{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:37:26Z","timestamp":1785411446440,"version":"3.56.0"},"posted":{"date-parts":[[2025,11,22]]},"group-title":"Bioinformatics","reference-count":95,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R35GM150620"],"award-info":[{"award-number":["R35GM150620"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/010r6td27","id-type":"ROR","asserted-by":"publisher"}]},{"name":"enter for Advanced Computing (CAC) at Queen\u2019s University"},{"id":[{"id":"https:\/\/ror.org\/01gavpb45","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/04j5jqy92","id-type":"ROR","asserted-by":"publisher"}]},{"id":[{"id":"https:\/\/ror.org\/04j5jqy92","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,11,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  <jats:monospace>Selector<\/jats:monospace>\n                  is a free, open-source Python library for selecting diverse subsets from any dataset, making it a versatile tool across a wide range of application domains.\n                  <jats:monospace>Selector<\/jats:monospace>\n                  implements different subset sampling algorithms based on sample distance, similarity, and spatial partitioning, along with metrics to quantify subset diversity. It is flexible and integrates seamlessly with popular Python libraries like\n                  <jats:monospace>Scikit-Learn<\/jats:monospace>\n                  , demonstrating the interoperability of the implemented algorithms with data analysis workflows.\n                  <jats:monospace>Selector<\/jats:monospace>\n                  is an operating-system agnostic, accessible, and easily extensible package designed with modern software development practices, including version control, unit testing, and continuous integration. Interactive quick-start notebooks, which are also web-accessible, provide user-friendly tutorials for all skill levels, showcasing applications in computational chemistry, drug discovery, and chemical library design. Additionally, a web interface has been developed that allows users to easily upload datasets, configure sampling settings, and run subset selection algorithms, with no programming required. This paper serves as the official release note for the\n                  <jats:monospace>Selector<\/jats:monospace>\n                  package, offering a technical overview of its features, use cases, and development practices that ensure its quality and maintainability.\n                <\/jats:p>","DOI":"10.1101\/2025.11.21.689756","type":"posted-content","created":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T03:05:21Z","timestamp":1763867121000},"source":"Crossref","is-referenced-by-count":0,"title":["Selector: A General Python Library for Diverse Subset Selection"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2886-7012","authenticated-orcid":false,"given":"Fanwang","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco Mart\u00ednez","family":"Gonz\u00e1lez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9360-2485","authenticated-orcid":false,"given":"Valerii","family":"Chuiko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alireza","family":"Tehrani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul Rahman","family":"Al Nabulsi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abigail","family":"Broscius","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hasan","family":"Khaleel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4401-0089","authenticated-orcid":false,"given":"Kenneth","family":"L\u00f3pez-P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2121-4449","authenticated-orcid":false,"given":"Ram\u00f3n Alain","family":"Miranda-Quintana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2605-3883","authenticated-orcid":false,"given":"Paul W.","family":"Ayers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2069-050X","authenticated-orcid":false,"given":"Farnaz","family":"Heidar-Zadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025112503350444000_2025.11.21.689756v1.1","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1007\/BF00031692","article-title":"On sampling