Interpretable graphical models for large multi-modal COPD data (R01HL159805)

大型多模态 COPD 数据的可解释图形模型 (R01HL159805)

基本信息

批准号：
10705824
负责人：
PANAGIOTIS V BENOS
金额：
$ 47.25万
依托单位：
UNIVERSITY OF FLORIDA
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：
2021-07-25 至 2025-06-30
项目状态：
未结题

来源：
https://reporter.nih.gov/project-details/10705824
关键词：
Address Affect Algorithms Area Biological Markers Cancer Patient Cause of Death Chronic Obstructive Pulmonary Disease Chronic lung disease Classification Clinical Clinical Data Combined Modality Therapy Complex Computer software Data Data Analyses Data Collection Data Set Diagnostic Procedure Disease Disease Progression Evaluation Explosion Face Genetic Genomics Grant Graph Health Care Costs Hospitals Image Internet Joints Knowledge Learning Letters Libraries Lung nodule Machine Learning Malignant Neoplasms Malignant neoplasm of lung Medical Medicine Methodology Methods Modality Modeling Outcome Pathogenesis Patients Pneumonia Probability Process Production Property Pythons Research Research Personnel Risk Factors Sampling Series System Theoretical model Time Training Validation X-Ray Computed Tomography biomarker selection clinical development clinically relevant cohort complex data data streams deep learning disability diverse data flexibility graph learning high dimensionality low dose computed tomography machine learning method microbiome modifiable risk mortality multimodal data multimodality novel personalized medicine precision medicine predictive modeling programs radiological imaging random forest screening success theories tool web portal web server

项目摘要

INTERPRETABLE GRAPHICAL MODELS FOR LARGE MULTI-MODAL COPD DATA ABSTRACT One of the most important tasks in today’s era of precision medicine is to understand the mechanisms and the factors affecting the development of clinical outcomes. Another important task is to develop interpretable, predictive models for outcomes. In the last years, many machine learning methods have dominated the task of predictive modeling, including deep learning, random forests and others. They are fueled by the unprecedent volume of data that have been generated in some research areas. However, the interpretability of these methods is not straight forward and their accuracy decreases when only small to medium size training datasets are available. Furthermore, their predictive models do not uncover the complex web of interactions between other variables in the dataset, which is essential for fully understanding disease mechanisms. Also, most such methods are not well suited to accommodate mixed data types (e.g., continuous, discrete) in the same dataset. Probabilistic graphical models (PGMs) offer a promising alternative to classical machine learning methods, because they are flexible and versatile. They can identify both the direct (causal) relations between variables, pointing to disease mechanisms, and build predictive models over diverse data, with good results even with smaller training datasets. They have been used for classification, biomarker selection, identification of modifiable risk factors of an outcome, or for mechanistic studies of perturbations of disease networks. In the previous years we extended the PGM theoretical framework to the analysis of mixed continuous and discrete variables, with or without unmeasured confounders; and we can now evaluate and incorporate prior information in mixed data graph learning. We successfully applied those methods to diverse clinically important problems, including malignancy prediction of undetermined lung nodules, identification of microbiome and other factors affecting pneumonia, selection of SNP biomarkers for combination treatment of cancer patients. Our objective is to develop novel interpretable methods for analysis of any-type data and use them to address clinically relevant questions in COPD, an important chronic lung disease. Method evaluation will be done on synthetic and real data, including parallel datasets with genomic, genetic, imaging and clinical COPD data. Our central aim is to identify factors of disease mechanisms of progression using different modalities of patient data. The deliverables will be (1) new PGM approaches for integrative analysis of any-type data; (2) a new, fully documented software package (in R, Python) that can be incorporated in other pipelines; (3) a new web portal to disseminate our methodologies to non-computer-savvy COPD researchers; (4) results on the pathogenesis and predictive features of chronic obstructive pulmonary disease (COPD). This cross-disciplinary team project is expected to have a positive impact beyond the above deliverables, since the generality of our approaches makes them suitable for studying any disease; and they can be easily integrated into personalized medicine strategies when high-throughput data collection will become a routine diagnostic procedure in all hospitals.

