{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T12:46:39Z","timestamp":1792154799891,"version":"4.4.0"},"reference-count":53,"publisher":"Royal Society of Chemistry (RSC)","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":279,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R35GM150620"],"award-info":[{"award-number":["R35GM150620"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["rsc.org"],"crossmark-restriction":true},"short-container-title":["Digital Discovery"],"abstract":"<jats:p>We present BitBIRCH-Lean, a fast, memory-efficient implementation of the BitBIRCH algorithm, designed for high-throughput clustering of huge molecular libraries (up to billions of drug-like molecules) on modern scientific workstations.<\/jats:p>","DOI":"10.1039\/d5dd00493d","type":"journal-article","created":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T09:41:37Z","timestamp":1791452497000},"update-policy":"https:\/\/doi.org\/10.1039\/rsc_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Commit: BitBIRCH: efficient clustering of large molecular libraries"],"prefix":"10.1039","author":[{"given":"Ignacio","family":"Pickering","sequence":"first","affiliation":[{"name":"Department of Chemistry & Quantum Theory Project, University of Florida, Gainesville, Florida 32611, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4394-8023","authenticated-orcid":false,"given":"Krisztina","family":"Zsigmond","sequence":"additional","affiliation":[{"name":"Department of Chemistry & Quantum Theory Project, University of Florida, Gainesville, Florida 32611, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth L\u00f3pez","family":"P\u00e9rez","sequence":"additional","affiliation":[{"name":"Department of Chemistry & Quantum Theory Project, University of Florida, Gainesville, Florida 32611, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"L\u017ei\u010da\u0159","sequence":"additional","affiliation":[{"name":"Deep MedChem a.s., Revolu\u010dn\u00ed 764\/17, Prague 1 - Old Town, Czechia"}],"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":[{"name":"Department of Chemistry & Quantum Theory Project, University of Florida, Gainesville, Florida 32611, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"292","published-online":{"date-parts":[[2026]]},"reference":[{"key":"D5DD00493D\/cit1\/1","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1007\/s11030-006-9041-5","volume":"10","author":"Hassan","year":"2006","journal-title":"Mol. Diversity"},{"key":"D5DD00493D\/cit2\/1","first-page":"1","volume-title":"Reviews in Computational Chemistry","author":"Downs","year":"2002","unstructured":"G. M.Downs  and  J. M.Barnard ,  Reviews in Computational Chemistry ,  John Wiley & Sons, Ltd ,  2002 ,  pp. 1\u201340"},{"key":"D5DD00493D\/cit3\/1","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1021\/jm00269a004","volume":"16","author":"Hansch","year":"1973","journal-title":"J. Med. Chem."},{"key":"D5DD00493D\/cit4\/1","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/S1359-6446(05)03419-7","volume":"10","author":"Koch","year":"2005","journal-title":"Drug Discovery Today"},{"key":"D5DD00493D\/cit5\/1","doi-asserted-by":"crossref","first-page":"5583","DOI":"10.1021\/acs.jctc.4c00308","volume":"20","author":"Chen","year":"2024","journal-title":"J. Chem. Theory Comput."},{"key":"D5DD00493D\/cit6\/1","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1021\/ct700119m","volume":"3","author":"Shao","year":"2007","journal-title":"J. Chem. Theory Comput."},{"key":"D5DD00493D\/cit7\/1","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1021\/ci970056l","volume":"38","author":"Reynolds","year":"1998","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"D5DD00493D\/cit8\/1","doi-asserted-by":"crossref","first-page":"105113","DOI":"10.1016\/j.apgeochem.2021.105113","volume":"135","author":"Khorshidi","year":"2021","journal-title":"Appl. Geochem."},{"key":"D5DD00493D\/cit9\/1","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1021\/ci049860f","volume":"44","author":"Harper","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"D5DD00493D\/cit10\/1","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1093\/bioinformatics\/btp623","volume":"26","author":"Bouvier","year":"2010","journal-title":"Bioinformatics"},{"key":"D5DD00493D\/cit11\/1","doi-asserted-by":"crossref","first-page":"1537","DOI":"10.1038\/s41467-020-15351-4","volume":"11","author":"Dorrity","year":"2020","journal-title":"Nat. Commun."