{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:43Z","timestamp":1766068123771,"version":"3.32.0"},"reference-count":63,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>A Directed Acyclic Graph (DAG) offers an easy approach to define causal structures among gathered nodes: causal linkages are represented by arrows between the variables, leading from cause to effect. Recently, industry and academics have paid close attention to DAG structure learning from observable data, and many techniques have been put out to address the problem. We provide a two-step approach, named <jats:monospace specific-use=\"no-wrap\">SEMdag()<\/jats:monospace>, that can be used to quickly learn high-dimensional linear SEMs. It is included in the R package <jats:bold>SEMgraph<\/jats:bold> and employs a two-stage order-based search using previous knowledge (Knowledge-based, KB) or data-driven method (Bottom-up, BU), under the premise that a linear SEM with equal variance error terms is assumed. We evaluated our framework\u2019s for finding plausible DAGs against six well-known causal discovery techniques (ARGES, GES, PC, LiNGAM, CAM, NOTEARS). We conducted a series of experiments using observed expression (or RNA-seq) data, taking into account a pair of training and testing datasets for four distinct diseases: Amyotrophic Lateral Sclerosis (ALS), Breast cancer (BRCA), Coronavirus disease (COVID-19) and ST-elevation myocardial infarction (STEMI). The results show that the <jats:monospace specific-use=\"no-wrap\">SEMdag()<\/jats:monospace> procedure can recover a graph structure with good disease prediction performance evaluated by a conventional supervised learning algorithm (RF): in the scenario where the initial graph is sparse, the BU approach may be a better choice than the KB one; in the case where the graph is denser, both BU an KB report high performance, with highest score for KB approach based on topological layers. Besides its superior disease predictive performance compared to previous research, <jats:monospace specific-use=\"no-wrap\">SEMdag()<\/jats:monospace> offers the user the flexibility to define distinct structure learning algorithms and can handle high dimensional issues with less computing load. <jats:monospace specific-use=\"no-wrap\">SEMdag()<\/jats:monospace> function is implemented in the R package <jats:bold>SEMgraph<\/jats:bold>, easily available at <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/CRAN.R-project.org\/package=SEMgraph\" xlink:type=\"simple\">https:\/\/CRAN.R-project.org\/package=SEMgraph<\/jats:ext-link>.<\/jats:p>","DOI":"10.1371\/journal.pone.0317283","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T19:22:22Z","timestamp":1736364142000},"page":"e0317283","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["SEMdag: Fast learning of Directed Acyclic Graphs via node or layer ordering"],"prefix":"10.1371","volume":"20","author":[{"given":"Mario","family":"Grassi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6384-2561","authenticated-orcid":true,"given":"Barbara","family":"Tarantino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,1,8]]},"reference":[{"key":"pone.0317283.ref001","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1126\/science.1105809","article-title":"Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data","volume":"308","author":"K Sachs","year":"2005","journal-title":"Science (New York, NY)"},{"key":"pone.0317283.ref002","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1057\/jors.2011.7","article-title":"A Bayesian network structure for operational risk modelling in structured finance operations","volume":"63","author":"A Sanford","year":"2012","journal-title":"Journal of the Operational Research Society"},{"issue":"3","key":"pone.0317283.ref003","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1111\/1468-0262.00037","article-title":"Nonparametric Estimation of Triangular Simultaneous Equations Models","volume":"67","author":"W Newey","year":"1999","journal-title":"Econometrica"},{"key":"pone.0317283.ref004","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1146\/annurev-statistics-060116-053803","article-title":"Structure Learning in Graphical Modeling","volume":"4","author":"Mathias Drton","year":"2017","journal-title":"Annual Review of Statistics and Its Application"},{"key":"pone.0317283.ref005","volume-title":"Causation, Prediction, and Search","author":"P Spirtes","year":"2000","edition":"2"},{"key":"pone.0317283.ref006","first-page":"507","article-title":"Optimal Structure Identification With Greedy Search","volume":"3","author":"DM Chickering","year":"2003","journal-title":"J Mach Learn Res"},{"issue":"1","key":"pone.0317283.ref007","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1093\/biomet\/asy057","article-title":"Constrained likelihood