GraphPro:一种基于神经网络的可解释图形模型,用于识别多种物种中的促进体.
Qi Zhang1, Yuxiao Wei2, Liwei Liu1
1College of Science, Dalian Jiaotong University, Dalian, 116028, China.
Computers in biology and medicine
|August 3, 2024
概括
这项研究介绍了GraphPro,一种新的可解释图形神经网络模型,用于准确的多种促进体识别. GraphPro 增强了基因转录起始点的计算预测,改善了生物洞察力.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 准确的促进体鉴定对于理解基因表达和疾病机制至关重要.
- 促进者识别的实验方法昂贵且耗时.
- 为促进者识别开发高效的计算模型是必不可少的.
研究的目的:
- 介绍GraphPro,一个新的可解释图形神经网络模型,用于多种促进体识别.
- 为了提高计算推动者识别的准确性和跨物种预测能力.
- 提高促进者识别模型的生物解释性.
主要方法:
- 使用k-tuple频率,物理化学性质和dna2vec.编码DNA序列.
- 使用卷积神经网络和图形神经网络进行特征提取.
- 采用完全连接的神经网络进行促销器预测.
- 在八种物种数据集上验证模型,包括人类,老鼠和大肠杆菌.
主要成果:
- GraphPro的平均Sn,Sp,Acc和MCC值分别为0.9123,0.9482,0.8840和0.7984,可以实现这些值.
- 与以前的方法相比,在多种物种中证明了更高的识别准确性.
- 在跨物种预测能力方面表现优于现有方法.
- 通过可视化和对转录因子结合基因的分析,验证了生物解释性.
结论:
- GraphPro提供了一个强大而易于解释的工具,用于准确识别多个物种的促销者.
- 该模型推进了基因组学和基因调节研究中的计算方法.
- GraphPro的可解释性为转录因子结合和促进器功能提供了宝贵的见解.
相关概念视频
02:40The Eukaryotic Promoter Region
16.2K
The eukaryotic promoter region is a segment of DNA located upstream of a gene. It contains an RNA polymerase binding site, a transcription start site, and several cis-regulatory sequences. The proximal promoter region is located in the vicinity of the gene and has cis-regulatory sequences and the core promoter. The core promoter is the binding site for RNA polymerase and is usually located between -35 and +35 nucleotides from the transcription start site. The distal promoter regions are...
16.2K
02:11Reporter Genes
11.3K
Reporter genes are a type of protein-coding gene that are often tagged to a gene of interest. Once inside a target cell, reporter genes usually produce visually identifiable characteristics like fluorescence and luminescence when expressed along with the gene of interest. Thus, reporter genes “report” the presence or absence of genes of interest in an organism, determine the gene expression pattern, or track the physical location of a DNA segment or protein in the cell.
11.3K