Scholarlink

<p>Improving the efficiency of data compression remains essential for feature selection and data modelling. Current approaches for compressing epigenomic/genomic data highly rely on autoencoder that requires substantial computing resources, parameter fine-tuning, training, and time. Here, we developed a training-free, Fast Fourier Transform (FFT)-based method, for data compression with high efficiency and full interpretability. Our FFT method compresses epigenomic data of histone modification up to 1,000-fold while still maintaining high reconstruction fidelity (cosine similarity, 99.7%), does not require any training and completes ultrafast within 70&#xa0;ms on GPU or 20&#xa0;s on CPU opposite to extensive training in hours/days for autoencoder on GPU/CPU, and offers full interpretability of compressed features from frequency components of original signals in contrast to the uninterpretable “black box” from autoencoder. This enables high accuracy in the classification model prediction (AUC, 0.960). Thus, our novel FFT method represents a major paradigm shift in data compression.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Fast Fourier transform is a training-free, ultrafast, highly efficient, and fully interpretable approach for epigenomic data compression

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月10日

查看全文
  • Max Ward,
  • Bac Dao,
  • Amitava Datta,
  • Zhaoyu Li

摘要

Improving the efficiency of data compression remains essential for feature selection and data modelling. Current approaches for compressing epigenomic/genomic data highly rely on autoencoder that requires substantial computing resources, parameter fine-tuning, training, and time. Here, we developed a training-free, Fast Fourier Transform (FFT)-based method, for data compression with high efficiency and full interpretability. Our FFT method compresses epigenomic data of histone modification up to 1,000-fold while still maintaining high reconstruction fidelity (cosine similarity, 99.7%), does not require any training and completes ultrafast within 70 ms on GPU or 20 s on CPU opposite to extensive training in hours/days for autoencoder on GPU/CPU, and offers full interpretability of compressed features from frequency components of original signals in contrast to the uninterpretable “black box” from autoencoder. This enables high accuracy in the classification model prediction (AUC, 0.960). Thus, our novel FFT method represents a major paradigm shift in data compression.