Predicting complexation performance between cyclodextrins and guest molecules by integrated machine learning and molecular modeling techniques

A Review of Machine Learning and QSAR/QSPR Predictions for Complexes of Organic Molecules with Cyclodextrins

Cyclodextrins are macrocyclic rings composed of glucose residues. Due to their remarkable structural properties, they can form host-guest inclusion complexes, which is why they are frequently used in the pharmaceutical, cosmetic, and food industries, as well as in environmental and analytical chemistry. This review presents the reports from 2011 to 2023 on the quantitative structure-activity/property relationship (QSAR/QSPR) approach, which is primarily employed to predict the thermodynamic stability of inclusion complexes. This article extensively discusses the significant developments related to the size of available experimental data, the available sets of descriptors, and the machine learning (ML) algorithms used, such as support vector machines, random forests, artificial neural networks, and gradient boosting. As QSAR/QPR analysis only requires molecular structures of guests and experimental values of stability constants, this approach may be particularly useful for predicting these values for complexes with randomly substituted cyclodextrins, as well as for estimating their dependence on pH. This work proposes solutions on how to effectively use this knowledge, which is especially important for researchers who will deal with this topic in the future. This review also presents other applications of ML in relation to CD complexes, including the prediction of physicochemical properties of CD complexes, the development of analytical methods based on complexation with CDs, and the optimisation of experimental conditions for the preparation of the complexes.

Stereoisomers Are Not Machine Learning's Best Friends

This study addresses the challenge of accurately identifying stereoisomers in cheminformatics, which originates from our objective to apply machine learning to predict the association constant between cyclodextrin and a guest. Identifying stereoisomers is indeed crucial for machine learning applications. Current tools offer various molecular descriptors, including their textual representation as Isomeric SMILES that can distinguish stereoisomers. However, such representation is text-based and does not have a fixed size, so a conversion is needed to make it usable to machine learning approaches. Word embedding techniques can be used to solve this problem. Mol2vec, a word embedding approach for molecules, offers such a conversion. Unfortunately, it cannot distinguish between stereoisomers due to its inability to capture the spatial configuration of molecular structures. This study proposes several approaches that use word embedding techniques to handle molecular discrimination using stereochemical information on molecules or considering Isomeric SMILES notation as a text in Natural Language Processing. Our aim is to generate a distinct vector for each unique molecule, correctly identifying stereoisomer information in cheminformatics. The proposed approaches are then compared to our original machine learning task: predicting the association constant between cyclodextrin and a guest molecule.

Computer-driven formulation development of Ginsenoside Rh2 ternary solid dispersion

(20 S)-Ginsenoside Rh2 is a natural saponin derived from Panax ginseng Meyer (P. ginseng), which showed significantly potent anticancer properties. However, its low water solubility and bioavailability strongly restrict its pharmaceutical applications. The aim of current research is to develop a modified (20 S)-Ginsenoside Rh2 formulation with high solubility, dissolution rate and bioavailability by combined computational and experimental methodology. The "PharmSD" model was employed to predict the optimal polymer for (20 S)-Ginsenoside Rh2 solid dispersion formulations. The solubility of (20 S)-Ginsenoside Rh2 in various polymers was assessed, and the optimal ternary solid dispersion was evaluated across different dissolution mediums. Characterization techniques included the Powder X-ray diffraction (PXRD) and Fourier transform infrared spectroscopy (FTIR). Molecular dynamics simulations were employed to elucidate the formation mechanism of the solid dispersion and the interactions among active pharmaceutical ingredient (API) and excipient molecules. Cell and animal experiments were conducted to evaluate the in vivo performance of the modified formulation. The "PharmSD" solid dispersion model identified Gelucire 44/14 as the most effective polymer for enhancing the dissolution rate of Rh2. Subsequent experiment also confirmed that Gelucire 44/14 outperformed the other selected polymers. Moreover, the addition of the third component, sodium dodecyl sulfate (SDS), in the ternary solid dispersion formulation significantly amplified dissolution rates than the binary systems. Characterization experiments revealed that the API existed in an amorphous state and interacted via hydrogen bonding with SDS and Gelucire. Moreover, molecular modeling results provided additional evidence of hydrogen bonding interactions between the API and excipient molecules within the optimal ternary solid dispersion. Cell experiments demonstrated efflux ratio (EfR) of Rh2 ternary solid dispersion was lower than that of pure Rh2. In vivo experiments revealed that the modified formulation substantially improved the absorption of Rh2 in rats. Our research successfully developed an optimal ternary solid dispersion for Rh2 with high solubility, dissolution rate and bioavailability by integrated computational and experimental tools. The combination of Artificial Intelligence (AI) technology and molecular dynamics simulation is a wise way to support the future formulation development.

