In Silico Prediction of Aqueous Solubility: The Solubility Challenge

Exploration of the Solubility Hyperspace of Selected Active Pharmaceutical Ingredients in Choline- and Betaine-Based Deep Eutectic Solvents: Machine Learning Modeling and Experimental Validation

Deep eutectic solvents (DESs) are popular green media used for various industrial, pharmaceutical, and biomedical applications. However, the possible compositions of eutectic systems are so numerous that it is impossible to study all of them experimentally. To remedy this limitation, the solubility landscape of selected active pharmaceutical ingredients (APIs) in choline chloride- and betaine-based deep eutectic solvents was explored using theoretical models based on machine learning. The available solubility data for the selected APIs, comprising a total of 8014 data points, were collected for the available neat solvents, binary solvent mixtures, and DESs. This set was augmented with new measurements for the popular sulfa drugs in dry DESs. The descriptors used in the machine learning protocol were obtained from the σ-profiles of the considered molecules computed within the COSMO-RS framework. A combination of six sets of descriptors and 36 regressors were tested. Taking into account both accuracy and generalization, it was concluded that the best regressor is nuSVR regressor-based predictive models trained using the relative intermolecular interactions and a twelve-step averaged simplification of the relative σ-profiles.

Tuning Ferulic Acid Solubility in Choline-Chloride- and Betaine-Based Deep Eutectic Solvents: Experimental Determination and Machine Learning Modeling

Deep eutectic solvents (DES) represent a promising class of green solvents, offering particular utility in the extraction and development of new formulations of natural compounds such as ferulic acid (FA). The experimental phase of the study undertook a systematic investigation of the solubility of FA in DES, comprising choline chloride or betaine as hydrogen bond acceptors and six different polyols as hydrogen bond donors. The results demonstrated that solvents based on choline chloride were more effective than those based on betaine. The optimal ratio of hydrogen bond acceptors to donors was found to be 1:2 molar. The addition of water to the DES resulted in a notable enhancement in the solubility of FA. Among the polyols tested, triethylene glycol was the most effective. Hence, DES composed of choline chloride and triethylene glycol (TEG) (1:2) with added water in a 0.3 molar ration is suggested as an efficient alternative to traditional organic solvents like DMSO. In the second part of this report, the affinities of FA in saturated solutions were computed for solute-solute and all solute-solvent pairs. It was found that self-association of FA leads to a cyclic structure of the C28 type, common among carboxylic acids, which is the strongest type of FA affinity. On the other hand, among all hetero-molecular bi-complexes, the most stable is the FA-TEG pair, which is an interesting congruency with the high solubility of FA in TEG containing liquids. Finally, this work combined COSMO-RS modeling with machine learning for the development of a model predicting ferulic acid solubility in a wide range of solvents, including not only DES but also classical neat and binary mixtures. A machine learning protocol developed a highly accurate model for predicting FA solubility, significantly outperforming the COSMO-RS approach. Based on the obtained results, it is recommended to use the support vector regressor (SVR) for screening new dissolution media as it is not only accurate but also has sound generalization to new systems.

Graph Neural Networks for Predicting Solubility in Diverse Solvents Using MolMerger Incorporating Solute-Solvent Interactions

The prediction of solubility is a complex and challenging physicochemical problem that has tremendous implications for the chemical and pharmaceutical industry. Recent advancements in machine learning methods have provided a great scope for predicting the reliable solubility of a large number of molecular systems. However, most of these methods rely on using physical properties obtained from experiments and expensive quantum chemical calculations. Here, we developed a method that utilizes a graphical representation of solute-solvent interactions using "MolMerger," which captures the strongest polar interactions between molecules using Gasteiger charges and creates a graph incorporating the true nature of the system. Using these graphs as input, a neural network learns the correlation between the structural properties of a molecule in the form of node embedding and its physicochemical properties as the output. This approach has been used to calculate molecular solubility by predicting the Log solubility values of various organic molecules and pharmaceuticals in diverse sets of solvents.

Experimental and Machine-Learning-Assisted Design of Pharmaceutically Acceptable Deep Eutectic Solvents for the Solubility Improvement of Non-Selective COX Inhibitors Ibuprofen and Ketoprofen

Deep eutectic solvents (DESs) are commonly used in pharmaceutical applications as excellent solubilizers of active substances. This study investigated the tuning of ibuprofen and ketoprofen solubility utilizing DESs containing choline chloride or betaine as hydrogen bond acceptors and various polyols (ethylene glycol, diethylene glycol, triethylene glycol, glycerol, 1,2-propanediol, 1,3-butanediol) as hydrogen bond donors. Experimental solubility data were collected for all DES systems. A machine learning model was developed using COSMO-RS molecular descriptors to predict solubility. All studied DESs exhibited a cosolvency effect, increasing drug solubility at modest concentrations of water. The model accurately predicted solubility for ibuprofen, ketoprofen, and related analogs (flurbiprofen, felbinac, phenylacetic acid, diphenylacetic acid). A machine learning approach utilizing COSMO-RS descriptors enables the rational design and solubility prediction of DES formulations for improved pharmaceutical applications.

Advances in machine intelligence-driven virtual screening approaches for big-data

Virtual screening (VS) is an integral and ever-evolving domain of drug discovery framework. The VS is traditionally classified into ligand-based (LB) and structure-based (SB) approaches. Machine intelligence or artificial intelligence has wide applications in the drug discovery domain to reduce time and resource consumption. In combination with machine intelligence algorithms, VS has emerged into revolutionarily progressive technology that learns within robust decision orders for data curation and hit molecule screening from large VS libraries in minutes or hours. The exponential growth of chemical and biological data has evolved as "big-data" in the public domain demands modern and advanced machine intelligence-driven VS approaches to screen hit molecules from ultra-large VS libraries. VS has evolved from an individual approach (LB and SB) to integrated LB and SB techniques to explore various ligand and target protein aspects for the enhanced rate of appropriate hit molecule prediction. Current trends demand advanced and intelligent solutions to handle enormous data in drug discovery domain for screening and optimizing hits or lead with fewer or no false positive hits. Following the big-data drift and tremendous growth in computational architecture, we presented this review. Here, the article categorized and emphasized individual VS techniques, detailed literature presented for machine learning implementation, modern machine intelligence approaches, and limitations and deliberated the future prospects.

Will we ever be able to accurately predict solubility?

Accurate prediction of thermodynamic solubility by machine learning remains a challenge. Recent models often display good performances, but their reliability may be deceiving when used prospectively. This study investigates the origins of these discrepancies, following three directions: a historical perspective, an analysis of the aqueous solubility dataverse and data quality. We investigated over 20 years of published solubility datasets and models, highlighting overlooked datasets and the overlaps between popular sets. We benchmarked recently published models on a novel curated solubility dataset and report poor performances. We also propose a workflow to cure aqueous solubility data aiming at producing useful models for bench chemist. Our results demonstrate that some state-of-the-art models are not ready for public usage because they lack a well-defined applicability domain and overlook historical data sources. We report the impact of factors influencing the utility of the models: interlaboratory standard deviation, ionic state of the solute and data sources. The herein obtained models, and quality-assessed datasets are publicly available.

In silico Exploration of a Novel ICMT Inhibitor with More Solubility than Cysmethynil against Membrane Localization of KRAS Mutant in Colorectal Cancer

BACKGROUND

ICMT (isoprenylcysteine carboxyl methyltransferase) is an enzyme that plays a key role in the post-translational modification of the K-Ras protein. The carboxyl methylation of this protein by ICMT is important for its proper localization and function. Cysmethynil (2-[5-(3-methylphenyl)-l-octyl-lH-indolo-3-yl] acetamide) causes K-Ras mislocalization and interrupts pathways that control cancer cell growth and division through inhibition of ICMT, but its poor water solubility makes it difficult and impractical for clinical use. This indicates that relatively high amounts of cysmethynil would be required to achieve an effective dose, which could result in significant adverse effects in patients.

OBJECTIVE

The general objective of this work was to find virtually new compounds that present high solubility in water and are similar to the pharmacological activity of cysmethynil.

MATERIALS AND METHODS

Pharmacophore modeling, pharmacophore-based virtual screening, prediction of ADMET properties (absorption, distribution, metabolism, excretion, and toxicity), and water solubility were performed to recover a water-soluble molecule that shares the same chemical characteristics as cysmethynil using Discovery Studio v16.1.0 (DS16.1), SwissADME server, and pkCSM server.

RESULTS

In this study, ten pharmacophore model hypotheses were generated by exploiting the characteristics of cysmethynil. The pharmacophore model validated by the set test method was used to screen the "Elite Library®" and "Synergy Library" databases of Asinex. Only 1533 compounds corresponding to all the characteristics of the pharmacophore were retained. Then, the aqueous solubility in water at 25°C of these 1533 compounds was predicted by the Cheng and Merz model. Among these 1533 compounds, two had the optimal water solubility. Finally, the ADMET properties and Log S water solubility by three models (ESOL, Ali, and SILICOS-IT) of the two compounds and cysmethynil were compared, resulting in compound 2 as a potential inhibitor of ICMT.

CONCLUSION

According to the results obtained, the identified compound presented a high solubility in water and could be similar to the pharmacological activity of cysmethynil.

Recent Studies of Artificial Intelligence on In Silico Drug Absorption

Absorption is an important area of research in pharmacochemistry and drug development, because the drug has to be absorbed before any drug effects can occur. Furthermore, the ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) profile of drugs can be directly and considerably altered by modulating factors affecting absorption. Many drugs in development fail because of poor absorption. The research and continuous efforts of researchers in recent years have brought many successes and promises in drug absorption property prediction, especially in silico, which helps to reduce the time and cost significantly for screening undesirable drug candidates. In this report, we explicitly provide an overview of recent in silico studies on predicting absorption properties, especially from 2019 to the present, using artificial intelligence. Additionally, we have collected and investigated public databases that support absorption prediction research. On those grounds, we also proposed the challenges and development directions of absorption prediction in the future. We hope this review can provide researchers with valuable guidelines on absorption prediction to facilitate the development of newer approaches in drug discovery.

COSMO Models for the Pharmaceutical Development of Parenteral Drug Formulations

The aqueous solubility of active pharmaceutical ingredients is one of the most important features to be considered during the development of parenteral formulations in the pharmaceutical industry. Computational modelling has become in the last years an integral part of pharmaceutical development. In this context, ab initio computational models, such as COnductor-like Screening MOdel (COSMO), have been proposed as promising tools for the prediction of results without the effective use of resources. Nevertheless, despite the clear evaluation of computational resources, some authors had not achieved satisfying results and new calculations and algorithms have been proposed over the years to improve the outcomes. In the development and production of aqueous parenteral formulations, the solubility of Active Pharmaceutical Ingredients (APIs) in an aqueous and biocompatible vehicle is a decisive step. This work aims to study the hypothesis that COSMO models could be useful in the development of new parenteral formulations, mainly aqueous ones.

