CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag167 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Xikang Feng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Research & Development Institute, Northwestern Polytechnical University, Sanhang Science & Technology Buliding, No. 45th, Gaoxin South 9th Road, Nans…. Hauptthemen laut MEDLINE: Deep Learning, DNA Copy Number Variations, Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Research Grants Council of Hong Kong.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Research & Development Institute, Northwestern Polytechnical University, Sanhang Science & Technology Buliding, No. 45th, Gaoxin South 9th Road, Nanshan District, Shenzhen City, 518063, China.
- School of Software, Northwestern Polytechnical University, 127 West Youyi Road, Beilin District, Xi'an Shaanxi, 710072, China.
- School of Civil Aviation, Northwestern Polytechnical University, 127 West Youyi Road, Beilin District, Xi'an Shaanxi, 710072, China.
- Department of Biomedical Sciences, College of Biomedicine, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon Tong, Kowloon, Hong Kong SAR, China.
ORCID-Profile: Xikang Feng, Lingxi Chen
Förderung
- National Natural Science Foundation of China
- Guangdong Basic and Applied Basic Research Foundation
- Research Grants Council of Hong Kong
- CityUHK Start-Up Grant
- Basic Research Programs of Taicang
Zitieren
APA
Feng, X., Xu, Z., Peng, S., Zheng, J., Ma, C., Jin, Q., & Chen, L. (2026). CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag167
Vancouver
Feng X, Xu Z, Peng S, Zheng J, Ma C, Jin Q, et al. CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag167
BibTeX
@article{Feng2026,
author = {Feng, Xikang and Xu, Zheng and Peng, Sisi and Zheng, Jieyi and Ma, Chuan and Jin, Qiangguo and Chen, Lingxi},
title = {CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag167}
}
EUVIMED