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

Over the last years, huge resources of biological and medical data havebecome available for research. This data offers great chances for machinelearning applications in health care, e.g. for precision medicine, but is alsochallenging to analyze. Typical challenges include a large number of possiblycorrelated features and heterogeneity in the data. One flourishing field ofbiological research in which this is relevant is epigenetics. Here, especiallylarge amounts of DNA methylation data have emerged. This epigenetic mark hasbeen used to predict a donor's 'epigenetic age' and increased epigenetic aginghas been linked to lifestyle and disease history. In this paper we propose anadaptive model which performs feature selection for each test sampleindividually based on the distribution of the input data. The method can beseen as partially blind domain adaptation. We apply the model to the problem ofage prediction based on DNA methylation data from a variety of tissues, andcompare it to a standard model, which does not take heterogeneity into account.The standard approach has particularly bad performance on one tissue type onwhich we show substantial improvement with our new adaptive approach eventhough no samples of that tissue were part of the training data.

Partially blind domain adaptation for age prediction from DNA methylation data