CAREER:A Unified Architecture for Data Mining Large Biomedical Literature Databases

生物医学文献数据库中的大量文献，以及这些文献中自然语言叙述缺乏形式结构，使得许多参与生物信息学研究的科学家很难进行搜索和处理。这个职业项目正在研究信息检索过程的效率和有效性，模式学习方法用于信息提取的有效性和稳健性，以及文本挖掘中的信息过载，同时在一个连贯和统一的生物医学文献数据挖掘框架中进行。本项目的主要成果是：(1)开发了一种面向大型生物医学文献数据库的基于语义的查询扩展方法；(2)设计了一种基于互引导和动态规划的无标签文本文件的自动模式生成和评估方法；(3)开发了一套新颖的文本挖掘算法，如本体增强的文本聚类和文本摘要。该项目正在测试其在现实世界生物信息学领域的应用，如染色质相互作用网络和微阵列数据分析。该项目对社会产生的广泛影响是为生物医学文献数据挖掘产生了一个新的统一架构。在统一的架构中，这种综合和互补的方法有可能为生物信息学和大多数文本处理任务创造一个非常强大的新工具。该项目有可能吸引对获取复杂的生物医学或一般科学数据和信息感兴趣的不同合作者。学生通过实践项目、合作项目以及研究生和本科生的课程参与到这项研究中来。

The large number of documents in biomedical literature databases and the lack of formal structure in the natural-language narrative in those documents make the search and processing very difficult to many scientists involved in bioinformatics research. This CAREER project is investigating the efficiency and effectiveness of information retrieval procedures, the effectiveness and robustness of pattern learning methods for information extraction, and information overload in text mining simultaneously in a coherent and unified framework for biomedical literature data mining. The deliverables of this project are: (1) to develop a semantic-based query expansion method for large biomedical literature databases; (2) to design an automatic pattern generation and evaluation method from unlabeled text files based on mutual bootstrapping and dynamic programming; (3) to develop a set of novel text mining algorithms such as ontology-enhanced textual clustering and text summarization. This project is testing its application in real-world bioinformatics domains such as chromatin interaction networks and microarray data analysis. The broad impact on society made by this project is the generation of a novel unified architecture for biomedical literature data mining. This integrated and complementary approach in a unified architecture has the potential to create a very powerful novel tool for bioinformatics and for most text processing tasks. This project has the potential to attract diverse collaborators who have an interest in accessing complex biomedical or general scientific data and information. Students are involved in this research through hands-on projects, a Co-Op program and courses at both the graduate and undergraduate level.