UniWave-2: A Hybrid Model for Nucleic Acid Waveform Feature Extraction Enhanced by Fourier and Wavelet Transforms
- 1Northwest Normal University
Abstract
Motivation: Traditional methods primarily rely on statistical features such as k-mers and GC content, making it difficult to capture complex internal relationships within sequences. Deep learning models typically rely on discrete encodings, leading to issues such as information sparsity, dimensional redun-dancy, and disruption of sequence continuity. Our previous UniWave-1 framework transforms se-quences into waveform signals; however, it lacks comprehensive physicochemical integration and com-putational efficiency. Results: We propose the UniWave-2 feature extraction framework. UniWave-2 incorporates three key advancements: (i) integration of hydrophobicity into the encoding scheme; (ii) enhancement of wave-form resolution through Fourier transform, coupled with wavelet transform to precisely capture both local details and global periodic patterns; and (iii) development of a lightweight multi-scale GRU model that facilitates cross-dimensional feature interactions, captures bidirectional temporal dependencies, and integrates long- and short-range patterns with spatial positional awareness, thereby yielding rich feature representations. UniWave-2 achieved competitive performance across multiple genomic tasks, while ISM analysis demonstrated that waveform encoding enables interpretable attribution without re-lying on gradient information. These results establish UniWave-2 as a lightweight and interpretable framework for nucleic acid sequence analysis.
Related
- Microfluidic Extraction of Extracellular Vesicle-Associated Nucleic Acids for Downstream Molecular Analysis
- Surfactant-Enhanced Hybridization Capture for Direct Sequence-Specific RNA Extraction from Plasma and Whole Blood
- Transfer Matrix and Tensor Approaches to Nucleic Acid Secondary Structure Thermodynamics
- The interaction between NC(p7)1-55 and p6 may regulate interactions with nucleic acids during assembly through modulation of Gag folding.
- Advanced molecular poliovirus diagnostics across multiple real-time PCR platforms with locked nucleic acids and primer overhangs
BibTeX
@misc{zhang2026uniwave2,
title = {{UniWave-2: A Hybrid Model for Nucleic Acid Waveform Feature Extraction Enhanced by Fourier and Wavelet Transforms}},
author = {H. Zhang and Y. Qi and Y. Feng and L. Wang},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.21.753349},
url = {https://www.biorxiv.org/content/10.64898/2026.09.21.753349v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - UniWave-2: A Hybrid Model for Nucleic Acid Waveform Feature Extraction Enhanced by Fourier and Wavelet Transforms
AU - H. Zhang
AU - Y. Qi
AU - Y. Feng
AU - L. Wang
PY - 2026
DA - 2026/09/21
PB - bioRxiv
DO - 10.64898/2026.09.21.753349
UR - https://www.biorxiv.org/content/10.64898/2026.09.21.753349v1
AB - Motivation: Traditional methods primarily rely on statistical features such as k-mers and GC content, making it difficult to capture complex internal relationships within sequences. Deep learning models typically rely on discrete encodings, leading to issues such as information sparsity, dimensional redun-dancy, and disruption of sequence continuity. Our previous UniWave-1 framework transforms se-quences into waveform signals; however, it lacks comprehensive physicochemical integration and com-putational efficiency. Results: We propose the UniWave-2 feature extraction framework. UniWave-2 incorporates three key advancements: (i) integration of hydrophobicity into the encoding scheme; (ii) enhancement of wave-form resolution through Fourier transform, coupled with wavelet transform to precisely capture both local details and global periodic patterns; and (iii) development of a lightweight multi-scale GRU model that facilitates cross-dimensional feature interactions, captures bidirectional temporal dependencies, and integrates long- and short-range patterns with spatial positional awareness, thereby yielding rich feature representations. UniWave-2 achieved competitive performance across multiple genomic tasks, while ISM analysis demonstrated that waveform encoding enables interpretable attribution without re-lying on gradient information. These results establish UniWave-2 as a lightweight and interpretable framework for nucleic acid sequence analysis.
ER -