Prediction model for milk transfer of drugs by primarily evaluating the area under the curve using QSAR/QSPR

PURPOSE

Information on milk transferability of drugs is important for patients who wish to breastfeed. The purpose of this study is to develop a prediction model for milk-to-plasma drug concentration ratio based on area under the curve (M/P_AUC). The quantitative structure-activity/property relationship (QSAR/QSPR) approach was used to predict compounds involved in active transport during milk transfer.

METHODS

We collected M/P ratio data from literature, which were curated and divided into M/P_AUC ≥ 1 and M/P_AUC < 1. Using the ADMET Predictor® and ADMET Modeler™, we constructed two types of binary classification models: an artificial neural network (ANN) and a support vector machine (SVM).

RESULTS

M/P ratios of 403 compounds were collected, M/P_AUC data were obtained for 173 compounds, while 230 compounds only had M/P_non-AUC values reported. The models were constructed using 129 of the 173 compounds, excluding colostrum data. The sensitivity of the ANN model was 0.969 for the training set and 0.833 for the test set, while the sensitivity of the SVM model was 0.971 for the training set and 0.667 for the test set. The contribution of the charge-based descriptor was high in both models.

CONCLUSIONS

We built a M/P_AUC prediction model using QSAR/QSPR. These predictive models can play an auxiliary role in evaluating the milk transferability of drugs.

Thermodynamic Correlation between Liquid-Liquid Phase Separation and Crystalline Solubility of Drug-Like Molecules

The purpose of the present study was to experimentally confirm the thermodynamic correlation between the intrinsic liquid−liquid phase separation (LLPS) concentration (S0LLPS) and crystalline solubility (S0c) of drug-like molecules. Based on the thermodynamic principles, the crystalline solubility LLPS concentration melting point (Tm) equation (CLME) was derived (log10S0C=log10S0LLPS−0.0095Tm−310 for 310 K). The S0LLPS values of 31 drugs were newly measured by simple bulk phase pH-shift or solvent-shift precipitation tests coupled with laser-assisted visual turbidity detection. To ensure the precipitant was not made crystalline at <10 s, the precipitation tests were also performed under the polarized light microscope. The calculated and observed log10S0C values showed a good correlation (root mean squared error: 0.40 log unit, absolute average error: 0.32 log unit).

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.

In Vitro and In Silico Study of Analogs of Plant Product Plastoquinone to Be Effective in Colorectal Cancer Treatment

Plants have paved the way for the attainment of molecules with a wide-range of biological activities. However, plant products occasionally show low biological activities and/or poor pharmacokinetic properties. In that case, development of their derivatives as drugs from the plant world has been actively performed. As plant products, plastoquinones (PQs) have been of high importance in anticancer drug design and discovery; we have previously evaluated and reported the potential cytotoxic effects of a series of PQ analogs. Among these analogs, PQ2, PQ3 and PQ10 were selected for National Cancer Institute (NCI) for in vitro screening of anticancer activity against a wide range of cancer cell lines. The apparent superior anticancer potency of PQ2 on the HCT-116 colorectal cancer cell line than that of PQ3 and PQ10 compared to other tested cell lines has encouraged us to perform further mechanistic studies to enlighten the mode of anti-colorectal cancer action of PQ2. For this purpose, its apoptotic effects on the HCT-116 cell line, DNA binding capacity and several crucial pharmacokinetic properties were investigated. Initially, MTT assay was conducted for PQ2 at different concentrations against HCT-116 cells. Results indicated that PQ2 exhibited significant cytotoxicity in HCT-116 cells with an IC₅₀ value of 4.97 ± 1.93 μM compared to cisplatin (IC₅₀ = 26.65 ± 7.85 μM). Moreover, apoptotic effects of PQ2 on HCT-116 cells were investigated by the annexin V/ethidium homodimer III staining method and PQ2 significantly induced apoptosis in HCT-116 cells compared to cisplatin. Based on the potent DNA cleavage capacity of PQ2, molecular docking studies were conducted in the minor groove of the double helix of DNA and PQ2 presented a key hydrogen bonding through its methoxy moiety. Overall, both in vitro and in silico studies indicated that effective, orally bioavailable drug-like PQ2 attracted attention for colorectal cancer treatment. The most important point to emerge from this study is that appropriate derivatization of a plant product leads to unique biologically active compounds.

Application of Artificial Neural Networks to Predict the Intrinsic Solubility of Drug-Like Molecules

Machine learning (ML) approaches are receiving increasing attention from pharmaceutical companies and regulatory agencies, given their ability to mine knowledge from available data. In drug discovery, for example, they are employed in quantitative structure-property relationship (QSPR) models to predict biological properties from the chemical structure of a drug molecule. In this paper, following the Second Solubility Challenge (SC-2), a QSPR model based on artificial neural networks (ANNs) was built to predict the intrinsic solubility (logS0) of the 100-compound low-variance tight set and the 32-compound high-variance loose set provided by SC-2 as test datasets. First, a training dataset of 270 drug-like molecules with logS0 value experimentally determined was gathered from the literature. Then, a standard three-layer feed-forward neural network was defined by using 10 ChemGPS physico-chemical descriptors as input features. The developed ANN showed adequate predictive performances on both of the SC-2 test datasets. Benefits and limitations of ML approaches have been highlighted and discussed, starting from this case-study. The main findings confirmed that ML approaches are an attractive and promising tool to predict logS0; however, many aspects, such as data quality, molecular descriptor computation and selection, and assessment of applicability domain, are crucial but often neglected, and should be carefully considered to improve predictions based on ML.