},{"key":"D5DD00493D\/cit12\/1","volume-title":"The Shape of Chemical Space","author":"Zsigmond","year":"2025","unstructured":"K.Zsigmond ,  A.Surendran ,  L.Chen  and  R. A.Miranda-Quintana ,  The Shape of Chemical Space ,  2025 ,  https:\/\/www.biorxiv.org\/content\/10.1101\/2025.09.23.678151v1 , ISSN: 2692-8205 Pages: 2025.09.23.678151 Section: New Results"},{"key":"D5DD00493D\/cit13\/1","doi-asserted-by":"crossref","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"D5DD00493D\/cit14\/1","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res."},{"key":"D5DD00493D\/cit15\/1","doi-asserted-by":"crossref","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"D5DD00493D\/cit16\/1","author":"Ltd","year":"2025","unstructured":"E.Ltd .,  Enamine REAL Space: Billions of Make-on-Demand Molecules ,  2025 ,  https:\/\/enamine.net\/compound-collections\/real-compounds\/real-space-navigator , Accessed: October 2025"},{"key":"D5DD00493D\/cit17\/1","doi-asserted-by":"crossref","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","volume":"26","author":"Meyers","year":"2021","journal-title":"Drug Discovery Today"},{"key":"D5DD00493D\/cit18\/1","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1080\/14686996.2017.1401424","volume":"18","author":"Yang","year":"2017","journal-title":"Sci. Technol. Adv. Mater."},{"key":"D5DD00493D\/cit19\/1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1109.2378","volume-title":"arXiv","author":"M\u00fcllner","year":"2011","unstructured":"D.M\u00fcllner ,  Modern hierarchical, agglomerative\nclustering algorithms ,  arXiv ,  2011 , preprint, arXiv:1109.2378,  10.48550\/arXiv.1109.2378"},{"key":"D5DD00493D\/cit20\/1","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1002\/widm.53","volume":"2","author":"Murtagh","year":"2012","journal-title":"WIREs Data Mining Knowl. Discov."},{"key":"D5DD00493D\/cit21\/1","doi-asserted-by":"crossref","first-page":"126433","DOI":"10.1016\/j.physa.2021.126433","volume":"585","author":"Tokuda","year":"2022","journal-title":"Phys. A"},{"key":"D5DD00493D\/cit22\/1","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1021\/ci00023a009","volume":"35","author":"Taylor","year":"1995","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"D5DD00493D\/cit23\/1","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1021\/ci9803381","volume":"39","author":"Butina","year":"1999","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"D5DD00493D\/cit24\/1","volume-title":"Innovative Integration of Butina Clustering with Ensemble Learning Techniques for the Refined Pharmacophore Modeling of Apelin Receptor Agonists: A High-Impact Computational Approach","author":"Tran","year":"2024","unstructured":"X.-T. D.Tran ,  T.-L.Phan ,  V.-T.To ,  N.-V. N.Tran ,  N.-N. S.Nguyen ,  D.-N. H.Nguyen ,  N.-T. N.Tran  and  T. N.Truong ,  Innovative Integration of Butina Clustering with Ensemble Learning Techniques for the Refined Pharmacophore Modeling of Apelin Receptor Agonists: A High-Impact Computational Approach ,  2024 ,  https:\/\/chemrxiv.org\/engage\/chemrxiv\/article-details\/65a9771b66c1381729c2d289"},{"key":"D5DD00493D\/cit25\/1","first-page":"949","volume-title":"7th International Forum on Electrical Engineering and Automation (IFEEA)","author":"Deng","year":"2020","unstructured":"D.Deng ,  7th International Forum on Electrical Engineering and Automation (IFEEA) ,  2020 ,  pp. 949\u2013953"},{"issue":"19","key":"D5DD00493D\/cit26\/1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3068335","volume":"42","author":"Schubert","year":"2017","journal-title":"ACM Trans. Database Syst."},{"key":"D5DD00493D\/cit27\/1","first-page":"232","volume-title":"The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014)","author":"Khan","year":"2014","unstructured":"K.Khan ,  S. U.Rehman ,  K.Aziz ,  S.Fong  and  S.Sarasvady ,  The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014) ,  2014 ,  pp. 232\u2013238"},{"key":"D5DD00493D\/cit28\/1","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"Lloyd","year":"1982","journal-title":"IEEE Trans. Inf. Theory"},{"key":"D5DD00493D\/cit29\/1","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem. Inf. Model."},{"key":"D5DD00493D\/cit30\/1","doi-asserted-by":"crossref","first-page":"1042","DOI":"10.1039\/D5DD00030K","volume":"4","author":"P\u00e9rez","year":"2025","journal-title":"Digital Discovery"},{"key":"D5DD00493D\/cit31\/1","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1039\/D4DD00041B","volume":"3","author":"L\u00f3pez-P\u00e9rez","year":"2024","journal-title":"Digital Discovery"},{"key":"D5DD00493D\/cit32\/1","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1186\/s13321-021-00505-3","volume":"13","author":"Miranda-Quintana","year":"2021","journal-title":"J. Cheminf."