Principle of Generative Chemistry

This figure illustrates the core principle of generative chemistry, where machine learning models optimize molecular structures in a multidimensional latent space to design improved compounds. A non-optimal seed molecule is encoded into numerical representations, refined through generator models using multi-objective optimization and decoded into new structures with enhanced properties. This template is adapted from Dr. Jeremy Jenkins' keynote presentation at BioRender's virtual event, 'Mastering the AI Era: Exclusive Insights from Novartis, MIT & Top Biotech Leaders'.

Yes, you can customize this template with a free BioRender account (no credit card required). Paid plans unlock additional export formats, higher-resolution downloads, and publication permissions.

Yes, every element is fully editable. Icons, labels, colors, arrows, shapes and layout can all be changed to match your preferences or needs using BioRender's drag-and-drop editor. You can add or remove elements to fully customize your use case.

Yes, BioRender icons and templates meet journal, grant, and copyright standards for publication, and many researchers cite BioRender directly in their figure legends.

Unlock publication permissions with a paid plan, and include 'Created with BioRender.com' in your figure legend, or cite BioRender directly per your journal's guidelines.

Researchers and scientists use this template for publications, funding proposals, grant applications, presentations, posters, and more.