Design, synthesis and investigation of the mechanism of action underlying anti-leukemic effects of the quinolinequinones as LY83583 analogs

Literature conclusively shows that one of the quinolinequinone analogs (6-anilino-5,8-quinolinequinone), referred to as LY83583 hereafter, an inhibitor of guanylyl cyclase, was used as the inhibitor of the cell proliferation in cancer cells. In the present work, a series of analogs of the LY83583 containing alkoxy group(s) in aminophenyl ring (AQQ1-15) were designed and synthesized via a two-step route and evaluated for their in vitro cytotoxic activity against four different cancer cell lines (K562, Jurkat, MT-2, and HeLa) and human peripheral blood mononuclear cells (PBMCs) by MTT assay. The analog (AQQ13) was identified to possess the most potent cytotoxic activity against K562 human chronic myelogenous (CML) cell line (IC₅₀ = 0.59 ± 0.07 μM) with significant selectivity (SI = 4.51) compared to imatinib (IC₅₀ = 5.46 ± 0.85 μM; SI = 4.60). Based on its superior cytotoxic activity, the analog AQQ13 was selected for further mechanistic studies including determination of its apoptotic effects on K562 cell line via annexin V/ethidium homodimer III staining potency, ABL1 kinase inhibitory activity, and DNA cleaving capacity. Results ascertained that the analog AQQ13 induced apoptosis in K562 cell line with notable DNA-cleaving activity. However, AQQ13 demonstrated weak ABL1 inhibition indicating the correlation between anti-K562 and anti-ABL1 activities. In continuance, respectively conducted in silico molecular docking and Absorption, Distribution, Metabolism, and Excretion (ADME) studies drew attention to enhanced binding interactions of AQQ13 towards DNA and its high compatibility with the potential limits of specified pharmacokinetic parameters making it as a potential anti-leukemic drug candidate. Our findings may provide a new insight for further development of novel quinolinequinone-based anticancer analogs against CML.

Potential inhibitors of methionine aminopeptidase type II identified via structure-based pharmacophore modeling

Methionine aminopeptidase (MetAP2) is a metal-containing enzyme that removes initiator methionine from the N-terminus of a newly synthesized protein. Inhibition of the enzyme is crucial in diminishing cancer growth and metastasis. Fumagillin-a natural irreversible inhibitor of MetAP2-and its derivatives are used as potent MetAP2 inhibitors. However, because of their adverse effects, none of them has progressed to clinical studies. In search for potential reversible inhibitors, we built structure-based pharmacophore models using the crystal structure of MetAP2 complexed with fumagillin (PDB ID: 1BOA). The pharmacophore models were validated using Gunner-Henry scoring method. The best pharmacophore consisting of 1 H-bond donor, 1 H-bond acceptor, and 3 hydrophobic features was used to conduct pharmacophore-based virtual screening of ZINC15 database against MetAP2. The top 10 compounds with pharmacophore fit values > 3.00 were selected for further analysis. These compounds were subjected to absorption, distribution, metabolism, elimination, and toxicity (ADMET) prediction and found to have druglike properties. Furthermore, molecular docking calculations was performed on these hits using AutoDock4 to predict their binding mode and binding energy. Three diverse compounds: ZINC000014903160, ZINC000040174591, and ZINC000409110720 with respective binding energy/docking scores of - 9.22, - 9.21, and -817 kcal/mol, were submitted to 100 ns (MD) simulations using Nanoscale MD (NAMD) software. The compounds showed stable binding mode over time. Therefore, they may serve as a scaffold for further computational and experimental optimization toward the design of more potent and safer MetAP2 inhibitors.

Pushing the limits of solubility prediction via quality-oriented data selection

Accurate prediction of the solubility of chemical substances in solvents remains a challenge. The sparsity of high-quality solubility data is recognized as the biggest hurdle in the development of robust data-driven methods for practical use. Nonetheless, the effects of the quality and quantity of data on aqueous solubility predictions have not yet been scrutinized. In this study, the roles of the size and the quality of data sets on the performances of the solubility prediction models are unraveled, and the concepts of actual and observed performances are introduced. In an effort to curtail the gap between actual and observed performances, a quality-oriented data selection method, which evaluates the quality of data and extracts the most accurate part of it through statistical validation, is designed. Applying this method on the largest publicly available solubility database and using a consensus machine learning approach, a top-performing solubility prediction model is achieved.

Molecular Dynamics Simulations in Drug Discovery and Pharmaceutical Development

Molecular dynamics (MD) simulations have become increasingly useful in the modern drug development process. In this review, we give a broad overview of the current application possibilities of MD in drug discovery and pharmaceutical development. Starting from the target validation step of the drug development process, we give several examples of how MD studies can give important insights into the dynamics and function of identified drug targets such as sirtuins, RAS proteins, or intrinsically disordered proteins. The role of MD in antibody design is also reviewed. In the lead discovery and lead optimization phases, MD facilitates the evaluation of the binding energetics and kinetics of the ligand-receptor interactions, therefore guiding the choice of the best candidate molecules for further development. The importance of considering the biological lipid bilayer environment in the MD simulations of membrane proteins is also discussed, using G-protein coupled receptors and ion channels as well as the drug-metabolizing cytochrome P450 enzymes as relevant examples. Lastly, we discuss the emerging role of MD simulations in facilitating the pharmaceutical formulation development of drugs and candidate drugs. Specifically, we look at how MD can be used in studying the crystalline and amorphous solids, the stability of amorphous drug or drug-polymer formulations, and drug solubility. Moreover, since nanoparticle drug formulations are of great interest in the field of drug delivery research, different applications of nano-particle simulations are also briefly summarized using multiple recent studies as examples. In the future, the role of MD simulations in facilitating the drug development process is likely to grow substantially with the increasing computer power and advancements in the development of force fields and enhanced MD methodologies.

