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

Recent emergence of high-throughput drug screening assays sparkled anintensive development of machine learning methods, including models forprediction of sensitivity of cancer cell lines to anti-cancer drugs, as well asmethods for generation of potential drug candidates. However, a concept ofgeneration of compounds with specific properties and simultaneous modeling oftheir efficacy against cancer cell lines has not been comprehensively explored.To address this need, we present VADEERS, a Variational Autoencoder-based DrugEfficacy Estimation Recommender System. The generation of compounds isperformed by a novel variational autoencoder with a semi-supervised GaussianMixture Model (GMM) prior. The prior defines a clustering in the latent space,where the clusters are associated with specific drug properties. In addition,VADEERS is equipped with a cell line autoencoder and a sensitivity predictionnetwork. The model combines data for SMILES string representations ofanti-cancer drugs, their inhibition profiles against a panel of proteinkinases, cell lines biological features and measurements of the sensitivity ofthe cell lines to the drugs. The evaluated variants of VADEERS achieve a highr=0.87 Pearson correlation between true and predicted drug sensitivityestimates. We train the GMM prior in such a way that the clusters in the latentspace correspond to a pre-computed clustering of the drugs by their inhibitoryprofiles. We show that the learned latent representations and new generateddata points accurately reflect the given clustering. In summary, VADEERS offersa comprehensive model of drugs and cell lines properties and relationshipsbetween them, as well as a guided generation of novel compounds.

A generative recommender system with GMM prior for cancer drug generation and sensitivity prediction