{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:31:59Z","timestamp":1772137919033,"version":"3.50.1"},"reference-count":54,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T00:00:00Z","timestamp":1724371200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100016818","name":"UT-Battelle, LLC","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100016818","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"crossref"}]},{"name":"DOE","award":["DE-AC05-00OR22725"],"award-info":[{"award-number":["DE-AC05-00OR22725"]}]},{"DOI":"10.13039\/501100001845","name":"SEED","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001845","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Arti\ufb01cial Intelligence Initiative"},{"name":"Laboratory Directed Research and Development Program of Oak Ridge National Laboratory"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predicting and enhancing inherent properties based on molecular structures is paramount to design tasks in medicine, materials science, and environmental management. Most of the current machine learning and deep learning approaches have become standard for predictions, but they face challenges when applied across different datasets due to reliance on correlations between molecular representation and target properties. These approaches typically depend on large datasets to capture the diversity within the chemical space, facilitating a more accurate approximation, interpolation, or extrapolation of the chemical behavior of molecules. In our research, we introduce an active learning approach that discerns underlying cause-effect relationships through strategic sampling with the use of a graph loss function. This method identifies the smallest subset of the dataset capable of encoding the most information representative of a much larger chemical space. The identified causal relations are then leveraged to conduct systematic interventions, optimizing the design task within a chemical space that the models have not encountered previously. While our implementation focused on the QM9 quantum-chemical dataset for a specific design task\u2014finding molecules with a large dipole moment\u2014our active causal learning approach, driven by intelligent sampling and interventions, holds potential for broader applications in molecular, materials design and discovery.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad6feb","type":"journal-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T18:57:50Z","timestamp":1723748270000},"page":"035056","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Active causal learning for decoding chemical complexities with targeted interventions"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0138-2867","authenticated-orcid":true,"given":"Zachary","family":"R Fox","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0432-3689","authenticated-orcid":true,"given":"Ayana","family":"Ghosh","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,8,23]]},"reference":[{"key":"mlstad6febbib1","doi-asserted-by":"crossref","article-title":"PubChem: a public information system for analyzing bioactivities of small molecules","author":"Wang","DOI":"10.1093\/nar\/gkp456"},{"key":"mlstad6febbib2","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.1021\/acs.jcim.0c00675","article-title":"ZINC20\u2014a free ultralarge-scale chemical database for ligand discovery","volume":"60","author":"Irwin","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad6febbib3","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"mlstad6febbib4","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad6febbib5","first-page":"111","article-title":"Pairwise likelihood ratios for estimation of non-Gaussian structural equation models","volume":"14","author":"Hyv\u00e4rinen","year":"2013","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad6febbib6","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1038\/s41597-020-0473-z","article-title":"The ANI-1ccx and ANI-1x data sets, coupled-cluster and density functional theory properties for molecules","volume":"7","author":"Smith","year":"2020","journal-title":"Sci. Data"},{"key":"mlstad6febbib7","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1038\/s41597-021-00812-2","article-title":"QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules","volume":"8","author":"Hoja","year":"2021","journal-title":"Sci. Data"},{"key":"mlstad6febbib8","doi-asserted-by":"publisher","first-page":"4538","DOI":"10.1016\/j.csbj.2021.08.011","article-title":"A review on machine learning approaches and trends in drug discovery","volume":"19","author":"Carracedo-Reboredo","year":"2021","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"mlstad6febbib9","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1021\/cc700187t","article-title":"Application of combinatorial chemistry science on modern drug discovery","volume":"10","author":"Kennedy","year":"2008","journal-title":"J. Comb. Chem."},{"key":"mlstad6febbib10","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s13321-020-00460-5","article-title":"Molecular representations in AI-driven drug discovery: a review and practical guide","volume":"12","author":"David","year":"2020","journal-title":"J. Chem."},{"key":"mlstad6febbib11","doi-asserted-by":"publisher","first-page":"3525","DOI":"10.1039\/d0cs00098a","article-title":"QSAR without borders","volume":"49","author":"Muratov","year":"2020","journal-title":"Chem. Soc. Rev."