{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:41:39Z","timestamp":1764398499220,"version":"3.46.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T00:00:00Z","timestamp":1763078400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Comput Aided Mol Des"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10822-025-00693-2","type":"journal-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T17:08:03Z","timestamp":1763140083000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LiteBoost: a lightweight and explainable boosting model for predicting polymer density from SMILES data"],"prefix":"10.1007","volume":"39","author":[{"given":"Tuan","family":"Nguyen-Sy","sequence":"first","affiliation":[]},{"given":"Hieu","family":"Do-Trung","sequence":"additional","affiliation":[]},{"given":"Nam","family":"Nguyen-Hoang","sequence":"additional","affiliation":[]},{"given":"Duc Toan","family":"Truong","sequence":"additional","affiliation":[]},{"given":"My-Kristyna","family":"Nguyen-Thao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"693_CR1","doi-asserted-by":"crossref","unstructured":"Akiba T, Sano S, Yanase T, Ohta T, & Koyama M (2019). Optuna: A next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining\u00a0(pp. 2623\u20132631)","DOI":"10.1145\/3292500.3330701"},{"issue":"1","key":"693_CR2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/s13321-023-00743-7","volume":"15","author":"D Boldini","year":"2023","unstructured":"Boldini D, Grisoni F, Kuhn D, Friedrich L, Sieber SA (2023) Practical guidelines for the use of gradient boosting for molecular property prediction. J Cheminform 15(1):73","journal-title":"J Cheminform"},{"key":"693_CR3","doi-asserted-by":"crossref","unstructured":"Chen T, & Guestrin C (2016) Xgboost: A scalable tree boosting system. In:\u00a0Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining\u00a0(pp. 785\u2013794)","DOI":"10.1145\/2939672.2939785"},{"key":"693_CR4","doi-asserted-by":"publisher","first-page":"100595","DOI":"10.1016\/j.mser.2020.100595","volume":"144","author":"L Chen","year":"2021","unstructured":"Chen L, Pilania G, Batra R, Huan TD, Kim C, Kuenneth C, Ramprasad R (2021) Polymer informatics: current status and critical next steps. Mater Sci Eng R Rep 144:100595","journal-title":"Mater Sci Eng R Rep"},{"key":"693_CR5","doi-asserted-by":"publisher","DOI":"10.1063\/5.0023759","author":"H Doan Tran","year":"2020","unstructured":"Doan Tran H, Kim C, Chen L, Chandrasekaran A, Batra R, Venkatram S, Ramprasad R (2020) Machine-learning predictions of polymer properties with polymer genome. J Appl Phys. https:\/\/doi.org\/10.1063\/5.0023759","journal-title":"J Appl Phys"},{"key":"693_CR6","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451","author":"JH Friedman","year":"2001","unstructured":"Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat. https:\/\/doi.org\/10.1214\/aos\/1013203451","journal-title":"Ann Stat"},{"key":"693_CR7","unstructured":"Liu G, Zhu Y, Chen J, & Jiang M (2025) NeurIPS - Open Polymer Prediction 2025. https:\/\/kaggle.com\/competitions\/neurips-open-polymer-prediction-2025, 2025. Kaggle."},{"issue":"3","key":"693_CR8","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1021\/acs.macromol.8b01836","volume":"52","author":"TE Gartner III","year":"2019","unstructured":"Gartner TE III, Jayaraman A (2019) Modeling and simulations of polymers: a roadmap. Macromolecules 52(3):755\u2013786","journal-title":"Macromolecules"},{"key":"693_CR9","first-page":"507","volume":"35","author":"L Grinsztajn","year":"2022","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G (2022) Why do tree-based models still outperform deep learning on typical tabular data? Adv Neural Inf Process Syst 35:507\u2013520","journal-title":"Adv Neural Inf Process Syst"},{"issue":"6","key":"693_CR10","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1021\/ci00028a014","volume":"35","author":"LH Hall","year":"1995","unstructured":"Hall LH, Kier LB (1995) Electrotopological state indices for atom types: a novel combination of electronic, topological, and valence state information. J Chem Inf Comput Sci 35(6):1039\u20131045","journal-title":"J Chem Inf