Research Initiation Award: Uncovering and Extracting Biological Information from Nanopore Long-read Sequencing Data with Machine Learning and Mathematical Approaches

HBCU-UP的研究启动奖为STEM教师开展研究活动提供支持，以进一步提高他们的研究能力和效率，并帮助提高hbcu的研究和教学水平。该奖项授予Tougaloo学院，旨在揭示基因表达和细胞分化的关键见解。它将通过利用创新技术和计算工具推进基因组学领域。本项目旨在通过使用长读测序技术，在了解基因表达的控制方面做出贡献，并将其具体应用于了解疾病。此外，它通过提供本科生，特别是那些来自历史上边缘化社区的学生，通过宝贵的研究经验，促进教育和多样性。通过将这项研究整合到课程中，Tougaloo学院旨在转变STEM教学法，丰富学生在各个学科的学习。这个项目的潜在效益是广泛的。它不仅可以提高教师的研究能力，还可以促进未来STEM专业人员的发展。通过让学生参与真实的研究，它将为他们成功的职业生涯做好准备，并有助于他们留在STEM领域。该项目的总体目标是利用高通量基因组和转录组数据集，主要基于纳米孔长读测序，研究DNA甲基化对不同生物系统和疾病中RNA速度轨迹的影响。该项目将开发创新的计算工具，以准确估计RNA速度和检测DNA甲基化模式，包括罕见或新颖的修饰。利用纳米孔长读测序的独特优势，如丰富的信号级信息，该项目将通过提供对DNA甲基化和RNA速度之间相互作用的全面理解，推动该领域的发展。本研究的技术方法包括开发用于RNA速度估计的计算工具箱和用于直接DNA甲基化检测的基于变压器的机器学习工具。通过整合RNA速度和DNA甲基化数据，该项目将揭示基因表达和细胞分化的调控机制。通过实现更准确的诊断、个性化治疗和基因组医学的变革性进步，预期的结果有可能影响包括医疗保健在内的各个行业。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

HBCU-UP’s Research Initiation Awards provide support for STEM faculty to pursue research activities to further their research capabilities and effectiveness and help enhance research and teaching at HBCUs. This award to Tougaloo College seeks to uncover crucial insights into gene expression and cellular differentiation. It will advance the field of genomics by utilizing innovative technology and computational tools. Through the use of long-read sequencing, the project aims to make contributions in understanding the control of gene expression in general, with specific application understanding diseases. Additionally, it promotes education and diversity by providing undergraduate students, particularly those from historically marginalized communities, through valuable research experiences. By integrating this research into the curriculum, Tougaloo College aims to transform STEM pedagogies and enrich the learning of students in various disciplines. The potential benefits of this project are wide-reaching. It will not only enhance the research capabilities of faculty members, but also foster the development of future STEM professionals. By engaging students in authentic research, it will prepare them for successful careers and contributes to their retention in STEM fields. The overarching goal of this project is to utilize high-throughput genomic and transcriptome data sets, primarily based on Nanopore long-read sequencing, to investigate the influence of DNA methylation on RNA velocity trajectories in diverse biological systems and diseases. The project will develop innovative computational tools to accurately estimate RNA velocity and detect DNA methylation patterns, including rare or novel modifications. Leveraging the unique advantages of Nanopore long-read sequencing, such as rich signal-level information, the project will advance the field by providing a comprehensive understanding of the interplay between DNA methylation and RNA velocity. This research's technical approach involves the development of a computational toolbox for RNA velocity estimation and a transformer-based machine learning tool for direct DNA methylation detection. Through the integration of RNA velocity and DNA methylation data, the project will shed light on the regulatory mechanisms underlying gene expression and cellular differentiation. The anticipated outcomes have the potential to impact various sectors, including healthcare, by enabling more accurate diagnostics, personalized therapies, and transformative advancements in genomic medicine.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.