深度学习捕捉了多因素疾病中的表现效应
Vladislav Perelygin1, Alexey Kamelin1,2, Nikita Syzrantsev2
1International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, Russia.
Frontiers in medicine
|January 22, 2025
概括
非线性机器学习和深度学习模型通过考虑复杂的基因相互作用 (epistasis) 来显著改善疾病风险预测. 这些先进的方法优于传统的线性模型,特别是在1型糖尿病,肥胖和牛皮等多因素疾病中.
科学领域:
- 遗传学和生物信息学
- 计算生物学 计算生物学
- 疾病风险预测 疾病风险预测
背景情况:
- 多基因风险评分 (PRS) 传统上使用线性模型,假设独立的SNP贡献.
- 复杂的疾病涉及非线性基因-基因相互作用 (表观),通常被线性模型遗漏.
- 准确预测多因素疾病需要采用捕捉这些复杂遗传结构的方法.
研究的目的:
- 评估非线性机器学习和深度学习模型在预测多因素疾病风险方面的性能.
- 为了研究表观症对疾病预测准确性的影响.
- 将非线性方法与遗传风险评估的传统线性模型进行比较.
主要方法:
- 使用GAMETES生成模拟遗传数据,使用不同的表现模型 (添加,乘法,值) 进行模拟.
- 采用机器学习算法,包括多层感知子 (MLP),卷积神经网络 (CNN),循环神经网络 (RNN),拉索回归,随机森林和梯度增强.
- 在模拟和真实遗传数据上使用准确度,AUC-ROC,AUC-PR,回忆,精度和F1得分等指标评估模型性能.
主要成果:
- 非线性模型的表现明显优于线性回归 (LASSO) 随着表现强度的增加.
- 渐变增强显示在肥胖和牛皮预测方面表现优越.
- 深度学习模型在1型糖尿病预测方面表现明显优于线性方法.
结论:
- 非线性机器学习和深度学习模型比线性模型更有效地预测在出现表皮病时的疾病风险.
- 这些先进的计算方法提高了复杂多因素疾病遗传风险评估的准确性.
- 该研究强调了在基因组预测模型中考虑非线性遗传相互作用的重要性.
相关概念视频
01:09Epistasis Analysis
4.9K
Although Mendel chose seven unrelated traits in peas to study gene segregation, most traits involve multiple gene interactions that create a spectrum of phenotypes. When the interaction of various genes or alleles at different locations influences a phenotype, this is called epistasis. Epistasis often involves one gene masking or interfering with the expression of another (antagonistic epistasis). Epistasis often occurs when different genes are part of the same biochemical pathway. The...
4.9K
01:39Epistasis
45.6K
In addition to multiple alleles at the same locus influencing traits, numerous genes or alleles at different locations may interact and influence phenotypes in a phenomenon called epistasis. For example, rabbit fur can be black or brown depending on whether the animal is homozygous dominant or heterozygous at a TYRP1 locus. However, if the rabbit is also homozygous recessive at a locus on the tyrosinase gene (TYR), it will have an unshaded coat that appears white, regardless of its TYRP1...
45.6K
01:33Pleiotropy
39.6K
Pleiotropy is the phenomenon in which a single gene impacts multiple, seemingly unrelated phenotypic traits. For example, defects in the SOX10 gene cause Waardenburg Syndrome Type 4, or WS4, which can cause defects in pigmentation, hearing impairments, and an absence of intestinal contractions necessary for elimination. This diversity of phenotypes results from the expression pattern of SOX10 in early embryonic and fetal development. SOX10 is found in neural crest cells that form melanocytes,...
39.6K
01:11Genetic Lingo
100.5K
Overview
100.5K
01:43Incomplete Dominance
21.2K
Gregor Mendel's work (1822 - 1884) was primarily focused on pea plants. Through his initial experiments, he determined that every gene in a diploid cell has two variants called alleles inherited from each parent. He suggested that amongst these two alleles, one allele is dominant in character and the other recessive. The combination of alleles determines the phenotype of a gene in an organism.
21.2K
01:28Human Genetics
529
Human genetics provides a profound framework for understanding the interplay between genetic predispositions and human psychology. At the heart of this discipline lies the study of how genes influence physical traits, behaviors, and susceptibility to diseases. Each person carries a unique genetic code that subtly or significantly shapes their psychological and behavioral landscape.
The complex relationship between genetics and psychology is observable through common biological components such...
The complex relationship between genetics and psychology is observable through common biological components such...
529