Neural Proteomics Fields for Super-resolved Spatial Proteomics Prediction

TL;DR

This paper introduces Neural Proteomics Fields, a deep learning model for super-resolving spatial proteomics data, significantly improving protein distribution predictions in tissues with a new benchmark dataset.

Contribution

The paper presents the first deep learning approach for spatial super-resolution in sequencing-based proteomics, combining tissue-specific modeling with morphological features.

Findings

Achieves state-of-the-art performance on the Pseudo-Visium SP dataset.

Uses fewer parameters than existing methods.

Provides an open-source benchmark for future research.

Abstract

Spatial proteomics maps protein distributions in tissues, providing transformative insights for life sciences. However, current sequencing-based technologies suffer from low spatial resolution, and substantial inter-tissue variability in protein expression further compromises the performance of existing molecular data prediction methods. In this work, we introduce the novel task of spatial super-resolution for sequencing-based spatial proteomics (seq-SP) and, to the best of our knowledge, propose the first deep learning model for this task--Neural Proteomics Fields (NPF). NPF formulates seq-SP as a protein reconstruction problem in continuous space by training a dedicated network for each tissue. The model comprises a Spatial Modeling Module, which learns tissue-specific protein spatial distributions, and a Morphology Modeling Module, which extracts tissue-specific morphological features. Furthermore, to facilitate rigorous evaluation, we establish an open-source benchmark dataset, Pseudo-Visium SP, for this task. Experimental results demonstrate that NPF achieves state-of-the-art performance with fewer learnable parameters, underscoring its potential for advancing spatial proteomics research. Our code and dataset are publicly available at https://github.com/Bokai-Zhao/NPF.