A scalable, multi-resolution consensus clustering approach for prioritizing robust signals from high-throughput screens

Bao, SC; Pishas, KI; Cowley, KJ; Zhao, Q; Goodall, ECA; Henderson, IR; Liu, X; Marinovic, E; Carey, MS; Campbell, IG; Simpson, KJ; Cheasley, D; Mizikovsky, D; Palpant, NJ

Author(s): Bao, SC; Pishas, KI; Cowley, KJ; Zhao, Q; Goodall, ECA; Henderson, IR; Liu, X; Marinovic, E; Carey, MS; Campbell, IG; Simpson, KJ; Cheasley, D; Mizikovsky, D; Palpant, NJ;
Details: Publication Year 2026-05-04,Volume 27,Issue #3,Page bbag242
Journal Title: Briefings in Bioinformatics
Publication Type: Research article
Abstract: Modern biology increasingly relies on large-scale screening to generate high dimensional datasets with potential to accelerate discovery. However, analysing these complex datasets remains challenging, due to hierarchical biological structure, uncertainty in the true number of groups, and high dimensional noise that confounds genuine biological signal. Here we present an unsupervised consensus clustering tool, Untangled, that aggregates clustering solutions across granularities to construct a stability-based representation, followed by cluster number optimization and systematic evaluation of cluster robustness. Through extensive benchmarking on simulated datasets, ground truth datasets and diverse high-dimensional screening applications, we demonstrate that Untangled reliably recovers underlying relationships, resolves stable meaningful substructure, and more effectively prioritizes robust clusters with shared biological mechanisms and conserved phenotypic responses than alternative clustering approaches. These results establish Untangled as a scalable framework for cluster discovery to guide efficient follow-up investigation from high-dimensional biological datasets.
Publisher: Oxford University Press
Keywords: Cluster Analysis; *High-Throughput Screening Assays/methods; Algorithms; Humans; *Computational Biology/methods; computational biology; consensus clustering; drug discovery; high dimensional data analysis; high-throughput screening; unsupervised learning
Department(s): Laboratory Research
Publisher's Version: https://doi.org/10.1093/bib/bbag242
Open Access at Publisher's Site: https://doi.org/10.1093/bib/bbag242
Terms of Use/Rights Notice: Refer to copyright notice on published article.

Creation Date: 2026-06-02 05:11:24

Last Modified: 2026-06-02 05:11:31