Big Data Training for Cancer Research

癌症研究大数据培训

基本信息

批准号：
10880158
负责人：
MIN ZHANG
金额：
$ 22.43万
依托单位：
UNIVERSITY OF CALIFORNIA-IRVINE
依托单位国家：
美国
项目类别：
财政年份：
2023
资助国家：
美国
起止时间：
2023-09-01 至 2024-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10880158
关键词：
Acceleration Address Basic Science Big Data Big Data to Knowledge Bioinformatics Biological Biology Cancer Biology Cancer Center Case Study Cause of Death Clinical Clinical Cancer Center Clinical Oncology Clinical Research Collaborations Collection Communication Communities Complement Complex Computers Computing Methodologies Country Data Data Analyses Data Set Development Disease Educational Curriculum Funding Genomics Goals Image Indiana Infrastructure Instruction Intervention Knowledge Malignant Neoplasms Medical Modification Molecular NCI Center for Cancer Research NCI-Designated Cancer Center Needs Assessment Oncology Participant Positioning Attribute Proteomics Public Domains Published Comment Research Research Personnel Science Scientist Source Statistical Methods Surveys Survival Analysis Technical Expertise The Cancer Genome Atlas Training Training Programs Translating Translations United States National Institutes of Health Universities Visualization Work anticancer research bench to bedside big-data science biomarker identification cancer type clinical practice computer science computerized tools data resource data to knowledge data tools density design disorder risk education resources experience high throughput technology improved interoperability knowledge translation large datasets large scale data metabolomics multidisciplinary neoplasm resource novel therapeutics precision oncology programs risk prediction skills statistics success tool transcriptomics virtual machine web site

项目摘要

PROJECT SUMMARY The increasing volume of big data in cancer research has the potential to dramatically accelerate the translation of knowledge from bench to bedside. Unfortunately, most cancer researchers are unable to: (i) utilize the valuable big data that is readily available in the public domain, and (ii) extract knowledge from cancer big data through communicating with computer scientists, statisticians and bioinformaticians. Traditionally, cancer researchers are trained in the biologically related sciences that are relevant to the manifestation of the disease. This knowledge is, and remains, critical for understanding the biological and molecular mechanisms that result in the disease and that can be targeted for clinical intervention. However, historically, cancer researchers have not been trained to handle large volumes of data. There was no need; there were not many approaches that were generating large scale data. Yet, with the advent of high-throughput approaches, in particular those related to genomics, proteomics and metabolomics, a significant gap in the training of cancer researchers has become apparent – the need for skills in computer science and statistics to analyze big data and interpret results from the analyses. In the absence of quantitative training for cancer researchers, a bottleneck will remain in the translation of the large body of cancer big data to clinical practice. This need was confirmed in a needs assessment of researchers from 95 Cancer Centers sent out last year (including all 69 NCI-Designated Cancer Centers). To address the need for a big data training course, the investigators propose to build on a previously NIH-funded big data training course, to develop and deliver a new training course tailored to cancer researchers across the country. In a partnership between the Purdue University Center for Cancer Research (PCCR), the Indiana University Simon Cancer Center (IUSCC), and a group of traditionally trained biostatisticians, the team is in a unique position to leverage basic and clinical cancer centers (the only two NCI-Designated Cancer Centers in the State), to work together on this multi-disciplinary training program. In contrast to the previous successful big data training course designed for general biomedical researchers who were novices in big data science, this new course will target cancer researchers with the knowledge of big data value but lacking the quantitative skills necessary to work with it. Based on case studies from both PCCR and IUSCC researchers, the goal of the course is to help participants develop skills for managing, visualizing, analyzing, and integrating various types of cancer big data that are publicly available. This is increasingly important as more and more precision oncology- focused treatments are coming on line. With this customized big data training, cancer researchers can realize the transformative potential of big data by translating it from bench to bedside.

项目概要癌症研究中不断增加的大数据量有可能大大加速转化不幸的是，大多数癌症研究人员无法：（i）利用有价值的知识。公共领域容易获得的大数据，以及（ii）通过以下方式从癌症大数据中提取知识：传统上，与计算机科学家、统计学家和生物信息学家进行交流。接受过与疾病表现相关的生物学相关科学方面的培训。知识对于理解导致疾病发生的生物和分子机制现在仍然至关重要。然而，从历史上看，癌症研究人员还没有这样做过。没有必要接受过处理大量数据的培训；没有太多方法。然而，随着高通量方法的出现，特别是与高通量方法相关的方法。基因组学、蛋白质组学和代谢组学，癌症研究人员培训方面的巨大差距已成为显而易见——需要计算机科学和统计学技能来分析大数据并解释结果由于缺乏对癌症研究人员的定量培训，分析仍将存在瓶颈。将大量癌症大数据转化为临床实践的需求在需求中得到了证实。对去年派出的 95 个癌症中心（包括所有 69 个 NCI 指定癌症中心）的研究人员进行评估中心）。为了满足大数据培训课程的需求，研究人员建议以先前由 NIH 资助的课程为基础大数据培训课程，为整个癌症研究人员开发和提供新的培训课程普渡大学癌症研究中心 (PCCR) 与印第安纳州合作。大学西蒙癌症中心 (IUSCC) 和一群经过传统培训的生物统计学家，该团队位于拥有利用基础和临床癌症中心（美国仅有的两个 NCI 指定癌症中心）的独特地位与之前成功的大型培训计划不同的是，共同开展这一多学科培训计划。专为大数据科学新手的一般生物医学研究人员设计的数据培训课程，这个新的课程将针对具有大数据价值知识但缺乏定量技能的癌症研究人员根据 PCCR 和 IUSCC 研究人员的案例研究，该目标是必要的。课程旨在帮助培养管理、可视化、分析和整合各种类型的技能随着肿瘤学变得越来越精确，公开的癌症大数据变得越来越重要。通过这种定制的大数据培训，癌症研究人员可以实现针对性的治疗。通过将大数据从实验室转化为临床，发挥大数据的变革潜力。