Background: Inference of gene regulatory networks from transcriptomic data has been a wide research area in recent years. Proposed methods are mainly based on the use of graphical Gaussian models for observational wild-type data and provide undirected graphs that are not able to accurately highlight the causal relationships among genes. In the present work, we seek to improve estimation of causal effects among genes by jointly modeling observational transcriptomic data with intervention data obtained by performing knock-outs or knock-downs on a subset of genes. By examining the impact of such expression perturbations on other genes, a more accurate reflection of regulatory relationships may be obtained than through the use of wild-type data alone. Results: Using the framework of Gaussian Bayesian networks, we propose a Markov chain Monte Carlo algorithm with a Mallows model and an analytical likelihood maximization to sample from the posterior distribution of causal node orderings, and in turn, to estimate causal effects. The main advantage of the proposed algorithm over previously proposed methods is that it has the flexibility to accommodate any kind of intervention design, including partial or multiple knock-out experiments. Methods were compared on simulated data as well as data from the DREAM 2007 challenge. Conclusions: The simulation study confirmed the impossibility of estimating causal orderings of genes with observation data only. The proposed algorithm was found, in most cases, to perform better than the previously proposed methods in terms of accuracy for the estimation of causal effects. In addition, multiple knock-outs proved to bring valuable additional information compared to single knock-outs. The choice of optimal intervention design therefore appears to be a crucial aspect for causal inference and an interesting challenge for future research.
Relaxing Faithfulness with Intervention-Only Causal Discovery
Thayer School of Engineering Dartmouth College(达特茅斯学院塞耶工程学院);Broad Institute of MIT and Harvard(麻省理工学院和哈佛大学布罗德研究所);Massachusetts Institute of Technology(麻省理工学院)
Deciphering interventional dynamical causality from non-intervention complex systems
Research Institute of Intelligent Complex Systems & CISOR, Fudan University(智能复杂系统研究所及CISOR,复旦大学);International Research Center for Neurointelligence, The University of Tokyo Institutes for Advanced Study, The University of Tokyo(神经智能国际研究中心,东京大学先进研究所,东京大学);School of Pharmacy, Shanghai University of Traditional Chinese Medicine(上海中医药大学药学院);Institute of AI and Robotics, College of Intelligent Robotics and Advanced Manufacturing, Fudan University(人工智能与机器人研究所,智能机器人与先进制造学院,复旦大学);Frontiers Science Center for Deep Ocean Multispheres and Earth System, Key Laboratory of Marine Chemistry Theory and Technology, Ministry of Education, Ocean University of China(深海多球体与地球系统前沿科学中心,海洋化学理论与技术重点实验室,教育部,中国海洋大学);School of Mathematical Sciences and School of AI, Shanghai Jiao Tong University(数学科学学院和人工智能学院,上海交通大学);Key Laboratory of Systems Health Science of Zhejiang Province, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences(浙江省系统健康科学重点实验室,杭州高级研究所,中国科学院大学,中国科学院)
Causal Data Fusion for Panel Data without a Pre-Intervention Period
Faculty of Computing and Data Sciences, Boston University(波士顿大学计算与数据科学学院);Division of Infectious Diseases, Boston Children’s Hospital & Harvard Medical School(波士顿儿童医院感染病科及哈佛医学院);Department of Mathematics and Statistics, Boston University(波士顿大学数学与统计系)
Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery
Warsaw University(华沙大学);IDEAS NCBR;Jagiellonian University(雅盖隆大学);ETH Zurich(苏黎世联邦理工学院);Helmholtz, TU Munich(慕尼黑工业大学亥姆霍兹中心);Institute of Mathematics, Polish Academy of Sciences(波兰科学院数学研究所)
McGill University(麦吉尔大学);ETH Zürich(苏黎世联邦理工学院);GlaxoSmithKline(葛兰素史克);TU Munich(慕尼黑工业大学);Helmholtz AI(亥姆霍兹人工智能研究所);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
Learning Neural Causal Models with Active Interventions
ETH Zurich(苏黎世联邦理工学院);Mila(米拉人工智能研究所);Universite de Montréal(蒙特利尔大学);GlaxoSmithKline(葛兰素史克);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);Google Research(谷歌研究院);KTH Stockholm(瑞典皇家理工学院);DeepMind(深度思维)
Scalable Contrastive Causal Discovery under Unknown Soft Interventions
Department of Systems Biology, Columbia University Irving Institute for Cancer Dynamics, Columbia University(系统生物学系,哥伦比亚大学伊万尼癌症动力学研究所,哥伦比亚大学);Irving Institute for Cancer Dynamics, Columbia University(伊万尼癌症动力学研究所,哥伦比亚大学);Department of Computer Science, Columbia University(计算机科学系,哥伦比亚大学);Department of Biomedical Engineering, Columbia University(生物医学工程系,哥伦比亚大学);Data Science Institute, Columbia University(数据科学研究所,哥伦比亚大学)
Instituto de Ciencias Matemáticas, CSIC(西班牙科学研究所数学科学研究所);Departamento de Matemáticas, Universidad Autónoma de Madrid(马德里自治大学数学系);Division of Biostatistics, University of California, Berkeley(加州大学伯克利分校生物统计学部)
Can Large Language Models Help Experimental Design for Causal Discovery?
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));MBZUAI(穆罕默德·本·扎耶德人工智能大学);Hong Kong Baptist University(香港浸会大学);The University of Sydney(悉尼大学);Carnegie Mellon University(卡内基梅隆大学)