跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.20255 · v1

Deep Sequence Model for Genome Wide Discovery of Coding and Regulatory Element Signatures

首次提交 2026-11-16 05:20
版本更新 2026-11-16 05:20
雷达观测 2026-11-17 17:12
arXiv ↗PDF ↗

摘要

Interpreting deep neural networks for genomic sequence classification remains challenging despite strong predictive performance. We develop a lightweight CNN with post-training gradient-based analysis to identify which sequence positions drive coding versus intergenomic classification. Applied to the standardized demo_coding_vs_intergenomic_seqs dataset, our model achieves 91.87% validation accuracy while revealing interpretable patterns: nine hot spots with consistently high importance, clear class-specific separation at positions 20-100 (coding) and 150-190 (intergenomic), and a strong mean-variance correlation (r = 0.530) indicating robust discriminative features. Gradient-based importance analysis shows that the model implicitly learns biologically meaningful sequence distinctions without explicit annotations. This work demonstrates that neural network interpretability and accuracy can coexist, providing a framework for understanding genomic sequence classification and enabling biology-driven hypothesis generation.

作者备注:4 pages, 3 figures, 1 table. Accepted at CVIS 2025. A shorter 3-page version was published in the Journal of Computational Vision and Imaging Systems, Vol. 11, No. 1 (2026)

期刊信息:Journal of Computational Vision and Imaging Systems, Vol. 11, No. 1, pp. 96-98 (2026). Shorter version

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-16 05:20 · 最新观测版本

Deep Sequence Model for Genome Wide Discovery of Coding and Regulatory Element Signatures

Interpreting deep neural networks for genomic sequence classification remains challenging despite strong predictive performance. We develop a lightweight CNN with post-training gradient-based analysis to identify which sequence positions drive coding versus intergenomic classification. Applied to the standardized demo_coding_vs_intergenomic_seqs dataset, our model achieves 91.87% validation accuracy while revealing interpretable patterns: nine hot spots with consistently high importance, clear class-specific separation at positions 20-100 (coding) and 150-190 (intergenomic), and a strong mean-variance correlation (r = 0.530) indicating robust discriminative features. Gradient-based importance analysis shows that the model implicitly learns biologically meaningful sequence distinctions without explicit annotations. This work demonstrates that neural network interpretability and accuracy can coexist, providing a framework for understanding genomic sequence classification and enabling biology-driven hypothesis generation.

查看此版本解读 →查看此版本原文 ↗