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 Tools annual

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 monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Informed selection of drug candidates for laboratory experimentation providesan efficient means of identifying suitable anti-cancer treatments. Theadvancement of artificial intelligence has led to the development ofcomputational models to predict cancer cell line response to drug treatment. Itis important to analyze the false positive rate (FPR) of the models, toincrease the number of effective treatments identified and to minimizeunnecessary laboratory experimentation. Such analysis will also aid inidentifying drugs or cancer types that require more data collection to improvemodel predictions. This work uses an attention based neural networkclassification model to identify responsive/non-responsive drug treatmentsacross multiple types of cancer cell lines. Two data filtering techniques havebeen applied to generate 10 data subsets, including removing samples for whichdose response curves are poorly fitted and removing samples whose area underthe dose response curve (AUC) values are marginal around 0.5 from the trainingset. One hundred trials of 10-fold cross-validation analysis is performed totest the model prediction performance on all the data subsets and the subsetwith the best model prediction performance is selected for further analysis.Several error analysis metrics such as the false positive rate (FPR), and theprediction uncertainty are evaluated, and the results are summarized by cancertype and drug mechanism of action (MoA) category. The FPR of cancer type spansbetween 0.262 and 0.5189, while that of drug MoA category spans almost the fullrange of [0, 1]. This study identifies cancer types and drug MoAs with highFPRs. Additional drug screening data of these cancer and drug categories mayimprove response modeling. Our results also demonstrate that the two datafiltering approaches help improve the drug response prediction performance.

Influencing factors on false positive rates when classifying tumor cell line response to drug treatment