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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Pharmaceutical researchers are continually searching for techniques toimprove both drug development processes and patient outcomes. An area of recentinterest is the potential for machine learning (ML) applications withinpharmacology. One such application not yet given close study is theunsupervised clustering of plasma concentration-time curves, hereafter,pharmacokinetic (PK) curves. In this paper, we present our findings on how tocluster PK curves by their similarity. Specifically, we find clustering to beeffective at identifying similar-shaped PK curves and informative forunderstanding patterns within each cluster of PK curves. Because PK curves aretime series data objects, our approach utilizes the extensive body of researchrelated to the clustering of time series data as a starting point. As such, weexamine many dissimilarity measures between time series data objects to findthose most suitable for PK curves. We identify Euclidean distance as generallymost appropriate for clustering PK curves, and we further show that dynamictime warping, Fr\'{e}chet, and structure-based measures of dissimilarity likecorrelation may produce unexpected results. As an illustration, we apply thesemethods in a case study with 250 PK curves used in a previous pharmacogenomicstudy. Our case study finds that an unsupervised ML clustering with Euclideandistance, without any subject genetic information, is able to independentlyvalidate the same conclusions as the reference pharmacogenomic results. To ourknowledge, this is the first such demonstration. Further, the case studydemonstrates how the clustering of PK curves may generate insights that couldbe difficult to perceive solely with population level summary statistics of PKmetrics.

Applications of Machine Learning in Pharmacogenomics: Clustering Plasma Concentration-Time Curves