LGITDec 15, 2025

Application of Deep Learning in Biological Data Compression

arXiv:2512.12975v1
Originality Synthesis-oriented
AI Analysis

This addresses storage challenges for researchers and educators working with Cryo-EM data, though it appears incremental as it builds on existing compression and neural representation techniques.

This paper tackles the problem of large storage requirements for cryogenic electron microscopy (Cryo-EM) biological data by applying implicit neural representation (INR) deep learning for compression, achieving a practical solution with reasonable compression ratios and reconstruction quality.

Cryogenic electron microscopy (Cryo-EM) has become an essential tool for capturing high-resolution biological structures. Despite its advantage in visualizations, the large storage size of Cryo-EM data file poses significant challenges for researchers and educators. This paper investigates the application of deep learning, specifically implicit neural representation (INR), to compress Cryo-EM biological data. The proposed approach first extracts the binary map of each file according to the density threshold. The density map is highly repetitive, ehich can be effectively compressed by GZIP. The neural network then trains to encode spatial density information, allowing the storage of network parameters and learnable latent vectors. To improve reconstruction accuracy, I further incorporate the positional encoding to enhance spatial representation and a weighted Mean Squared Error (MSE) loss function to balance density distribution variations. Using this approach, my aim is to provide a practical and efficient biological data compression solution that can be used for educational and research purpose, while maintaining a reasonable compression ratio and reconstruction quality from file to file.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes