{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:18:20Z","timestamp":1770333500536,"version":"3.49.0"},"reference-count":66,"publisher":"American Chemical Society (ACS)","issue":"11","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100016382","name":"Schmidt Family Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016382","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Chem. Inf. Model."],"published-print":{"date-parts":[[2025,6,9]]},"DOI":"10.1021\/acs.jcim.5c00516","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T14:51:29Z","timestamp":1747752689000},"page":"5424-5437","source":"Crossref","is-referenced-by-count":1,"title":["Machine Learning Pipeline for Molecular Property Prediction Using ChemXploreML"],"prefix":"10.1021","volume":"65","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5444-6401","authenticated-orcid":true,"given":"Aravindh Nivas","family":"Marimuthu","sequence":"first","affiliation":[{"name":"Department of Chemistry","place":["Cambridge, United States"]},{"name":"Massachusetts Institute of Technology","place":["Cambridge, United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1254-4817","authenticated-orcid":true,"given":"Brett A.","family":"McGuire","sequence":"additional","affiliation":[{"name":"Department of Chemistry","place":["Cambridge, United States"]},{"name":"Massachusetts Institute of Technology","place":["Cambridge, United States"]},{"name":"National Radio Astronomy Observatory","place":["Charlottesville, United States"]}]}],"member":"316","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"ref1\/cit1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00460-5"},{"key":"ref2\/cit2","series-title":"ACS In Focus","doi-asserted-by":"crossref","DOI":"10.1021\/acs.infocus.7e4001","volume-title":"Machine Learning in Chemistry","author":"Janet J. P.","year":"2020"},{"key":"ref3\/cit3","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1439"},{"key":"ref4\/cit4","doi-asserted-by":"publisher","DOI":"10.1021\/ie990579d"},{"key":"ref5\/cit5","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690190416"},{"key":"ref6\/cit6","doi-asserted-by":"publisher","DOI":"10.1021\/ie960512f"},{"key":"ref7\/cit7","doi-asserted-by":"publisher","DOI":"10.1063\/1.2827056"},{"key":"ref8\/cit8","doi-asserted-by":"publisher","DOI":"10.1080\/1062936X.2016.1217270"},{"key":"ref9\/cit9","doi-asserted-by":"publisher","DOI":"10.1897\/01-363"},{"key":"ref10\/cit10","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.2786"},{"key":"ref11\/cit11","doi-asserted-by":"publisher","DOI":"10.1038\/d41573-019-00074-z"},{"key":"ref12\/cit12","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.7b00616"},{"key":"ref13\/cit13","unstructured":"Lee, K. L. K. Language models for astrochemistry, 2021. https:\/\/zenodo.org\/records\/7559628."},{"key":"ref14\/cit14","doi-asserted-by":"publisher","DOI":"10.3847\/1538-4357\/ad004c"},{"key":"ref15\/cit15","doi-asserted-by":"publisher","DOI":"10.3847\/2041-8213\/ac194b"},{"key":"ref16\/cit16","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"ref17\/cit17","doi-asserted-by":"crossref","unstructured":"Chen, T.; Guestrin, C. In XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA, 2016; pp 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"ref18\/cit18","unstructured":"Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.Y. In LightGBM: A Highly Efficient Gradient Boosting Decision Tree, Advances in Neural Information Processing Systems, 2017."},{"key":"ref19\/cit19","unstructured":"Prokhorenkova, L.; Gusev, G.; Vorobev, A.; Dorogush, A. V.; Gulin, A. In CatBoost: unbiased boosting with categorical features, Advances in Neural Information Processing Systems, 2018."},{"key":"ref20\/cit20","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-023-00743-7"},{"key":"ref21\/cit21","unstructured":"Marimuthu, A. N. aravindhnivas\/ChemXploreML: v4.0.0, 2025. https:\/\/zenodo.org\/doi\/10.5281\/zenodo.14977096."},{"key":"ref22\/cit22","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"ref23\/cit23","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-4-22"},{"key":"ref24\/cit24","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba947"},{"key":"ref25\/cit25","unstructured":"Team, T. C. Tauri: Build smaller, faster, and more secure desktop applications with a web frontend, Version 2.1.1, 2024. https:\/\/tauri.app."},{"key":"ref26\/cit26","unstructured":"Harris, R.; Team, S. C. Svelte: Cybernetically enhanced web applications, Version 4.2.1, 2024. https:\/\/svelte.dev."},{"key":"ref27\/cit27","unstructured":"Python Core\nTeam Python: A dynamic, open source\nprogramming language, Version\n3.12, 2019. https:\/\/www.python.org\/."},{"key":"ref28\/cit28","unstructured":"Landrum, G.  rdkit\/rdkit: 2024_09_2 (Q3 2024) Release, 2024. https:\/\/zenodo.org\/doi\/10.5281\/zenodo.591637."