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

Sample efficiency is a fundamental challenge in de novo molecular design.Ideally, molecular generative models should learn to satisfy a desiredobjective under minimal oracle evaluations (computational prediction or wet-labexperiment). This problem becomes more apparent when using oracles that canprovide increased predictive accuracy but impose a significant cost.Consequently, these oracles cannot be directly optimized under a practicalbudget. Molecular generative models have shown remarkable sample efficiencywhen coupled with reinforcement learning, as demonstrated in the PracticalMolecular Optimization (PMO) benchmark. Here, we propose a novel algorithmcalled Augmented Memory that combines data augmentation with experience replay.We show that scores obtained from oracle calls can be reused to update themodel multiple times. We compare Augmented Memory to previously proposedalgorithms and show significantly enhanced sample efficiency in an exploitationtask and a drug discovery case study requiring both exploration andexploitation. Our method achieves a new state-of-the-art in the PMO benchmarkwhich enforces a computational budget, outperforming the previous bestperforming method on 19/23 tasks.

Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design