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

Conformation Generation is a fundamental problem in drug discovery andcheminformatics. And organic molecule conformation generation, particularly invacuum and protein pocket environments, is most relevant to drug design.Recently, with the development of geometric neural networks, the data-drivenschemes have been successfully applied in this field, both for molecularconformation generation (in vacuum) and binding pose generation (in proteinpocket). The former beats the traditional ETKDG method, while the latterachieves similar accuracy compared with the widely used molecular dockingsoftware. Although these methods have shown promising results, some researchershave recently questioned whether deep learning (DL) methods perform better inmolecular conformation generation via a parameter-free method. To our surprise,what they have designed is some kind analogous to the famous infinite monkeytheorem, the monkeys that are even equipped with physics education. To discussthe feasibility of their proving, we constructed a real infinite stochasticmonkey for molecular conformation generation, showing that even with a morestochastic sampler for geometry generation, the coverage of the benchmarkQM-computed conformations are higher than those of most DL-based methods. Byextending their physical monkey algorithm for binding pose prediction, we alsodiscover that the successful docking rate also achieves near-best performanceamong existing DL-based docking models. Thus, though their conclusions areright, their proof process needs more concern.

Infinite Physical Monkey: Do Deep Learning Methods Really Perform Better in Conformation Generation?