Machine learning approaches for improved accuracy and speed in sequence annotation: supplement for software enhancement

提高序列注释准确性和速度的机器学习方法：软件增强的补充

• 批准号: 10406630
• 负责人: Travis John Wheeler
• 金额: $ 22.19万
• 依托单位: UNIVERSITY OF MONTANA
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-09-20 至 2023-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10406630
• 关键词: Address; Biological; Centromere; Classification; Cloud Computing; Complex; Computer software; Consensus; DNA Transposable Elements; Data; Development; Documentation; Elements; Error Sources; Galaxy; Genetic Recombination; Genome; Goals; Human; Label; Libraries; Machine Learning; Maintenance; Methods; Modernization; Molecular Biology; Output; Parents; Pathway interactions; Pattern; Process; Repetitive Sequence; Reporting; Sequence Alignment; Sequence Analysis; Software Engineering; Software Tools; Source; Speed; Structure; System; Testing; Uncertainty; Visualization; adjudicate; base; cloud based; genome annotation; improved; molecular sequence database; parent grant; searchable database; software development; support tools; telomere; tool; web server

Summary The goal of this parent grant for this supplement request is to develop Machine Learning approaches to improve both accuracy and speed of highly-sensitive sequence database search and alignment. We have developed three software tools associated with this effort of correctly annotating genomes: (i) ULTRA, which labels repetitive sequence, (ii) PolyA which integrates such labels with other sequence annotations in a probabilistic framework, computing uncertainty and improving accuracy, and (iii) SODA, which aids in visualization of annotations and supporting evidence. Here, we describe a plan to refactor these software tools and their documentation to improve robustness and reliability, and to improve their availability through package management systems and incorporation into cloud-based analysis frameworks.

总结 这项补充申请的父母补助金的目标是开发机器学习方法， 提高了高灵敏度序列数据库搜索和比对准确性和速度。我们有 开发了三种与正确注释基因组的努力相关的软件工具：（i）ULTRA， 标记重复序列，（ii）PolyA，其将这些标记与其他序列注释整合在一个或多个标记中， 概率框架，计算不确定性和提高准确性，以及（iii）SODA，这有助于 注释和支持证据的可视化。在这里，我们描述了一个重构这些软件的计划 工具及其文档，以提高健壮性和可靠性，并通过 软件包管理系统，并纳入基于云的分析框架。