procedures in population and community ecology","volume":"83","year":"1989","journal-title":"Vegetatio"},{"key":"2025112503350444000_2025.11.21.689756v1.2","doi-asserted-by":"crossref","first-page":"2913","DOI":"10.1007\/s10531-004-0224-z","article-title":"An ED-based Protocol for Optimal Sampling of Biodiversity","volume":"14","year":"2005","journal-title":"Biodiversity & Conservation"},{"key":"2025112503350444000_2025.11.21.689756v1.3","doi-asserted-by":"publisher","DOI":"10.1890\/04-0576"},{"key":"2025112503350444000_2025.11.21.689756v1.4","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1002\/wcms.33","article-title":"Diversity Selection Algorithms","volume":"1","year":"2011","journal-title":"WIREs Computational Molecular Science"},{"key":"2025112503350444000_2025.11.21.689756v1.5","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1021\/ci9700337","article-title":"Stochastic algorithms for maximizing molecular diversity","volume":"37","year":"1997","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"2025112503350444000_2025.11.21.689756v1.6","doi-asserted-by":"crossref","unstructured":"Liu, H. ; Yucel, B. ; Ganapathysubramanian, B. ; Kalidindi, S. R. ; Wheeler, D. ; Wodo, O. Active learning for regression of structure\u2013property mapping: the importance of sampling and representation. Digital Discovery 2024, \u2013.","DOI":"10.1039\/D4DD00073K"},{"key":"2025112503350444000_2025.11.21.689756v1.7","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2111786119"},{"key":"2025112503350444000_2025.11.21.689756v1.8","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1021\/ci025662h","article-title":"OptDesign: extending optimizable k-dissimilarity selection to combinatorial library design","volume":"43","year":"2003","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"2025112503350444000_2025.11.21.689756v1.9","doi-asserted-by":"crossref","first-page":"1966","DOI":"10.1021\/acs.jcim.3c01674","article-title":"Exploiting Vector Pattern Diversity of Molecular Scaffolds for Cheminformatics Tasks in Drug Discovery","volume":"64","year":"2024","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2025112503350444000_2025.11.21.689756v1.10","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01790"},{"key":"2025112503350444000_2025.11.21.689756v1.11","first-page":"344","article-title":"Sample-Size Determination Methodologies for Machine Learning in Medical Imaging Research: A Systematic Review","volume":"70","year":"2020","journal-title":"Canadian Association of Radiologists Journal"},{"key":"2025112503350444000_2025.11.21.689756v1.12","doi-asserted-by":"publisher","DOI":"10.1140\/epjb\/s10051-021-00220-w"},{"key":"2025112503350444000_2025.11.21.689756v1.13","first-page":"2320","article-title":"Stratified Sampling Meets Machine Learning","volume":"48","year":"2016","journal-title":"Proceedings of The 33rd International Conference on Machine Learning"},{"key":"2025112503350444000_2025.11.21.689756v1.14","first-page":"339","volume-title":"In 3D QSAR in Drug Design","volume":"2","year":"2002"},{"key":"2025112503350444000_2025.11.21.689756v1.15","doi-asserted-by":"crossref","first-page":"W78","DOI":"10.1093\/nar\/gkad380","article-title":"ChemMaps.com v2.0: exploring the environmental chemical universe","volume":"51","year":"2023","journal-title":"Nucleic Acids Research"},{"key":"2025112503350444000_2025.11.21.689756v1.16","doi-asserted-by":"crossref","unstructured":"Naveja-Romero, J. ; Saldivar-Gonzalez, F. I. ; Prado-Romero, D. L. ; Ruiz-Moreno, A. J. ; Velasco-Velazquez, M. ; Miranda-Quintana, R. A. ; Medina-Franco, J. L. ViSAS for Entering Chemical Space: Virtual Screening of Analog Series and Related Advances. 