A prediction method of interaction based on Bilinear Attention Networks for designing polyphenol-protein complexes delivery systems

Polyphenol-protein complexes delivery systems are gaining attention for their potential health benefits and food industry development. However, creating an ideal delivery system requires extensive wet-lab experimentation. To address this, we collected 525 ligand-protein interaction data pairs and established an interaction prediction model using Bilinear Attention Networks. We utilized 10-fold cross validation to address potential overfitting issues in the model, resulting in showed higher average AUROC (0.8443), AUPRC (0.7872), and F1 (0.8164). The optimal threshold (0.3739) was selected for the model to be used for subsequent analysis. Based on the model prediction results and optimal threshold, by verifying experimental analysis, the interaction of paeonol with the following proteins was obtained, including bovine serum albumin (lgKa = 6.2759), bovine β-lactoglobulin (lgKa = 6.7479), egg ovalbumin (lgKa = 5.1806), zein (lgKa = 6.0122), bovine α-lactalbumin (lgKa = 3.9170), bovine lactoferrin (lgKa = 4.5380), the first four proteins are consistent with the predicted results of the model, with lgKa >5. The established model can accurately and rapidly predict the interaction of polyphenol-protein complexes. This study is the first to combine open ligand-protein interaction experiments with Deep Learning algorithms in the food industry, greatly improving research efficiency and providing a novel perspective for future complex delivery system construction.

Gut microbiome features and metabolites in non-alcoholic fatty liver disease among community-dwelling middle-aged and older adults

BACKGROUND

The specific microbiota and associated metabolites linked to non-alcoholic fatty liver disease (NAFLD) are still controversial. Thus, we aimed to understand how the core gut microbiota and metabolites impact NAFLD.

METHODS

The data for the discovery cohort were collected from the Guangzhou Nutrition and Health Study (GNHS) follow-up conducted between 2014 and 2018. We collected 272 metadata points from 1546 individuals. The metadata were input into four interpretable machine learning models to identify important gut microbiota associated with NAFLD. These models were subsequently applied to two validation cohorts [the internal validation cohort (n = 377), and the prospective validation cohort (n = 749)] to assess generalizability. We constructed an individual microbiome risk score (MRS) based on the identified gut microbiota and conducted animal faecal microbiome transplantation experiment using faecal samples from individuals with different levels of MRS to determine the relationship between MRS and NAFLD. Additionally, we conducted targeted metabolomic sequencing of faecal samples to analyse potential metabolites.

RESULTS

Among the four machine learning models used, the lightGBM algorithm achieved the best performance. A total of 12 taxa-related features of the microbiota were selected by the lightGBM algorithm and further used to calculate the MRS. Increased MRS was positively associated with the presence of NAFLD, with odds ratio (OR) of 1.86 (1.72, 2.02) per 1-unit increase in MRS. An elevated abundance of the faecal microbiota (f__veillonellaceae) was associated with increased NAFLD risk, whereas f__rikenellaceae, f__barnesiellaceae, and s__adolescentis were associated with a decreased presence of NAFLD. Higher levels of specific gut microbiota-derived metabolites of bile acids (taurocholic acid) might be positively associated with both a higher MRS and NAFLD risk. FMT in mice further confirmed a causal association between a higher MRS and the development of NAFLD.

CONCLUSIONS

We confirmed that an alteration in the composition of the core gut microbiota might be biologically relevant to NAFLD development. Our work demonstrated the role of the microbiota in the development of NAFLD.

FormulationAI: a novel web-based platform for drug formulation design driven by artificial intelligence

Today, pharmaceutical industry faces great pressure to employ more efficient and systematic ways in drug discovery and development process. However, conventional formulation studies still strongly rely on personal experiences by trial-and-error experiments, resulting in a labor-consuming, tedious and costly pipeline. Thus, it is highly required to develop intelligent and efficient methods for formulation development to keep pace with the progress of the pharmaceutical industry. Here, we developed a comprehensive web-based platform (FormulationAI) for in silico formulation design. First, the most comprehensive datasets of six widely used drug formulation systems in the pharmaceutical industry were collected over 10 years, including cyclodextrin formulation, solid dispersion, phospholipid complex, nanocrystals, self-emulsifying and liposome systems. Then, intelligent prediction and evaluation of 16 important properties from the six systems were investigated and implemented by systematic study and comparison of different AI algorithms and molecular representations. Finally, an efficient prediction platform was established and validated, which enables the formulation design just by inputting basic information of drugs and excipients. FormulationAI is the first freely available comprehensive web-based platform, which provides a powerful solution to assist the formulation design in pharmaceutical industry. It is available at https://formulationai.computpharm.org/.

