Themed collection Data Driven Crystal Engineering
![](https://www.rsc-cdn.org/pubs-core/2022.0.147/content/NewImages/Ajax-GA-Loader.gif)
Theoretical insight into the relevance between the oxidation states of CeO2 supported Pt4+/2+/1+/0/2− and their HER performance
The CeO2 supported electron-enriched Pt2− is more suitable for HER than Pt0 and Ptδ+.
CrystEngComm, 2023,25, 40-47
https://doi.org/10.1039/D2CE01246D
Predictive nonlinear optical crystal formation energy regression model based on convolutional neural networks
A convolutional neural network (CNN) model has been constructed to predict the formation energy of nonlinear optical crystals solely based on their chemical formulas.
CrystEngComm, 2024,26, 2652-2661
https://doi.org/10.1039/D4CE00133H
Toward predicting surface energy of rutile TiO2 with machine learning
A database of rutile TiO2 containing 3000 morphologies was established. With this database, the surface energy was predicted from the experimentally observed crystal equilibrium morphology using the KNN model.
CrystEngComm, 2023,25, 199-205
https://doi.org/10.1039/D2CE01310J
![Open Access](https://www.rsc-cdn.org/pubs-core/2022.0.147/content/NewImages/open-access-icon-orange.png)
Predicting pharmaceutical crystal morphology using artificial intelligence
We present the use of artificial intelligence to predict the morphology of crystallizing active pharmaceutical ingredients, first using publicly available data, and then using our own screening efforts to address the limitations we identified.
CrystEngComm, 2022,24, 7545-7553
https://doi.org/10.1039/D2CE00992G
A study to discover novel pharmaceutical cocrystals of pelubiprofen with a machine learning approach compared
Pharmaceutical cocrystals of pelubiprofen (PF) were discovered for the first time. 16 candidates to form cocrystals with PF were selected via the ANN model and the pKa rule.
CrystEngComm, 2022,24, 3938-3952
https://doi.org/10.1039/D2CE00153E
Importance of raw material features for the prediction of flux growth of Al2O3 crystals using machine learning
We evaluated the role of raw-material features for machine-learning prediction of the flux crystal growth of Al2O3 in MoO3 based on 185 types of growth trials.
CrystEngComm, 2022,24, 3179-3188
https://doi.org/10.1039/D2CE00010E
Virtual coformer screening by a combined machine learning and physics-based approach
Cocrystals as a solid form technology for improving physicochemical properties have gained increasing popularity in the pharmaceutical, nutraceutical, and agrochemical industries.
CrystEngComm, 2021,23, 6039-6044
https://doi.org/10.1039/D1CE00587A
Actuation performance of a photo-bending crystal modeled by machine learning-based regression
The bending deflection and blocking force of photo-bending crystals of different sizes were experimentally measured at various light intensities, and then modeled by the machine learning-based regression.
CrystEngComm, 2021,23, 5839-5847
https://doi.org/10.1039/D1CE00208B
Geometrical design of a crystal growth system guided by a machine learning algorithm
This study proposes a new high-speed method for designing crystal growth systems. It is capable of optimizing large numbers of parameters simultaneously which is difficult for traditional experimental and computational techniques.
CrystEngComm, 2021,23, 2695-2702
https://doi.org/10.1039/D1CE00106J
Adaptive process control for crystal growth using machine learning for high-speed prediction: application to SiC solution growth
A time-dependent recipe designed by an adaptive control method can consistently maintain the optimal growth conditions despite the unsteady growth environment.
CrystEngComm, 2021,23, 1982-1990
https://doi.org/10.1039/D0CE01824D
Evaluation of focused beam reflectance measurement (FBRM) for monitoring and predicting the crystal size of carbamazepine in crystallization processes
Pharmaceutical crystallization affects the properties of APIs as it determines the purity and crystal size distribution, among other attributes. This work presents two CLD–CSD models, theoretical and empirical, for a model compound.
CrystEngComm, 2021,23, 972-985
https://doi.org/10.1039/D0CE01388A
About this collection
Artificial intelligence technologies, large-scale tag data and improvement of computing performance warrant opportunities for intelligent analysis of crystal engineering big data. Machine learning can well learn and extract the crystal engineering characteristics of complex data and help to promote the generation of new mechanisms and new knowledge. For this, it is important to develop new models and methodologies to address big crystal engineering data challenges. This themed collection, guest edited by Professor Dongfeng Xue and Dr Haitao Zhao (Multiscale Crystal Materials Research Centre, Shenzhen Institute of Advanced Technology, CAS, China) aims to develop the ‘Fourth Paradigm’; revolutionizing crystalline materials R&D methods using advanced data-driven approaches to crystalline materials discovery with articles that show the significant potential of interdisciplinary research into data-driven discovery and digital manufacturing of crystalline materials.