Digital Discovery, 2023, 2,1368-1379
DOI: 10.1039/D3DD00030C, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Noah Hoffmann, Jonathan Schmidt, Silvana Botti, Miguel A. L. Marques
Pretraining on large, lower-fidelity datasets enables extremely effective training of graph neural networks on smaller, high-fidelity datasets.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1425-1435
DOI: 10.1039/D3DD00082F, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Eric S. Muckley, James E. Saal, Bryce Meredig, Christopher S. Roper, John H. Martin
On average, simple linear models perform equivalently to black box machine learning models on extrapolation tasks.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1436-1451
DOI: 10.1039/D3DD00083D, Paper

Open Access

  This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Ajay Manicka, Andrew Stephan, Sriram Chari, Gemma Mendonsa, Peyton Okubo, John Stolzberg-Schray, Anil Reddy, Marc Riedel
Automated routing of droplets for DNA storage on an industrial-scale digital microfluidics platform.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1506-1521
DOI: 10.1039/D3DD00106G, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Krishnendu Mukherjee, Etinosa Osaro, Yamil J. Colón
We present the development of an active learning framework to model multicomponent gas adsorption in metal–organic frameworks.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1251-1258
DOI: 10.1039/D3DD00094J, Perspective

Open Access

  This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Line Pouchard, Kristofer G. Reyes, Francis J. Alexander, Byung-Jun Yoon
The capability to replicate the predictions by machine learning (ML) or artificial intelligence (AI) models and the results in scientific workflows that incorporate such ML/AI predictions is driven by a variety of factors.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1461-1470
DOI: 10.1039/D3DD00101F, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Tudur David, Nik Khadijah Nik Aznan, Kathryn Garside, Thomas Penfold
A machine learning model capable of extracting structural information from XANES spectra is introduced. This approach, analogous to a Fourier transform of EXAFS spectra, can predict first coordination shell bond-lengths with a median error of 0.1 Å.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1471-1483
DOI: 10.1039/D3DD00105A, Paper

Open Access

  This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Kiran Vaddi, Karen Li, Lilo D. Pozzo
We present an automated method to extract phase maps from experimental data that is of the functional form (e.g.: spectroscopy, scattering, diffraction) using the notion of shape distance between two curves represented as one dimensional functions.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1289-1296
DOI: 10.1039/D3DD00039G, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Markus Orsi, Daniel Probst, Philippe Schwaller, Jean-Louis Reymond
Reaction informatics is used to map the chemical space of drugs paired by similarity according to different molecular fingerprints.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1484-1493
DOI: 10.1039/D3DD00107E, Paper

Open Access

  This article is licensed under a Creative Commons Attribution-NonCommercial 3.0 Unported Licence.

Jiaquan Huang, Qiandi Gao, Ying Tang, Yaxin Wu, Heqian Zhang, Zhiwei Qin
Utilizing a large protein language model, we have formulated a deep learning framework designed for predicting type II polyketide natural products.
The content of this RSS Feed (c) The Royal Society of Chemistry

Digital Discovery, 2023, 2,1494-1505
DOI: 10.1039/D3DD00098B, Paper

Open Access

  This article is licensed under a Creative Commons Attribution 3.0 Unported Licence.

Edgar López-López, Oscar Robles, Fabien Plisson, José L. Medina-Franco
Peptide structure–activity/property relationship (P-SA/PR) studies focus on understanding how the structural variations of peptides influence their biological activities and other functional properties.
The content of this RSS Feed (c) The Royal Society of Chemistry