• Preprint 300

Technical Report 300, c4e-Preprint Series, Cambridge

Knowledge Engineering in Chemistry: From Expert Systems to Agents of Creation

Reference: Technical Report 300, c4e-Preprint Series, Cambridge, 2022

Associated Themes:
  Theme icon


Highlights
  • Knowledge engineering (KE) is a branch of Artificial Intelligence (AI) that emulates the decision-making process of a human expert.
  • In a KE approach, instances of knowledge are semantically described with the help of ontologies.
  • Software agents are used to facilitate reasoning and execution of various operations.
  • KE in chemistry covers many areas, such as rational design, multiscale modelling, lab automation and others.
  • Broad chemical knowledge ecosystems are developed through multidisciplinary knowledge graphs.
Abstract

Graphical abstract This account introduces the history, the core principles of KE, and its applications within chemical research and engineering. In this regard, we first discuss how chemical knowledge is formalised and how a chemist's cognition can be emulated with the help of reasoning algorithms. Following this, we discuss various applications of knowledge graph and agent technology used to solve chemistry-related problems related to molecular engineering, chemical mechanisms, multi-scale modelling, automation of calculations and experiments, and chemist-machine interactions. These developments are discussed in the context of a universal and dynamic knowledge ecosystem, referred to as The World Avatar (TWA).

Material from this preprint has been published in Accounts of Chemical Research.

Download

PDF (1.3 MB)