for reconstructing a directed acyclic Gaussian graph","volume":"106","author":"Y Yuan","year":"2018","journal-title":"Biometrika"},{"key":"pone.0317283.ref008","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10994-006-6889-7","article-title":"The Max-Min Hill-Climbing Bayesian Network Structure Learning Algorithm","volume":"65","author":"I Tsamardinos","year":"2006","journal-title":"Machine Learning"},{"issue":"6A","key":"pone.0317283.ref009","doi-asserted-by":"crossref","first-page":"3151","DOI":"10.1214\/17-AOS1654","article-title":"High-dimensional consistency in score-based and hybrid structure learning","volume":"46","author":"P Nandy","year":"2018","journal-title":"Annals of Statistics"},{"issue":"4","key":"pone.0317283.ref010","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1093\/biomet\/asz049","article-title":"On Causal Discovery with an Equal-Variance Assumption","volume":"106","author":"W Chen","year":"2019","journal-title":"Biometrika"},{"issue":"72","key":"pone.0317283.ref011","first-page":"2003","article-title":"A Linear Non-Gaussian Acyclic Model for Causal Discovery","volume":"7","author":"S Shimizu","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0317283.ref012","first-page":"597","article-title":"Identifying Cause and Effect on Discrete Data using Additive Noise Models","volume":"9","author":"J Peters","year":"2010","journal-title":"Journal of Machine Learning Research\u2014Proceedings Track"},{"issue":"6","key":"pone.0317283.ref013","doi-asserted-by":"crossref","first-page":"2526","DOI":"10.1214\/14-AOS1260","article-title":"CAM: Causal Additive Models, high-dimensional order search and penalized regression","volume":"42","author":"P B\u00fchlmann","year":"2014","journal-title":"The Annals of Statistics"},{"issue":"1","key":"pone.0317283.ref014","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1093\/biomet\/ast043","article-title":"Identifiability of Gaussian structural equation models with equal error variances","volume":"101","author":"J Peters","year":"2014","journal-title":"Biometrika"},{"issue":"20","key":"pone.0317283.ref015","doi-asserted-by":"crossref","first-page":"4829","DOI":"10.1093\/bioinformatics\/btac567","article-title":"SEMgraph: an R package for causal network inference of high-throughput data with structural equation models","volume":"38","author":"M Grassi","year":"2022","journal-title":"Bioinformatics"},{"issue":"3","key":"pone.0317283.ref016","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1093\/biomet\/asq038","article-title":"Penalized Likelihood Methods for Estimation of Sparse High-Dimensional Directed Acyclic Graphs","volume":"97","author":"A Shojaie","year":"2010","journal-title":"Biometrika"},{"key":"pone.0317283.ref017","doi-asserted-by":"crossref","first-page":"65","DOI":"10.2333\/bhmk.41.65","article-title":"Lingam: Non-Gaussian Methods for Estimating Causal Structures","volume":"41","author":"S Shimizu","year":"2014","journal-title":"Behaviormetrika"},{"key":"pone.0317283.ref018","volume-title":"Advances in Neural Information Processing Systems","author":"X Zheng","year":"2018"},{"key":"pone.0317283.ref019","first-page":"333","article-title":"The chain graph Markov property","volume":"17","author":"M Frydenberg","year":"1990","journal-title":"Scandinavian Journal of Statistics"},{"key":"pone.0317283.ref020","article-title":"Equivalence and Synthesis of Causal Models","author":"T Verma","year":"1990","journal-title":"Probabilistic and Causal Inference"},{"key":"pone.0317283.ref021","article-title":"A Characterization of Markov Equivalence Classes for Acyclic Digraphs","volume":"25","author":"S Andersson","year":"2000","journal-title":"Annals of Statistics"},{"key":"pone.0317283.ref022","volume-title":"Adaptive Computation and Machine Learning","author":"J Peters","year":"2017"},{"issue":"22","key":"pone.0317283.ref023","first-page":"613","article-title":"Estimating High-Dimensional Directed Acyclic Graphs with the PC-Algorithm","volume":"8","author":"M Kalisch","year":"2007","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0317283.ref024","unstructured":"Meek C. Causal inference and causal explanation with background knowledge. In: Kaufmann M, editor. Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence; 1995. p. 403\u2013411."},{"issue":"116","key":"pone.0317283.ref025","first-page":"3921","article-title":"Order-Independent Constraint-Based Causal Structure Learning","volume":"15","author":"D Colombo","year":"2014","journal-title":"Journal of Machine Learning Research"},{"issue":"2","key":"pone.0317283.ref026","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"G Schwarz","year":"1978","journal-title":"Annals of Statistics"},{"key":"pone.0317283.ref027","unstructured":"Ghoshal A, Honorio J. Learning linear structural equation models in polynomial time and sample complexity. In: Storkey A, Perez-Cruz F, editors. