{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T08:49:28Z","timestamp":1791535768254,"version":"4.3.4"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":2,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"publisher","award":["EP\/L015684\/1"],"award-info":[{"award-number":["EP\/L015684\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>With the proliferation of screening tools for chemical testing, it is now possible to create vast databases of chemicals easily. However, rigorous statistical methodologies employed to analyze these databases are in their infancy, and further development to facilitate chemical discovery is imperative. In this paper, we address the challenge of predicting an organic solvent\u2019s water pollution class based on its chemical structure. We hypothesize that solvents with similar chemical structure are more likely to belong in the same hazard class. This chemical similarity is measured by the Tanimoto distance, a non-Euclidean metric on the chemical space. To incorporate the similarity between chemical structures in the model, we propose a Gaussian process model on the chemical space, with the kernel being a function of the Tanimoto distance. A novel feature of the proposed model is the inclusion of a scale parameter in the kernel, which controls the strength of the correlation between compounds and offers additional flexibility. We find that accounting for correlation between chemical compounds substantially improves predictive performance over the uncorrelated model, where compound similarity is unaccounted for. Our model also compares favorably against other established models in the literature. Furthermore, we present a genetic algorithm designed to identify important features to a compound\u2019s efficacy, with the goal of facilitating chemical discovery. The algorithm operates based on two criteria derived from the proposed model. Simulation studies are conducted to demonstrate the suitability of the proposed methods.<\/jats:p>","DOI":"10.1093\/biomtc\/ujag168","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:26:52Z","timestamp":1789673212000},"source":"Crossref","is-referenced-by-count":0,"title":["A Gaussian process model for chemoinformatics with application to the hazard classification of organic solvents"],"prefix":"10.1093","volume":"82","author":[{"given":"Arron","family":"Gosnell","sequence":"first","affiliation":[{"name":"Department of Mathematical Sciences, University of Bath , Bath BA2 7AY ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1603-7460","authenticated-orcid":false,"given":"Evangelos","family":"Evangelou","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, University of Bath , Bath BA2 7AY ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"2026100903592986500_bib1","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s13321-015-0069-3","article-title":"Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?","volume":"7","author":"Bajusz","year":"2015","journal-title":"Journal of Cheminformatics"},{"key":"2026100903592986500_bib2","doi-asserted-by":"crossref","first-page":"20220006","DOI":"10.1515\/jib-2022-0006","article-title":"Evaluating molecular representations in machine learning models for drug response prediction and interpretability","volume":"19","author":"Baptista","year":"2022","journal-title":"Journal of Integrative Bioinformatics"},{"key":"2026100903592986500_bib3","doi-asserted-by":"crossref","first-page":"3204","DOI":"10.1039\/b409813g","article-title":"Molecular similarity: A key technique in molecular informatics","volume":"2","author":"Bender","year":"2004","journal-title":"Organic and Biomolecular Chemistry"},{"key":"2026100903592986500_bib4","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1080\/01621459.1998.10474107","article-title":"Standard errors of prediction in generalized linear mixed models","volume":"93","author":"Booth","year":"1998","journal-title":"Journal of the American Statistical Association"},{"key":"2026100903592986500_bib5","doi-asserted-by":"crossref","first-page":"1636","DOI":"10.3390\/en11071636","article-title":"Optimal deep learning LSTM model for electric load forecasting using feature selection and genetic algorithm: Comparison with machine learning approaches","volume":"11","author":"Bouktif","year":"2018","journal-title":"Energies"},{"key":"2026100903592986500_bib6","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1007\/s004770070001","article-title":"Norm-dependent covariance permissibility of weakly homogeneous spatial random fields and its consequences in spatial statistics","volume":"14","author":"Christakos","year":"2000","journal-title":"Stochastic Environmental Research and Risk Assessment"},{"key":"2026100903592986500_bib7","first-page":"1019","article-title":"Gaussian processes for ordinal regression","volume":"6","author":"Chu","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"2026100903592986500_bib8","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/0378-3758(92)90069-5","article-title":"The effect of link misspecification on binary regression inference","volume":"33","author":"Czado","year":"1992","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2026100903592986500_bib9","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1111\/j.1541-0420.2006.00622.x","article-title":"Statistical analysis of unlabeled point sets: Comparing molecules in chemoinformatics","volume":"63","author":"Dryden","year":"2007","journal-title":"Biometrics"},{"key":"2026100903592986500_bib10","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1145\/35078.214351","article-title":"Algorithm 655: Iqpack: Fortran subroutines for the weights of interpolatory quadratures","volume":"13","author":"Elhay","year":"1987","journal-title":"ACM Transactions on Mathematical