Big Data Training for Cancer Research

项目摘要 在NIH Big Data to Knowledge（BD 2K）计划之后，我们一直得到NCI的资助， 为期两周的夏季培训计划，针对癌症研究人员，他们是大数据分析的新手。期间 在过去的七年里，我们成功地组织了面对面和在线实践培训机会， 传统上训练有素的生物医学和癌症研究人员。我们目前的研讨会使用涉及癌症的应用程序 数据教授有价值的数据科学和生物信息学方法。但是，我们坚信， 数据科学技能是有点普遍的。有了这个融资机会，我们很高兴能扩大我们的研讨会， 材料与一个额外的模块利用熟悉的传染病和免疫介导的疾病（IID）的数据 研究人员和相关的方法，如R脚本，探索性分析，数据争论， 纵向数据可视化。拟议补充文件直接响应NOT-AI-23-010， 使IID研究人员能够更自信地探索现有的IID数据，建立自己的分析计划， 在研究团队中进行沟通。 我们建议的补充课程有三个目标：（1）开发两个新的与IID相关的教学案例研究 目的，与IID研究人员和生物医学研究人员的更广泛受众相关;（2）创建 为IID和癌症研究社区提供指导的可公开访问、可重复使用的在线材料 在探索性数据分析，数据争论，质量控制和计算机编程;（3）增加这些新的 案例研究和材料，以补充目前资助的关于癌症大数据的研讨会，作为一种新的混合体（在 个人和在线）前模块。像我们最初的R25研讨会一样，本课程将针对研究生， 博士后学员，医生科学家和生物医学科学家，具有强大的IID背景，但有限 统计学、生物信息学和计算机科学的高级课程。 我们计划提供这个新的模块作为我们目前的课程，而不是作为一个单独的课程。甚至 对当前文献的简要浏览将提供癌症、免疫学（包括COVID）和 微生物组我们期望基于跨学科的互动和知识为参与者带来额外的好处 他们将通过参加合并课程获得。最后，过去课程的许多参与者指出， 有专门的时间与教师和其他参与者互动，并独立探索感兴趣的话题 让他们有信心提问和回答问题--本质上是自我指导的学习者。

PROJECT SUMMARY Following the NIH Big Data to Knowledge (BD2K) initiative, we have been continuously funded by NCI to create a two-week summer training program for cancer researchers who are novices in big data analysis. During the past seven years, we have successfully organized both in-person and online hands-on training opportunities for traditionally trained biomedical and cancer researchers. Our current workshop uses applications involving cancer data to teach valuable data science and bioinformatics approaches. However, we strongly believe that these data science skills are somewhat general. With this funding opportunity, we are excited to extend our workshop materials with an additional module utilizing data familiar to infectious and immune-mediated disease (IID) researchers and relevant approaches such as scripting in R, exploratory analysis, data wrangling, and visualization of longitudinal data. The proposed supplement is directly responsive to NOT-AI-23-010 and will enable IID researchers to more confidently explore existing IID data, set up their own analysis plans, and communicate within research teams. Our proposed supplement course has three goals: (1) Develop two new IID-related case studies for teaching purposes, both relevant to IID researchers and a more general audience of biomedical researchers; (2) Create publicly accessible, reusable online materials for IID and cancer research communities that provide instruction in exploratory data analysis, data wrangling, quality control, and computer programming; and (3) Add these new case studies and materials to supplement the currently funded workshop on big cancer data as a new hybrid (in- person and online) pre-module. Like our original R25 workshop, this course will target graduate students, postdoctoral trainees, physician-scientists, and biomedical scientists, with strong IID backgrounds yet limited advanced coursework in statistics, bioinformatics, and computer science. We plan to offer this new module as an addition to our current course rather than as a separate course. Even a brief scan of the current literature will provide evidence between cancer, immunology (including COVID), and microbiome. We expect additional benefits for participants based on interdisciplinary interactions and knowledge they will obtain through participation in the combined course. Finally, many participants in past courses state that having dedicated time to interact with faculty and other participants and to explore topics of interest independently gave them the confidence to ask and answer questions—in essence to be self-directed learners.