{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:59:33Z","timestamp":1785340773036,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,30]]},"DOI":"10.1145\/3807503.3819382","type":"proceedings-article","created":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T02:55:27Z","timestamp":1785293727000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Stratified Molecular Data Splitting using Topological Graph Barycenter"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7634-0913","authenticated-orcid":false,"given":"Giuseppe","family":"Albi","sequence":"first","affiliation":[{"name":"University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2870-4935","authenticated-orcid":false,"given":"Giovanni","family":"Sclavi","sequence":"additional","affiliation":[{"name":"University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2857-5773","authenticated-orcid":false,"given":"Alberto","family":"Malovini","sequence":"additional","affiliation":[{"name":"Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8090-9895","authenticated-orcid":false,"given":"Sandra","family":"Atlante","sequence":"additional","affiliation":[{"name":"Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5238-1832","authenticated-orcid":false,"given":"Carlo","family":"Gaetano","sequence":"additional","affiliation":[{"name":"Istituti Clinici Scientifici Maugeri IRCCS, Pavia, Italy and Saint Camillus International University of Health and Medical Sciences, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6974-9808","authenticated-orcid":false,"given":"Riccardo","family":"Bellazzi","sequence":"additional","affiliation":[{"name":"University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-0409","authenticated-orcid":false,"given":"Arianna","family":"Dagliati","sequence":"additional","affiliation":[{"name":"University of Pavia, Pavia, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"G. Albi A. Gerbasi M. Chiesa G.\u00a0I. Colombo R. Bellazzi and A. Dagliati. 2023. A Topological Data Analysis Framework for Computational Phenotyping. Artificial Intelligence in Medicine (2023) 323\u2013327. 10.1007\/978-3-031-34344-5_48","DOI":"10.1007\/978-3-031-34344-5_48"},{"key":"e_1_3_3_1_4_2","unstructured":"F. Belch\u00ed J. Brodzki M. Burfitt and M. Niranjan. 2020. A numerical measure of the instability of mapper-type algorithms. Journal of Machine Learning Research (2020) 202:8347\u2013202:8391."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"G.\u00a0W. Bemis and M.\u00a0A. Murcko. 1996. The properties of known drugs. 1. Molecular frameworks. Journal of Medicinal Chemistry (1996) 2887\u20132893. 10.1021\/jm9602928","DOI":"10.1021\/jm9602928"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"D. Butina. 1999. Unsupervised Data Base Clustering Based on Daylight\u2019s Fingerprint and Tanimoto Similarity: A Fast and Automated Way To Cluster Small and Large Data Sets. Journal of Chemical Information and Computer Sciences (1999) 747\u2013750. 10.1021\/ci9803381","DOI":"10.1021\/ci9803381"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI59109.2023.00026"},{"key":"e_1_3_3_1_8_2","unstructured":"R. Flamary N. Courty A. Gramfort M.\u00a0Z. Alaya A. Auricchio A. Rakotomamonjy and I. Redko. 2021. POT: Python Optimal Transport. Journal of Machine Learning Research (2021) 1\u20138."},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"H. Fooladi T.\u00a0N.\u00a0L. Vu M. Mathea and J. Kirchmair. 2025. Evaluating Machine Learning Models for Molecular Property Prediction: Performance and Robustness on Out-of-Distribution Data. Journal of Chemical Information and Modeling (2025) 9871\u20139891. 10.1021\/acs.jcim.5c00475","DOI":"10.1021\/acs.jcim.5c00475"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"P. Gabriel and C. Marco. 2019. Computational Optimal Transport with Applications to Data Sciences. Foundations and Trends in Machine Learning (2019) 355\u2013607. 10.1561\/2200000073","DOI":"10.1561\/2200000073"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Q. Guo S. Hernandez-Hernandez and P.\u00a0J. Ballester. 2025. UMAP-based clustering split for rigorous evaluation of AI models for virtual screening on cancer cell lines. Journal of Cheminformatics (2025) 94. 10.1186\/s13321-025-01039-8","DOI":"10.1186\/s13321-025-01039-8"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"K. Huang T. Fu W. Gao Y. Zhao Y. Roohani J. Leskovec C.\u00a0W. Coley C. Xiao J. Sun and M. Zitnik. 2022. Artificial intelligence foundation for therapeutic science. Nature Chemical Biology (2022) 1033\u20131036. 10.1038\/s41589-022-01131-2","DOI":"10.1038\/s41589-022-01131-2"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"S.\u00a0J. Kang and Y. Lim. 2021. Ensemble mapper. Stat (2021) e405. 10.1002\/sta4.405","DOI":"10.1002\/sta4.405"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"K. L\u00f3pez-P\u00e9rez J.\u00a0F. Avellaneda-Tamayo L. Chen E. L\u00f3pez-L\u00f3pez K.\u00a0E. Ju\u00e1rez-Mercado J.\u00a0L. Medina-Franco and R.\u00a0A. Miranda-Quintana. 2024. Molecular similarity: Theory applications and perspectives. Artificial Intelligence Chemistry (2024) 100077. 10.1016\/j.aichem.2024.100077","DOI":"10.1016\/j.aichem.2024.100077"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"L. McInnes J. Healy N. Saul and L. Gro\u00dfberger. 