CREaTor:使用注意力机制的零射击cis-regulatory模式建模.
Yongge Li1,2, Fusong Ju1, Zhiyuan Chen1,3
1Microsoft Research AI4Science, Beijing, China.
Genome biology
|November 24, 2023
概括
我们开发了CREaTor,这是一种深度学习工具,可以将基因调节元素与目标基因联系起来. 它只使用RNA-seq和ChIP-seq数据准确地预测新细胞类型中的基因表达.
科学领域:
- 基因组学就是基因组学.
- 计算生物学 计算生物学
- 分子生物学分子生物学
背景情况:
- 将cis调节序列与它们的目标基因联系起来对于理解基因调节至关重要,但仍然是一个重大挑战.
- 现有的方法往往需要对特定相互作用的先验知识或每个细胞类型的广泛训练数据.
研究的目的:
- 介绍CREaTor,一个基于注意力的深度神经网络,用于建模cis-regulatory模式.
- 为了使细胞类型特定的 cis-regulatory 模式建模,而无需先前的相互作用知识或再培训.
主要方法:
- 开发了CREaTor,这是一个深层神经网络,利用注意力机制来模拟cis-regulatory模式.
- 实施了一种训练策略,预测来自候选cis调节元件 (cCREs) 的基因表达.
- 杆RNA测序 (RNA-seq) 和ChIP测序 (ChIP-seq) 数据用于模型训练和应用.
主要成果:
- CREaTor有效地模拟了基因组元素的cis-regulatory模式,从目标基因中获得高达2兆基 (Mb) 的数据.
- 该模型展示了"零射击"能力,在没有特殊训练的情况下预测新细胞类型中的细胞类型特定模式.
- 仅使用RNA-seq和ChIP-seq数据实现了跨多种细胞类型的概括.
结论:
- CREaTor提供了一种强大而可通用的方法,可以将cis-regulatory序列与目标基因联系起来.
- 零射击学习能力显著减少了对细胞类型特定训练数据的需求.
- 这种方法有助于更深入地了解各种细胞环境中的基因调节.
相关概念视频
Stereotype Content Model
14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K
Cis-regulatory Sequences
9.9K
Cis-regulatory sequences are short fragments of non-coding DNA that are present on the same chromosomes as the genes that they regulate. These fragments serve as binding sites for transcriptional regulators, proteins that are responsible for controlling gene transcription and differential gene expression across cell types in eukaryotes. Cis-regulatory sequences can be close to the gene of interest or thousands of bases away in the DNA sequence; however, those sequences that are further away are...
9.9K
Co-activators and Co-repressors
7.4K
Gene transcription is regulated by the synergistic action of several proteins that form a complex at a gene regulatory site. This is observed in eukaryotes, where the regulation of gene expression is a complex process. Regulatory proteins in eukaryotes can broadly be classified into two types – regulators that bind directly to specific DNA sequences and co-regulators that associate with regulatory proteins but cannot directly bind to the DNA. These co-regulators are further divided into...
7.4K
Master Transcription Regulators
6.9K
Master transcription regulators are regulatory proteins that are predominantly responsible for regulating the expression of multiple genes. Often these genes work in concert to drive a complex process. Activation of a master transcription regulator can lead to a cascade of transcriptional activation necessary for that outcome. These regulators can directly bind to the regulatory sequences of the various genes involved, or they can indirectly regulate transcription by binding to regulatory...
6.9K