},{"key":"ref29\/cit29","first-page":"2825","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref30\/cit30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1907.10902"},{"key":"ref31\/cit31","doi-asserted-by":"crossref","unstructured":"Rocklin, M. In Dask: Parallel Computation with Blocked algorithms and Task Scheduling, SciPy, Texas, Austin, 2015; pp 126\u2013132.","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"ref32\/cit32","series-title":"CRC handbook of chemistry and physics\/Chemical Rubber Company 105th ed. (2024)","volume-title":"CRC handbook of chemistry and physics: a ready-reference book of chemical and physical data","author":"Rumble J. R.","year":"2024","edition":"105"},{"key":"ref33\/cit33","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0375-2"},{"key":"ref34\/cit34","unstructured":"mcs07\/CIRpy: Python wrapper for the NCI Chemical Identifier\nResolver\n(CIR). https:\/\/github.com\/mcs07\/CIRpy."},{"key":"ref35\/cit35","unstructured":"cleanlab, 2024; original-date:\n2018-05-11T01:55:21Z. https:\/\/github.com\/cleanlab\/cleanlab."},{"key":"ref36\/cit36","unstructured":"Zhou, H.; Mueller, J.; Kumar, M.; Wang, J.L.; Lei, J. In Detecting Errors in Numerical Data via any Regression Model, ICML Workshop on Data-centric Machine Learning Research, 2023."},{"key":"ref37\/cit37","unstructured":"Kuan, J.; Mueller, J. In Model-agnostic label quality scoring to detect real-world label errors, ICML DataPerf Workshop, 2022."},{"key":"ref38\/cit38","doi-asserted-by":"publisher","DOI":"10.1186\/1758-2946-5-26"},{"key":"ref39\/cit39","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-016-0148-0"},{"key":"ref40\/cit40","doi-asserted-by":"publisher","DOI":"10.1021\/ci400466r"},{"key":"ref41\/cit41","doi-asserted-by":"publisher","DOI":"10.3389\/fenvs.2015.00080"},{"key":"ref42\/cit42","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.6b01611"},{"key":"ref43\/cit43","doi-asserted-by":"publisher","DOI":"10.1002\/cmdc.201700180"},{"key":"ref44\/cit44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1301.3781"},{"key":"ref45\/cit45","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"ref46\/cit46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ygeno.2020.11.009"},{"key":"ref47\/cit47","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00803"},{"key":"ref48\/cit48","doi-asserted-by":"publisher","DOI":"10.1039\/d3dd00020f"},{"key":"ref49\/cit49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.04906"},{"key":"ref50\/cit50","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jmedchem.9b00959"},{"key":"ref51\/cit51","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"ref52\/cit52","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b01076"},{"key":"ref53\/cit53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1712.02034"},{"key":"ref54\/cit54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.09885"},{"key":"ref55\/cit55","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7181815"},{"key":"ref56\/cit56","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.09553"},{"key":"ref57\/cit57","doi-asserted-by":"publisher","DOI":"10.1063\/5.0171540"},{"key":"ref58\/cit58","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c01862"},{"key":"ref59\/cit59","doi-asserted-by":"publisher","DOI":"10.3390\/molecules15085079"},{"key":"ref60\/cit60","unstructured":"Ester, M.; Kriegel, H.P.; Sander, J.; Xu, X. In A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise, Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, OR; AAAI Press, 1996; pp 226\u2013231."},{"key":"ref61\/cit61","doi-asserted-by":"publisher","DOI":"10.1145\/3068335"},{"key":"ref62\/cit62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.11127"},{"key":"ref63\/cit63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1206.2944"},{"key":"ref64\/cit64","doi-asserted-by":"publisher","DOI":"10.3390\/molecules23061379"},{"key":"ref65\/cit65","doi-asserted-by":"publisher","DOI":"10.1021\/ci5005288"},{"key":"ref66\/cit66","doi-asserted-by":"publisher","DOI":"10.1002\/minf.201500052"}],"container-title":["Journal of Chemical Information and Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.5c00516","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.5c00516","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T08:09:55Z","timestamp":1749456595000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/doi\/10.1021\/acs.jcim.5c00516"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,20]]},"references-count":66,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,6,9]]}},"alternative-id":["10.1021\/acs.jcim.5c00516"],"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.5c00516","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,20]]}}}