2018. UMAP: Uniform Manifold Approximation and Projection. Journal of Open Source Software (2018) 861. 10.21105\/joss.00861","DOI":"10.21105\/joss.00861"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"H.\u00a0L. Morgan. 1965. The Generation of a Unique Machine Description for Chemical Structures-A Technique Developed at Chemical Abstracts Service. Journal of Chemical Documentation (1965) 107\u2013113. 10.1021\/c160017a018","DOI":"10.1021\/c160017a018"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"F. M\u00e9moli. 2011. Gromov\u2013Wasserstein Distances and the Metric Approach to Object Matching. Foundations of Computational Mathematics (2011) 417\u2013487. 10.1007\/s10208-011-9093-5","DOI":"10.1007\/s10208-011-9093-5"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"M. Nicolau A.\u00a0J. Levine and G. Carlsson. 2011. Topology based data analysis identifies a subgroup of breast cancers with a unique mutational profile and excellent survival. Proceedings of the National Academy of Sciences (2011) 7265\u20137270. 10.1073\/pnas.1102826108","DOI":"10.1073\/pnas.1102826108"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Y. Ozaki Y. Tanigaki S. Watanabe M. Nomura and M. Onishi. 2022. Multiobjective Tree-Structured Parzen Estimator. Journal of Artificial Intelligence Research (2022) 1209\u20131250. 10.1613\/jair.1.13188","DOI":"10.1613\/jair.1.13188"},{"key":"e_1_3_3_1_20_2","volume-title":"The PageRank Citation Ranking: Bringing Order to the Web","author":"Page L.","year":"1999","unstructured":"L. Page, S. Brin, R. Motwani, and T. Winograd. 1999. The PageRank Citation Ranking: Bringing Order to the Web. Technical Report. Technical Report."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TopoInVis60193.2023.00008"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Jerret Ross Brian Belgodere Vijil Chenthamarakshan Inkit Padhi Youssef Mroueh and Payel Das. 2022. Large-scale chemical language representations capture molecular structure and properties. Nature Machine Intelligence 4 12 (2022) 1256\u20131264. 10.1038\/s42256-022-00580-7","DOI":"10.1038\/s42256-022-00580-7"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Y. Rubner C. Tomasi and L.\u00a0J. Guibas. 2000. The Earth Mover\u2019s Distance as a Metric for Image Retrieval. International Journal of Computer Vision (2000) 99\u2013121. 10.1023\/A:1026543900054","DOI":"10.1023\/A:1026543900054"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.2312\/SPBG\/SPBG07\/091-100"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"Thereza\u00a0A. Soares Ariane Nunes-Alves Angelica Mazzolari Fiorella Ruggiu Guo-Wei Wei and Kenneth Merz. 2022. The (Re)-Evolution of Quantitative Structure\u2013Activity Relationship (QSAR) Studies Propelled by the Surge of Machine Learning Methods. Journal of Chemical Information and Modeling 62 22 (nov 2022) 5317\u20135320. 10.1021\/acs.jcim.2c01422","DOI":"10.1021\/acs.jcim.2c01422"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2816"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","unstructured":"Y. Tao and S. Ge. 2025. A distribution-guided Mapper algorithm. BMC Bioinformatics (2025) 73. 10.1186\/s12859-025-06085-5","DOI":"10.1186\/s12859-025-06085-5"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"P. Tossou C. Wognum M. Craig H. Mary and E. Noutahi. 2024. Real-World Molecular Out-Of-Distribution: Specification and Investigation. Journal of Chemical Information and Modeling (2024) 697\u2013711. 10.1021\/acs.jcim.3c01774","DOI":"10.1021\/acs.jcim.3c01774"},{"key":"e_1_3_3_1_29_2","first-page":"6275","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Vayer T.","year":"2019","unstructured":"T. Vayer, N. Courty, R. Tavenard, L. Chapel, and R. Flamary. 2019. Optimal Transport for structured data with application on graphs. In Proceedings of the 36th International Conference on Machine Learning. 6275\u20136284."},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Yuyang Wang Jianren Wang Zhonglin Cao and Amir\u00a0Barati Farimani. 2022. Molecular contrastive learning of representations via graph neural networks. Nature Machine Intelligence 4 3 (2022) 279\u2013287. 10.1038\/s42256-022-00447-x","DOI":"10.1038\/s42256-022-00447-x"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"D. Weininger. 1988. SMILES a chemical language and information system. 1. Introduction to methodology and encoding rules. Journal of Chemical Information and Computer Sciences (1988) 31\u201336. 10.1021\/ci00057a005","DOI":"10.1021\/ci00057a005"}],"event":{"name":"BCB '26: 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","location":"Rende (CS) Italy","acronym":"BCB '26","sponsor":["SIGBio ACM Special Interest Group on Bioinformatics"]},"container-title":["Proceedings of the 17th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3807503.3819382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T15:15:12Z","timestamp":1785338112000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3807503.3819382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":30,"alternative-id":["10.1145\/3807503.3819382","10.1145\/3807503"],"URL":"https:\/\/doi.org\/10.1145\/3807503.3819382","relation":{},"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2026-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}