从基因组深度神经网络中解释cis-regulatory机制,使用代用模型
Evan E Seitz1, David M McCandlish1, Justin B Kinney1
1Simons Center for Quantitative Biology, Cold Spring Harbor Laboratory, Cold Spring Harbor, NY, USA.
Nature machine intelligence
|February 14, 2025
概括
我们开发了SQUID,这是一个用于解读基因组学深度神经网络 (DNN) 的新框架. SQUID使用特定域的替代模型来揭示基因组功能预测的基础生物机制.
科学领域:
- 基因组学就是基因组学.
- 计算生物学 计算生物学
- 机器学习 机器学习
背景情况:
- 深度神经网络 (DNN) 擅长从DNA序列预测基因组功能.
- 解释这些基因组DNN学到的生物机制是困难的.
- 目前的可解释性方法,通常来自一般机器学习,对于生物数据可能不是最佳的.
研究的目的:
- 引入SQUID,一个用于解释基因组DNN的新框架.
- 为了利用特定领域的代孕模型来增强生物机制的阐明.
- 解决因数据非线性和噪声而导致的DNN解释方面的挑战.
主要方法:
- 开发了SQUID,一个基因组DNN解释性框架.
- 采用域特定替代模型来在序列空间中近似DNN.
- 纳入生物知识来建模 cis 调节机制.
- 考虑了功能基因组学数据中的非线性和异构基因组噪声.
主要成果:
- 与现有的方法相比,SQUID在基因组位置上发现了更一致的动机.
- SQUID 提高了单核酸变异效应的预测准确度.
- 证明了SQUID模拟复杂相互作用并提供全球机制解释的能力.
结论:
- SQUID提供了一种强大的新方法,用于机械地解释基因组DNN.
- 该框架增强了对Cis监管机制的理解.
- 在将机器学习应用于基因组学方面,SQUID代表了重大进展.
更多相关视频
11:36Author Spotlight: An Integrated Workflow to Study the Promoter-Centric Spatio-Temporal Genome Architecture in Scarce Cell Populations
Published on: April 21, 2023
1.9K
09:06High-throughput Identification of Gene Regulatory Sequences Using Next-generation Sequencing of Circular Chromosome Conformation Capture 4C-seq
Published on: October 5, 2018
10.2K
相关概念视频
02:02Cis-regulatory Sequences
9.7K
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...
9.7K
02:13Cooperative Binding of Transcription Regulators
6.3K
Transcriptional regulators bind to specific cis-regulatory sequences in the DNA to regulate gene transcription. These cis-regulatory sequences are very short, usually less than ten nucleotide pairs in length. The short length means that there is a high probability of the exact same sequence randomly occurring throughout the genome. Since regulators can also bind to groups of similar sequences, this further increases the chances of random binding. Transcriptional regulators form...
6.3K