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics. vol. 84 of Proceedings of Machine Learning Research. PMLR; 2018. p. 1466\u20131475."},{"issue":"1","key":"pone.0317283.ref028","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1007\/s42952-019-00019-7","article-title":"Identifiability of Gaussian linear structural equation models with homogeneous and heterogeneous error variances","volume":"49","author":"G Park","year":"2020","journal-title":"Journal of the Korean Statistical Society"},{"issue":"75","key":"pone.0317283.ref029","first-page":"1","article-title":"Identifiability of Additive Noise Models Using Conditional Variances","volume":"21","author":"G Park","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0317283.ref030","first-page":"11599","volume-title":"Advances in Neural Information Processing Systems","author":"M Gao","year":"2020"},{"issue":"33","key":"pone.0317283.ref031","first-page":"1225","article-title":"DirectLiNGAM: A Direct Method for Learning a Linear Non-Gaussian Structural Equation Model","volume":"12","author":"S Shimizu","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0317283.ref032","unstructured":"Ng I, Ghassami A, Zhang K. On the Role of Sparsity and DAG Constraints for Learning Linear DAGs. In: NIPS\u201920: Proceedings of the 34th International Conference on Neural Information Processing Systems; 2020. p. 17943\u2013\u201317954."},{"key":"pone.0317283.ref033","unstructured":"Yu Y, Chen J, Gao T, Yu M. DAG-GNN: DAG Structure Learning with Graph Neural Networks. In: PMLR, editor. International Conference on Machine Learning; 2019. p. 7154\u20137163. Available from: https:\/\/api.semanticscholar.org\/CorpusID:128358697."},{"key":"pone.0317283.ref034","volume-title":"Advances in Neural Information Processing Systems","author":"K Bello","year":"2022"},{"key":"pone.0317283.ref035","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016"},{"issue":"4","key":"pone.0317283.ref036","doi-asserted-by":"crossref","DOI":"10.1145\/3527154","article-title":"D\u2019ya Like DAGs? A Survey on Structure Learning and Causal Discovery","volume":"55","author":"MJ Vowels","year":"2022","journal-title":"ACM Comput Surv"},{"key":"pone.0317283.ref037","author":"K Zhang","year":"2021","journal-title":"gCastle: A Python Toolbox for Causal Discovery"},{"key":"pone.0317283.ref038","author":"I Ng","year":"2023","journal-title":"Structure Learning with Continuous Optimization: A Sober Look and Beyond"},{"key":"pone.0317283.ref039","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1038\/msb.2009.52","article-title":"Genomic analysis shows a tight link between transcription factor dynamics and regulatory network architecture","volume":"5","author":"R Jothi","year":"2009","journal-title":"Molecular systems biology"},{"key":"pone.0317283.ref040","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1093\/biostatistics\/kxm045","article-title":"Sparse inverse covariance estimation with the graphical LASSO","volume":"9","author":"J Friedman","year":"2008","journal-title":"Biostatistics (Oxford, England)"},{"issue":"1","key":"pone.0317283.ref041","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1214\/15-EJS1031","article-title":"Confidence intervals for high-dimensional inverse covariance estimation","volume":"9","author":"J Jankov\u00e1","year":"2015","journal-title":"Electronic Journal of Statistics"},{"key":"pone.0317283.ref042","unstructured":"Friedman J, Hastie T, Tibshirani R. Graphical Lasso: Estimation of Gaussian Graphical Models; 2019. Available from: https:\/\/CRAN.R-project.org\/package=glasso."},{"key":"pone.0317283.ref043","author":"J Friedman","year":"2023","journal-title":"glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models"},{"issue":"5","key":"pone.0317283.ref044","doi-asserted-by":"crossref","first-page":"e0127376","DOI":"10.1371\/journal.pone.0127376","article-title":"C9ORF72 GGGGCC Expanded Repeats Produce Splicing Dysregulation which Correlates with Disease Severity in Amyotrophic Lateral Sclerosis","volume":"10","author":"J Cooper-Knock","year":"2015","journal-title":"PLoS One"},{"issue":"1A","key":"pone.0317283.ref045","first-page":"A68","volume":"19","author":"K Tomczak","year":"2015","journal-title":"The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge Contemp Oncol (Pozn)"},{"key":"pone.0317283.ref046","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1200\/PO.17.00135","article-title":"Clinical Value of RNA Sequencing\u2013Based Classifiers for Prediction of the Five Conventional Breast Cancer Biomarkers: A Report From the Population-Based Multicenter Sweden Cancerome Analysis Network\u2014Breast Initiative","volume":"2","author":"C Brueffer","year":"2018","journal-title":"JCO Precision