Comput Sci"},{"issue":"1","key":"693_CR11","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1186\/s40537-020-00369-8","volume":"7","author":"JT Hancock","year":"2020","unstructured":"Hancock JT, Khoshgoftaar TM (2020) Catboost for big data: an interdisciplinary review. J Big Data 7(1):94","journal-title":"J Big Data"},{"issue":"1","key":"693_CR12","first-page":"2354649","volume":"4","author":"M Ishii","year":"2024","unstructured":"Ishii M, Ito T, Sado H, Kuwajima I (2024) NIMS polymer database polyinfo (I): an overarching view of half a million data points. Sci Technol Adv Mater Methods 4(1):2354649","journal-title":"Sci Technol Adv Mater Methods"},{"key":"693_CR13","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, ... & Liu T Y (2017) Lightgbm: A highly efficient gradient boosting decision tree.\u00a0Adv Neural Inform Process Syst\u00a030."},{"issue":"31","key":"693_CR14","doi-asserted-by":"publisher","first-page":"17575","DOI":"10.1021\/acs.jpcc.8b02913","volume":"122","author":"C Kim","year":"2018","unstructured":"Kim C, Chandrasekaran A, Huan TD, Das D, Ramprasad R (2018) Polymer genome: a data-powered polymer informatics platform for property predictions. J Phys Chem C 122(31):17575\u201317585","journal-title":"J Phys Chem C"},{"key":"693_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2021.100238","author":"C Kuenneth","year":"2021","unstructured":"Kuenneth C, Rajan AC, Tran H, Chen L, Kim C, Ramprasad R (2021) Polymer informatics with multi-task learning. Patterns. https:\/\/doi.org\/10.1016\/j.patter.2021.100238","journal-title":"Patterns"},{"issue":"1","key":"693_CR16","doi-asserted-by":"publisher","first-page":"4099","DOI":"10.1038\/s41467-023-39868-6","volume":"14","author":"C Kuenneth","year":"2023","unstructured":"Kuenneth C, Ramprasad R (2023) PolyBERT: a chemical language model to enable fully machine-driven ultrafast polymer informatics. Nat Commun 14(1):4099","journal-title":"Nat Commun"},{"issue":"1\u201379","key":"693_CR17","first-page":"4","volume":"1","author":"G Landrum","year":"2013","unstructured":"Landrum G (2013) Rdkit documentation. Release 1(1\u201379):4","journal-title":"Release"},{"key":"693_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2022.100931","author":"Z Liang","year":"2022","unstructured":"Liang Z, Li Z, Zhou S, Sun Y, Yuan J, Zhang C (2022) Machine-learning exploration of polymer compatibility. Cell Rep Phys Sci. https:\/\/doi.org\/10.1016\/j.xcrp.2022.100931","journal-title":"Cell Rep Phys Sci"},{"issue":"9","key":"693_CR19","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1021\/acscentsci.9b00476","volume":"5","author":"TS Lin","year":"2019","unstructured":"Lin TS, Coley CW, Mochigase H, Beech HK, Wang W, Wang Z, Woods E, Craig SL, Johnson JA, Kalow JA, Jensen KF, Olsen BD (2019) Bigsmiles: a structurally-based line notation for describing macromolecules. ACS Cent Sci 5(9):1523\u20131531","journal-title":"ACS Cent Sci"},{"issue":"3","key":"693_CR20","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1021\/acspolymersau.2c00053","volume":"3","author":"TB Martin","year":"2023","unstructured":"Martin TB, Audus DJ (2023) Emerging trends in machine learning: a polymer perspective. ACS Polym Au 3(3):239\u2013258","journal-title":"ACS Polym Au"},{"issue":"1","key":"693_CR21","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1186\/s12874-025-02561-x","volume":"25","author":"C Meaney","year":"2025","unstructured":"Meaney C, Wang X, Guan J, Stukel TA (2025) Comparison of methods for tuning machine learning model hyper-parameters: with application to predicting high-need high-cost health care users. BMC Med Res Methodol 25(1):134","journal-title":"BMC Med Res Methodol"},{"issue":"4","key":"693_CR22","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1021\/acspolymersau.1c00050","volume":"2","author":"J Park","year":"2022","unstructured":"Park J, Shim Y, Lee F, Rammohan A, Goyal S, Shim M, Jeong C, Kim DS (2022) Prediction and interpretation of polymer properties using the graph convolutional network. ACS Polym Au 2(4):213\u2013222","journal-title":"ACS Polym Au"},{"key":"693_CR23","unstructured":"Prokhorenkova L, Gusev G, Vorobev A, Dorogush A V, & Gulin A (2018) CatBoost: unbiased boosting with categorical features.