Guiding Lead Optimization for Solubility Improvement with Physics-Based Modeling

Free Energy Perturbation Approach for Accurate Crystalline Aqueous Solubility Predictions

Early assessment of crystalline thermodynamic solubility continues to be elusive for drug discovery and development despite its critical importance, especially for the ever-increasing fraction of poorly soluble drug candidates. Here we present a detailed evaluation of a physics-based free energy perturbation (FEP+) approach for computing the thermodynamic aqueous solubility. The predictive power of this approach is assessed across diverse chemical spaces, spanning pharmaceutically relevant literature compounds and more complex AbbVie compounds. Our approach achieves predictive (RMSE = 0.86) and differentiating power (R2 = 0.69) and therefore provides notably improved correlations to experimental solubility compared to state-of-the-art machine learning approaches that utilize quantum mechanics-based descriptors. The importance of explicit considerations of crystalline packing in predicting solubility by the FEP+ approach is also highlighted in this study. Finally, we show how computed energetics, including hydration and sublimation free energies, can provide further insights into molecule design to feed the medicinal chemistry DMTA cycle.

Ensemble Geometric Deep Learning of Aqueous Solubility

Geometric deep learning is one of the main workhorses for harnessing the power of big data to predict molecular properties such as aqueous solubility, which is key to the pharmacokinetic improvement of drug candidates. Two ensembles of graph neural network architectures were built, one based on spectral convolution and the other on spatial convolution. The pretrained models, denoted respectively as SolNet-GCN and SolNet-GAT, significantly outperformed the existing neural networks benchmarked on a validation set of 207 molecules. The SolNet-GCN model demonstrated the best performance on both the training and validation sets, with RMSE values of 0.53 and 0.72 log molar unit and Pearson r2 values of 0.95 and 0.75, respectively. Further, the ranking power of the SolNet models agreed well with a QM-based thermodynamic cycle approach at the PBE-vdW level of theory on a series of benzophenylurea derivatives and a series of benzodiazepine derivatives. Nevertheless, testing the resultant models on a set of inhibitors of the macrophage migration inhibitory factor (MIF) illustrated that the inclusion of atomic attributes to discriminate atoms with a higher tendency to form intermolecular hydrogen bonds in the crystalline state and to identify planar or nonplanar substructures can be beneficial for the prediction of aqueous solubility.

Blinded Predictions and Post Hoc Analysis of the Second Solubility Challenge Data: Exploring Training Data and Feature Set Selection for Machine and Deep Learning Models

Accurate methods to predict solubility from molecular structure are highly sought after in the chemical sciences. To assess the state of the art, the American Chemical Society organized a "Second Solubility Challenge" in 2019, in which competitors were invited to submit blinded predictions of the solubilities of 132 drug-like molecules. In the first part of this article, we describe the development of two models that were submitted to the Blind Challenge in 2019 but which have not previously been reported. These models were based on computationally inexpensive molecular descriptors and traditional machine learning algorithms and were trained on a relatively small data set of 300 molecules. In the second part of the article, to test the hypothesis that predictions would improve with more advanced algorithms and higher volumes of training data, we compare these original predictions with those made after the deadline using deep learning models trained on larger solubility data sets consisting of 2999 and 5697 molecules. The results show that there are several algorithms that are able to obtain near state-of-the-art performance on the solubility challenge data sets, with the best model, a graph convolutional neural network, resulting in an RMSE of 0.86 log units. Critical analysis of the models reveals systematic differences between the performance of models using certain feature sets and training data sets. The results suggest that careful selection of high quality training data from relevant regions of chemical space is critical for prediction accuracy but that other methodological issues remain problematic for machine learning solubility models, such as the difficulty in modeling complex chemical spaces from sparse training data sets.

Purely Predicting the Pharmaceutical Solubility: What to Expect from PC-SAFT and COSMO-RS?

