通过域知识集成与逻辑 Tensor 网络增强转录因子预测
IEEE transactions on computational biology and bioinformatics
|October 3, 2025
概括
我们开发了LTN-TFpredict,一种神经符号AI模型,可以提高转录因子 (TF) 预测的准确性和可解释性. 它将深度学习与生物规则相结合,优于基因表达调节研究的现有方法.
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.
- 人工智能的人工智能
背景情况:
- 转录因子 (TFs) 对基因表达调节至关重要.
- 当前的TF预测方法缺乏准确性或可解释性,特别是当生物知识有限时.
- 深度学习模型通常需要大量的数据,并且很难将特定领域的见解纳入其中.
研究的目的:
- 引入LTN-TFpredict,一种用于增强TF预测的新型神经象征框架.
- 提高TF预测模型的准确性和可解释性.
- 将深度学习与象征性推理和生物领域知识相结合.
主要方法:
- 使用逻辑 Tensor 网络 (LTNs) 集成与深度学习.
- 使用预先训练的蛋白质语言模型用于序列嵌入.
- 嵌入了五个关键TF动图 (指,白拉链等) 的逻辑约束. 为了指导学习.
主要成果:
- 在TF预测中,LTN-TFpredict实现了最先进的准确性.
- 该模型始终优于传统和深度学习方法,包括CNN和变压器.
- 证明了改善的生物有效性和符合已知的TF特征的逻辑性.
结论:
- LTN-TFpredict为TF预测提供了一个强大的,可解释的,生物依据的解决方案.
- 神经符号方法有效地弥合了深度学习和象征性推理在计算生物学中的桥梁.
- 这一框架促进了人工智能的应用,以了解基因调节机制.
相关概念视频
Transcription Factors
82.2K
Tissue-specific transcription factors contribute to diverse cellular functions in mammals. For example, the gene for beta globin, a major component of hemoglobin, is present in all cells of the body. However, it is only expressed in red blood cells because the transcription factors that can bind to the promoter sequences of the beta globin gene are only expressed in these cells. Tissue-specific transcription factors also ensure that mutations in these factors may impair only the function of...
82.2K
General Transcription Factors
6.7K
Tissue-specific transcription factors contribute to diverse cellular functions in mammals. For example, the gene for beta globin, a major component of hemoglobin, is present in all cells of the body. However, it is only expressed in red blood cells because the transcription factors that can bind to the promoter sequences of the beta globin gene are only expressed in these cells. Tissue-specific transcription factors also ensure that mutations in these factors may impair only the function of...
6.7K
Eukaryotic Transcription Activators
12.5K
Transcription activators are proteins that promote the transcription of genes from DNA to RNA. In most cases, these proteins contain two separate domains ‒ a domain that binds to DNA and a domain for activating transcription; however, in some cases, a single domain is responsible for both binding and activation of transcription, as seen in the glucocorticoid receptor and MyoD.
The binding domains are capable of recognizing and interacting with regulatory sequences on the DNA. These...
The binding domains are capable of recognizing and interacting with regulatory sequences on the DNA. These...
12.5K
RNA Polymerase II Accessory Proteins
10.8K
Proteins that regulate transcription can do so either via direct contact with RNA Polymerase or through indirect interactions facilitated by adaptors, mediators, histone-modifying proteins, and nucleosome remodelers. Direct interactions to activate transcription is seen in bacteria as well as in some eukaryotic genes. In these cases, upstream activation sequences are adjacent to the promoters, and the activator proteins interact directly with the transcriptional machinery. For example, in...
10.8K
Cooperative Binding of Transcription Regulators
7.1K
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...
7.1K
Cooperative Binding of Transcription Regulators
2.5K
2.5K