ADME prediction with KNIME: In silico aqueous solubility consensus model based on supervised recursive random forest approaches

In-silico prediction of aqueous solubility plays an important role during the drug discovery and development processes. For many years, the limited performance of in-silico solubility models has been attributed to the lack of high-quality solubility data for pharmaceutical molecules. However, some studies suggest that the poor accuracy of solubility prediction is not related to the quality of the experimental data and that more precise methodologies (algorithms and/or set of descriptors) are required for predicting aqueous solubility for pharmaceutical molecules. In this study a large and diverse database was generated with aqueous solubility values collected from two public sources; two new recursive machine-learning approaches were developed for data cleaning and variable selection, and a consensus model based on regression and classification algorithms was created. The modeling protocol, which includes the curation of chemical and experimental data, was implemented in KNIME, with the aim of obtaining an automated workflow for the prediction of new databases. Finally, we compared several methods or models available in the literature with our consensus model, showing results comparable or even outperforming previous published models.

Different molecular enumeration influences in deep learning: an example using aqueous solubility

Aqueous solubility is the key property driving many chemical and biological phenomena and impacts experimental and computational attempts to assess those phenomena. Accurate prediction of solubility is essential and challenging, even with modern computational algorithms. Fingerprint-based, feature-based and molecular graph-based representations have all been used with different deep learning methods for aqueous solubility prediction. It has been clearly demonstrated that different molecular representations impact the model prediction and explainability. In this work, we reviewed different representations and also focused on using graph and line notations for modeling. In general, one canonical chemical structure is used to represent one molecule when computing its properties. We carefully examined the commonly used simplified molecular-input line-entry specification (SMILES) notation representing a single molecule and proposed to use the full enumerations in SMILES to achieve better accuracy. A convolutional neural network (CNN) was used. The full enumeration of SMILES can improve the presentation of a molecule and describe the molecule with all possible angles. This CNN model can be very robust when dealing with large datasets since no additional explicit chemistry knowledge is necessary to predict the solubility. Also, traditionally it is hard to use a neural network to explain the contribution of chemical substructures to a single property. We demonstrated the use of attention in the decoding network to detect the part of a molecule that is relevant to solubility, which can be used to explain the contribution from the CNN.

Prediction of adsorption capacity for pharmaceuticals, personal care products and endocrine disrupting chemicals onto various adsorbent materials

Adsorption is a common process used to remove pharmaceuticals, personal care products and endocrine disrupting chemicals (PPCPs/EDCs) from water. However, as PPCPs/EDCs cover a wide range of molecules and chemical structures, prediction of the adsorption capacity is very challenging. In this study, a novel model was developed to predict adsorption isotherms of PPCPs/EDCs onto various types of adsorbents using a combination of Polanyi potential theory, molecular connectivity indices (MCIs) and molecular characteristics. Polanyi theory provided the basic mathematical form for the correlation. MCIs, hydrophobicity and H-bond count were used to normalize the Polanyi equation based on the molecular structure and interactions among the chemicals, the adsorbents, and the solution. In total, adsorption data were collected from 158 reports for 55 PPCPs/EDCs onto 306 different adsorbent materials. The correlation was first trained with 46 PPCPs/EDCs adsorbed onto 162 carbonaceous adsorbents (CAs), with 44.8% SDEV. Then the model was employed to predict 46 PPCPs/EDCs onto 118 other CAs and 9 new PPCPs/EDCs onto 23 CAs in ultrapure water, with error from 42 to 48% SDEV. When applying to non-carbonaceous adsorbents, the models can still predict the adsorption of PPCPs/EDCs with 90.09% SDEV. For the first time, a model, the PD - MCI - hydrophobic - H bond model, was developed to predict adsorption of a wide group of complicated PPCPs/EDCs onto a big variety of carbonaceous and non-carbonaceous adsorbents. The proposed model approach may provide a simple means for predicting adsorption capacities of PPCPs/EDCs onto various adsorbents.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

In silico Tools at Early Stage of Pharmaceutical Development: Data Needs and Software Capabilities

In early drug development, the selection of a formulation platform and decisions on formulation strategies have to be made within a short timeframe and often with minimal use of the active pharmaceutical ingredient (API). The current work evaluated the various physicochemical parameters required to improve the prediction accuracy of simulation software for immediate release tablets in early drug development. DDDPlus™ was used in simulating dissolution test profiles of immediate release tablets of ritonavir and all simulations were compared with experimental results. The minimum data requirements to make useful predictions were assessed using the ADMET predictor (part of DDDPlus) and Chemicalize (an online resource). A surfactant model was developed to estimate the solubility enhancement in media containing surfactant and the software's transfer model based on the USP two-tiered dissolution test was assessed. One measured data point was shown to be sufficient to make predictive simulations in DDDPlus. At pH 2.0, the software overestimated drug release while at pH 1.0 and 6.8, simulations were close to the measured values. A surfactant solubility model established with measured data gave good dissolution predictions. The transfer model uses a single-vessel model and was unable to predict the two in vivo environments separately. For weak bases like ritonavir, a minimum of three solubility data points is recommended for in silico predictions in buffered media. A surfactant solubility model is useful when predicting dissolution behavior in surfactant media and in silico predictions need measured solubility data to be predictive.

Molecular simulation as a computational pharmaceutics tool to predict drug solubility, solubilization processes and partitioning

In this review we will discuss how computational methods, and in particular classical molecular dynamics simulations, can be used to calculate solubility of pharmaceutically relevant molecules and systems. To the extent possible, we focus on the non-technical details of these calculations, and try to show also the added value of a more thorough and detailed understanding of the solubilization process obtained by using computational simulations. Although the main focus is on classical molecular dynamics simulations, we also provide the reader with some insights into other computational techniques, such as the COSMO-method, and also discuss Flory-Huggins theory and solubility parameters. We hope that this review will serve as a valuable starting point for any pharmaceutical researcher, who has not yet fully explored the possibilities offered by computational approaches to solubility calculations.