大型多模态 COPD 数据的可解释图形模型抽象的当今精准医学时代最重要的任务之一是了解其机制和作用影响临床结果发展的因素另一个重要任务是开发可解释的、在过去的几年里，许多机器学习方法主导了结果的预测模型。预测模型，包括深度学习、随机森林等，都是由前所未有的技术推动的。一些研究领域产生的数据量很大，但是这些方法的可解释性。并不简单，当仅使用中小型训练数据集时，其准确性会降低此外，他们的预测模型并没有揭示其他人之间复杂的相互作用网络。数据集中的变量，这对于充分理解疾病机制至关重要。不太适合在同一数据集中容纳混合数据类型（例如连续、离散）。概率图模型（PGM）为经典机器学习方法提供了一种有前景的替代方案，因为它们灵活且用途广泛，可以识别变量之间的直接（因果）关系，指出疾病机制，并根据不同的数据建立预测模型，即使使用它们已用于分类、生物标志物选择、可修改的识别。结果的危险因素，或用于前几年疾病网络扰动的机制研究。我们将 PGM 理论框架扩展到混合连续变量和离散变量的分析，其中或没有未测量的混杂因素；我们现在可以评估混合数据中的先验信息；我们成功地将这些方法应用于各种临床重要问题，包括未确定的肺结节的恶性预测、微生物组的鉴定和其他影响因素肺炎，SNP生物标志物的选择用于癌症患者的联合治疗。我们的目标是开发新颖的可解释方法来分析任何类型的数据，并用它们来解决慢性阻塞性肺病（一种重要的慢性肺部疾病）的临床相关问题将进行方法评估。合成数据和真实数据，包括基因组、遗传、成像和临床慢性阻塞性肺病数据的并行数据集。中心目标是利用不同方式的患者数据来确定疾病进展机制的因素。可交付成果将是 (1) 用于对任何类型数据进行综合分析的新 PGM 方法；(2) 一种新的、全面的方法；（3）新的门户网站向不懂计算机的慢性阻塞性肺病研究人员传播我们的方法；(4) 发病机制的结果；这个跨学科团队项目。由于我们方法的普遍性，预计将产生超出上述可交付成果的积极影响使它们适合研究任何疾病，并且可以轻松集成到个性化医疗中；当高通量数据收集将成为所有医院的常规诊断程序时的策略。

项目成果

期刊论文数量（9）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Integrated unbiased multiomics defines disease-independent placental clusters in common obstetrical syndromes.

综合无偏多组学定义了常见产科综合征中与疾病无关的胎盘簇。

DOI：
发表时间：
2023-09-08
期刊：
影响因子：
9.3
作者：
Barak, Oren;Lovelace, Tyler;Piekos, Samantha;Chu, Tianjiao;Cao, Zhishen;Sadovsky, Elena;Mouillet, Jean;Ouyang, Yingshi;Parks, W Tony;Hood, Leroy;Price, Nathan D;Benos, Panayiotis V;Sadovsky, Yoel
通讯作者：
Sadovsky, Yoel

Early events marking lung fibroblast transition to profibrotic state in idiopathic pulmonary fibrosis.

特发性肺纤维化中标志着肺成纤维细胞转变为促纤维化状态的早期事件。

DOI：
发表时间：
2023-04-21
期刊：
影响因子：
5.8
作者：
Jia, Minxue;Rosas, Lorena;Kapetanaki, Maria G;Tabib, Tracy;Sebrat, John;Cruz, Tamara;Bondonese, Anna;Mora, Ana L;Lafyatis, Robert;Rojas, Mauricio;Benos, Panayiotis V
通讯作者：
Benos, Panayiotis V

LEF1 isoforms regulate cellular senescence and aging.

LEF1 同工型调节细胞衰老和老化。

DOI：
发表时间：
2023-07-21
期刊：
影响因子：
0
作者：
Jia, Minxue;Sayed, Khaled;Kapetanaki, Maria G;Dion, William;Rosas, Lorena;Irfan, Saad;Valenzi, Eleanor;Mora, Ana L;Lafyatis, Robert A;Rojas, Mauricio;Zhu, Bokai;Benos, Panayiotis V
通讯作者：
Benos, Panayiotis V

Mechanisms of stochastic onset and termination of atrial fibrillation episodes: Insights using a cellular automaton model

房颤发作随机发作和终止的机制：使用细胞自动机模型的见解