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

In this work, we propose two novel methodologies to study temporal andmorphological phenotypic effects caused by different experimental conditionsusing imaging data. As a proof of concept, we apply them to analyze drugeffects in 2D cancer cell cultures. We train a convolutional autoencoder on 1Mimages dataset with random augmentations and multi-crops to use as featureextractor. We systematically compare it to the pretrained state-of-the-artmodels. We further use the feature extractor in two ways. First, we applydistance-based analysis and dynamic time warping to cluster temporal patternsof 31 drugs. We identify clusters allowing annotation of drugs as havingcytotoxic, cytostatic, mixed or no effect. Second, we implement anadversarial/regularized learning setup to improve classification of 31 drugsand visualize image regions that contribute to the improvement. We increasetop-3 classification accuracy by 8% on average and mine examples ofmorphological feature importance maps. We provide the feature extractor and theweights to foster transfer learning applications in biology. We also discussutility of other pretrained models and applicability of our methods to othertypes of biomedical data.

Self-supervised learning for analysis of temporal and morphological drug effects in cancer cell imaging data