Aqueous Drug Solubility: What Do We Measure, Calculate and QSPR Predict?

Detailed critical analysis of publications devoted to QSPR of aqueous solubility is presented in the review with discussion of four types of aqueous solubility (three different thermodynamic solubilities with unknown solute structure, intrinsic solubility, solubility in physiological media at pH=7.4 and kinetic solubility), variety of molecular descriptors (from topological to quantum chemical), traditional statistical and machine learning methods as well as original QSPR models.

Visual and Semantic Enrichment of Analytical Chemistry Literature Searches by Combining Text Mining and Computational Chemistry

The open-access scientific literature contains a wealth of information for meaningful text mining. However, this information is not always easy to retrieve. This technical note addresses the problem by a new flexible method combining in a single workflow existing resources for literature searches, text mining, and large-scale prediction of physicochemical and biological properties. The results are visualized as virtual mass spectra, chromatograms, or images in styles new to text mining but familiar to analytical chemistry. The method is demonstrated on comparisons of analytical-chemistry techniques and semantically enriched searches for proteins and their activities, but it may also be of general utility in experimental design, drug discovery, chemical syntheses, business intelligence, and historical studies. The method is realized in shareable scientific workflows using only freely available data, services, and software that scale to millions of publications and named chemical entities in the literature.

Improved understanding of aqueous solubility modeling through topological data analysis

Topological data analysis is a family of recent mathematical techniques seeking to understand the 'shape' of data, and has been used to understand the structure of the descriptor space produced from a standard chemical informatics software from the point of view of solubility. We have used the mapper algorithm, a TDA method that creates low-dimensional representations of data, to create a network visualization of the solubility space. While descriptors with clear chemical implications are prominent features in this space, reflecting their importance to the chemical properties, an unexpected and interesting correlation between chlorine content and rings and their implication for solubility prediction is revealed. A parallel representation of the chemical space was generated using persistent homology applied to molecular graphs. Links between this chemical space and the descriptor space were shown to be in agreement with chemical heuristics. The use of persistent homology on molecular graphs, extended by the use of norms on the associated persistence landscapes allow the conversion of discrete shape descriptors to continuous ones, and a perspective of the application of these descriptors to quantitative structure property relations is presented.

Brief overview of solubility methods: Recent trends in equilibrium solubility measurement and predictive models

Solubility is a crucial physicochemical parameter affecting the whole process of drug discovery and development. Thus, understanding of the methods and concepts to measure and predict this propensity are of utmost importance for the pharmaceutical scientist. Despite their inherent limitations, kinetic solubility screening methods became routine assays by mimicking bioassay conditions and guiding the lead optimization process. In contrast, thermodynamic solubility methods show a clear evolution: miniaturized high throughput assays coupled to analytical techniques such as solid-state characterization, ultra performance liquid chromatography, or polychromatic turbidimetry, have been developed, thereby enabling a more complex physicochemical profiling at the early discovery stage. Solubility prediction still poses a significant challenge at the industrial level. Classification and critical evaluation of recent in silico models are provided. Discussion of experimental and computational methods: was based on relevant industrial references.

Automated assays for thermodynamic (equilibrium) solubility determination

Solubility is a crucial physicochemical property for drug candidates and is important in both drug discovery and development. Poor solubility is detrimental to absorption after oral administration and can mask compound activity in bioassays in various ways. Hence, solubility liabilities should ideally be identified as early as possible in the drug development process. With the increasing number of compounds as potential drug candidates, automated thermodynamic solubility assays for high throughput screening enabling rapid evaluation of a large number of compounds are becoming increasingly important. This review discusses the current status of the most widely used automated assays for thermodynamic solubility, followed by recent high throughput measurements of properties related to solubility (e.g. dissolution rate and supersaturation) and a brief overview of predictive computational methods for thermodynamic solubility reported in the literature.

OPERA models for predicting physicochemical properties and environmental fate endpoints

The collection of chemical structure information and associated experimental data for quantitative structure–activity/property relationship (QSAR/QSPR) modeling is facilitated by an increasing number of public databases containing large amounts of useful data. However, the performance of QSAR models highly depends on the quality of the data and modeling methodology used. This study aims to develop robust QSAR/QSPR models for chemical properties of environmental interest that can be used for regulatory purposes. This study primarily uses data from the publicly available PHYSPROP database consisting of a set of 13 common physicochemical and environmental fate properties. These datasets have undergone extensive curation using an automated workflow to select only high-quality data, and the chemical structures were standardized prior to calculation of the molecular descriptors. The modeling procedure was developed based on the five Organization for Economic Cooperation and Development (OECD) principles for QSAR models. A weighted k-nearest neighbor approach was adopted using a minimum number of required descriptors calculated using PaDEL, an open-source software. The genetic algorithms selected only the most pertinent and mechanistically interpretable descriptors (2–15, with an average of 11 descriptors). The sizes of the modeled datasets varied from 150 chemicals for biodegradability half-life to 14,050 chemicals for logP, with an average of 3222 chemicals across all endpoints. The optimal models were built on randomly selected training sets (75%) and validated using fivefold cross-validation (CV) and test sets (25%). The CV Q² of the models varied from 0.72 to 0.95, with an average of 0.86 and an R² test value from 0.71 to 0.96, with an average of 0.82. Modeling and performance details are described in QSAR model reporting format and were validated by the European Commission’s Joint Research Center to be OECD compliant. All models are freely available as an open-source, command-line application called OPEn structure–activity/property Relationship App (OPERA). OPERA models were applied to more than 750,000 chemicals to produce freely available predicted data on the U.S. Environmental Protection Agency’s CompTox Chemistry Dashboard.

