2026*
CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations
Xikang Feng†*, Zheng Xu†, Sisi Peng, Jieyi Zheng, Chuan Ma, Qiangguo Jin*, Lingxi Chen*
copy number alterationsrecurrent CNAfocal CNAcancer analysisdeep learning
Abs
Abstract Recurrent copy number alterations (CNAs) are fundamental drivers of tumorigenesis, yet identifying them reliably remains a challenge due to the extreme variability in their genomic scale and context. Current methods often struggle to balance sensitivity across focal, segmental, and arm-level events. Here, we present CRESCENT, a deep learning framework designed to detect recurrent CNAs by integrating multi-scale sampling with convolutional neural networks and self-attention mechanisms. By processing copy number profiles from 7689 cases across 20 The Cancer Genome Atlas (TCGA) cancer projects, CRESCENT learns to distinguish recurrent drivers from background noise through parallel feature fusion. In rigorous leave-one-project-out cross-validation, the model demonstrated robust generalization, achieving area under the curves of 0.894–0.967 for amplifications and 0.804–0.929 for deletions in representative cohorts (Bladder Urothelial Carcinoma, Sarcoma, Glioblastoma Multiforme, Uterine Corpus Endometrial Carcinoma). Finally, extending beyond the TCGA-specific cross-validation, we trained a unified pan-cancer model to assess CRESCENT’s generalizability on simulated datasets and independent, non-TCGA cancer cohorts (CGCI and TARGET). Benchmarking against standard tools, including GISTIC2 and RUBIC, reveals that CRESCENT offers superior detection balance, identifying the highest total number of significant events across focal and broad scales. Moreover, extensive focal gene expression validation and pathway annotation, coupled with survival analysis, highlight that CRESCENT identifies critical oncogenic drivers and prognostic markers that conventional statistical methods often overlook. In all, CRESCENT provides a highly sensitive, generalized approach for decoding tumor evolution.
Bib
@article{doi_101093bibbbag167,
title = {{CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations}},
author = {Xikang Feng and Zheng Xu and Sisi Peng and Jieyi Zheng and Chuan Ma and Qiangguo Jin and Lingxi Chen},
journal = {Briefings in Bioinformatics},
year = {2026},
volume = {27},
number = {2},
doi = {10.1093/bib/bbag167},
url = {https://doi.org/10.1093/bib/bbag167}
}Journal metrics
BIOCHEMICAL RESEARCH METHODS JCR Q1 JIF rank 4/85
MATHEMATICAL & COMPUTATIONAL BIOLOGY JCR Q1 JIF rank 6/67
2025 annual data · ShowJCR community dataset · Retrieved 2026-10-09 · Source ↗