},{"key":"mlstad6febbib12","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1016\/j.cell.2020.01.021","article-title":"A deep learning approach to antibiotic discovery","volume":"180","author":"Stokes","year":"2020","journal-title":"Cell"},{"key":"mlstad6febbib13","doi-asserted-by":"publisher","first-page":"2260","DOI":"10.1021\/acscatal.9b04186","article-title":"Machine learning for catalysis informatics: recent applications and prospects","volume":"10","author":"Toyao","year":"2020","journal-title":"ACS Catal."},{"key":"mlstad6febbib14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1021\/acsomega.9b03673","article-title":"Machine learning in catalysis, from proposal to practicing","volume":"5","author":"Yang","year":"2020","journal-title":"ACS Omega"},{"key":"mlstad6febbib15","doi-asserted-by":"publisher","first-page":"eaay4275","DOI":"10.1126\/sciadv.aay4275","article-title":"Machine learning-assisted molecular design and efficiency prediction for high-performance organic photovoltaic materials","volume":"5","author":"Sun","year":"2019","journal-title":"Sci. Adv."},{"key":"mlstad6febbib16","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1038\/nmat4717","article-title":"Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach","volume":"15","author":"G\u00f3mez-Bombarelli","year":"2016","journal-title":"Nat. Mater."},{"key":"mlstad6febbib17","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1039\/C4SC03030C","article-title":"Computational design of molecules for an all-quinone redox flow battery","volume":"6","author":"Er","year":"2015","journal-title":"Chem. Sci."},{"key":"mlstad6febbib18","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.1021\/acs.jcim.5b00110","article-title":"The relative importance of domain applicability metrics for estimating prediction errors in QSAR varies with training set diversity","volume":"55","author":"Sheridan","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad6febbib19","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.1039\/C6SC05720A","article-title":"ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost","volume":"8","author":"Smith","year":"2017","journal-title":"Chem. Sci."},{"key":"mlstad6febbib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.crmeth.2023.100621","article-title":"Molecular geometric deep learning","volume":"3","author":"Shen","year":"2023","journal-title":"Cell Rep. Methods"},{"key":"mlstad6febbib21","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","article-title":"Inverse molecular design using machine learning: generative models for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science"},{"key":"mlstad6febbib22","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/s41524-021-00670-x","article-title":"Inverse design of two-dimensional materials with invertible neural networks","volume":"7","author":"Fung","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstad6febbib23","doi-asserted-by":"publisher","first-page":"14711","DOI":"10.1609\/aaai.v37i12.26719","article-title":"Accelerating inverse learning via intelligent localization with exploratory sampling","volume":"37","author":"Bi","year":"2023","journal-title":"Proc. AAAI Conf. on Artificial Intelligence"},{"key":"mlstad6febbib24","doi-asserted-by":"publisher","first-page":"7563","DOI":"10.1021\/acs.chemmater.2c00217","article-title":"Insights into cation ordering of double perovskite oxides from machine learning and causal relations","volume":"34","author":"Ghosh","year":"2022","journal-title":"Chem. Mater."},{"key":"mlstad6febbib25","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1038\/s41567-022-01666-0","article-title":"From atomically resolved imaging to generative and causal models","volume":"18","author":"Kalinin","year":"2022","journal-title":"Nat. Phys."},{"key":"mlstad6febbib26","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1038\/s41524-020-00396-2","article-title":"Causal analysis of competing atomistic mechanisms in ferroelectric materials from high-resolution scanning transmission electron microscopy data","volume":"6","author":"Ziatdinov","year":"2020","journal-title":"npj Comput. Mater."},{"key":"mlstad6febbib27","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acsnano.1c09059","article-title":"Exploring causal physical mechanisms via non-Gaussian linear models and deep kernel learning: applications for ferroelectric domain structures","volume":"16","author":"Liu","year":"2021","journal-title":"ACS Nano"},{"key":"mlstad6febbib28","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/s41524-019-0248-2","article-title":"Reliable and explainable machine-learning methods for accelerated material discovery","volume":"5","author":"Kailkhura","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstad6febbib29","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1021\/accountsmr.1c00244","article-title":"Interpretable and explainable machine learning for materials science and chemistry","volume":"3","author":"Oviedo","year":"2022","journal-title":"Acc. Mater. Res."},{"key":"mlstad6febbib30","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug discovery with explainable artificial intelligence","volume":"2","author":"Jim\u00e9nez-Luna","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"mlstad6febbib31","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1038\/s41524-022-00884-7","article-title":"Explainable machine learning in materials science","volume":"8","author":"Zhong","year":"2022","journal-title":"npj Comput. Mater."