A pair of popular thermodynamic models for pharmaceutical applications, namely, the perturbed-chain statistical associating fluid theory (PC-SAFT) equation of state and the conductor-like screening model for real solvents (COSMO-RS) are thoroughly benchmarked for their performance in predicting the solubility of active pharmaceutical ingredients (APIs) in pure solvents. The ultimate goal is to provide an illustration of what to expect from these progressive frameworks when applied to the thermodynamic solubility of APIs based on activity coefficients in a purely predictive regime without specific experimental solubility data (the fusion properties of pure APIs were taken from experiments). While this kind of prediction represents the typical modus operandi of the first-principles-aided COSMO-RS, PC-SAFT is a relatively highly parametrized model that relies on experimental data, against which its pure-substance and binary interaction parameters (k_ij) are fitted. Therefore, to make this benchmark as fair as possible, we omitted any binary parameters of PC-SAFT (i.e., k_ij = 0 in all cases) and preferred pure-substance parameter sets for APIs not trained to experimental solubility data. This computational approach, together with a detailed assessment of the obtained solubility predictions against a large experimental data set, revealed that COSMO-RS convincingly outperformed PC-SAFT both qualitatively (i.e., COSMO-RS was better in solvent ranking) and quantitatively, even though the former is independent of both substance- and mixture-specific experimental data. Regarding quantitative comparison, COSMO-RS outperformed PC-SAFT for 9 of the 10 APIs and for 63% of the API-solvent systems, with root-mean-square deviations of the predicted data from the entire experimental data set being 0.82 and 1.44 log units, respectively. The results were further analyzed to expand the picture of the performance of both models with respect to the individual APIs and solvents. Interestingly, in many cases, both models were found to qualitatively incorrectly predict the direction of deviations from ideality. Furthermore, we examined how the solubility predictions from both models are sensitive to different API parametrizations.

Designing Soluble PROTACs: Strategies and Preliminary Guidelines

Solubility optimization is a crucial step to obtaining oral PROTACs. Here we measured the thermodynamic solubilities (log S) of 21 commercial PROTACs. Next, we measured BRlogD and log k_w^IAM (lipophilicity), EPSA, and Δ log k_w^IAM (polarity) and showed that lipophilicity plays a major role in governing log S, but a contribution of polarity cannot be neglected. Two-/three-dimensional descriptors calculated on conformers arising from conformational sampling and steered molecular dynamics failed in modeling solubility. Infographic tools were used to identify a privileged region of soluble PROTACs in a chemical space defined by BRlogD, log k_w^IAM and topological polar surface area, while machine learning provided a log S classification model. Finally, for three pairs of PROTACs we measured the solubility, lipophilicity, and polarity of the building blocks and identified the limits of estimating PROTAC solubility from the synthetic components. Overall, this paper provides promising guidelines for optimizing PROTAC solubility in early drug discovery programs.

Boosting the predictive performance with aqueous solubility dataset curation

Intrinsic solubility is a critical property in pharmaceutical industry that impacts in-vivo bioavailability of small molecule drugs. However, solubility prediction with Artificial Intelligence(AI) are facing insufficient data, poor data quality, and no unified measurements for AI and physics-based approaches. We collect 7 aqueous solubility datasets, and present a dataset curation workflow. Evaluating the curated data with two expanded deep learning methods, improved RMSE scores on all curated thermodynamic datasets are observed. We also compare expanded Chemprop enhanced with curated data and state-of-art physics-based approach using pearson and spearman correlation coefficients. A similar performance on pearson with 0.930 and spearman with 0.947 from expanded Chemprop is achieved. A steadily improved pearson and spearman values with increasing data points are also illustrated. Besides that, the computation advantage of AI models enables quick evaluation of a large set of molecules during the hit identification or lead optimization stages, which helps further decision making within the time cycle at drug discovery stage.

Emerging Landscape of Computational Modeling in Pharmaceutical Development

Computational chemistry applications have become an integral part of the drug discovery workflow over the past 35 years. However, computational modeling in support of drug development has remained a relatively uncharted territory for a significant part of both academic and industrial communities. This review considers the computational modeling workflows for three key components of drug preclinical and clinical development, namely, process chemistry, analytical research and development, as well as drug product and formulation development. An overview of the computational support for each step of the respective workflows is presented. Additionally, in context of solid form design, special consideration is given to modern physics-based virtual screening methods. This covers rational approaches to polymorph, coformer, counterion, and solvent virtual screening in support of solid form selection and design.