\u00a0Adv Neural Inform Process Syst,\u00a031."},{"issue":"16","key":"693_CR24","doi-asserted-by":"publisher","first-page":"8761","DOI":"10.1021\/acs.jmedchem.9b01101","volume":"63","author":"R Rodr\u00edguez-P\u00e9rez","year":"2019","unstructured":"Rodr\u00edguez-P\u00e9rez R, Bajorath J (2019) Interpretation of compound activity predictions from complex machine learning models using local approximations and shapley values. J Med Chem 63(16):8761\u20138777","journal-title":"J Med Chem"},{"issue":"10","key":"693_CR25","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1007\/s10822-020-00314-0","volume":"34","author":"R Rodr\u00edguez-P\u00e9rez","year":"2020","unstructured":"Rodr\u00edguez-P\u00e9rez R, Bajorath J (2020) Interpretation of machine learning models using shapley values: application to compound potency and multi-target activity predictions. J Comput Aided Mol Des 34(10):1013\u20131026","journal-title":"J Comput Aided Mol Des"},{"key":"693_CR26","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","volume":"81","author":"R Shwartz-Ziv","year":"2022","unstructured":"Shwartz-Ziv R, Armon A (2022) Tabular data: deep learning is not all you need. Inf Fusion 81:84\u201390","journal-title":"Inf Fusion"},{"issue":"1","key":"693_CR27","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1038\/s41524-023-01040-5","volume":"9","author":"S Stuart","year":"2023","unstructured":"Stuart S, Watchorn J, Gu FX (2023) Sizing up feature descriptors for macromolecular machine learning with polymeric biomaterials. NPJ Comput Mater 9(1):102","journal-title":"NPJ Comput Mater"},{"issue":"12","key":"693_CR28","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1038\/s41578-024-00708-8","volume":"9","author":"H Tran","year":"2024","unstructured":"Tran H, Gurnani R, Kim C, Pilania G, Kwon HK, Lively RP, Ramprasad R (2024) Design of functional and sustainable polymers assisted by artificial intelligence. Nat Rev Mater 9(12):866\u2013886","journal-title":"Nat Rev Mater"},{"issue":"1","key":"693_CR29","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1038\/s41524-023-01000-z","volume":"9","author":"P Xu","year":"2023","unstructured":"Xu P, Ji X, Li M, Lu W (2023) Small data machine learning in materials science. NPJ Comput Mater 9(1):42","journal-title":"NPJ Comput Mater"},{"key":"693_CR30","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1162\/tacl_a_00322","volume":"8","author":"X Zhang","year":"2020","unstructured":"Zhang X, Duh K (2020) Reproducible and efficient benchmarks for hyperparameter optimization of neural machine translation systems. Trans Assoc Comput Linguist 8:393\u2013408","journal-title":"Trans Assoc Comput Linguist"},{"issue":"1","key":"693_CR31","doi-asserted-by":"publisher","first-page":"204","DOI":"10.1038\/s41524-022-00884-7","volume":"8","author":"X Zhong","year":"2022","unstructured":"Zhong X, Gallagher B, Liu S, Kailkhura B, Hiszpanski A, Han TYJ (2022) Explainable machine learning in materials science. NPJ Comput Mater 8(1):204","journal-title":"NPJ Comput Mater"}],"container-title":["Journal of Computer-Aided Molecular Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-025-00693-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10822-025-00693-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10822-025-00693-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T06:38:24Z","timestamp":1764398304000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10822-025-00693-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["693"],"URL":"https:\/\/doi.org\/10.1007\/s10822-025-00693-2","relation":{},"ISSN":["0920-654X","1573-4951"],"issn-type":[{"type":"print","value":"0920-654X"},{"type":"electronic","value":"1573-4951"}],"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"11 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"We wish to confirm that there are no known conflicts of interest associated with this publication and there has been no significant financial support for this work that could have influenced its outcome.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"125"}}