2022.","DOI":"10.26434\/chemrxiv-2022-9t2rj"},{"key":"2025112503350444000_2025.11.21.689756v1.17","doi-asserted-by":"publisher","DOI":"10.1021\/cc0000388"},{"key":"2025112503350444000_2025.11.21.689756v1.18","doi-asserted-by":"crossref","first-page":"22790","DOI":"10.1021\/acs.jpcc.8b08063","article-title":"Toward Reliable and Transferable Machine Learning Potentials: Uniform Training by Overcoming Sampling Bias","volume":"122","year":"2018","journal-title":"The Journal of Physical Chemistry C"},{"key":"2025112503350444000_2025.11.21.689756v1.19","first-page":"151","article-title":"A Review on Optimal Subsampling Methods for Massive Datasets","volume":"19","year":"2021","journal-title":"Journal of Data Science"},{"key":"2025112503350444000_2025.11.21.689756v1.20","doi-asserted-by":"crossref","first-page":"e48476","DOI":"10.1371\/journal.pone.0048476","article-title":"Inside the Mind of a Medicinal Chemist: The Role of Human Bias in Compound Prioritization during Drug Discovery","volume":"7","year":"2012","journal-title":"PLoS ONE"},{"key":"2025112503350444000_2025.11.21.689756v1.21","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat2663"},{"key":"2025112503350444000_2025.11.21.689756v1.22","doi-asserted-by":"crossref","first-page":"2300056","DOI":"10.1002\/minf.202300056","article-title":"Exploring activity landscapes with extended similarity: is Tanimoto enough?","volume":"42","year":"2023","journal-title":"Molecular Informatics"},{"key":"2025112503350444000_2025.11.21.689756v1.23","doi-asserted-by":"publisher","DOI":"10.1021\/ci060117s"},{"key":"2025112503350444000_2025.11.21.689756v1.24","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01073"},{"key":"2025112503350444000_2025.11.21.689756v1.25","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c00433"},{"key":"2025112503350444000_2025.11.21.689756v1.26","doi-asserted-by":"crossref","first-page":"144108","DOI":"10.1063\/5.0166172","article-title":"Vendi sampling for molecular simulations: Diversity as a force for faster convergence and better exploration","volume":"159","year":"2023","journal-title":"The Journal of Chemical Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/nmat4717"},{"key":"2025112503350444000_2025.11.21.689756v1.28","doi-asserted-by":"crossref","unstructured":"Schwalbe-Koda, R. ; Gomez-Bombarelli, R. In Machine Learning Meets Quantum Physics; Schutt, K. , Chmiela, S. , Von Lilienfeld, O. A. , Tkatchenko, A. , Tsuda, A. , Muller, K.-R. , Eds.; Springer, 2020; pp 445\u2013467.","DOI":"10.1007\/978-3-030-40245-7_21"},{"key":"2025112503350444000_2025.11.21.689756v1.29","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic Chemical Design Using a DataDriven Continuous Representation of Molecules","volume":"4","year":"2018","journal-title":"ACS Central Science"},{"key":"2025112503350444000_2025.11.21.689756v1.30","doi-asserted-by":"crossref","first-page":"7079","DOI":"10.1039\/D1SC00231G","article-title":"Beyond generative models: superfast traversal, optimization, novelty, exploration and discovery (STONED) algorithm for molecules using SELFIES","volume":"12","year":"2021","journal-title":"Chemical Science"},{"key":"2025112503350444000_2025.11.21.689756v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/S1367-5931(99)80051-9"},{"key":"2025112503350444000_2025.11.21.689756v1.32","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/S1093-3263(00)00072-3","article-title":"Combinatorial library design for diversity, cost efficiency, and drug-like character","volume":"18","year":"2000","journal-title":"Journal of Molecular Graphics and Modelling"},{"key":"2025112503350444000_2025.11.21.689756v1.33","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1186\/s13321-021-00498-z","article-title":"Diversity oriented deep reinforcement learning for targeted molecule generation","volume":"13","year":"2021","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.34","doi-asserted-by":"crossref","first-page":"bbae174","DOI":"10.1093\/bib\/bbae174","article-title":"Guided diffusion for molecular generation with interaction prompt","volume":"25","year":"2024","journal-title":"Briefings in Bioinformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.35","doi-asserted-by":"crossref","first-page":"7526","DOI":"10.1039\/D2SC00821A","article-title":"Graph-based molecular Pareto optimisation","volume":"13","year":"2022","journal-title":"Chemical Science"},{"key":"2025112503350444000_2025.11.21.689756v1.36","first-page":"035008","article-title":"Curiosity in exploring chemical spaces: intrinsic rewards for molecular reinforcement learning","volume":"3","year":"2022","journal-title":"Machine Learning: Science and Technology"},{"key":"2025112503350444000_2025.11.21.689756v1.37","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S1093-3263(98)80008-9","article-title":"DISSIM: a program for the analysis of chemical diversity","volume":"16","year":"1998","journal-title":"Journal of Molecular Graphics and Modelling"},{"key":"2025112503350444000_2025.11.21.689756v1.38","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1016\/S1093-3263(98)00008-4","article-title":"Comparison of algorithms for dissimilarity-based compound selection","volume":"15","year":"1997","journal-title":"Journal of Molecular Graphics and Modelling"},{"key":"2025112503350444000_2025.11.21.689756v1.39","doi-asserted-by":"crossref","first-page":"657","DOI":"10.3390\/70800657","article-title":"DivCalc: A Utility for Diversity Analysis and Compound Sampling","volume":"7","year":"2002","journal-title":"Molecules"},{"key":"2025112503350444000_2025.11.21.689756v1.40","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v028.i08"},{"key":"2025112503350444000_2025.11.21.689756v1.41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2015.08.010","article-title":"PKOM: A tool for clustering, analysis and comparison of big chemical collections","volume":"48","year":"2016","journal-title":"Digital Signal Processing"},{"key":"2025112503350444000_2025.11.21.689756v1.42","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1038\/s41598-022-04967-9","article-title":"Selecting molecules with diverse structures and properties by maximizing submodular functions of descriptors learned with graph neural networks","volume":"12","year":"2022","journal-title":"Scientific reports"},{"key":"2025112503350444000_2025.11.21.689756v1.43","doi-asserted-by":"crossref","first-page":"5996","DOI":"10.21105\/joss.05996","article-title":"Machine Learning Validation via Rational Dataset Sampling with astartes","volume":"8","year":"2023","journal-title":"Journal of Open Source Software"},{"key":"2025112503350444000_2025.11.21.689756v1.44","first-page":"1241","article-title":"Effect of information leakage and method of splitting (rational and random) on external predictive ability and behavior of different statistical parameters of QSAR model","volume":"24","year":"2014","journal-title":"Medicinal Chemistry Research"},{"key":"2025112503350444000_2025.11.21.689756v1.45","doi-asserted-by":"publisher","DOI":"10.2307\/1266770"},{"key":"2025112503350444000_2025.11.21.689756v1.46","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1021\/ci970282v","article-title":"OptiSim: an extended dissimilarity selection method for finding diverse representative subsets","volume":"37","year":"1997","journal-title":"Journal of Chemical Information and Computer Sciences"},{"key":"2025112503350444000_2025.11.21.689756v1.47","first-page":"1","article-title":"The chemfp project","volume":"11","year":"2019","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.48","first-page":"31","article-title":"RDKit: A software suite for Cheminformatics, computational chemistry, and predictive modeling","volume":"8","year":"2013","journal-title":"Greg Landrum"},{"key":"2025112503350444000_2025.11.21.689756v1.49","first-page":"8219","article-title":"Comprehensive survey on hierarchical clustering algorithms and the recent developments","volume":"56","year":"2022","journal-title":"Artificial Intelligence Review"},{"key":"2025112503350444000_2025.11.21.689756v1.50","first-page":"1","article-title":"Scalable estimator of the diversity for de novo molecular generation resulting in a more robust QM dataset (OD9) and a more efficient molecular optimization","volume":"13","year":"2021","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.51","doi-asserted-by":"crossref","first-page":"162501","DOI":"10.1063\/5.0196638","article-title":"The tale of HORTON: Lessons learned in a decade of scientific software development","volume":"160","year":"2024","journal-title":"The Journal of Chemical Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.52","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1002\/jcc.26468","article-title":"IOData: A python library for reading, writing, and converting computational