Computational pharmaceutics - A new paradigm of drug delivery

In recent decades pharmaceutics and drug delivery have become increasingly critical in the pharmaceutical industry due to longer time, higher cost, and less productivity of new molecular entities (NMEs). However, current formulation development still relies on traditional trial-and-error experiments, which are time-consuming, costly, and unpredictable. With the exponential growth of computing capability and algorithms, in recent ten years, a new discipline named "computational pharmaceutics" integrates with big data, artificial intelligence, and multi-scale modeling techniques into pharmaceutics, which offered great potential to shift the paradigm of drug delivery. Computational pharmaceutics can provide multi-scale lenses to pharmaceutical scientists, revealing physical, chemical, mathematical, and data-driven details ranging across pre-formulation studies, formulation screening, in vivo prediction in the human body, and precision medicine in the clinic. The present paper provides a comprehensive and detailed review in all areas of computational pharmaceutics and "Pharma 4.0", including artificial intelligence and machine learning algorithms, molecular modeling, mathematical modeling, process simulation, and physiologically based pharmacokinetic (PBPK) modeling. We not only summarized the theories and progress of these technologies but also discussed the regulatory requirements, current challenges, and future perspectives in the area, such as talent training and a culture change in the future pharmaceutical industry.

Impact of Laser Speed and Drug Particle Size on Selective Laser Sintering 3D Printing of Amorphous Solid Dispersions

This research demonstrates the influence of laser speed and the drug particle size on the manufacturing of amorphous solid dispersions (ASD) and dosage forms thereof using selective laser sintering 3-dimensional (3D) printing. One-step manufacturing of ASD is possible using selective laser sintering 3D printing processes, however, the mechanism of ASD formation by this process is not completely understood and it requires further investigation. We hypothesize that the mechanism of ASD formation is the diffusion and dissolution of the drug in the polymeric carrier during the selective laser sintering (SLS) process and the drug particle size plays a critical role in the formation of said ASDs as there is no mixing involved in the sintering process. Herein, indomethacin was used as a model drug and introduced into the feedstock (Kollidon® VA64 and Candurin® blend) as either unprocessed drug crystals (particle size > 50 µm) or processed hot-melt extruded granules (DosePlus) with reduced drug particle size (<5 µm). These feedstocks were processed at 50, 75, and 100 mm/s scan speed using SLS 3D printing process. Characterization and performance testing were conducted on these tablets which revealed the amorphous conversion of the drug. Both MANOVA and ANOVA analyses depicted that the laser speed and drug particle size significantly impact the drug's apparent solubility and drug release. This significant difference in performance between formulations is attributed to the difference in the extent of dissolution of the drug in the polymeric matrix, leading to residual crystallinity, which is detrimental to ASD's performance. These results demonstrate the influence of drug particle size on solid-state and performance of 3D printed solid dispersions, and, hence, provide a better understanding of the mechanism and limitations of SLS 3D printing of ASDs and its dosage forms.

Toward Physics-Based Solubility Computation for Pharmaceuticals to Rival Informatics

We demonstrate that physics-based calculations of intrinsic aqueous solubility can rival cheminformatics-based machine learning predictions. A proof-of-concept was developed for a physics-based approach via a sublimation thermodynamic cycle, building upon previous work that relied upon several thermodynamic approximations, notably the 2RT approximation, and limited conformational sampling. Here, we apply improvements to our sublimation free-energy model with the use of crystal phonon mode calculations to capture the contributions of the vibrational modes of the crystal. Including these improvements with lattice energies computed using the model-potential-based Ψ_mol method leads to accurate estimates of sublimation free energy. Combining these with hydration free energies obtained from either molecular dynamics free-energy perturbation simulations or density functional theory calculations, solubilities comparable to both experiment and informatics predictions are obtained. The application to coronene, succinic acid, and the pharmaceutical desloratadine shows how the methods must be adapted for the adoption of different conformations in different phases. The approach has the flexibility to extend to applications that cannot be covered by informatics methods.

