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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Artificial intelligence (AI) and machine learning (ML) are expanding inpopularity for broad applications to challenging tasks in chemistry andmaterials science. Examples include the prediction of properties, the discoveryof new reaction pathways, or the design of new molecules. The machine needs toread and write fluently in a chemical language for each of these tasks. Stringsare a common tool to represent molecular graphs, and the most popular molecularstring representation, SMILES, has powered cheminformatics since the late1980s. However, in the context of AI and ML in chemistry, SMILES has severalshortcomings -- most pertinently, most combinations of symbols lead to invalidresults with no valid chemical interpretation. To overcome this issue, a newlanguage for molecules was introduced in 2020 that guarantees 100\% robustness:SELFIES (SELF-referencIng Embedded Strings). SELFIES has since simplified andenabled numerous new applications in chemistry. In this manuscript, we look tothe future and discuss molecular string representations, along with theirrespective opportunities and challenges. We propose 16 concrete Future Projectsfor robust molecular representations. These involve the extension toward newchemical domains, exciting questions at the interface of AI and robustlanguages and interpretability for both humans and machines. We hope that theseproposals will inspire several follow-up works exploiting the full potential ofmolecular string representations for the future of AI in chemistry andmaterials science.

SELFIES and the future of molecular string representations