使用生物注释神经网络框架提高乳牛基因组预测的准确性
Xue Wang1, Shaolei Shi1, Md Yousuf Ali Khan1,2
1State Key Laboratory of Animal Biotech Breeding, National Engineering Laboratory for Animal Breeding, Key Laboratory of Animal Genetics, Breeding and Reproduction of Ministry of Agriculture and Rural Affairs, College of Animal Science and Technology, China Agricultural University, Beijing 100193, China.
生物注释神经网络 (BANNs) 提高了乳牛的基因组预测准确性. 班的框架,特别是使用100kb的窗口,超过了传统的方法,如GBLUP和随机森林.
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.
- 机器学习 机器学习
背景情况:
- 生物注释神经网络 (BANNs) 是可解释的贝叶斯神经网络模型.
- BANNs使用部分连接的架构,由SNP-set注释提供信息.
- 它们在基因组预测中的应用在本研究之前仍然未被探索.
研究的目的:
- 扩大BANNs框架用于乳牛的基因组选择.
- 调查BANN的最佳SNP集分区策略.
- 将BANN的性能与已建立的基因组预测方法进行比较.
主要方法:
- 应用的BANN与SNP集由基因注释 (BANN_gene) 和100kb窗口 (BANN_100kb) 分区.
- 利用中国Holstein的基因型和表型数据来确定牛奶生产,类型和健康特征.
- 进行了五倍交叉验证的五次复制,将BANN与GBLUP,RF,BayesB和BayesCπ进行比较.
主要成果:
- BANNs框架实现了比GBLUP,RF和贝叶斯方法更高的基因组预测准确度.
- BANN_100kb表现出卓越的准确性,比GBLUP,RF,BayesB和BayesCπ的平均改进分别为4.86%,3.95%,3.84%和1.92%.
- 与传统方法相比,BANN_100kb和BANN_gene的平均平方误差都较低.
结论:
- BANNs框架显示了乳牛基因组预测的卓越性能.
- BANN_100kb分区策略被证明是最有效的.
- 在畜牧种群中,BANNs代表了基因组预测的有希望的替代方案.
更多相关视频
09:04Transcriptome Profiling of In-Vivo Produced Bovine Pre-implantation Embryos Using Two-color Microarray Platform
Published on: January 30, 2017
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
相关概念视频
Genome Annotation and Assembly
The Central Dogma
RNA is the Missing Link Between DNA and Proteins
In the early 1900s, scientists discovered that DNA stores all the information needed for cellular functions and that proteins perform most of these functions. However, the mechanisms of converting genetic information into functional proteins remained unknown for many years. Initially, it was believed that a single gene is...
Plant Breeding and Biotechnology
