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

According to Cobanoglu et al and Murphy, it is now widely acknowledged thatthe single target paradigm (one protein or target, one disease, one drug) thathas been the dominant premise in drug development in the recent past isuntenable. More often than not, a drug-like compound (ligand) can bepromiscuous - that is, it can interact with more than one target protein. Inrecent years, in in silico target prediction methods the promiscuity issue hasbeen approached computationally in different ways. In this study we confineattention to the so-called ligand-based target prediction machine learningapproaches, commonly referred to as target-fishing. With a few exceptions, thetarget-fishing approaches that are currently ubiquitous in cheminformaticsliterature can be essentially viewed as single-label multi-classificationschemes; these approaches inherently bank on the single target paradigmassumption that a ligand can home in on one specific target. In order toaddress the ligand promiscuity issue, one might be able to cast target-fishingas a multi-label multi-class classification problem. For illustrative andcomparison purposes, single-label and multi-label Naive Bayes classificationmodels (denoted here by SMM and MMM, respectively) for target-fishing wereimplemented. The models were constructed and tested on 65,587 compounds and 308targets retrieved from the ChEMBL17 database. SMM and MMM performeddifferently: for 16,344 test compounds, the MMM model returned recall andprecision values of 0.8058 and 0.6622, respectively; the corresponding recalland precision values yielded by the SMM model were 0.7805 and 0.7596,respectively. However, at a significance level of 0.05 and one degree offreedom McNemar test performed on the target prediction results returned by SMMand MMM for the 16,344 test ligands gave a chi-squared value of 15.656, infavour of the MMM approach.

Target Fishing: A Single-Label or Multi-Label Problem?