chemistry file formats and generating input files","volume":"42","year":"2021","journal-title":"Journal of Computational Chemistry"},{"key":"2025112503350444000_2025.11.21.689756v1.53","doi-asserted-by":"crossref","first-page":"172503","DOI":"10.1063\/5.0202240","article-title":"Grid: A Python library for molecular integration, interpolation, differentiation, and more","volume":"160","year":"2024","journal-title":"The Journal of Chemical Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.54","doi-asserted-by":"crossref","first-page":"042503","DOI":"10.1063\/5.0216776","article-title":"GBasis: A Python library for evaluating functions, functionals, and integrals expressed with Gaussian basis functions","volume":"161","year":"2024","journal-title":"The Journal of Chemical Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.55","doi-asserted-by":"crossref","unstructured":"Pujal, L. ; Tehrani, A. ; Heidar-Zadeh, F. Conceptual Density Functional Theory; John Wiley & Sons, Ltd, 2022; Chapter 32, pp 649\u2013661.","DOI":"10.1002\/9783527829941.ch32"},{"key":"2025112503350444000_2025.11.21.689756v1.56","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.cplett.2016.07.039","article-title":"An explicit approach to conceptual density functional theory descriptors of arbitrary order","volume":"660","year":"2016","journal-title":"Chemical Physics Letters"},{"key":"2025112503350444000_2025.11.21.689756v1.57","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1002\/jcc.27034","article-title":"Fanpy: A python library for prototyping multideterminant methods in ab initio quantum chemistry","volume":"44","year":"2023","journal-title":"Journal of Computational Chemistry"},{"key":"2025112503350444000_2025.11.21.689756v1.58","doi-asserted-by":"crossref","first-page":"072501","DOI":"10.1063\/5.0216781","article-title":"CuGBasis: High-performance CUDA\/Python library for efficient computation of quantum chemistry density-based descriptors for larger systems","volume":"161","year":"2024","journal-title":"The Journal of Chemical Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.59","doi-asserted-by":"crossref","unstructured":"Chuiko, V. ; Richards, A. ; Sanchez-Diaz, G. ; Martinez-Gonzalez, M. ; Sanchez, W. ; Rosa, G. B. D. ; Richer, M. ; Zhao, Y. ; Adams, W. ; Johnson, P. ; Heidar-Zadeh, F. ; ; Ayers, P. ModelHamiltonian: A Python-scriptable library for generating 0-, 1-, and 2-electron integrals. The Journal of Chemical Physics 2024, submitted JCP24-SW-MIS2023-02100, \u2013.","DOI":"10.1063\/5.0219015"},{"key":"2025112503350444000_2025.11.21.689756v1.60","doi-asserted-by":"crossref","unstructured":"Richer, M. ; S\u00e1nchez-D\u00edaz, G. ; Mart\u00ednez-Gonz\u00e1lez, M. ; Chuiko, V. ; Kim, T. D. ; Tehrani, A. ; Wang, S. ; Gaikwad, P. B. ; de Moura, C. E. V. ; Masschelein, C. ; Miranda-Quintana, R. A. ; Gerolin, A. ; Heidar-Zadeh, F. ; Ayers, P. W. PyCI: A Python-scriptable library for arbitrary determinant CI. The Journal of Chemical Physics 2024, submitted JCP24-SW-MIS2023-02097R, \u2013.","DOI":"10.1063\/5.0219010"},{"key":"2025112503350444000_2025.11.21.689756v1.61","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-D\u00edaz, G. ; Richer, M. ; Mart\u00ednez-Gonz\u00e1lez, M. ; van Zyl, M. ; Pujal, L. ; Tehrani, A. ; Bianchi, J. ; Chuiko, V. ; Erhard, J. ; Ayers, P. W. ; Heidar-Zadeh, F. AtomDB: A Python Library for Atomic and Promolecular Properties. The Journal of Chemical Physics 2024, submitted.","DOI":"10.1021\/acs.jpca.4c07353"},{"key":"2025112503350444000_2025.11.21.689756v1.62","doi-asserted-by":"crossref","first-page":"1998","DOI":"10.1002\/jcc.27170","article-title":"An Information-Theoretic Approach to Basis-Set Fitting of Electron Densities and Other Non-Negative Functions","volume":"44","year":"2023","journal-title":"Journal of Computational Chemistry"},{"key":"2025112503350444000_2025.11.21.689756v1.63","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2022.108334"},{"key":"2025112503350444000_2025.11.21.689756v1.64","doi-asserted-by":"crossref","unstructured":"Lee, B. D. Ten simple rules for documenting scientific software. 