Thermodynamics of Indomethacin Adsorption to Phospholipid Membranes

Using second-harmonic generation, we directly monitored adsorption of indomethacin, a nonsteroidal anti-inflammatory drug, to supported lipid bilayers composed of phospholipids of varying phase, cholesterol content, and head group charge without the use of extrinsic labels at therapeutically relevant aqueous concentrations. Indomethacin adsorbed to gel-phase lipids with a high binding affinity, suggesting that like other arylacetic acid-containing drugs, it preferentially interacts with ordered lipid domains. We discovered that adsorption of indomethacin to gel-phase phospholipids was endothermic and entropically driven, whereas adsorption to fluid-phase phospholipids was exothermic and enthalpically driven. As temperature increased from 19 to 34 °C, binding affinities to gel-phase lipids increased by 7-fold but relative surface concentration decreased to one-fifth of the original value. We also compared our results to the entropies reported for indomethacin adsorbed to surfactant micelles, which are used in drug delivery systems, and assert that adsorbed water molecules in the phospholipid bilayer may be buried deeper into the acyl chains and less accessible for disruption. The thermodynamic studies reported here provide mechanistic insight into indomethacin interactions with mammalian plasma membranes in the gastrointestinal tract and inform studies of drug delivery, where indomethacin is commonly used as a prototypical, hydrophobic small-molecule drug.

In Silico Prediction of Physicochemical Properties of Environmental Chemicals Using Molecular Fingerprints and Machine Learning

There are little available toxicity data on the vast majority of chemicals in commerce. High-throughput screening (HTS) studies, such as those being carried out by the U.S. Environmental Protection Agency (EPA) ToxCast program in partnership with the federal Tox21 research program, can generate biological data to inform models for predicting potential toxicity. However, physicochemical properties are also needed to model environmental fate and transport, as well as exposure potential. The purpose of the present study was to generate an open-source quantitative structure-property relationship (QSPR) workflow to predict a variety of physicochemical properties that would have cross-platform compatibility to integrate into existing cheminformatics workflows. In this effort, decades-old experimental property data sets available within the EPA EPI Suite were reanalyzed using modern cheminformatics workflows to develop updated QSPR models capable of supplying computationally efficient, open, and transparent HTS property predictions in support of environmental modeling efforts. Models were built using updated EPI Suite data sets for the prediction of six physicochemical properties: octanol-water partition coefficient (logP), water solubility (logS), boiling point (BP), melting point (MP), vapor pressure (logVP), and bioconcentration factor (logBCF). The coefficient of determination (R2) between the estimated values and experimental data for the six predicted properties ranged from 0.826 (MP) to 0.965 (BP), with model performance for five of the six properties exceeding those from the original EPI Suite models. The newly derived models can be employed for rapid estimation of physicochemical properties within an open-source HTS workflow to inform fate and toxicity prediction models of environmental chemicals.

Using MD Simulations To Calculate How Solvents Modulate Solubility

Here, our interest is in predicting solubility in general, and we focus particularly on predicting how the solubility of particular solutes is modulated by the solvent environment. Solubility in general is extremely important, both for theoretical reasons - it provides an important probe of the balance between solute-solute and solute-solvent interactions - and for more practical reasons, such as how to control the solubility of a given solute via modulation of its environment, as in process chemistry and separations. Here, we study how the change of solvent affects the solubility of a given compound. That is, we calculate relative solubilities. We use MD simulations to calculate relative solubility and compare our calculated values with experiment as well as with results from several other methods, SMD and UNIFAC, the latter of which is commonly used in chemical engineering design. We find that straightforward solubility calculations based on molecular simulations using a general small-molecule force field outperform SMD and UNIFAC both in terms of accuracy and coverage of the relevant chemical space.

In silico ADME/T modelling for rational drug design

In recent decades, in silico absorption, distribution, metabolism, excretion (ADME), and toxicity (T) modelling as a tool for rational drug design has received considerable attention from pharmaceutical scientists, and various ADME/T-related prediction models have been reported. The high-throughput and low-cost nature of these models permits a more streamlined drug development process in which the identification of hits or their structural optimization can be guided based on a parallel investigation of bioavailability and safety, along with activity. However, the effectiveness of these tools is highly dependent on their capacity to cope with needs at different stages, e.g. their use in candidate selection has been limited due to their lack of the required predictability. For some events or endpoints involving more complex mechanisms, the current in silico approaches still need further improvement. In this review, we will briefly introduce the development of in silico models for some physicochemical parameters, ADME properties and toxicity evaluation, with an emphasis on the modelling approaches thereof, their application in drug discovery, and the potential merits or deficiencies of these models. Finally, the outlook for future ADME/T modelling based on big data analysis and systems sciences will be discussed.

