existing R methods for CNV detection from ST, including Visium HD, or scRNA-seq data in terms of speed, memory usage, sensitivity and accuracy. This highlights its potential to advance cancer research and personalized medicine. FastCNV is available at https://github.com/must-bioinfo/fastCNV/.

bioinformatics↗