Digital Discovery Blog

Our new infographic highlights work from Hilton et al. on a 3D-printed, modular system for classical and photochemical synthesis:

Read their paper below to find out more:

Digitisation of a modular plug and play 3D printed continuous flow system for chemical synthesis

Mireia Benito Montaner, Matthew R. Penny and Stephen T. Hilton, Digital Discovery, 2023, 2, 1797–1805

Work by Coley et al. features in the next Digital Discovery infographic, which introduces  a reformulation of the roughness index (ROGI) to help understand the roughtness of QSPR surfaces created by new models.

Get the whole story in their article, available open access:

Evaluating the roughness of structure–property relationships using pretrained molecular representations

David E. Graff, Edward O. Pyzer-Knapp, Kirk E. Jordan, Eugene I. Shakhnovich and Connor W. Coley, Digital Discovery, 2023, 2, 1452–1460

Our latest research infographic shares Snapp and Brown’s heuristic framework for defining the operaiton of self-driving labs.

Find out more in their open access article here:

Driving school for self-driving labs

Kelsey L. Snapp and Keith A. Brown, Digital Discovery, 2023, 2, 1620–1629, DOI: 10.1039/D3DD00150D

Discover new research on feature selection for molecular systems in this new infographic:

Read the open access full article at the link below:

Feature selection in molecular graph neural networks based on quantum chemical approaches

Daisuke Yokogawa and Kayo Suda, Digital Discovery, 2023, 2, 1089–1097, DOI: 10.1039/D3DD00010A

Our newest infographic presents research from Jiscoot, Uslamin, and Pidko, developing an algorithm for constructing and evaluating kinetic models which has a a grounding in physical effects.

Read their full article, open access, at the link below:

Model-based evaluation and data requirements for parallel kinetic experimentation and data-driven reaction identification and optimization

Nathan Jiscoot, Evgeny A. Uslamin, and Evgeny A. Pidko, Digital Discovery, 2023, 2, 994–1005, DOI: 10.1039/D3DD00016H

We’re pleased to share this new infographic based on research from Florence et al., which uses machine learning techniques to predict the flow behaviour of pharmaceutical powders from their physical properties:

Read the full article (open access) for more:

Machine learning approaches to the prediction of powder flow behaviour of pharmaceutical materials from physical properties

We’re pleased to share this infographic on research by Hagai, Yanai et al. that exploits neural networks and quantum computing to describe the entanglement of many-body quantum systems:

Read the full article (open access) for more:

Artificial neural network encoding of molecular wavefunctions for quantum computing

Link-INVENT, an extension to REINVENT for the design of PROTACs, fragment linking, and scaffold hopping, is the subject of our new infographic:

Read the full open access article:

Link-INVENT: generative linker design with reinforcement learning

Our latest infographic highlights work from Choudhary et al. on a machine learning force field for solids covering 89 elements:

Find out more in the open access article:

Unified graph neural network force-field for the periodic table: solid state applications

Our next infographic presents work from Rieger et al., using explainability and uncertainty to efficiently predict battery degradation and end-of-life.

Find out more in their full open-access article:

Uncertainty-aware and explainable machine learning for early prediction of battery degradation trajectory