{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T01:43:50Z","timestamp":1793324630839,"version":"4.5.0"},"posted":{"date-parts":[[2025,10,23]]},"group-title":"Bioinformatics","reference-count":53,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"award":["R35GM150620"],"award-info":[{"award-number":["R35GM150620"]}],"id":[{"id":"https:\/\/ror.org\/01cwqze88","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,10,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  We present BitBIRCH-Lean, a fast, memory-efficient implementation of the Bit-BIRCH algorithm, designed for high-throughput clustering of huge molecular libraries (up to billions of drug-like molecules) on typical workstations. BitBIRCH-Lean considerably improves on the original BitBIRCH implementation by incorporating dynamic types and bit-packed fingerprints inside the clustering tree. Most operations in BitBIRCH-Lean are efficiently performed on compressed data, and optional C++ extension accelerate the bottleneck calculations, providing up to 2X speedup. Benchmark tests against GPU-accelerated methods highlight BitBIRCH-Lean as an efficient alternative for processing vast amounts of molecules. We further demonstrate the versatility of this new package by showcasing a parallel, multi-round variant of the Bit- BIRCH algorithm that exploits the gains in efficiency to cluster hundreds of millions of molecules in minutes, with no loss in cluster quality. The code is freely available at:\n                  <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/mqcomplab\/bblean\">https:\/\/github.com\/mqcomplab\/bblean<\/jats:ext-link>\n                  .\n                <\/jats:p>","DOI":"10.1101\/2025.10.22.684015","type":"posted-content","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T18:00:12Z","timestamp":1761242412000},"source":"Crossref","is-referenced-by-count":3,"title":["BitBIRCH-Lean: chemical space in the palm of your workstation"],"prefix":"10.64898","author":[{"given":"Ignacio","family":"Pickering","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Krisztina","family":"Zsigmond","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kenneth L\u00f3pez","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miroslav","family":"L\u017ei\u010da\u0159","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"}]}],"member":"54368","reference":[{"key":"2025102511550734000_2025.10.22.684015v1.1","doi-asserted-by":"publisher","DOI":"10.1007\/s11030-006-9041-5"},{"key":"2025102511550734000_2025.10.22.684015v1.2","unstructured":"Downs, G. M. ; Barnard, J. M. Reviews in Computational Chemistry ; John Wiley & Sons, Ltd, 2002; pp 1\u201340, Section: 1 eprint: https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/0471433519.ch1."},{"key":"2025102511550734000_2025.10.22.684015v1.3","first-page":"1217","volume-title":"Journal of Medicinal Chemistry","volume":"16","year":"1973"},{"key":"2025102511550734000_2025.10.22.684015v1.4","doi-asserted-by":"publisher","DOI":"10.1016\/S1359-6446(05)03419-7"},{"key":"2025102511550734000_2025.10.22.684015v1.5","first-page":"5583","volume-title":"Journal of Chemical Theory and Computation","volume":"20","year":"2024"},{"key":"2025102511550734000_2025.10.22.684015v1.6","first-page":"2312","volume-title":"Journal of Chemical Theory and Computation","volume":"3","year":"2007"},{"key":"2025102511550734000_2025.10.22.684015v1.7","first-page":"305","volume-title":"Journal of Chemical Information and Computer Sciences","volume":"38","year":"1998"},{"key":"2025102511550734000_2025.10.22.684015v1.8","doi-asserted-by":"crossref","first-page":"105113","DOI":"10.1016\/j.apgeochem.2021.105113","article-title":"Identification of heavy metal pollution sources and its associated risk assessment in an industrial town using the K-means clustering technique","volume":"135","year":"2021","journal-title":"Applied Geochemistry"},{"key":"2025102511550734000_2025.10.22.684015v1.9","first-page":"2145","volume-title":"Journal of Chemical Information and Computer Sciences","volume":"44","year":"2004"},{"key":"2025102511550734000_2025.10.22.684015v1.10","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btp623"},{"key":"2025102511550734000_2025.10.22.684015v1.11","first-page":"1537","volume-title":"Nature Communications","volume":"11","year":"2020"},{"key":"2025102511550734000_2025.10.22.684015v1.12","unstructured":"Zsigmond, K. ; Surendran, A. ; Chen, L. ; Miranda-Quintana, R. A. 