Simulation of in vitro dissolution behavior using DDDPlus™

Dissolution testing is a performance test for many dosage forms including tablets and capsules. The objective of this study was to evaluate if computer simulations can predict the in vitro dissolution of two model drugs for which different dissolution data were available. Published montelukast sodium and glyburide dissolution data was used for the simulations. Different pharmacopeial and biorelevant buffers, volumes, and rotations speeds were evaluated. Additionally, a pH change protocol was evaluated using these buffers. DDDPlus™ 3, Beta version (Simulation Plus, Inc.), was used to simulate the in vitro dissolution data. The simulated data were compared with the in vitro data. A regression coefficient between predicted and observed data was used to assess the simulations. The statistical analysis of Montelukast sodium showed that there was a significant correlation between the in vitro release data and the predicted data for all cases except for one buffer. For glyburide, there was also a significant correlation between the experimental data and the predicted data using single pH conditions. Using the dynamic pH protocol, a correlation was significant for one biorelevant media. The simulations showed that both in vitro drug releases were sensitive to solubility effects which confirmed their BCS class II category. Computer simulations of the in vitro release using DDDPlus™ have the potential to estimate the in vivo dissolution at an early stage in the drug development process. This might be used to choose the most appropriate dissolution condition to establish IVIVC and to develop biorelevant in vitro performance tests to capture critical product attributes for quality control procedures in quality by design environments.

Comparing multilabel classification methods for provisional biopharmaceutics class prediction

The biopharmaceutical classification system (BCS) is now well established and utilized for the development and biowaivers of immediate oral dosage forms. The prediction of BCS class can be carried out using multilabel classification. Unlike single label classification, multilabel classification methods predict more than one class label at the same time. This paper compares two multilabel methods, binary relevance and classifier chain, for provisional BCS class prediction. Large data sets of permeability and solubility of drug and drug-like compounds were obtained from the literature and were used to build models using decision trees. The separate permeability and solubility models were validated, and a BCS validation set of 127 compounds where both permeability and solubility were known was used to compare the two aforementioned multilabel classification methods for provisional BCS class prediction. Overall, the results indicate that the classifier chain method, which takes into account label interactions, performed better compared to the binary relevance method. This work offers a comparison of multilabel methods and shows the potential of the classifier chain multilabel method for improved biological property predictions for use in drug discovery and development.

Machine-learning approaches in drug discovery: methods and applications

During the past decade, virtual screening (VS) has evolved from traditional similarity searching, which utilizes single reference compounds, into an advanced application domain for data mining and machine-learning approaches, which require large and representative training-set compounds to learn robust decision rules. The explosive growth in the amount of public domain-available chemical and biological data has generated huge effort to design, analyze, and apply novel learning methodologies. Here, I focus on machine-learning techniques within the context of ligand-based VS (LBVS). In addition, I analyze several relevant VS studies from recent publications, providing a detailed view of the current state-of-the-art in this field and highlighting not only the problematic issues, but also the successes and opportunities for further advances.

Uniting cheminformatics and chemical theory to predict the intrinsic aqueous solubility of crystalline druglike molecules

We present four models of solution free-energy prediction for druglike molecules utilizing cheminformatics descriptors and theoretically calculated thermodynamic values. We make predictions of solution free energy using physics-based theory alone and using machine learning/quantitative structure–property relationship (QSPR) models. We also develop machine learning models where the theoretical energies and cheminformatics descriptors are used as combined input. These models are used to predict solvation free energy. While direct theoretical calculation does not give accurate results in this approach, machine learning is able to give predictions with a root mean squared error (RMSE) of ∼1.1 log S units in a 10-fold cross-validation for our Drug-Like-Solubility-100 (DLS-100) dataset of 100 druglike molecules. We find that a model built using energy terms from our theoretical methodology as descriptors is marginally less predictive than one built on Chemistry Development Kit (CDK) descriptors. Combining both sets of descriptors allows a further but very modest improvement in the predictions. However, in some cases, this is a statistically significant enhancement. These results suggest that there is little complementarity between the chemical information provided by these two sets of descriptors, despite their different sources and methods of calculation. Our machine learning models are also able to predict the well-known Solubility Challenge dataset with an RMSE value of 0.9–1.0 log S units.

Machine learning methods in chemoinformatics

Machine learning algorithms are generally developed in computer science or adjacent disciplines and find their way into chemical modeling by a process of diffusion. Though particular machine learning methods are popular in chemoinformatics and quantitative structure-activity relationships (QSAR), many others exist in the technical literature. This discussion is methods-based and focused on some algorithms that chemoinformatics researchers frequently use. It makes no claim to be exhaustive. We concentrate on methods for supervised learning, predicting the unknown property values of a test set of instances, usually molecules, based on the known values for a training set. Particularly relevant approaches include Artificial Neural Networks, Random Forest, Support Vector Machine, k-Nearest Neighbors and naïve Bayes classifiers.

Modeling bioconcentration factor (BCF) using mechanistically interpretable descriptors computed from open source tool "PaDEL-Descriptor"

Predictive regression-based models for bioconcentration factor (BCF) have been developed using mechanistically interpretable descriptors computed from open source tool PaDEL-Descriptor ( http://padel.nus.edu.sg/software/padeldescriptor/ ). A data set of 522 diverse chemicals has been used for this modeling study, and extended topochemical atom (ETA) indices developed by the present authors' group were chosen as the descriptors. Due to the importance of lipohilicity in modeling BCF, XLogP (computed partition coefficient) was also tried as an additional descriptor. Genetic function approximation followed by multiple linear regression algorithm was applied to select descriptors, and subsequent partial least squares analyses were performed to establish mathematical equations for BCF prediction. The model generated from only ETA indices shows importance of seven descriptors in model development, while the model generated from ETA descriptors along with XlogP shows importance of four descriptors in model development. In general, BCF depends on lipophilicity, presence of heteroatoms, presence of halogens, fused ring system, hydrogen bonding groups, etc. The developed models show excellent statistical qualities and predictive ability. The developed models were used also for prediction of an external data set available from the literature, and good quality of predictions (R (2) pred = 0.812 and 0.826) was demonstrated. Thus, BCF can be predicted using ETA and XlogP descriptors calculated from open source PaDEL-Descriptor software in the context of aquatic chemical toxicity management.