美国麻省理工学院Caroline Uhler课题组提出了单细胞中蛋白质亚细胞定位的预测。这一研究成果于2025年5月13日发表在国际顶尖学术期刊《自然—方法学》上。

本文提出了一种未知蛋白亚细胞定位（PUPS）预测方法。PUPS结合了蛋白质语言模型和图像绘制模型，利用蛋白质序列和细胞图像。研究组证明，蛋白质序列输入可以泛化到看不见的蛋白质，细胞图像输入捕获单细胞变异性，从而实现细胞类型特异性预测。实验验证表明，在以训练为主题的人类蛋白质图谱之外的新进行的实验中，PUPS可以预测蛋白质的定位。总的来说，PUPS提供了一个框架，用于预测细胞系之间和细胞系内单个细胞的差异蛋白质定位，包括突变驱动的蛋白质定位变化。

据介绍，蛋白质的亚细胞定位对其功能至关重要，其错误定位与许多疾病有关。现有的数据集捕获了有限的蛋白质对和细胞系，现有的蛋白质定位预测模型要么缺少细胞类型特异性，要么不能推广到看不见的蛋白质。

附：英文原文

Title: Prediction of protein subcellular localization in single cells

Author: Zhang, Xinyi, Tseo, Yitong, Bai, Yunhao, Chen, Fei, Uhler, Caroline

Issue&Volume: 2025-05-13

Abstract: The subcellular localization of a protein is important for its function, and its mislocalization is linked to numerous diseases. Existing datasets capture limited pairs of proteins and cell lines, and existing protein localization prediction models either miss cell-type specificity or cannot generalize to unseen proteins. Here we present a method for Prediction of Unseen Proteins’ Subcellular localization (PUPS). PUPS combines a protein language model and an image inpainting model to utilize both protein sequence and cellular images. We demonstrate that the protein sequence input enables generalization to unseen proteins, and the cellular image input captures single-cell variability, enabling cell-type-specific predictions. Experimental validation shows that PUPS can predict protein localization in newly performed experiments outside the Human Protein Atlas used for training. Collectively, PUPS provides a framework for predicting differential protein localization across cell lines and single cells within a cell line, including changes in protein localization driven by mutations.

DOI: 10.1038/s41592-025-02696-1

Source: https://www.nature.com/articles/s41592-025-02696-1