Lagrangian computational modeling for biomedical data science

生物医学数据科学的拉格朗日计算模型

基本信息

批准号：
10063532
负责人：
Gustavo Kunde Rohde
金额：
$ 36.02万
依托单位：
UNIVERSITY OF VIRGINIA
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-03-01 至 2022-11-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/10063532
关键词：
3-Dimensional Accountability Address Algorithmic Analysis Area Biological Biological Models Biology Biophysics Brain Cancer Detection Cartilage Cell model Cells Classification Collaborations Communication Communities Computer Models Computer software Data Data Analyses Data Reporting Data Science Data Scientist Data Set Development Disease Drug Screening Engineering Flow Cytometry Fluorescence Gene Expression Generations Goals Heart Image Knee Laboratories Learning Letters Libraries Link Machine Learning Magnetic Resonance Magnetic Resonance Imaging Malignant Neoplasms Mass Spectrum Analysis Mathematics Measurement Medical Imaging Methodology Modeling Molecular Morphology Optics Organ Performance Plant Roots Population Pythons Research Scientist Signal Transduction System Techniques Technology Training Universities Virginia Visualization absorption algorithm development artificial neural network base biomedical data science biophysical properties brain morphology cellular imaging clinical application clinical practice convolutional neural network cost data space deep learning deep neural network effectiveness testing electric impedance experimental study graphical user interface gray matter heart imaging image reconstruction learning strategy mathematical algorithm mathematical model mathematical theory microscopic imaging models and simulation neural network patient stratification patient subsets predictive modeling radiological imaging technology research and development tool voltage

3-Dimensional Accountability Address Algorithmic Analysis Area Biological Biological Models Biology Biophysics Brain Cancer Detection Cartilage Cell model Cells Classification Collaborations Communication Communities Computer Models Computer software Data Data Analyses Data Reporting Data Science Data Scientist Data Set Development Disease Drug Screening Engineering Flow Cytometry Fluorescence Gene Expression Generations Goals Heart Image Knee Laboratories Learning Letters Libraries Link Machine Learning Magnetic Resonance Magnetic Resonance Imaging Malignant Neoplasms Mass Spectrum Analysis Mathematics Measurement Medical Imaging Methodology Modeling Molecular Morphology Optics Organ Performance Plant Roots Population Pythons Research Scientist Signal Transduction System Techniques Technology Training Universities Virginia Visualization absorption algorithm development artificial neural network base biomedical data science biophysical properties brain morphology cellular imaging clinical application clinical practice convolutional neural network cost data space deep learning deep neural network effectiveness testing electric impedance experimental study graphical user interface gray matter heart imaging image reconstruction learning strategy mathematical algorithm mathematical model mathematical theory microscopic imaging models and simulation neural network patient stratification patient subsets predictive modeling radiological imaging technology research and development tool voltage

展开

项目摘要

The goal of the project is to develop a new mathematical and computational modeling framework for from biomedical data extracted from biomedical experiments such as voltages, spectra (e.g. mass, magnetic resonance, impedance, optical absorption, …), microscopy or radiology images, gene expression, and many others. Scientists who are looking to understand relationships between different molecular and cellular measurements are often faced with questions involving deciphering differences between different cell or organ measurements. Current approaches (e.g. feature engineering and classification, end-to-end neural networks) are often viewed as “black boxes,” given their lack of connection to any biological mechanistic effects. The approach we propose builds from the “ground up” an entirely new modeling framework build based on recently developed invertible transformation. As such, it allows for any machine learning model to be represented in original data space, allowing for not only increased accuracy in prediction, but also direct visualization and interpretation. Preliminary data including drug screening, modeling morphological changes in cancer, cardiac image reconstruction, modeling subcellular organization, and others are discussed.

该项目的目的是开发新的数学和计算从生物医学提取的生物医学数据的建模框架诸如电压，光谱之类的实验（例如质量，磁共振，，阻抗，光学滥用，…），显微镜或放射学图像，基因表达，还有许多其他。希望了解的科学家不同分子和细胞测量之间的关系通常是面对涉及不同单元或不同细胞之间差异的问题器官测量。当前方法（例如功能工程和分类，端到端神经网络）通常被视为“黑匣子”，鉴于他们缺乏与任何生物机械作用的联系。方法我们提出从“扎根”一个全新的建模框架中提出的构建基于最近开发的可逆转换的构建。因此，它允许任何在原始数据空间中表示的机器学习模型，允许不仅提高了预测准确性，还可以直接可视化和解释。初步数据，包括药物筛查，建模形态学癌症的变化，心脏图像重建，对亚细胞的建模组织和其他人进行了讨论。