2018.","DOI":"10.1371\/journal.pcbi.1006561"},{"key":"2025112503350444000_2025.11.21.689756v1.65","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"2025112503350444000_2025.11.21.689756v1.66","unstructured":"Krekel, H. ; Oliveira Pfannschmidt, R. ; Bruynooghe, F. ; Laugher, B. ; Bruhin, F. pytest 8.4.0. https:\/\/github.com\/pytest-dev\/pytest, 2004; Version 8.4.0 Contributors include Holger Krekel, Bruno Oliveira, Ronny Pfannschmidt, Floris Bruynooghe, Brianna Laugher, Florian Bruhin, and others."},{"key":"2025112503350444000_2025.11.21.689756v1.67","doi-asserted-by":"publisher","DOI":"10.1089\/106652799318382"},{"key":"2025112503350444000_2025.11.21.689756v1.68","doi-asserted-by":"crossref","unstructured":"Willett, P. Subset-Selection Methods For Chemical Databases: Methods for Subset Selection. Molecular Diversity in Drug Design 2002, 115\u2013140.","DOI":"10.1007\/0-306-46873-5_6"},{"key":"2025112503350444000_2025.11.21.689756v1.69","doi-asserted-by":"publisher","DOI":"10.1021\/ci025554v"},{"key":"2025112503350444000_2025.11.21.689756v1.70","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s13321-021-00505-3","article-title":"Extended similarity indices: the benefits of comparing more than two objects simultaneously. Part 1: Theory and characteristics","volume":"13","year":"2021","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.71","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13321-021-00504-4","article-title":"Extended similarity indices: the benefits of comparing more than two objects simultaneously. Part 2: speed, consistency, diversity selection","volume":"13","year":"2021","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.72","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1039\/D4DD00041B","article-title":"iSIM: instant similarity","volume":"3","year":"2024","journal-title":"Digital Discovery"},{"key":"2025112503350444000_2025.11.21.689756v1.73","doi-asserted-by":"crossref","first-page":"6303","DOI":"10.1021\/acs.jctc.4c00362","article-title":"Protein Retrieval via Integrative Molecular Ensembles (PRIME) through Extended Similarity Indices","volume":"20","year":"2024","journal-title":"Journal of Chemical Theory and Computation"},{"key":"2025112503350444000_2025.11.21.689756v1.74","first-page":"1","article-title":"Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?","volume":"7","year":"2015","journal-title":"Journal of Cheminformatics"},{"key":"2025112503350444000_2025.11.21.689756v1.75","doi-asserted-by":"publisher","DOI":"10.1198\/004017002317375064"},{"key":"2025112503350444000_2025.11.21.689756v1.76","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python","volume":"17","year":"2020","journal-title":"Nature Methods"},{"key":"2025112503350444000_2025.11.21.689756v1.77","first-page":"2825","article-title":"Scikit-Learn: Machine Learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2025112503350444000_2025.11.21.689756v1.78","first-page":"1","article-title":"More on multidimensional scaling and unfolding in R: smacof version 2","volume":"102","year":"2022","journal-title":"Journal of Statistical Software"},{"key":"2025112503350444000_2025.11.21.689756v1.79","doi-asserted-by":"publisher","DOI":"10.1021\/ci900159f"},{"key":"2025112503350444000_2025.11.21.689756v1.80","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1021\/ci060074f","article-title":"Explicit Diversity Index (EDI): a novel measure for assessing the diversity of compound databases","volume":"46","year":"2006","journal-title":"Journal of Chemical Information and Modeling"},{"key":"2025112503350444000_2025.11.21.689756v1.81","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1002\/jcc.24423","article-title":"Using the Gini coefficient to measure the chemical diversity of small-molecule libraries","volume":"37","year":"2016","journal-title":"Journal of Computational Chemistry"},{"key":"2025112503350444000_2025.11.21.689756v1.82","doi-asserted-by":"crossref","unstructured":"Dral, P. O. ; Owens, A. ; Dral, A. ; Cs\u00e1nyi, G. Hierarchical machine learning of potential energy surfaces. The Journal of Chemical Physics 2020, 152.","DOI":"10.1063\/5.0006498"},{"key":"2025112503350444000_2025.11.21.689756v1.83","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1016\/j.chempr.2020.05.014","article-title":"Learning