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":"2025102511550734000_2025.10.22.684015v1.13","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac956"},{"key":"2025102511550734000_2025.10.22.684015v1.14","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr777"},{"key":"2025102511550734000_2025.10.22.684015v1.15","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad1004"},{"key":"2025102511550734000_2025.10.22.684015v1.16","unstructured":"Ltd., E. Enamine REAL Space: Billions of Make-on-Demand Molecules. 2025; https:\/\/enamine.net\/compound-collections\/real-compounds\/real-space-navigator, Accessed: October 2025."},{"key":"2025102511550734000_2025.10.22.684015v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2021.05.019"},{"key":"2025102511550734000_2025.10.22.684015v1.18","doi-asserted-by":"publisher","DOI":"10.1080\/14686996.2017.1401424"},{"key":"2025102511550734000_2025.10.22.684015v1.19","year":"2011","journal-title":"Modern hierarchical, agglomerative clustering algorithms"},{"key":"2025102511550734000_2025.10.22.684015v1.20","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1002\/widm.53","article-title":"Algorithms for hierarchical clustering: an overview","volume":"2","year":"2012","journal-title":"WIREs Data Mining and Knowledge Discovery"},{"key":"2025102511550734000_2025.10.22.684015v1.21","doi-asserted-by":"crossref","first-page":"126433","DOI":"10.1016\/j.physa.2021.126433","article-title":"Revisiting agglomerative clustering","volume":"585","year":"2022","journal-title":"Physica A: Statistical Mechanics and its Applications"},{"key":"2025102511550734000_2025.10.22.684015v1.22","doi-asserted-by":"publisher","DOI":"10.1021\/ci00023a009"},{"key":"2025102511550734000_2025.10.22.684015v1.23","doi-asserted-by":"publisher","DOI":"10.1021\/ci9803381"},{"key":"2025102511550734000_2025.10.22.684015v1.24","doi-asserted-by":"crossref","unstructured":"Tran, X.-T. D. ; Phan, T.-L. ; To, V.-T. ; Tran, N.-V. N. ; Nguyen, N.-N. S. ; Nguyen, D.N. H. ; Tran, N.-T. N. ; Truong, T. N. Innovative Integration of Butina Cluster-ing 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.","DOI":"10.26434\/chemrxiv-2024-k6wtc"},{"key":"2025102511550734000_2025.10.22.684015v1.25","doi-asserted-by":"crossref","unstructured":"Deng, D. DBSCAN Clustering Algorithm Based on Density. 2020 7th International Forum on Electrical Engineering and Automation (IFEEA). 2020; pp 949\u2013953.","DOI":"10.1109\/IFEEA51475.2020.00199"},{"key":"2025102511550734000_2025.10.22.684015v1.26","first-page":"1","article-title":"DBSCAN Revisited, Re-visited: Why and How You Should (Still) Use DBSCAN","volume":"19","year":"2017","journal-title":"ACM Trans. Database Syst"},{"key":"2025102511550734000_2025.10.22.684015v1.27","doi-asserted-by":"crossref","unstructured":"Khan, K. ; Rehman, S. U. ; Aziz, K. ; Fong, S. ; Sarasvady, S. DBSCAN: Past, present and future. The Fifth International Conference on the Applications of Digital Information and Web Technologies (ICADIWT 2014). 2014; pp 232\u2013238.","DOI":"10.1109\/ICADIWT.2014.6814687"},{"key":"2025102511550734000_2025.10.22.684015v1.28","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"2025102511550734000_2025.10.22.684015v1.29","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"2025102511550734000_2025.10.22.684015v1.30","first-page":"1042","volume-title":"Digital Discovery","volume":"4","year":"2025"},{"key":"2025102511550734000_2025.10.22.684015v1.31","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":"2025102511550734000_2025.10.22.684015v1.32","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\u2020","volume":"13","year":"2021","journal-title":"Journal of