相关实验视频

Updated: Jul 3, 2025

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Single-cell RNA-Seq of Defined Subsets of Retinal Ganglion Cells

Published on: May 22, 2017

参数高效微调提高了单细胞大语言模型的适应性,用于细胞类型识别

Fei He¹, Ruixin Fei², Mingyue Gao²

¹Department of Electrical Engineering and Computer Science, Bond Life Sciences Center, University of Missouri, Columbia, MO, 65211, USA.

bioRxiv : the preprint server for biology

|February 14, 2024

概括

参数高效微调 (PEFT) 改进了单细胞大语言模型 (scLLM) 用于细胞类型识别. 与传统的微调相比,这种方法提高了性能,同时大大降低了计算成本.

科学领域:

计算生物学计算生物学
基因组学就是基因组学.
人工智能的人工智能

背景情况:

单细胞测序提供高分辨率的细胞数据,但具有很高的可变性.
单细胞大语言模型 (scLLM) 旨在识别这些数据中的通用模式.
现有的scLLM在零射击环境中扎,需要更好的适应技术.

研究的目的:

为SCLLM开发新的适应技术.
为下游任务提高scLLM的性能和效率.
为了解决传统微调的局限性,例如灾难性遗忘和计算费用.

主要方法:

为 scLLM 提出的参数有效微调 (PEFT) 策略.
专注于选择性地更新新引入的张量,同时保留原始模型参数.
应用PEFT来改进scLLM用于使用scGPT进行细胞类型识别.

主要成果:

在细胞类型识别中,PEFT显著提高了scLLM的性能.
与传统微调相比,实现了高达90%的参数训练减少.
在单细胞数据分析中证明了PEFT在改善信号噪声比的有效性.

结论:

PEFT提供了一种高效有效的方法来调整 scLLM.
这种方法克服了与传统微调相关的关键挑战.
为scLLM在单细胞生物学中的更广泛,更有效的应用铺平了道路.

关键词:

细胞类型识别细胞类型识别基金会模型基金会模型在PEFT中,PEFT是PEFT.一个单细胞的单细胞.

更多相关视频

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

相关概念视频

Overview Of Cell Separation And Isolation

Overview Of Cell Separation And Isolation

Cell separation was first achieved in 1964 by S. H. Seal, who separated large tumor cells from the smaller blood cells using filtration. Two years later, Pohl and Hawk performed experiments on how cells respond differently to a nonuniform electric field based on the cell type. Such observations were the inception of cell separation methods, which allow isolating a single cell type from a heterogeneous sample.