PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 19, 2026Briefings in Bioinformatics0 citationsOpen Access

CRESCENT: a deep learning framework with multi-scale attention for detecting recurrent copy number alterations

View Full Paper
XFXikang FengZXZheng XuSPSisi Peng

Key Points

  • To develop a framework that reliably detects recurrent copy number alterations in tumor samples.
  • Developed the CRESCENT deep learning framework integrating multi-scale sampling and self-attention mechanisms.
  • Analyzed copy number profiles from 7689 cases across 20 TCGA cancer projects.
  • Conducted leave-one-project-out cross-validation to evaluate model performance.
  • Trained a unified pan-cancer model on simulated datasets and independent cohorts.
  • Achieved area under the curve of 0.894–0.967 for amplifications and 0.804–0.929 for deletions.
  • CRESCENT showed improved detection balance over traditional tools like GISTIC2 and RUBIC.
  • Identified critical oncogenic drivers and prognostic markers often missed by conventional methods.

Abstract

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.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Feng et al. (2026) studied this question.

synapsesocial.com/papers/69e47282010ef96374d8e7b4https://doi.org/10.1093/bib/bbag167
Ask AI
Helpful
Bookmark
Share
View Full Paper