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

An important first step in computational SAR modeling is to transform thecompounds into a representation that can be processed by predictive modelingtechniques. This is typically a feature vector where each feature indicates thepresence or absence of a molecular fragment. While the traditional approach toSAR modeling employed size restricted fingerprints derived from path fragments,much research in recent years focussed on mining more complex graph basedfragments. Today, there seems to be a growing consensus in the data miningcommunity that these more expressive fragments should be more useful. Wequestion this consensus and show experimentally that fragments of lowcomplexity, i.e. sequences, perform better than equally large sets of morecomplex ones, an effect we explain by pairwise correlation among fragments andthe ability of a fragment set to encode compounds from different classesdistinctly. The size restriction on these sets is based on ordering thefragments by class-correlation scores. In addition, we also evaluate theeffects of using a significance value instead of a length restriction for pathfragments and find a significant reduction in the number of features withlittle loss in performance.

Exploring the efficacy of molecular fragments of different complexity in computational SAR modeling