Deep Learning for Identifying Promising Drug Candidates in Drug-Phospholipid Complexes

Drug-phospholipid complexing is a promising formulation technology for improving the low bioavailability of active pharmaceutical ingredients (APIs). However, identifying whether phospholipid and candidate drug can form a complex through in vitro tests can be costly and time-consuming due to the physicochemical properties and experimental environment. In a previous study, the authors developed seven machine learning models to predict drug-phospholipid complex formation, and the lightGBM model demonstrated the best performance. However, the previous study was unable to sufficiently address the degradation of test performance caused by the small size of the training data with class imbalance, and it had the limitation of considering only machine learning techniques. To overcome these limitations, we propose a new deep learning-based prediction model that employs variational autoencoder (VAE) and principal component analysis (PCA) techniques to improve prediction performance. The model uses a multi-layer one-dimensional convolutional neural network (CNN) with a skip connection to effectively capture the complex relationship between drugs and lipid molecules. The computer simulation results demonstrate that our proposed model performs better than the previous model in all performance metrics.

A Review on Cyclodextrins/Estrogens Inclusion Complexes

This review focuses on the methods of preparation and biological, physiochemical, and theoretical analysis of the inclusion complexes formed between estrogens and cyclodextrins (CDs). Because estrogens have a low polarity, they can interact with some cyclodextrins' hydrophobic cavities to create inclusion complexes, if their geometric properties are compatible. For the last forty years, estrogen-CD complexes have been widely applied in several fields for various objectives. For example, CDs have been used as estrogen solubilizers and absorption boosters in pharmaceutical formulations, as well as in chromatographic and electrophoretic procedures for their separation and quantification. Other applications include the removal of the endocrine disruptors from environmental materials, the preparation of the samples for mass spectrometric analysis, or solid-phase extractions based on complex formation with CDs. The aim of this review is to gather the most important outcomes from the works related to this topic, presenting the results of synthesis, in silico, in vitro, and in vivo analysis.

How can machine learning and multiscale modeling benefit ocular drug development?

The eyes possess sophisticated physiological structures, diverse disease targets, limited drug delivery space, distinctive barriers, and complicated biomechanical processes, requiring a more in-depth understanding of the interactions between drug delivery systems and biological systems for ocular formulation development. However, the tiny size of the eyes makes sampling difficult and invasive studies costly and ethically constrained. Developing ocular formulations following conventional trial-and-error formulation and manufacturing process screening procedures is inefficient. Along with the popularity of computational pharmaceutics, non-invasive in silico modeling & simulation offer new opportunities for the paradigm shift of ocular formulation development. The current work first systematically reviews the theoretical underpinnings, advanced applications, and unique advantages of data-driven machine learning and multiscale simulation approaches represented by molecular simulation, mathematical modeling, and pharmacokinetic (PK)/pharmacodynamic (PD) modeling for ocular drug development. Following this, a new computer-driven framework for rational pharmaceutical formulation design is proposed, inspired by the potential of in silico explorations in understanding drug delivery details and facilitating drug formulation design. Lastly, to promote the paradigm shift, integrated in silico methodologies were highlighted, and discussions on data challenges, model practicality, personalized modeling, regulatory science, interdisciplinary collaboration, and talent training were conducted in detail with a view to achieving more efficient objective-oriented pharmaceutical formulation design.

Prediction of ADMET Properties of Anti-Breast Cancer Compounds Using Three Machine Learning Algorithms

In recent years, machine learning methods have been applied successfully in many fields. In this paper, three machine learning algorithms, including partial least squares-discriminant analysis (PLS-DA), adaptive boosting (AdaBoost), and light gradient boosting machine (LGBM), were applied to establish models for predicting the Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET for short) properties, namely Caco-2, CYP3A4, hERG, HOB, MN of anti-breast cancer compounds. To the best of our knowledge, the LGBM algorithm was applied to classify the ADMET property of anti-breast cancer compounds for the first time. We evaluated the established models in the prediction set using accuracy, precision, recall, and F1-score. Compared with the performance of the models established using the three algorithms, the LGBM yielded most satisfactory results (accuracy > 0.87, precision > 0.72, recall > 0.73, and F1-score > 0.73). According to the obtained results, it can be inferred that LGBM can establish reliable models to predict the molecular ADMET properties and provide a useful tool for virtual screening and drug design researchers.

Could artificial intelligence revolutionize the development of nanovectors for gene therapy and mRNA vaccines?

