Leveraging Machine Learning to Explore the Effects of the Design2Data Course-based Undergraduate Research Experience

利用机器学习探索基于 Design2Data 课程的本科生研究经验的效果

• 批准号: 2315767
• 负责人: Justin Siegel
• 金额: $ 39.75万
• 依托单位: University of California-Davis
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-15 至 2026-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2315767&HistoricalAwards=false
• 关键词: Leveraging; Machine; Learning; Explore; Effects

This project aims to serve the national interest by engaging students in the Design to Data (D2D) program, a nationally networked biochemistry Course-based Undergraduate Research Experience (CURE). The project will help to determine which parts of the student experience positively impact graduation and access to STEM careers. D2D engages students in exploring protein science through a cutting-edge computationally driven research project. This project anchors the curriculum across a network of highly motivated, early-adopter faculty members teaching students in varied STEM disciplines and levels. The hands-on D2D learning experience prepares students for success in this new era of biology while crowdsourcing data collection for improved protein modeling artificial intelligence methods. The large, diverse D2D student body offers a rich opportunity to explore novel, machine learning-based assessment methods for CURE education research. In reaching the aims of this grant, this project will (a) pioneer a cutting-edge approach to investigating student learning in research experiences and will make these data analysis methods broadly accessible to STEM education researchers, and (b) create equitable, meaningful research experiences for thousands of students, many of whom would not have otherwise had the opportunity. D2D’s undergraduate research project anchors the program, and D2D faculty network members facilitate its implementation by integrating the project into their classes on a wide variety of campuses across the United States. Participating students functionally characterize novel enzyme mutants generating data for protein modeling stakeholders to explore with the goal of developing better functionally predictive tools for more rapid solutions to human-centered problems. Not only is there potential to meaningfully advance science through the program, but the experience enables equitable access to cutting-edge biotechnology training that is in high demand by employers. Reaching many students with this program is tractable: D2D readily integrates into lab practicum settings across the disciplines and from first-year to senior-level classes. The network includes forty institutions and will engage approximately 4,000 students over the funding period. The project objective is to use this large, diverse population in assessing mediators to psycho-social and behavioral outcomes linked to STEM persistence by collecting multi-level motivational data at scale with layered variables and benchmark cutting edge machine learning methods for the data analysis. The project activities will (a) support dedicated network continuity coordination to maintain current levels of faculty participation, and (b) assessment activities to plan and execute comprehensive data collection and machine learning (ML)-based analysis that captures and evaluates a deep set of discrete CURE-implementation variables. From these activities, meaningful professional development beyond the D2D Network will be promoted by making the cutting-edge student learning data analysis methods accessible to other education researchers. Finally, this project will put research into hands of thousands of students and enable more equitable access to CUREs, increasing the diversity of students participating in research. The NSF IUSE: EDU Program supports research and development projects to improve the effectiveness of STEM education for all students. Through its Engaged Student Learning track, the program supports the creation, exploration, and implementation of promising practices and tools.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

该项目旨在通过让学生参与数据设计 (D2D) 项目来服务国家利益，该项目是一个全国网络化的基于生物化学课程的本科生研究体验 (CURE) 项目，将有助于确定学生的哪些部分经历对毕业产生积极影响。 D2D 通过尖端的计算驱动的研究项目让学生探索蛋白质科学，该项目通过一个由积极主动的早期采用者组成的网络来教授不同 STEM 学科的学生。实践 D2D 学习经验为学生在这个生物学新时代取得成功做好准备，同时众包数据收集以改进蛋白质建模人工智能方法，庞大而多样化的 D2D 学生群体提供了探索基于机器学习的新颖机会。 CURE 教育研究的评估方法 为了实现这项资助的目标，该项目将 (a) 开创一种调查学生研究经验学习的前沿方法，并使这些数据分析方法可供 STEM 教育研究人员广泛使用，以及 ( b) 为数千人创造公平、有意义的研究体验的学生，其中许多人本来没有机会参与该项目，D2D 教师网络成员通过将该项目融入到美国各地参与学生的课堂中来促进该项目的实施。对新型酶突变体进行功能表征，为蛋白质建模利益相关者生成数据，以开发更好的功能预测工具，以更快速地解决以人类为中心的问题，不仅有潜力通过该计划有意义地推进科学，而且经验可以实现公平。访问雇主急需的尖端生物技术培训很容易吸引许多学生：D2D 很容易融入跨学科的实验室实习环境，从一年级到高级课程。该网络包括 40 个机构和意愿。该项目的目标是在资助期间吸引大约 4,000 名学生，通过大规模收集具有分层变量的多层次动机数据，利用这一庞大、多样化的人群来评估与 STEM 坚持相关的社会心理和行为结果的中介因素。该项目活动将（a）支持专门的网络连续性协调，以维持当前教师的参与水平，以及（b）评估活动，以规划和执行全面的数据收集和机器学习（ML）。基于分析，捕获和评估一组深层的离散 CURE 实施变量，通过向其他教育研究人员提供尖端的学生学习数据分析方法，将促进 D2D 网络之外有意义的专业发展。该项目将把研究成果交给数千名学生NSF IUSE：EDU 计划支持研究和开发项目，以提高所有学生 STEM 教育的有效性。创建、探索和实施有前景的实践和工具。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。