Software"},{"key":"2026100903592986500_bib11","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1016\/j.jspi.2012.05.008","article-title":"Optimal predictive design augmentation for spatial generalised linear mixed models","volume":"142","author":"Evangelou","year":"2012","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2026100903592986500_bib12","first-page":"3866","article-title":"Privacy-preserving Gaussian process regression: A modular approach to the application of homomorphic encryption","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Fenner","year":"2020"},{"key":"2026100903592986500_bib13","doi-asserted-by":"crossref","first-page":"857","DOI":"10.2307\/2528823","article-title":"A general coefficient of similarity and some of its properties","volume":"27","author":"Gower","year":"1971","journal-title":"Biometrics"},{"key":"2026100903592986500_bib14","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/0024-3795(85)90187-9","article-title":"Properties of Euclidean and non-Euclidean distance matrices","volume":"67","author":"Gower","year":"1985","journal-title":"Linear Algebra and its Applications"},{"key":"2026100903592986500_bib15","doi-asserted-by":"crossref","first-page":"8091","DOI":"10.1007\/s11042-020-10139-6","article-title":"A review on genetic algorithm: Past, present, and future","volume":"80","author":"Katoch","year":"2021","journal-title":"Multimedia Tools and Applications"},{"key":"2026100903592986500_bib16","doi-asserted-by":"publisher","DOI":"10.17632\/b4dmjzk8w6.1","article-title":"List of Organic Solvents with Information about Hansen Solubility Parameter, Solvent-Properties, Hazardousness and Cost-Analysis","volume-title":"Mendeley Data","author":"Langner","year":"2022"},{"key":"2026100903592986500_bib17","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4020-6291-9","volume-title":"An Introduction To Chemoinformatics","author":"Leach","year":"2007"},{"key":"2026100903592986500_bib18","first-page":"1","article-title":"Bayesian multi-group Gaussian process models for heterogeneous group-structured data","volume":"26","author":"Li","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"2026100903592986500_bib19","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1023\/A:1019154432472","article-title":"A proof of the triangle inequality for the Tanimoto distance","volume":"26","author":"Lipkus","year":"1999","journal-title":"Journal of Mathematical Chemistry"},{"key":"2026100903592986500_bib20","article-title":"Gaussian process molecule property prediction with FlowMO","volume-title":"Machine Learning for Molecules Workshop at NeurIPS 2020, Neural Iformation Processing Systems","author":"Moss","year":"2020"},{"key":"2026100903592986500_bib21","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/S0167-9473(99)00073-0","article-title":"A Monte Carlo EM method for estimating multinomial probit models","volume":"34","author":"Natarajan","year":"2000","journal-title":"Computational Statistics and Data Analysis"},{"key":"2026100903592986500_bib22","article-title":"CheMixNet: Mixed DNN architectures for predicting chemical properties using multiple molecular representations","volume-title":"Workshop on Machine Learning for Molecules and Materials, 32nd Conference on Neural Information Processing Systems (NeurIPS)","author":"Paul","year":"2018"},{"key":"2026100903592986500_bib23","volume-title":"geoR: Analysis of Geostatistical Data","author":"Ribeiro","year":"2024"},{"key":"2026100903592986500_bib24","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/S0098-3004(98)00020-X","article-title":"An algorithm for the construction of spatial coverage designs with implementation in S-PLUS","volume":"24","author":"Royle","year":"1998","journal-title":"Computers and Geosciences"},{"key":"2026100903592986500_bib25","doi-asserted-by":"crossref","first-page":"1379","DOI":"10.1016\/j.chempr.2020.02.017","article-title":"A structure-based platform for predicting chemical reactivity","volume":"6","author":"Sandfort","year":"2020","journal-title":"Chem"},{"key":"2026100903592986500_bib26","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1111\/j.2517-6161.1995.tb02060.x","article-title":"Laplace approximation of high dimensional integrals","volume":"57","author":"Shun","year":"1995","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"key":"2026100903592986500_bib27","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1080\/02664769300000013","article-title":"Hitch-hiker\u2019s guide to genetic algorithms","volume":"20","author":"South","year":"1993","journal-title":"Journal of Applied Statistics"},{"key":"2026100903592986500_bib28","doi-asserted-by":"crossref","first-page":"i359","DOI":"10.1093\/bioinformatics\/bti1055","article-title":"Kernels for small molecules and the prediction of mutagenicity, toxicity and anti-cancer activity","volume":"21","author":"Swamidass","year":"2005","journal-title":"Bioinformatics (Oxford, England)"},{"key":"2026100903592986500_bib29","doi-asserted-by":"crossref","first-page":"3230","DOI":"10.1038\/s41467-020-17035-5","article-title":"Representation of molecular structures with persistent homology for machine learning applications in chemistry","volume":"11","author":"Townsend","year":"2020","journal-title":"Nature Communications"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/4\/ujag168\/71761842\/ujag168.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/4\/ujag168\/71761842\/ujag168.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T07:59:40Z","timestamp":1791532780000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujag168\/8894036"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":29,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,10,7]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujag168","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,12]]},"published":{"date-parts":[[2026,10,7]]},"article-number":"ujag168"}}