Novel Physics-Based Ensemble Modeling Approach That Utilizes 3D Molecular Conformation and Packing to Access Aqueous Thermodynamic Solubility: A Case Study of Orally Available Bromodomain and Extraterminal Domain Inhibitor Lead Optimization Series

Drug design with patient centricity for ease of administration and pill burden requires robust understanding of the impact of chemical modifications on relevant physicochemical properties early in lead optimization. To this end, we have developed a physics-based ensemble approach to predict aqueous thermodynamic crystalline solubility, with a 2D chemical structure as the input. Predictions for the bromodomain and extraterminal domain (BET) inhibitor series show very close match (0.5 log unit) with measured thermodynamic solubility for cases with low crystal anisotropy and good match (1 log unit) for high anisotropy structures. The importance of thermodynamic solubility is clearly demonstrated by up to a 4 log unit drop in solubility compared to kinetic (amorphous) solubility in some cases and implications thereof, for instance on human dose. We have also demonstrated that incorporating predicted crystal structures in thermodynamic solubility prediction is necessary to differentiate (up to 4 log unit) between solubility of molecules within the series. Finally, our physics-based ensemble approach provides valuable structural insights into the origins of 3-D conformational landscapes, crystal polymorphism, and anisotropy that can be leveraged for both drug design and development.

Virtual Coformer Screening by Crystal Structure Predictions: Crucial Role of Crystallinity in Pharmaceutical Cocrystallization

One of the most popular strategies of the optimization of drug properties in the pharmaceutical industry appears to be a solid form changing into a cocrystalline form. A number of virtual screening approaches have been previously developed to allow a selection of the most promising cocrystal formers (coformers) for an experimental follow-up. A significant drawback of those methods is related to the lack of accounting for the crystallinity contribution to cocrystal formation. To address this issue, we propose in this study two virtual coformer screening approaches based on a modern cloud-computing crystal structure prediction (CSP) technology at a dispersion-corrected density functional theory (DFT-D) level. The CSP-based methods were for the first time validated on challenging cases of indomethacin and paracetamol cocrystallization, for which the previously developed approaches provided poor predictions. The calculations demonstrated a dramatic improvement of the virtual coformer screening performance relative to the other methods. It is demonstrated that the crystallinity contribution to the formation of paracetamol and indomethacin cocrystals is a dominant one and, therefore, should not be ignored in the virtual screening calculations. Our results encourage a broad utilization of the proposed CSP-based technology in the pharmaceutical industry as the only virtual coformer screening method that directly accounts for the crystallinity contribution.

Lead Compounds in the Context of Extracellular Vesicle Research

Studies of small extracellular vesicles (sEVs), known as exosomes, have been flourishing in the last decade with several achievements, from advancing biochemical knowledge to use in biomedical applications. Physiological changes of sEVs due to the variety of cargos they carry undoubtedly leave an impression that affects the understanding of the mechanism underlying disease and the development of sEV-based shuttles used for treatments and non-invasive diagnostic tools. Indeed, the remarkable properties of sEVs are based on their nature, which helps shield them from recognition by the immune system, protects their payload from biochemical degradation, and contributes to their ability to translocate and convey information between cells and their inherent ability to target disease sites such as tumors that is valid for sEVs derived from cancer cells. However, their transport, biogenesis, and secretion mechanisms are still not thoroughly clear, and many ongoing investigations seek to determine how these processes occur. On the other hand, lead compounds have been playing critical roles in the drug discovery process and have been recently employed in studies of the biogenesis and secretion of sEVs as external agents, affecting sEV release and serving as drug payloads in sEV drug delivery systems. This article gives readers an overview of the roles of lead compounds in these two research areas of sEVs, the rising star in studies of nanoscale medicine.