相关实验视频

Updated: Jan 6, 2026

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells

Multi-color Localization Microscopy of Single Membrane Proteins in Organelles of Live Mammalian Cells

Published on: June 30, 2018

ProteinFormer:基于生物图像和修改的预训练变压器的蛋白质亚细胞定位

Xinyi An¹, Yixin Li¹, Huiping Liao¹

¹School of Mathematics and Computational Science, Xiangtan University, Xiangtan, 411105, China.

|November 8, 2025

概括

一个新的深度学习模型ProteinFormer准确地使用生物图像和变压器架构预测蛋白质细胞下定位. 它的性能优于现有的方法,特别是在数据有限的场景中,提供了高效的解决方案.

科学领域:

计算生物学计算生物学
生物信息学是一种生物信息学.
机器学习机器学习

背景情况:

传统的蛋白质定位实验是昂贵和低效的.
基于序列的方法与蛋白质转位动态作斗争.
现有的深度学习模型缺乏全球图像集成以实现本地化.

研究的目的:

开发一种用于蛋白质细胞下定位的新型深度学习模型.
将生物图像与增强的变压器架构集成在一起.
为了应对小样本场景和数据稀缺的挑战.

主要方法:

拟议的ProteinFormer模型结合了ResNet用于本地特征和修改后的变压器用于全球融合.
开发了GL-ProteinFormer变体,具有残留学习,感应偏差和ConvFFN,用于数据稀缺.
利用生物图像进行培训和评估.

主要成果:

在Cyto_2017数据集上,ProteinFormer实现了最先进的性能 (91%的单标签,81%的多标签).
在有限样本IHC_2021数据集 (81%) 上,GL-ProteinFormer显示出优异的概括性.
ConvFFN提高了准确度4%并降低了计算成本.

结论:

ProteinFormer和GL-ProteinFormer的性能优于现有的基于卷积的方法.
生物图像与基于变压器的全球建模的融合提供了一个强大的解决方案.
这种方法在数据有限的环境中对蛋白质亚细胞局部化特别有效.

关键词:

生物图像生物图像这就是ConvFFNNN的意思.蛋白质亚细胞局部化这就是ResNet ResNet.变压器变压器变压器

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

相关概念视频

Subcellular Fractionation

Subcellular Fractionation

The homogenate obtained after cell lysis contains various membrane-bound organelles that can be further separated into pure fractions by subcellular fractionation. These isolates are used to study specific cellular components, analyze localized protein activity, and are even employed in diagnostics. Fractionation is typically achieved using centrifugation methods, the most common being density-gradient and differential centrifugation.
Differential Centrifugation
Differential centrifugation is...

Nuclear Localization Signals and Import

Nuclear Localization Signals and Import

Proteins targeted to the nucleus carry short stretches of amino acid sequences called the nuclear localization signal or NLS. Classical nuclear localization signals are of two types: monopartite and bipartite NLS. Monopartite classical NLS (cNLS) consists of a single cluster of 4-8 amino acids. Bipartite cNLS consists of two clusters of 2-3 amino acids and a 9-12 residue long proline-rich linker bridging the two clusters. Signal clusters are rich in positively charged amino acids such as...