},{"key":"mlstad6febbib32","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/e23010018","article-title":"Explainable AI: a review of machine learning interpretability methods","volume":"23","author":"Linardatos","year":"2020","journal-title":"Entropy"},{"key":"mlstad6febbib33","doi-asserted-by":"publisher","first-page":"2149","DOI":"10.1021\/acs.jctc.2c01235","article-title":"A perspective on explanations of molecular prediction models","volume":"19","author":"Wellawatte","year":"2023","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad6febbib34","doi-asserted-by":"publisher","first-page":"3697","DOI":"10.1039\/D1SC05259D","article-title":"Model agnostic generation of counterfactual explanations for molecules","volume":"13","author":"Wellawatte","year":"2022","journal-title":"Chem. Sci."},{"key":"mlstad6febbib35","doi-asserted-by":"crossref","DOI":"10.1063\/5.0157644","article-title":"Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space","author":"Ghosh","year":"2023"},{"key":"mlstad6febbib36","first-page":"2003","article-title":"A linear non-Gaussian acyclic model for causal discovery","volume":"7","author":"Shimizu","year":"2006","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad6febbib37","volume":"vol 210","author":"Bollen","year":"1989"},{"key":"mlstad6febbib38","first-page":"pp 148","article-title":"Heterogeneous uncertainty sampling for supervised learning","author":"Lewis","year":"1994"},{"key":"mlstad6febbib39","doi-asserted-by":"publisher","first-page":"3330","DOI":"10.1109\/IJCNN.2016.7727625","article-title":"Unsupervised entropy-based selection of data sets for improved model fitting pp","author":"Ferreira","year":"2016"},{"key":"mlstad6febbib40","article-title":"Deep batch active learning by diverse, uncertain gradient lower bounds","author":"Ash","year":"2019"},{"key":"mlstad6febbib41","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1016\/j.ijar.2013.11.007","article-title":"Two optimal strategies for active learning of causal models from interventional data","volume":"55","author":"Hauser","year":"2014","journal-title":"Int. J. Approx. Reason."},{"key":"mlstad6febbib42","first-page":"2523","article-title":"Active learning of causal networks with intervention experiments and optimal designs","volume":"9","author":"Yang-Bo","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad6febbib43","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0150611","article-title":"Reconstructing causal biological networks through active learning","volume":"11","author":"Cho","year":"2016","journal-title":"PLoS One"},{"key":"mlstad6febbib44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0228728","article-title":"Metrics for graph comparison: a practitioner\u2019s guide","volume":"15","author":"Wills","year":"2020","journal-title":"PLoS One"},{"key":"mlstad6febbib45","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inform. Model."},{"key":"mlstad6febbib46","author":"Isaakovich Minkin","year":"2012"},{"key":"mlstad6febbib47","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1002\/jps.2600710611","article-title":"Use of dipole moment as a parameter in drug\u2013receptor interaction and quantitative structure\u2013activity relationship studies","volume":"71","author":"Lien","year":"1982","journal-title":"J. Pharm. Sci."},{"key":"mlstad6febbib48","article-title":"Scalable fragment-based 3D molecular design with reinforcement learning","author":"Flam-Shepherd","year":"2022"},{"key":"mlstad6febbib49","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1038\/s42256-021-00410-2","article-title":"A deep generative model for molecule optimization via one fragment modification","volume":"3","author":"Chen","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstad6febbib50","doi-asserted-by":"publisher","first-page":"6234","DOI":"10.1038\/s41467-023-41454-9","article-title":"A pharmacophore-guided deep learning approach for bioactive molecular generation","volume":"14","author":"Zhu","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad6febbib51","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1039\/C9SC04503A","article-title":"Scaffold-based molecular design with a graph generative model","volume":"11","author":"Lim","year":"2020","journal-title":"Chem. Sci."},{"key":"mlstad6febbib52","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","article-title":"De novo molecular design and generative models","volume":"26","author":"Meyers","year":"2021","journal-title":"Drug Discov. Today"},{"key":"mlstad6febbib53","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1038\/s43588-023-00532-0","article-title":"Guided diffusion for inverse molecular design","volume":"3","author":"Weiss","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"mlstad6febbib54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-018-0296-5","article-title":"Machine learning for the prediction of molecular dipole moments obtained by density functional theory","volume":"10","author":"Pereira","year":"2018","journal-title":"J. Cheminform."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T07:57:39Z","timestamp":1724399859000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad6feb"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,23]]},"references-count":54,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,8,23]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad6feb","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/AD6FEB\/v2\/response1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,23]]},"assertion":[{"value":"Active causal learning for decoding chemical complexities with targeted interventions","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-05-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-15","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-08-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}