<HashMap><database>biostudies-literature</database><scores/><additional><submitter>Blumenberg L</submitter><funding>National Cancer Institute</funding><funding>NCI NIH HHS</funding><pagination>428</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC7525959</full_dataset_link><repository>biostudies-literature</repository><omics_type>Unknown</omics_type><volume>21(1)</volume><pubmed_abstract>&lt;h4>Background&lt;/h4>Unsupervised clustering is a common and exceptionally useful tool for large biological datasets. However, clustering requires upfront algorithm and hyperparameter selection, which can introduce bias into the final clustering labels. It is therefore advisable to obtain a range of clustering results from multiple models and hyperparameters, which can be cumbersome and slow.&lt;h4>Results&lt;/h4>We present hypercluster, a python package and SnakeMake pipeline for flexible and parallelized clustering evaluation and selection. Users can efficiently evaluate a huge range of clustering results from multiple models and hyperparameters to identify an optimal model.&lt;h4>Conclusions&lt;/h4>Hypercluster improves ease of use, robustness and reproducibility for unsupervised clustering applicati</pubmed_abstract><journal>BMC bioinformatics</journal><pubmed_title>Hypercluster: a flexible tool for parallelized unsupervised clustering optimization.</pubmed_title><pmcid>PMC7525959</pmcid><funding_grant_id>U24CA210972</funding_grant_id><pubmed_authors>Blumenberg L</pubmed_authors><pubmed_authors>Ruggles KV</pubmed_authors></additional><is_claimable>false</is_claimable><name>Hypercluster: a flexible tool for parallelized unsupervised clustering optimization.</name><description>&lt;h4>Background&lt;/h4>Unsupervised clustering is a common and exceptionally useful tool for large biological datasets. However, clustering requires upfront algorithm and hyperparameter selection, which can introduce bias into the final clustering labels. It is therefore advisable to obtain a range of clustering results from multiple models and hyperparameters, which can be cumbersome and slow.&lt;h4>Results&lt;/h4>We present hypercluster, a python package and SnakeMake pipeline for flexible and parallelized clustering evaluation and selection. Users can efficiently evaluate a huge range of clustering results from multiple models and hyperparameters to identify an optimal model.&lt;h4>Conclusions&lt;/h4>Hypercluster improves ease of use, robustness and reproducibility for unsupervised clustering applicati</description><dates><release>2020-01-01T00:00:00Z</release><publication>2020 Sep</publication><modification>2025-04-26T21:22:52.675Z</modification><creation>2020-10-08T07:28:49Z</creation></dates><accession>S-EPMC7525959</accession><cross_references><pubmed>32993491</pubmed><doi>10.1186/s12859-020-03774-1</doi></cross_references></HashMap>