AI/ML Ready appraoches for integrative RNA processing, splicing and spatial genomics

用于整合 RNA 处理、剪接和空间基因组学的 AI/ML Ready 方法

基本信息

批准号：
10407768
负责人：
Julia Salzman
金额：
$ 15.75万
依托单位：
STANFORD UNIVERSITY
依托单位国家：
美国
项目类别：
财政年份：
2021
资助国家：
美国
起止时间：
2021-01-01 至 2025-12-31
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10407768
关键词：
Address Algorithms Alternative Splicing Base Sequence Biological Biological Markers Biology Cells Code Communities Complex Computer software DNA DNA Sequence Data Development Diagnostic Disease Disease Marker Docking Drug Targeting Engineering Eukaryota Eukaryotic Cell Evolution Foundations Future Generations Genes Genetic Genetic Transcription Genome Genomics Goals Individual Knowledge Life Methods Minority Modality Nucleic Acids Nucleotides Organism Output Pathogenicity Polyadenylation Process Processed Genes Protein Isoforms Proteins Public Domains RNA RNA Processing RNA Splicing Readiness Regulation Reproducibility Research Research Personnel Resolution Role Statistical Algorithm Transcript Untranslated RNA Untranslated Regions Variant cell type digital experimental study genetic variant insight nervous system disorder novel parent grant programs public health relevance public repository single cell sequencing single-cell RNA sequencing tool transcriptomics

项目摘要

Project Summary/Abstract From parent grant: Cells and organisms, from simple to complex, carry the same genetic DNA sequence organized into genes. Multicellular eukaryotes transcribe and process genes into RNA isoforms through a process called alternative splicing. Alternative splicing is developmentally, and cell-type specifically regulated. It is foundational to how higher organisms’ genomes are decoded. Yet, critical, and fundamental questions regarding its regulation and the function of its output remain unanswered. For example, circRNA being a ubiquitous product of alternative splicing was only discovered in 2012, and its regulation and function remains enigmatic. circRNAs’ discovery revealed a larger critical knowledge gap in the field for “what, how and why” genes are alternatively spliced. What RNA splice variants are expressed, how splicing is regulated, and which spliced RNAs have essential functions? Answering these questions is critical for predicting which of myriad genetic variants cause disease and why they do so. Answers will also enable a new generation of digital nucleic acid biomarkers and diagnostics for disease, drug targets for correcting dysregulated splicing and identification of pathogenic protein- or non-coding products (respectively) as well as fundamental basic scientific insight into evolution and function of eukaryotic genomes.. Despite the great promise for discovering how splicing is regulated in massive single cell RNAseq experiments, the field is still lacking unbiased precise methods to address statistical and computational challenges of splicing analysis in scRNA-Seq. State-of-the-art, reproducible, statistical algorithms to achieve precise splice variant calls, detecting how they are regulated in cell types and subcellularly lag far behind the rate at which single cell RNA- seq (scRNA-seq) data is generated, limiting ML/AI readiness. Here, we will open the possibility of analyzing novel RNA regulatory biology through ML/AI-ready software and processed data to a huge community of biomedical researchers enabling new basic and translational discoveries.

项目摘要/摘要来自家长资助：细胞和生物体，从简单到复杂，都具有相同的特征基因 DNA 序列组织成基因多细胞真核生物将基因转录并加工成 RNA。同种型通过称为选择性剪接的过程产生，并且是细胞类型的。它是高等生物基因组解码的基础。例如，有关其监管及其输出功能的基本问题仍未得到解答。 circRNA是一种普遍存在的选择性剪接产物，直到2012年才被发现，其调控和调控 circRNA 的功能仍然是个谜。如何和为什么”基因被选择性剪接，哪些RNA剪接变体被表达，剪接是如何进行的。哪些剪接RNA具有必要的功能？回答这些问题至关重要？预测众多基因变异中的哪一种会导致疾病以及它们为何会导致疾病，也将带来新的答案。生成数字核酸生物标志物和疾病诊断、校正药物靶点剪接失调和致病蛋白或非编码产物（分别）的识别以及尽管伟大，但对真核基因组进化和功能的基本科学见解。尽管有望在大规模单细胞 RNAseq 实验中发现剪接的调控方式，但该领域仍处于研究阶段缺乏公正的精确方法来解决剪接分析的统计和计算挑战 scRNA-Seq。最先进的、可重复的统计算法，以实现精确的剪接变异调用，检测它们在细胞类型中的调节方式，并且亚细胞的调节速度远远落后于单细胞 RNA- seq (scRNA-seq) 数据已生成，限制了 ML/AI 准备情况在这里，我们将开启分析的可能性。通过 ML/AI 就绪软件和处理数据向庞大的社区提供新颖的 RNA 调控生物学生物医学研究人员实现新的基础和转化发现。