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

By combining various cancer cell line (CCL) drug screening panels, the sizeof the data has grown significantly to begin understanding how advances in deeplearning can advance drug response predictions. In this paper we train >35,000neural network models, sweeping over common featurization techniques. We foundthe RNA-seq to be highly redundant and informative even with subsets largerthan 128 features. We found the inclusion of single nucleotide polymorphisms(SNPs) coded as count matrices improved model performance significantly, and nosubstantial difference in model performance with respect to molecularfeaturization between the common open source MOrdred descriptors and Dragon7descriptors. Alongside this analysis, we outline data integration between CCLscreening datasets and present evidence that new metrics and imbalanced datatechniques, as well as advances in data standardization, need to be developed.

A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning