Progress in Research on Artificial Intelligence Applied to Polymorphism and Cocrystal Prediction

Thermodynamic Stability Is a Poor Indicator of Cocrystallization in Models of Organic Molecules

Cocrystallizing a given molecule with another can be useful for adjusting the physical properties of molecules in the solid state. However, most combinations of molecules do not readily cocrystallize but form either one-component crystals or amorphous solids. Computational methods of crystal structure prediction can, in principle, identify the thermodynamically stable cocrystal and thus predict if molecules will cocrystallize or not. However, the pronounced polymorphism and tendency of many organic molecules to form disordered solids suggest that kinetic factors can play an important role in cocrystallization. The question remains: if a binary system of molecules has a thermodynamically stable cocrystal, will it indeed cocrystallize? To address this question, we simulate the crystallization of more than 2600 distinct pairs of chiral model molecules of similar size in 2D and calculate accurate crystal energy landscapes for all of them. Our analysis shows that thermodynamic criteria alone are unreliable in the prediction of cocrystallization. While the vast majority of cocrystals that form in our simulations are thermodynamically favorable, most coformer systems that have a thermodynamically stable cocrystal do not cocrystallize. We furthermore show that cocrystallization rates increase 3-fold when coformers are used that do not form well-ordered single-component crystals. Our results suggest that kinetic factors of cocrystallization are decisive in many cases.

In silico co-crystal design: Assessment of the latest advances

Pharmaceutical co-crystals represent a growing class of crystal forms in the context of pharmaceutical science. They are attractive to pharmaceutical scientists because they significantly expand the number of crystal forms that exist for an active pharmaceutical ingredient and can lead to improvements in physicochemical properties of clinical relevance. At the same time, machine learning is finding its way into all areas of drug discovery and delivers impressive results. In this review, we attempt to provide an overview of machine learning, deep learning and network-based recommendation approaches applied to pharmaceutical co-crystallization. We also present crystal structure prediction as an alternative to machine learning approaches.

Recent Advances in Co-Former Screening and Formation Prediction of Multicomponent Solid Forms of Low Molecular Weight Drugs

Multicomponent solid forms of low molecular weight drugs, such as co-crystals, salts, and co-amorphous systems, are a result of the combination of an active pharmaceutical ingredient (API) with a pharmaceutically acceptable co-former. These solid forms can enhance the physicochemical and pharmacokinetic properties of APIs, making them increasingly interesting and important in recent decades. Nevertheless, predicting the formation of API multicomponent solid forms in the early stages of formulation development can be challenging, as it often requires significant time and resources. To address this, empirical and computational methods have been developed to help screen for potential co-formers more efficiently and accurately, thus reducing the number of laboratory experiments needed. This review provides a comprehensive overview of current screening and prediction methods for the formation of API multicomponent solid forms, covering both crystalline states (co-crystals and salts) and amorphous forms (co-amorphous). Furthermore, it discusses recent advances and emerging trends in prediction methods, with a particular focus on artificial intelligence.

Applications of Artificial Intelligence and Machine Learning Algorithms to Crystallization

Artificial intelligence and specifically machine learning applications are nowadays used in a variety of scientific applications and cutting-edge technologies, where they have a transformative impact. Such an assembly of statistical and linear algebra methods making use of large data sets is becoming more and more integrated into chemistry and crystallization research workflows. This review aims to present, for the first time, a holistic overview of machine learning and cheminformatics applications as a novel, powerful means to accelerate the discovery of new crystal structures, predict key properties of organic crystalline materials, simulate, understand, and control the dynamics of complex crystallization process systems, as well as contribute to high throughput automation of chemical process development involving crystalline materials. We critically review the advances in these new, rapidly emerging research areas, raising awareness in issues such as the bridging of machine learning models with first-principles mechanistic models, data set size, structure, and quality, as well as the selection of appropriate descriptors. At the same time, we propose future research at the interface of applied mathematics, chemistry, and crystallography. Overall, this review aims to increase the adoption of such methods and tools by chemists and scientists across industry and academia.

Enhancing the stability of active pharmaceutical ingredients by the cocrystal strategy

Cocrystal strategies to achieve excellent physiochemical performance under different environmental stress were highlighted here. The lattice energy and the energy barrier of degradation reactions are two pillars in a stable cocrystal construction.

Prediction of Mefenamic Acid Crystal Shape by Random Forest Classification

OBJECTIVE

Particle shape can have a significant impact on the bulk properties of materials. This study describes the development and application of machine-learning models to predict the crystal shape of mefenamic acid recrystallized from organic solvents.

METHODS

Crystals were grown in 30 different solvents to establish a dataset comprising solvent molecular descriptors, process conditions and crystal shape. Random forest classification models were trained on this data and assessed for prediction accuracy.

RESULTS

The highest prediction accuracy of crystal shape was 93.5% assessed by fourfold cross-validation. When solvents were sequentially excluded from the training data, 32 out of 84 models predicted the shape of mefenamic acid crystals for the excluded solvent with 100% accuracy and a further 21 models had prediction accuracies from 50-100%. Reducing the feature set to only solvent physical property descriptors and supersaturations resulted in higher overall prediction accuracies than the models trained using all available or another selected subset of molecular descriptors. For the 8 solvents on which the models performed poorly (< 50% accuracy), further characterisation of crystals grown in these solvents resulted in the discovery of a new mefenamic acid solvate whereas all other crystals were the previously known form I.

CONCLUSIONS

Random forest classification models using solvent physical property descriptors can reliably predict crystal morphologies for mefenamic acid crystals grown in 20 out of the 28 solvents included in this work. Poor prediction accuracies for the remaining 8 solvents indicate that further factors will be required in the feature set to provide a more generalized predictive morphology model.