},{"key":"D5DD00493D\/cit33\/1","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13321-021-00504-4","volume":"13","author":"Miranda-Quintana","year":"2021","journal-title":"J. Cheminf."},{"key":"D5DD00493D\/cit34\/1","doi-asserted-by":"crossref","first-page":"5280","DOI":"10.1021\/acs.jcim.5c00627","volume":"65","author":"L\u00f3pez P\u00e9rez","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"D5DD00493D\/cit35\/1","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1023\/A:1009783824328","volume":"1","author":"Zhang","year":"1997","journal-title":"Data Min. Knowl. Discov."},{"key":"D5DD00493D\/cit36\/1","first-page":"2825","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"D5DD00493D\/cit37\/1","volume-title":"API Design for Machine Learning Software: Experiences from the Scikit-Learn Project","author":"Buitinck","year":"2013","unstructured":"L.Buitinck ,  G.Louppe ,  M.Blondel ,  F.Pedregosa ,  A.Mueller ,  O.Grisel ,  V.Niculae ,  P.Prettenhofer ,  A.Gramfort ,  J.Grobler ,  R.Layton ,  J.Vanderplas ,  A.Joly ,  B.Holt  and  G.Varoquaux ,  API Design for Machine Learning Software: Experiences from the Scikit-Learn Project ,  2013"},{"key":"D5DD00493D\/cit38\/1","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"Hunter","year":"2007","journal-title":"Comput. Sci. Eng."},{"key":"D5DD00493D\/cit39\/1","doi-asserted-by":"crossref","first-page":"861","DOI":"10.21105\/joss.00861","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open Source Softw."},{"key":"D5DD00493D\/cit40\/1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v109.i03","volume":"109","author":"Poli\u010dar","year":"2024","journal-title":"J. Stat. Software"},{"key":"D5DD00493D\/cit41\/1","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1021\/acs.jcim.2c01253","volume":"63","author":"Tingle","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"D5DD00493D\/cit42\/1","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"D5DD00493D\/cit43\/1","volume-title":"nvMolKit: A GPU-accelerated library for computational chemistry","author":"NVIDIA-Digital-Bio","year":"2025","unstructured":"NVIDIA-Digital-Bio ,  nvMolKit: A GPU-accelerated library for computational chemistry ,  GitHub repository ,  2025 ,  https:\/\/github.com\/NVIDIA-Digital-Bio\/nvMolKit"},{"key":"D5DD00493D\/cit44\/1","author":"Jakob","year":"2017","unstructured":"W.Jakob ,  J.Rhinelander  and  D.Moldovan ,  pybind11 \u2013 Seamless operability between C++11 and Python ,  2017 ,  https:\/\/github.com\/pybind\/pybind11"},{"key":"D5DD00493D\/cit45\/1","volume-title":"Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems","author":"Okuta","year":"2017","unstructured":"R.Okuta ,  Y.Unno ,  D.Nishino ,  S.Hido  and  C.Loomis ,  Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems ,  NIPS ,  2017"},{"key":"D5DD00493D\/cit46\/1","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"D5DD00493D\/cit47\/1","volume-title":"RDKit: Open-Source Cheminformatics","author":"Landrum","year":"2006","unstructured":"G.Landrum ,  RDKit: Open-Source Cheminformatics ,  2006"},{"key":"D5DD00493D\/cit48\/1","first-page":"2837","volume":"11","author":"Vinh","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"D5DD00493D\/cit49\/1","first-page":"2579","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"D5DD00493D\/cit50\/1","unstructured":"zswap - ArchWiki ,  https:\/\/wiki.archlinux.org\/title\/Zswap , accessed October 2025"},{"key":"D5DD00493D\/cit51\/1","unstructured":"zswap \u2014 The Linux Kernel documentation ,  https:\/\/www.kernel.org\/doc\/html\/v4.19\/vm\/zswap.html , accessed October 2025"},{"key":"D5DD00493D\/cit52\/1","unstructured":"zram - ArchWiki ,  https:\/\/wiki.archlinux.org\/title\/Zram , accessed October 2025"},{"key":"D5DD00493D\/cit53\/1","unstructured":"zram: Compressed RAM-based block devices \u2014 The Linux Kernel documentation ,  https:\/\/docs.kernel.org\/admin-guide\/blockdev\/zram.html , accessed October 2025"}],"container-title":["Digital Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/pubs.rsc.org\/DD\/article-pdf\/doi\/10.1039\/D5DD00493D\/0\/D5DD00493D.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T11:53:10Z","timestamp":1792151590000},"score":1,"resource":{"primary":{"URL":"http:\/\/pubs.rsc.org\/DD\/article-lookup\/doi\/10.1039\/D5DD00493D"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1039\/d5dd00493d","relation":{},"ISSN":["2635-098X"],"issn-type":[{"value":"2635-098X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}