Predictive Modeling of Alternative Splicing and Polyadenylation from Millions of Random Sequences

数百万随机序列的选择性剪接和聚腺苷酸化的预测模型

• 批准号: 9306648
• 负责人: Georg Seelig
• 金额: $ 59.66万
• 依托单位: UNIVERSITY OF WASHINGTON
• 依托单位国家: 美国
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-04-21 至 2021-01-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9306648
• 关键词: Adopted; Algorithms; Alternative Splicing; Area; Basic Science; Behavior; Big Data; Biological Assay; Biological Phenomena; CRISPR/Cas technology; Clinical Medicine; Code; Complex; Computers; DNA Sequence; Data; Data Set; Databases; Dependency; Disease; Gene Expression; Gene Expression Regulation; Generations; Genes; Genetic; Genetic Polymorphism; Genetic Variation; Genome; Genomics; Haplotypes; Human; Human Genome; Lead; Learning; Libraries; Machine Learning; Measurement; Measures; Mediating; Mendelian disorder; Modeling; Mutation; Natural Language Processing; Nucleotides; Polyadenylation; Protein Isoforms; Proteins; Publishing; RNA Splicing; RNA-Binding Proteins; Regulation; Regulator Genes; Reporter; Research; Risk; Scientist; Shapes; Specific qualifier value; Testing; Training; Transcript; Untranslated RNA; Validation; Variant; Work; base; clinically relevant; data modeling; disease-causing mutation; exon skipping; experimental study; genetic variant; human disease; knock-down; novel strategies; predictive modeling; repaired; synthetic biology; synthetic construct

The proportion of the human genome that underlies gene regulation dwarfs the proportion that encodes proteins. However, we remain poorly equipped for identifying which genetic variants compromise gene regulatory function in ways that may contribute to risk for both rare and common human diseases. Understanding how non-coding sequences regulate gene expression, as well as being able to predict the functional consequences of genetic variation for gene regulation, are paramount challenges for the field. Here, we propose to combine synthetic biology, massively parallel functional assays, and machine learning to profoundly advance our understanding of the `regulatory code' of the human genome. While challenging, the task of unravelling complex codes from large amounts of empirical data is not without precedent. For example, over the past decade, computer scientists working in natural language processing have made immense progress, driven in large part by a combination of algorithmic and computational improvements and enormously larger training datasets than were available to the previous generations of scientists working in this area. Inspired by the revolutionizing impact of “big data” for traditional problems in machine learning, we propose to model gene regulatory phenomena using training datasets with several orders of magnitude more examples than naturally exist in the human genome. We predict that the models learned from massive numbers of synthetic examples will strongly outperform models learned from the small number of natural examples. We will demonstrate our approach by developing comprehensive, quantitative, and predictive models for alternative splicing and alternative polyadenylation, two widespread regulatory mechanisms by which a single gene can code for multiple transcripts and proteins. However, we anticipate that this basic paradigm – specifically, the massively parallel measurement of the functional behavior of extremely large numbers of synthetic sequences followed by quantitative modeling of sequence-function relationships – can be generalized to advance our understanding of diverse forms of gene regulation.

人类基因组中作为基因调控基础的比例使编码的比例相形见绌 蛋白质。然而，我们仍然缺乏识别哪些遗传变异损害基因的能力 调节功能可能会增加罕见和常见人类疾病的风险。 了解非编码序列如何调节基因表达，以及能够预测 遗传变异对基因调控的功能影响是该领域面临的首要挑战。这里， 我们建议将合成生物学、大规模并行功能分析和机器学习结合起来 深刻推进我们对人类基因组“调控密码”的理解。在充满挑战的同时， 从大量经验数据中解开复杂密码的任务并非没有先例。例如， 在过去的十年中，从事自然语言处理工作的计算机科学家取得了巨大的成就 进步在很大程度上是由算法和计算改进的结合推动的 比前几代从事该领域工作的科学家可用的训练数据集要大得多 区域。受到“大数据”对机器学习传统问题的革命性影响的启发，我们 提议使用几个数量级的训练数据集来模拟基因调控现象 人类基因组中自然存在的例子。我们预测模型会从大量的数据中学习 大量的合成示例将远远优于从少量自然示例中学习到的模型 例子。我们将通过开发全面的、定量的和预测性的方法来展示我们的方法 选择性剪接和选择性多腺苷酸化的模型，这两种广泛的调节机制 单个基因可以编码多个转录本和蛋白质。然而，我们预计这一基本 范式——具体来说，是对极大的功能行为的大规模并行测量 合成序列的数量，然后对序列-功能关系进行定量建模 - 可以是 推广以增进我们对多种形式的基因调控的理解。