Text Mining as a Translational Tool in Biomedicine

描述（由申请人提供）： 候选人的长期职业目标是成为生物医学信息学的独立研究者，特别关注文本挖掘作为生物医学研究中的翻译工具。候选人的近期目标是加强他作为耶鲁大学教师的独立地位，将生物医学文本挖掘定位为大学课程的重要组成部分，并与计算语言学和基础生物医学研究领域的科学家建立强有力的合作。候选人的职业发展计划是他以前工作的合理延续。拟议的项目将有助于建立候选人作为一个独立的研究人员在更广泛的生物医学信息学界。该提案的总体目标是开发一种基于文本挖掘的翻译信息学工具，帮助遗传学家从全基因组连锁扫描中精确定位可能的疾病候选基因。耶鲁大学的协作环境使这些发现得到实验验证，并对分析方法进行迭代改进。虽然该项目的重点是遗传学，但在各个学科中分析和理解全基因组高通量信息的需求不断增长。候选人的目标是建立文本挖掘作为实现这一目的的重要工具。

DESCRIPTION (provided by applicant): The candidate's long-term career goal is to become an independent investigator in biomedical informatics, with a specific focus on text mining as a translational tool in biomedical research. The candidate's immediate goals are to strengthen his independent position as a faculty at Yale University, to position biomedical text mining as an essential part of the University's curriculum and to build strong collaboration with scientists in both computational linguistics and basic biomedical research. The candidate career development plan is a logical continuation of his previous work. The proposed project will help to establish the candidate as an independent researcher in the wider biomedical informatics community. The general aim of this proposal is to develop a text mining-based translation informatics tool that helps geneticists in pinpointing likely disease candidate genes from whole genome linkage scans. A collaborative environment here at Yale enables the experimental validation of these findings, and an iterative refinement of analytical methods. While the focus of the project is on genetics, there is a growing demand to analyze and make sense of whole genome high throughput information in various disciplines. The candidate aims at establishing text mining as an important tool for such purposes.