Oncology"},{"key":"pone.0317283.ref047","doi-asserted-by":"crossref","DOI":"10.1186\/s13058-023-01677-6","article-title":"Exploring breast tissue microbial composition and the association with breast cancer risk factors","volume":"25","author":"R German","year":"2023","journal-title":"Breast Cancer Research"},{"issue":"1","key":"pone.0317283.ref048","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.cels.2020.10.003","article-title":"Large-Scale Multi-omic Analysis of COVID-19 Severity","volume":"12","author":"KA Overmyer","year":"2021","journal-title":"Cell Systems"},{"key":"pone.0317283.ref049","doi-asserted-by":"crossref","first-page":"101947","DOI":"10.1016\/j.isci.2020.101947","article-title":"Transcriptomic Similarities and Differences in Host Response between SARS-CoV-2 and Other Viral Infections","volume":"24","author":"S Thair","year":"2020","journal-title":"iScience"},{"key":"pone.0317283.ref050","doi-asserted-by":"crossref","DOI":"10.1186\/s13073-015-0149-z","article-title":"Gene expression profiling reveals potential prognostic biomarkers associated with the progression of heart failure","volume":"7","author":"A Maciejak","year":"2015","journal-title":"Genome Medicine"},{"key":"pone.0317283.ref051","doi-asserted-by":"crossref","first-page":"e50054","DOI":"10.1371\/journal.pone.0050054","article-title":"Altered Gene Expression Pattern in Peripheral Blood Mononuclear Cells in Patients with Acute Myocardial Infarction","volume":"7","author":"M Kiliszek","year":"2012","journal-title":"PloS one"},{"key":"pone.0317283.ref052","first-page":"397","volume-title":"limma: Linear Models for Microarray Data","author":"R Gentleman","year":"2005"},{"key":"pone.0317283.ref053","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling The False Discovery Rate\u2014A Practical And Powerful Approach To Multiple Testing","volume":"57","author":"Y Benjamini","year":"1995","journal-title":"J Royal Statist Soc, Series B"},{"key":"pone.0317283.ref054","doi-asserted-by":"crossref","DOI":"10.1214\/20-AOS2021","article-title":"Causal discovery in heavy-tailed models","volume":"49","author":"N Gnecco","year":"2021","journal-title":"The Annals of Statistics"},{"key":"pone.0317283.ref055","first-page":"1695","article-title":"The igraph software package for complex network research","author":"G Csardi","year":"2006","journal-title":"InterJournal"},{"key":"pone.0317283.ref056","author":"R Lebr\u00f3n","year":"2021","journal-title":"gnlearn: Genetic Network Learning"},{"key":"pone.0317283.ref057","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"pone.0317283.ref058","doi-asserted-by":"crossref","first-page":"27522","DOI":"10.1109\/ACCESS.2022.3146312","article-title":"A Survey of Machine Learning Approaches Applied to Gene Expression Analysis for Cancer Prediction","volume":"10","author":"M Khalsan","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0317283.ref059","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1186\/1471-2105-9-439","article-title":"CMA\u2014A comprehensive Bioconductor package for supervised classification with high dimensional data","volume":"9","author":"M Slawski","year":"2008","journal-title":"BMC bioinformatics"},{"issue":"2","key":"pone.0317283.ref060","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/0005-2795(75)90109-9","article-title":"Comparison of the predicted and observed secondary structure of T4 phage lysozyme","volume":"405","author":"BW Matthews","year":"1975","journal-title":"Biochimica et Biophysica Acta (BBA)\u2014Protein Structure"},{"issue":"5","key":"pone.0317283.ref061","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1093\/bioinformatics\/16.5.412","article-title":"Assessing the accuracy of prediction algorithms for classification: an overview","volume":"16","author":"P Baldi","year":"2000","journal-title":"Bioinformatics"},{"key":"pone.0317283.ref062","doi-asserted-by":"crossref","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"D Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"pone.0317283.ref063","doi-asserted-by":"crossref","first-page":"567","DOI":"10.5614\/ejgta.2021.9.2.25","article-title":"Evaluating topological ordering in directed acyclic graphs","volume":"9","author":"Suzana Antunovi\u0107","year":"2021","journal-title":"Electronic Journal of Graph Theory and Applications"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317283","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T19:22:45Z","timestamp":1736364165000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0317283"}},"subtitle":[],"editor":[{"given":"Tao","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,8]]},"references-count":63,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,8]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0317283","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,8]]}}}