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

Designing novel materials that possess desired properties is a central needacross many manufacturing industries. Driven by that industrial need, a varietyof algorithms and tools have been developed that combine AI (machine learningand analytics) with domain knowledge in physics, chemistry, and materialsscience. AI-driven materials design can be divided to mainly two stages; thefirst one is the modeling stage, where the goal is to build an accurateregression or classification model to predict material properties (e.g. glasstransition temperature) or attributes (e.g. toxic/non-toxic). The next stage isdesign, where the goal is to assemble or tune material structures so that theycan achieve user-demanded target property values based on a prediction modelthat is trained in the modeling stage. For maximum benefit, these two stagesshould be architected to form a coherent workflow. Today there are severalemerging services and tools for AI-driven material design, however, most ofthem provide only partial technical components (e.g. data analyzer, regressionmodel, structure generator, etc.), that are useful for specific purposes, butfor comprehensive material design, those components need to be orchestratedappropriately. Our material design system provides an end-to-end solution tothis problem, with a workflow that consists of data input, feature encoding,prediction modeling, solution search, and structure generation. The systembuilds a regression model to predict properties, solves an inverse problem onthe trained model, and generates novel chemical structure candidates thatsatisfy the target properties. In this paper we will introduce the methodologyof our system, and demonstrate a simple example of inverse design generatingnew chemical structures that satisfy targeted physical property values.

AI-driven Inverse Design System for Organic Molecules