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/

Zendy Plus

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

Zendy Tools

Zendy Open

DNA-Encoded Library (DEL) technology has enabled significant advances in hitidentification by enabling efficient testing of combinatorially-generatedmolecular libraries. DEL screens measure protein binding affinity thoughsequencing reads of molecules tagged with unique DNA-barcodes that survive aseries of selection experiments. Computational models have been deployed tolearn the latent binding affinities that are correlated to the sequenced countdata; however, this correlation is often obfuscated by various sources of noiseintroduced in its complicated data-generation process. In order to denoise DELcount data and screen for molecules with good binding affinity, computationalmodels require the correct assumptions in their modeling structure to capturethe correct signals underlying the data. Recent advances in DEL models havefocused on probabilistic formulations of count data, but existing approacheshave thus far been limited to only utilizing 2-D molecule-levelrepresentations. We introduce a new paradigm, DEL-Dock, that combinesligand-based descriptors with 3-D spatial information from dockedprotein-ligand complexes. 3-D spatial information allows our model to learnover the actual binding modality rather than using only structured-basedinformation of the ligand. We show that our model is capable of effectivelydenoising DEL count data to predict molecule enrichment scores that are bettercorrelated with experimental binding affinity measurements compared to priorworks. Moreover, by learning over a collection of docked poses we demonstratethat our model, trained only on DEL data, implicitly learns to perform gooddocking pose selection without requiring external supervision fromexpensive-to-source protein crystal structures.

DEL-Dock: Molecular Docking-Enabled Modeling of DNA-Encoded Libraries