Network-based prediction of polygenic disease genes involved in cell motility
Network-based prediction of polygenic disease genes involved in cell motility
复制标题
DOI：
10.1186/s12859-019-2834-1
复制
发表时间：
2019-06-20
影响因子：
3
通讯作者：
Ritz, Anna
中科院分区：
文献类型：
--
作者：
Bern, Miriam;King, Alexander;Ritz, Anna
背景精神分裂症和自闭症是由多种遗传变异引起的多基因疾病的例子，其中许多遗传变异仍然知之甚少。最近，这两种疾病都与神经元运动和迁移模式破坏有关，表明异常的细胞运动是这些神经系统疾病的一种表型。结果我们提出了多基因疾病表型问题，旨在识别可能与细胞运动等表型相关的候选疾病基因。我们提出了一种机器学习方法来解决大脑特定功能交互网络中的精神分裂症和自闭症基因的问题。我们的方法优于同行半监督学习方法，在不同的黄金标准正值集上实现了更好的交叉验证准确性。我们确定了精神分裂症和自闭症的最佳候选基因，并选择了六个标记为精神分裂症阳性的基因，这些基因预计与细胞运动相关，用于后续实验。结论通过我们的方法预测的候选基因提出了关于这些基因的可检验的假设x2019；在细胞运动调节中的作用，为生成实验验证的预测提供了框架。
BackgroundSchizophrenia and autism are examples of polygenic diseases caused by a multitude of genetic variants, many of which are still poorly understood. Recently, both diseases have been associated with disrupted neuron motility and migration patterns, suggesting that aberrant cell motility is a phenotype for these neurological diseases.ResultsWe formulate the Polygenic Disease Phenotype Problem which seeks to identify candidate disease genes that may be associated with a phenotype such as cell motility. We present a machine learning approach to solve this problem for schizophrenia and autism genes within a brain-specific functional interaction network. Our method outperforms peer semi-supervised learning approaches, achieving better cross-validation accuracy across different sets of gold-standard positives. We identify top candidates for both schizophrenia and autism, and select six genes labeled as schizophrenia positives that are predicted to be associated with cell motility for follow-up experiments.ConclusionsCandidate genes predicted by our method suggest testable hypotheses about these genesx2019; role in cell motility regulation, offering a framework for generating predictions for experimental validation.