cs.LGNov 15, 2026

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

Authors: Rayhaneh Shabani Nia, Ali Karkehabadi

Organizations: University of California, Davis

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. AttnGen: Attention-Guided Saliency Learning for Interpretable Genomic Sequence Classification

    May 13, 2026Rayhaneh Shabani Nia, Ali KarkehabadiNeural Network InterpretabilityAttention Mechanisms

  2. Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees

    Apr 13, 2026Nicolas Huynh, Krzysztof Kacprzyk, Ryan Sheridan +2Interpretable MLDecision Tree Learning

  3. SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable machine learning

    Sep 14, 2026Evgeny S. Saveliev, Krzysztof Kacprzyk, Charlotte Capitanchik +7Interpretable MLGenomics