Predicting clonal mutations from tumour spatial transcriptomics data using a graph convolutional neural network
- 1Ghent University
Abstract
Spatial transcriptomics (ST) has revolutionized our understanding of tumour biology but inherently lacks information on the upstream somatic driver mutations. We developed a spatially-aware graph convolutional neural network approach (SPOT-Mut) that infers mutated (sub)clones directly from ST data. SPOT-Mut was trained on virtual ST slides with clones simulated from a large collection of existing RNA and matched DNA sequencing data. SPOT-Mut was first evaluated for predicting mutations in TP53, the most frequently mutated gene in human cancer. Precision and recall values exceeded 95% in most analysed cancer types and the model was validated on ST and matched DNA sequencing data from serial slices obtained from cutaneous SCC samples. SPOT-Mut was then trained on 62 frequently mutated driver genes, resulting in highly performing somatic mutation prediction models for 40 driver genes, including KRAS, KEAP1, CTNNB1 and APC. With the increasing availability of ST data and upcoming atlases, SPOT-Mut potentiates the localization of (sub)clonal alterations in TP53 and other common driver mutations.
Related
- A convolutional autoencoder network based on multi-dimensional spatial feature reconstruction for anomaly detection of rotating machinery under complex operating conditions
- Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
- Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
- Evaluating Pedestrian Crossing Safety: Implementing and Evaluating a Convolutional Neural Network Model Trained on Paired Aerial and Subjective Perspective Images (Vol 11, E42428, 2025)
- The Role of Spatial Transcriptomics in Exploring the Tumor Microenvironment in Neuroblastoma
BibTeX
@misc{luijts2026predicting,
title = {{Predicting clonal mutations from tumour spatial transcriptomics data using a graph convolutional neural network}},
author = {T. Luijts and S. Hoogstoel and S. Wen and E. Pappaert and E. De Meester and F. Van Nieuwerburgh and E. Van Hamme and S. De Schepper and W. Willaert and A. Vral and I. Hoorens and J. Van den Eynden},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.08.737173},
url = {https://www.biorxiv.org/content/10.64898/2026.07.08.737173v2},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Predicting clonal mutations from tumour spatial transcriptomics data using a graph convolutional neural network
AU - T. Luijts
AU - S. Hoogstoel
AU - S. Wen
AU - E. Pappaert
AU - E. De Meester
AU - F. Van Nieuwerburgh
AU - E. Van Hamme
AU - S. De Schepper
AU - W. Willaert
AU - A. Vral
AU - I. Hoorens
AU - J. Van den Eynden
PY - 2026
DA - 2026/07/08
PB - bioRxiv
DO - 10.64898/2026.07.08.737173
UR - https://www.biorxiv.org/content/10.64898/2026.07.08.737173v2
AB - Spatial transcriptomics (ST) has revolutionized our understanding of tumour biology but inherently lacks information on the upstream somatic driver mutations. We developed a spatially-aware graph convolutional neural network approach (SPOT-Mut) that infers mutated (sub)clones directly from ST data. SPOT-Mut was trained on virtual ST slides with clones simulated from a large collection of existing RNA and matched DNA sequencing data. SPOT-Mut was first evaluated for predicting mutations in TP53, the most frequently mutated gene in human cancer. Precision and recall values exceeded 95% in most analysed cancer types and the model was validated on ST and matched DNA sequencing data from serial slices obtained from cutaneous SCC samples. SPOT-Mut was then trained on 62 frequently mutated driver genes, resulting in highly performing somatic mutation prediction models for 40 driver genes, including KRAS, KEAP1, CTNNB1 and APC. With the increasing availability of ST data and upcoming atlases, SPOT-Mut potentiates the localization of (sub)clonal alterations in TP53 and other common driver mutations.
ER -