Micropublications for Automating Genome Sequence Variant Interpretation from Medical Literature

用于从医学文献中自动解释基因组序列变异的微型出版物

• 批准号: 10255401
• 负责人: Mark Julin Kiel
• 金额: $ 85.5万
• 依托单位: GENOMENON, INC.
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-05-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10255401
• 关键词: Achievement; Address; Adoption; Automation; Categories; Classification; ClinVar; Clinic; Clinical; Clinical Research; Clinical Treatment; Clinical Trials; Collaborations; Communities; Computer software; Consultations; Consumption; Country; Data; Data Set; Databases; Diagnosis; Diagnostic; Disease; Documentation; Drug Industry; Ensure; Frequencies; Genes; Genetic; Genetic Databases; Genome; Genomics; Goals; Gold; Grant; Human Genome; Human Genome Project; Individual; Industry; Information Retrieval; Laboratory Research; Literature; Manuals; Medical; Methods; Mission; Oncologist; Pathogenicity; Pathologist; Patients; Phase; Population; Procedures; Process; Public Health; Published Comment; Publishing; Quality Control; Rare Diseases; Reproducibility; Research Personnel; Scientist; Source; Speed; System; Testing; Therapeutic Intervention; Time; United States National Institutes of Health; Update; Variant; Work; base; clinical Diagnosis; clinical decision-making; clinical practice; community based evaluation; cost; cost effective; crowdsourcing; data curation; design; exome; genetic variant; genome sequencing; genome-wide; improved; indexing; member; migration; next generation sequencing; novel strategies; patient population; quality assurance; search engine; standardize guidelines; success; targeted treatment

PROJECT SUMMARY Accurate and efficient interpretation of genomic variants for clinical decision making is predicated on ready access to and extraction of information from the medical literature. The sheer number of potentially relevant articles that must be examined during this process poses a significant challenge in ensuring the accuracy and reproducibility of clinical interpretation as it is time-consuming, error-prone, and highly user-dependent. To this end, we have developed the Mastermind Genomic Search Engine - a commercial database that automatically organizes disease, gene and variant information from the medical literature by systematically indexing millions of scientific articles. Mastermind is used by over 9,100 variant scientists in more than 100 different countries to more quickly interpret genetic variants in clinical settings. In Phase I of this project, we developed and tested a micropublication platform within Mastermind that assembles literature curation along with population frequency data, computational predictions of pathogenicity, and automated ACMG/AMP classifications that improves the speed of variant interpretation by more than 70% and increases the sensitivity of these results by 2-20x. The present proposal seeks to build on the success of Phase I by 1) integrating the micropublication platform into Mastermind with migration of collaborative features for community-based evaluation of variant interpretations; 2) optimizing and improving automated variant interpretation/prioritization of articles and implementing a rigorous quality assurance process; and 3) using these improvements to curate all evidence in all variants in all genes comprising the entire human genome, beginning with the clinical exome. Integration of the pre-curated genome data in the micropublication platform will result in Mastermind Enterprise, allowing for immediate and accurate genome-wide variant interpretations with collaborative curation in real-time at the point of interaction with source material (i.e. individual references). This work will mitigate reproducibility challenges plaguing other large-scale crowd-sourced projects, including those undertaken by groups like NIH’s ClinVar and QIAGEN’s HGMD. In addition, our novel approach will not suffer from poor sensitivity as it relies on a comprehensive source of medical literature pre-annotated based on genetic content. This work will permit dramatic scaling of variant interpretation activities and allow for complete and accurate curation of the entire human genome within 2 years – a feat that could not be completed utilizing current manual methods for variant interpretation. Mastermind Enterprise will be revolutionary in the genomics industry and will represent a natural next step to build on the achievements provided by the Human Genome Project and the reduced cost of next-generation sequencing. It will substantially improve diagnostic rates and accuracy in the clinic, especially in rare disease, where a lack of genetic evidence often results in severely delayed and inaccurate diagnoses. Additionally, it will allow the pharmaceutical industry to develop more successful targeted therapies and to design more inclusive clinical trials as well as to more reliably identify patients who would benefit from therapeutic intervention. [Word count – 468; Line count – 30]

项目摘要 准确和有效地解释基因组变异以用于临床决策的前提是准备就绪 从医学文献中获取和提取信息。潜在相关的 在此过程中必须检查的物品在确保准确性方面构成了重大挑战， 临床解释的可重复性，因为它是耗时的，容易出错的，并且高度依赖于用户。本 最后，我们开发了Mastermind Genomic Search Engine -一个商业数据库， 组织疾病，基因和变异信息从医学文献系统索引数以百万计 的科学文章。Mastermind被100多个不同国家的9,100多名变异科学家使用， 更快地解释临床环境中的遗传变异。在这个项目的第一阶段，我们开发和测试了一个 Mastermind中的微型出版平台，它将文献整理沿着人群频率一起收集 数据，致病性的计算预测，以及自动化ACMG/AMP分类， 变异判读速度提高了70%以上，结果的灵敏度提高了2- 20倍。的 目前的建议旨在通过以下方式在第一阶段成功的基础上再接再厉：1）将微型出版物平台整合到 策划协作特征的迁移，用于基于社区的变体解释评估; 2） 优化和改进文章的自动化变体解释/优先级排序，并实施严格的 质量保证过程;以及3）使用这些改进来管理所有基因中所有变体的所有证据 包括从临床外显子组开始的整个人类基因组。预策展基因组的整合 微出版平台中的数据将产生Mastermind Enterprise，允许即时和准确地 全基因组变异解释与协作策展在实时点的互动与源 材料（即个人参考）。这项工作将减轻重现性挑战， 众包项目，包括由NIH的ClinVar和QIAGEN的HGMD等团体进行的项目。在 此外，我们的新方法不会受到灵敏度差的影响，因为它依赖于全面的医学来源。 基于遗传内容预先注释的文献。这项工作将允许显着缩放的变异解释 活动，并允许在2年内完整和准确地管理整个人类基因组-这一壮举， 无法使用当前的变量解释手动方法完成。企业策划者将 这是基因组学行业的革命性成果，将代表着在已取得的成就基础上自然迈出的下一步。 人类基因组计划所提供的技术和下一代测序的低成本。它将大大 提高临床诊断率和准确性，特别是在缺乏遗传证据的罕见疾病中 常常导致严重延迟和不准确的诊断。此外，它还将使制药行业 开发更成功的靶向疗法，设计更具包容性的临床试验， 可靠地确定哪些患者将受益于治疗干预。 [Word count - 468; Line count - 30]