English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Investigating molecular heterogeneity provides insights about tumor originand metabolomics. The increasing amount of data gathered makes manual analysesinfeasible - therefore, automated unsupervised learning approaches are utilizedfor discovering heterogeneity. However, automated unsupervised analyses requirea lot of experience with setting their hyperparameters and usually an upfrontknowledge about the number of expected substructures. Moreover, numerousmeasured molecules require an additional step of feature engineering to providevaluable results. In this work, we propose DiviK: a scalable stepwise algorithmwith local data-driven feature space adaptation for the segmentation ofhigh-dimensional datasets. The combination of three quality indices: DiceIndex, Rand Index and EXIMS score are used to assess the quality ofunsupervised analyses in 3D space. DiviK was validated on two separatehigh-throughput datasets acquired by Mass Spectrometry Imaging in 2D and 3D.DiviK could be one of the default choices to consider during the initialexploration of Mass Spectrometry Imaging data. It provides a trade-off betweenabsolute heterogeneity detection and focus on biologically plausiblestructures, and does not require specifying the number of expected structuresbefore the analysis. With its unique local feature space adaptation, it isrobust against dominating global patterns when focusing on the detail. Finally,due to its simplicity, DiviK is easily generalizable to an even more flexibleframework, useful for other '-omics' data, or tabular data in general(including medical images after appropriate embedding). A genericimplementation is freely available under Apache 2.0 license athttps://github.com/gmrukwa/divik.

DiviK: Divisive intelligent K-Means for hands-free unsupervised clustering in big biological data