Deciphering gene regulatory networks is a central problem in computational biology. Here, we explore the use of multi-modal neural networks to learn predictive models of gene expression that include cis and trans regulatory components. We learn models of stress response in the budding yeast Saccharomyces cerevisiae. Our models achieve high performance and substantially outperform other state-of-the-art methods such as boosting algorithms that use pre-defined cis-regulatory features. Our model learns several cis and trans regulators including well-known master stress response regulators. We use our models to perform in-silico TF knock-out experiments and demonstrate that in-silico predictions of target gene changes correlate with the results of the corresponding TF knockout microarray experiment.
通过长链聚合物物理学的镜头,我们对染色体结构组织和动态相互作用的理解发生了革命性的变化。染色体结构和动力学的主要蛋白质贡献者是凝聚素和粘着素,它们在链内和链间产生环,并捕获姐妹染色单体的近端链。在本文中,我们探讨了瞬时的,蛋白质介导的,基因-基因交联诱导基因簇的能力,从而动态架构,在高度重复的核糖体DNA,包括核仁的芽殖酵母。我们采用三种方法:活细胞显微术;芽殖酵母G1期全基因组的计算建模,探索染色体XII上核仁中5 k bp结构域之间瞬时交联的四十年时间尺度;以及应用于全系列4D建模数据集的自动社区检测算法的时间网络模型。数据分析工具检测和跟踪基因簇,它们的大小,数量,持续时间和可塑性。生物学意义,我们的分析揭示了一个最佳的平均交联寿命,促进成对和集群基因的相互作用,通过“灵活”的聚类。在这种状态下,大的基因簇自组装,但频繁地相互作用,以簇之间的基因交换为标志,这反过来又使核仁中的全局基因相互作用最大化。这种制度之间的两个限制的情况下,每个少得多的全球基因相互作用:与较短的交联寿命,“刚性”集群出现的集群,相互作用不频繁;与较长的交联寿命,有一个溶解的集群。这些观察结果与正常酵母菌株和两个凝聚酶修饰的突变细胞株的成像实验进行了比较,将相同的图像分析管道应用于实验和模拟数据集。
From data towards knowledge: Revealing the architecture of signaling systems by unifying knowledge mining and data mining of systematic perturbation data
Annotation-Informed Block-Sparse Bayesian Modeling for cis-Expression Prediction
School of Computing Sciences and Computer Engineering, University of Southern Mississippi(南密西西比大学计算机科学与计算机工程学院);Tulane Center for Biomedical Informatics and Genomics, Deming Department of Medicine, School of Medicine, Tulane University(路易斯安那大学医学中心生物医学信息学与基因组学中心,德明医学部);Texas Tech University Health Sciences Center, School of Medicine, Texas Tech University(德克萨斯科技大学健康科学中心,德克萨斯科技大学医学院)