Doc Sherlock: An Autonomous Relay Agent for Discovering the "Unknown Knowns" in Precision Medicine

夏洛克博士：发现精准医学中“未知的知识”的自主中继代理

• 批准号: 10333495
• 负责人: William E Byrd
• 金额: $ 92.23万
• 依托单位: UNIVERSITY OF ALABAMA AT BIRMINGHAM
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-01-24 至 2022-01-23
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10333495
• 关键词: 16p11.2; Back; Collaborations; Data; Data Discovery; Data Set; Data Sources; Disease; Genes; Harvest; Intelligence; Knowledge; Language; Logic; Measures; Mind; Modeling; Modernization; Ontology; Patients; Pharmaceutical Preparations; Phase; Physicians; Provider; Publications; Publishing; Role; Scientist; Simvastatin; Site; Source; Syndrome; Visit; Work; cost; new growth; precision medicine; tool

Component: We propose a generalization of our Translator reasoner tool mediKanren [1] into “Doc Sherlock”: an Autonomous Relay Agent (ARA) to answer biomedical queries from multiple Knowledge Providers (KPs) via probabilistic, logical and abductive inference. Problem: Eliminating the “Unknown Known”: With the explosive growth of new publications, data sets and discoveries, a distinctly modern problem has emerged: the rapid expansion of the “unknown known.” The unknown known are facts that are either (1) forgotten -- facts published but not known widely -- or (2) uninferred -- facts inferable from known facts but not yet deduced. We take it as the role of KPs to uncover the forgotten by systematically harvesting existing sources of knowledge. We thus take it as the role of ARAs to tackle the uninferred -- the conclusions that could have been drawn if only all of the premises were co-resident in a single reasoner’s mind. For pragmatic purposes, we restrict the queries to a tractable yet ambitious class: queries raised by physician-scientists -- for whom the cost of the unknown known is measured in patients' lives. Plan : Doc Sherlock will use the advanced logic programming engine miniKanren [2,3] , and it will use probabilistic inference rules to tackle queries inspired by physician-scientists and rank results by confidence. For example, we imagine Doc Sherlock answering the question, “What may treat 16p11.2 deletion syndrome?” by using a KP backed by something like Ensembl [4] to look up all the genes in 16p11.2; a second KP backed by a dataset like gnomAD [5,6] to rank haploinsufficient genes, e.g., “KCTD13 is haploinsufficient” [97% confidence]; a gene-gene KP like SemMedDB [7] to find a relationship like “KCTD13 inhibits RhoA” [97% confidence] and then using a drug-gene KP to find that “Simvastatin inhibits RhoA” [99% confidence] to hypothesize that “Simvastatin may mitigate 16p11.2 deletion via RhoA inhibition” [93% imputed confidence]. To answer queries from physician-scientists, data sources which have gene-gene, drug-gene, disease-gene or drug-disease relationships will be high priority. Collaboration : Building on our collaboration model from the current Translator phase, we plan to visit other sites and have them visit us to work on problems from physician-scientists. We will support the ARA standard API, and other Translator Standards. For queries richer than the designated API, we will support programmatic access to Doc Sherlock’s query language. Challenges: The primary technical challenge in reasoning across distinct KPs is intelligently aliasing identical concepts within different data sets. To connect ontologies from different KPs, we propose exploring the use of Galois connections [8,9] -- a generalization of isomorphism suitable for use between two partial orders (such as ontologies). A major benefit will be the ability to conduct abductive reasoning and to go beyond the restrictions of living within a single KP -- our preliminary data shows a 43% improvement in inference across KPs [see Plan].

组件：我们建议将我们的翻译器推理工具Medikanren[1]推广为 《神探夏洛克》：一个可回答多个生物医学问题的自主中继代理(ARA) 知识提供者(KPS)通过概率推理、逻辑推理和溯因推理。 问题：消除“未知的已知”：随着新出版物的爆炸性增长， 数据集和发现，一个明显的现代问题已经出现：数据的快速扩展 “未知已知。”未知的已知事实或者是(1)忘记的事实--公布的事实 但不是广为人知的--或(2)不可推断的--可从已知事实推断但尚未推论的事实。 我们认为KPS的作用是通过系统地收获现有的东西来发现被遗忘的东西 知识的来源。因此，我们将其视为Aras的角色，以解决未知的-- 如果所有的房产都共住在一个单独的 推理者的思想。出于实用目的，我们将查询限制在易于处理但雄心勃勃的 类：由医生-科学家提出的问题--对他们来说，未知的成本是 在病人的生活中衡量。 计划：《神探夏洛克》将使用高级逻辑编程引擎mini Kanren[2，3]，它将 使用概率推理规则处理由医生-科学家和排名启发的问题 满怀信心地取得成果。例如，我们想象夏洛克医生回答这样一个问题：“什么？ 可以治疗16p11.2缺失综合征吗？通过使用由EnSembl[4]之类的东西支持的KP来 查找16p11.2中的所有基因；由gnomAD[5，6]这样的数据集支持的第二个KP进行排名 单倍体不足的基因，例如“KCTD13是单倍体不足的”[97%的置信度]；基因-基因Kp 就像SemMedDB[7]一样，找到像“KCTD13抑制RhoA”这样的关系[97%的可信度]和 然后用药物基因Kp发现“辛伐他汀抑制RhoA”[99%可信] 假设“辛伐他汀可通过抑制RhoA减少16p11.2的缺失”[93%被归因于 信心]。回答来自医学科学家、具有基因-基因的数据源、 药物与基因、疾病与基因或药物与疾病的关系将是高度优先的。 协作：在当前翻译阶段的协作模式基础上，我们计划 访问其他网站，并让他们访问我们来解决内科科学家的问题。我们会 支持ARA标准API，以及其他翻译器标准。对于比 指定的API，我们将支持编程访问Doc Sherlock的查询语言。 挑战：跨不同KPS进行推理的主要技术挑战是智能 使不同数据集中的相同概念产生别名。为了连接来自不同KPS的本体， 我们建议探索Galois联络[8，9]的用途--同构的推广 适用于两个偏序之间(如本体论)。一个主要的好处是 进行诱拐推理的能力，并超越生活在一个 KP--我们的初步数据显示，在整个KPS中，推理能力提高了43%[参见计划]。