Shaocong Mo | Searcharxiv

arXiv2026

Evolutionary characterization of whole-genome doubling across human cancers

Whole-genome doubling (WGD) is common across human cancers and is associated with tumour progression and adverse clinical outcomes. However, how genome-doubled tumours evolve across diverse cancer types remains poorly understood. Here we characterize WGD-associated tumour evolution by integrating genomic analyses of 41,332 tumours from 12 cancer types with evolutionary timing and multi-omic data. Several canonical driver mutations generally preceded WGD when both occurred, as did the onset of homologous recombination deficiency-associated mutagenesis. Notably, post-WGD chromosome-arm losses showed substantially weaker cancer-type dependence than pre-WGD losses, with 61-75% less variance explained by cancer type. Beyond chromosomal evolution, WGD+ tumours showed reduced interferon-response and HLA antigen-presentation programmes linked to epigenetic remodelling, without disproportionate enrichment of genetic immune-escape alterations. Our findings highlight WGD as a recurrent evolutionary transition associated with altered chromosomal evolution and epigenetically linked immune adaptation across cancers.

q-bio.GN↗

arXiv2025

A Text-Image Fusion Method with Data Augmentation Capabilities for Referring Medical Image Segmentation

Deep learning relies heavily on data augmentation to mitigate limited data, especially in medical imaging. Recent multimodal learning integrates text and images for segmentation, known as referring or text-guided image segmentation. However, common augmentations like rotation and flipping disrupt spatial alignment between image and text, weakening performance. To address this, we propose an early fusion framework that combines text and visual features before augmentation, preserving spatial consistency. We also design a lightweight generator that projects text embeddings into visual space, bridging semantic gaps. Visualization of generated pseudo-images shows accurate region localization. Our method is evaluated on three medical imaging tasks and four segmentation frameworks, achieving state-of-the-art results. Code is publicly available on GitHub: https://github.com/11yxk/MedSeg_EarlyFusion.

cs.CV↗