BAYESIAN DIFFERENTIAL CAUSAL DIRECTED ACYCLIC GRAPHS FOR OBSERVATIONAL ZERO-INFLATED COUNTS WITH AN APPLICATION TO TWO-SAMPLE SINGLE-CELL DATA.

IF 1.4 4区 数学 Q2 STATISTICS & PROBABILITY
Annals of Applied Statistics Pub Date : 2025-09-01 Epub Date: 2025-08-28 DOI:10.1214/25-aoas2042
Junsouk Choi, Robert S Chapkin, Yang Ni
{"title":"BAYESIAN DIFFERENTIAL CAUSAL DIRECTED ACYCLIC GRAPHS FOR OBSERVATIONAL ZERO-INFLATED COUNTS WITH AN APPLICATION TO TWO-SAMPLE SINGLE-CELL DATA.","authors":"Junsouk Choi, Robert S Chapkin, Yang Ni","doi":"10.1214/25-aoas2042","DOIUrl":null,"url":null,"abstract":"<p><p>Observational zero-inflated count data arise in a wide range of areas such as genomics. One of the common research questions is to identify causal relationships by learning the structure of a sparse directed acyclic graph (DAG). While structure learning of DAGs has been an active research area, existing methods do not adequately account for excessive zeros and therefore are not suitable for modeling zero-inflated count data. Moreover, it is often interesting to study differences in the causal networks for data collected from two experimental groups (control vs treatment). To explicitly account for zero-inflation and identify differential causal networks, we propose a novel Bayesian differential zero-inflated negative binomial DAG (DAG0) model. We prove that the causal relationships under the proposed DAG0 are fully identifiable from purely observational, cross-sectional data, using a general proof technique that is applicable beyond the proposed model. Bayesian inference based on parallel-tempered Markov chain Monte Carlo is developed to efficiently explore the multi-modal posterior landscape. We demonstrate the utility of the proposed DAG0 by comparing it with state-of-the-art alternative methods through extensive simulations. An application in a single-cell RNA-sequencing dataset generated under two experimental groups finds some interesting results that appear to be consistent with existing knowledge. A user-friendly R package that implements DAG0 is available at https://github.com/junsoukchoi/BayesDAG0.git.</p>","PeriodicalId":50772,"journal":{"name":"Annals of Applied Statistics","volume":"19 3","pages":"1908-1930"},"PeriodicalIF":1.4000,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12395422/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Applied Statistics","FirstCategoryId":"100","ListUrlMain":"https://doi.org/10.1214/25-aoas2042","RegionNum":4,"RegionCategory":"数学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/8/28 0:00:00","PubModel":"Epub","JCR":"Q2","JCRName":"STATISTICS & PROBABILITY","Score":null,"Total":0}
引用次数: 0

Abstract

Observational zero-inflated count data arise in a wide range of areas such as genomics. One of the common research questions is to identify causal relationships by learning the structure of a sparse directed acyclic graph (DAG). While structure learning of DAGs has been an active research area, existing methods do not adequately account for excessive zeros and therefore are not suitable for modeling zero-inflated count data. Moreover, it is often interesting to study differences in the causal networks for data collected from two experimental groups (control vs treatment). To explicitly account for zero-inflation and identify differential causal networks, we propose a novel Bayesian differential zero-inflated negative binomial DAG (DAG0) model. We prove that the causal relationships under the proposed DAG0 are fully identifiable from purely observational, cross-sectional data, using a general proof technique that is applicable beyond the proposed model. Bayesian inference based on parallel-tempered Markov chain Monte Carlo is developed to efficiently explore the multi-modal posterior landscape. We demonstrate the utility of the proposed DAG0 by comparing it with state-of-the-art alternative methods through extensive simulations. An application in a single-cell RNA-sequencing dataset generated under two experimental groups finds some interesting results that appear to be consistent with existing knowledge. A user-friendly R package that implements DAG0 is available at https://github.com/junsoukchoi/BayesDAG0.git.

观测零膨胀计数的贝叶斯微分因果有向无环图及其在双样本单细胞数据中的应用。
观测零膨胀计数数据出现在广泛的领域,如基因组学。一个常见的研究问题是通过学习稀疏有向无环图(DAG)的结构来识别因果关系。虽然dag的结构学习一直是一个活跃的研究领域,但现有的方法不能充分考虑过多的零,因此不适合建模零膨胀计数数据。此外,研究从两个实验组(对照组与实验组)收集的数据的因果网络差异通常是有趣的。为了明确地解释零膨胀和识别差分因果网络,我们提出了一个新的贝叶斯微分零膨胀负二项DAG (DAG0)模型。我们使用一种适用于所提出模型之外的一般证明技术,证明了所提出的DAG0下的因果关系完全可以从纯粹的观察性横截面数据中识别出来。为了有效地探索多模态后验景观,提出了基于并行调节马尔可夫链蒙特卡罗的贝叶斯推理方法。我们通过广泛的模拟将所提出的DAG0与最先进的替代方法进行比较,从而证明了它的实用性。在两个实验组生成的单细胞rna测序数据集中的应用发现了一些有趣的结果,这些结果似乎与现有知识一致。一个实现DAG0的用户友好的R包可以在https://github.com/junsoukchoi/BayesDAG0.git上获得。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Annals of Applied Statistics
Annals of Applied Statistics 社会科学-统计学与概率论
CiteScore
3.10
自引率
5.60%
发文量
131
审稿时长
6-12 weeks
期刊介绍: Statistical research spans an enormous range from direct subject-matter collaborations to pure mathematical theory. The Annals of Applied Statistics, the newest journal from the IMS, is aimed at papers in the applied half of this range. Published quarterly in both print and electronic form, our goal is to provide a timely and unified forum for all areas of applied statistics.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信