Cheminformatics"},{"key":"2025102511550734000_2025.10.22.684015v1.33","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":"2025102511550734000_2025.10.22.684015v1.34","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c00627"},{"key":"2025102511550734000_2025.10.22.684015v1.35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009783824328"},{"key":"2025102511550734000_2025.10.22.684015v1.36","first-page":"2825","article-title":"Scikit-Learn: Machine Learning in Python","volume":"12","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"2025102511550734000_2025.10.22.684015v1.37","unstructured":"Buitinck, L. ; Louppe, G. ; Blondel, M. ; Pedregosa, F. ; Mueller, A. ; Grisel, O. ; Niculae, V. ; Prettenhofer, P. ; Gramfort, A. ; Grobler, J. ; Layton, R. ; Vanderplas, J. ; Joly, A. ; Holt, B. ; Varoquaux, G. API Design for Machine Learning Software: Experiences from the Scikit-Learn Project. 2013."},{"key":"2025102511550734000_2025.10.22.684015v1.38","doi-asserted-by":"publisher","DOI":"10.1109\/mcse.2007.55"},{"key":"2025102511550734000_2025.10.22.684015v1.39","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"2025102511550734000_2025.10.22.684015v1.40","first-page":"1","article-title":"openTSNE: A Modular Python Library for tSNE Dimensionality Reduction and Embedding","volume":"109","year":"2024","journal-title":"Journal of Statistical Software"},{"key":"2025102511550734000_2025.10.22.684015v1.41","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01253"},{"key":"2025102511550734000_2025.10.22.684015v1.42","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2649-2"},{"key":"2025102511550734000_2025.10.22.684015v1.43","unstructured":"NVIDIA-Digital-Bio nvMolKit: A GPU-accelerated library for computational chemistry. 2025; https:\/\/github.com\/NVIDIA-Digital-Bio\/nvMolKit, GitHub repository."},{"key":"2025102511550734000_2025.10.22.684015v1.44","unstructured":"Jakob, W. ; Rhinelander, J. ; Moldovan, D. pybind11 \u2013 Seamless operability between C++11 and Python. 2017; https:\/\/github.com\/pybind\/pybind11."},{"key":"2025102511550734000_2025.10.22.684015v1.45","unstructured":"Okuta, R. ; Unno, Y. ; Nishino, D. ; Hido, S. ; Loomis, C. CuPy: A NumPy-Compatible Library for NVIDIA GPU Calculations. Proceedings of Workshop on Machine Learning Systems (LearningSys) in The Thirty-first Annual Conference on Neural Information Processing Systems (NIPS). 2017."},{"key":"2025102511550734000_2025.10.22.684015v1.46","unstructured":"Paszke, A. ; Gross, S. ; Massa, F. ; Lerer, A. ; Bradbury, J. ; Chanan, G. ; Killeen, T. ; Lin, Z. ; Gimelshein, N. ; Antiga, L. ; others Pytorch: An imperative style, highperformance deep learning library. Advances in neural information processing systems 2019, 32."},{"key":"2025102511550734000_2025.10.22.684015v1.47","unstructured":"Landrum, G. RDKit: Open-Source Cheminformatics. 2006\u20132025."},{"key":"2025102511550734000_2025.10.22.684015v1.48","first-page":"2837","article-title":"Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance","volume":"11","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"2025102511550734000_2025.10.22.684015v1.49","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"2025102511550734000_2025.10.22.684015v1.50","unstructured":"zswap - ArchWiki. https:\/\/wiki.archlinux.org\/title\/Zswap, (accessed October 2025)."},{"key":"2025102511550734000_2025.10.22.684015v1.51","unstructured":"zswap \u2014 The Linux Kernel documentation. https:\/\/www.kernel.org\/doc\/html\/v4.19\/vm\/zswap.html, (accessed October 2025)."},{"key":"2025102511550734000_2025.10.22.684015v1.52","unstructured":"zram - ArchWiki. https:\/\/wiki.archlinux.org\/title\/Zram, (accessed October 2025)."},{"key":"2025102511550734000_2025.10.22.684015v1.53","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":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.10.22.684015","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T09:52:23Z","timestamp":1768470743000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2025.10.22.684015"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1101\/2025.10.22.684015","relation":{},"subject":[],"published":{"date-parts":[[2025,10,23]]},"subtype":"preprint"}}