to Make Chemical Predictions: The Interplay of Feature Representation, Data, and Machine Learning Methods","volume":"6","year":"2020","journal-title":"Chem"},{"key":"2025112503350444000_2025.11.21.689756v1.84","doi-asserted-by":"crossref","unstructured":"Nandi, A. ; Qu, C. ; Houston, P. L. ; Conte, R. ; Bowman, J. M. ? -machine learning for potential energy surfaces: A PIP approach to bring a DFT-based PES to CCSD(T) level of theory. The Journal of Chemical Physics 2021, 154.","DOI":"10.1063\/5.0038301"},{"key":"2025112503350444000_2025.11.21.689756v1.85","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1039\/D2DD00008C","article-title":"NewtonNet: a Newtonian message passing network for deep learning of interatomic potentials and forces","volume":"1","year":"2022","journal-title":"Digital Discovery"},{"key":"2025112503350444000_2025.11.21.689756v1.86","doi-asserted-by":"crossref","unstructured":"Anstine, D. ; Zubatyuk, R. ; Isayev, O. AIMNet2: A Neural Network Potential to Meet your Neutral, Charged, Organic, and Elemental-Organic Needs. ChemRxiv 2024,","DOI":"10.26434\/chemrxiv-2023-296ch-v3"},{"key":"2025112503350444000_2025.11.21.689756v1.87","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1038\/s43588-023-00561-9","article-title":"Recent advances and outstanding challenges for machine learning interatomic potentials","volume":"3","year":"2023","journal-title":"Nature Computational Science"},{"key":"2025112503350444000_2025.11.21.689756v1.88","doi-asserted-by":"crossref","first-page":"1613","DOI":"10.1021\/acs.jpca.8b12005","article-title":"Global Potential Energy Surface for HO2+ Using the CHIPR Method","volume":"123","year":"2019","journal-title":"The Journal of Physical Chemistry A"},{"key":"2025112503350444000_2025.11.21.689756v1.89","doi-asserted-by":"crossref","unstructured":"Alves, M. O. ; Gon\u00e7alves, C. E. M. ; Braga, J. P. ; Mota, V. C. ; Varandas, A. J. C. ; Galv\u00e3o, B. R. L. Accurate DMBE potential-energy surface for CNO(2A\u201d) and rate coefficients in C(3P)+NO collisions. The Journal of Chemical Physics 2021, 154.","DOI":"10.1063\/5.0031199"},{"key":"2025112503350444000_2025.11.21.689756v1.90","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1038\/s41597-022-01330-5","article-title":"A benchmark dataset for Hydrogen Combustion","volume":"9","year":"2022","journal-title":"Scientific Data"},{"key":"2025112503350444000_2025.11.21.689756v1.91","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1080\/00268970500460390","article-title":"A Hamilton\u2013Jacobi type equation for computing minimum potential energy paths","volume":"104","year":"2006","journal-title":"Molecular Physics"},{"key":"2025112503350444000_2025.11.21.689756v1.92","unstructured":"Liu, Y. L. ; Burger, S. K. ; Dey, B. K. ; Sarkar, U. ; Janicki, M. ; Ayers, P. W. In Quantum Biochemistry; Matta, C. F. , Ed.; Wiley-VCH: Boston, 2010."},{"key":"2025112503350444000_2025.11.21.689756v1.93","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01073"},{"key":"2025112503350444000_2025.11.21.689756v1.94","unstructured":"Wang, P. ; Shen, Y. ; Guo, Z. ; Stallone, M. ; Kim, Y. ; Golland, P. ; Panda, R. Diversity Measurement and Subset Selection for Instruction Tuning Datasets. 2024; https:\/\/arxiv.org\/abs\/2402.02318."},{"key":"2025112503350444000_2025.11.21.689756v1.95","unstructured":"Meng, F. ; Gonz\u00e1lez, M. M. ; Chuiko, V. ; Tehrani, A. ; Nabulsi, A. R. A. ; Broscius, A. ; Khaleel, H. ; L\u00f3pez-P\u00e9rez, K. ; Miranda-Quintana, R. A. ; Ayers, P. W. ; Zadeh, F. H. Codes and Data for Generating Figures of Selector Paper. 2024,"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.11.21.689756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:06:22Z","timestamp":1782277582000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.11.21.689756"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":95,"URL":"https:\/\/doi.org\/10.1101\/2025.11.21.689756","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1021\/acs.jcim.5c01499","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2025,11,22]]},"subtype":"preprint"}}