Gene therapy enables the introduction of nucleic acids like DNA and RNA into host cells, and is expected to revolutionize the treatment of a wide range of diseases. This growth has been further accelerated by the discovery of CRISPR/Cas technology, which allows accurate genomic editing in a broad range of cells and organisms in vitro and in vivo. Despite many advances in gene delivery and the development of various viral and non-viral gene delivery vectors, the lack of highly efficient non-viral systems with low cellular toxicity remains a challenge. The application of cutting-edge technologies such as artificial intelligence (AI) has great potential to find new paradigms to solve this issue. Herein, we review AI and its major subfields including machine learning (ML), neural networks (NNs), expert systems, deep learning (DL), computer vision and robotics. We discuss the potential of AI-based models and algorithms in the design of targeted gene delivery vehicles capable of crossing extracellular and intracellular barriers by viral mimicry strategies. We finally discuss the role of AI in improving the function of CRISPR/Cas systems, developing novel nanobots, and mRNA vaccine carriers.

Prediction of the Aqueous Solubility of Compounds Based on Light Gradient Boosting Machines with Molecular Fingerprints and the Cuckoo Search Algorithm

Aqueous solubility is one of the most important physicochemical properties in drug discovery. At present, the prediction of aqueous solubility of compounds is still a challenging problem. Machine learning has shown great potential in solubility prediction. Most machine learning models largely rely on the setting of hyperparameters, and their performance can be improved by setting the hyperparameters in a better way. In this paper, we used MACCS fingerprints to represent the structural features and optimized the hyperparameters of the light gradient boosting machine (LightGBM) with the cuckoo search algorithm (CS). Based on the above representation and optimization, the CS-LightGBM model was established to predict the aqueous solubility of 2446 organic compounds and the obtained prediction results were compared with those obtained with the other six different machine learning models (RF, GBDT, XGBoost, LightGBM, SVR, and BO-LightGBM). The comparison results showed that the CS-LightGBM model had a better prediction performance than the other six different models. RMSE, MAE, and R ² of the CS-LightGBM model were, respectively, 0.7785, 0.5117, and 0.8575. In addition, this model has good scalability and can be used to solve solubility prediction problems in other fields such as solvent selection and drug screening.

Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts

NIR spectroscopy is a non-destructive characterization tool for the blend uniformity (BU) assessment. However, NIR spectra of powder blends often contain overlapping physical and chemical information of the samples. Deconvoluting the information related to chemical properties from that associated with the physical effects is one of the major objectives of this work. We achieve this aim in two ways. Firstly, we identified various sources of variability that might affect the BU results. Secondly, we leverage the machine learning-based sophisticated data analytics processes. To accomplish the aforementioned objectives, calibration samples of amlodipine as an active pharmaceutical ingredient (API) with the concentrations ranging between 67 and 133% w/w (dose ~ 3.6% w/w), in powder blends containing excipients, were prepared using a gravimetric approach and assessed using NIR spectroscopic analysis, followed by HPLC measurements. The bias in NIR results was investigated by employing data quality metrics (DQM) and bias-variance decomposition (BVD). To overcome the bias, the clustered regression (non-parametric and linear) was applied. We assessed the model's performance by employing the hold-out and k-fold internal cross-validation (CV). NIR-based blend homogeneity with low mean absolute error and an interval estimates of 0.674 (mean) ± 0.218 (standard deviation) w/w was established. Additionally, bootstrapping-based CV was leveraged as part of the NIR method lifecycle management that demonstrated the mean absolute error (MAE) of BU ± 3.5% w/w and BU ± 1.5% w/w for model generalizability and model transferability, respectively. A workflow integrating machine learning to NIR spectral analysis was established and implemented. Impact of various data learning approaches on NIR spectral data.

Opportunities and challenges of physiologically based pharmacokinetic modeling in drug delivery

Physiologically based pharmacokinetic (PBPK) modeling is an important in silico tool to bridge drug properties and in vivo PK behaviors during drug development. Over the recent decade, the PBPK method has been largely applied to drug delivery systems (DDS), including oral, inhaled, transdermal, ophthalmic, and complex injectable products. The related therapeutic agents have included small-molecule drugs, therapeutic proteins, nucleic acids, and even cells. Simulation results have provided important insights into PK behaviors of new dosage forms, which strongly support drug regulation. In this review, we comprehensively summarize recent progress in PBPK applications in drug delivery, which shows large opportunities for facilitating drug development. In addition, we discuss the challenges of applying this methodology from a practical viewpoint.

Exploring two types of prenylated bitter compounds from hop plant (Humulus lupulus L.) against α-glucosidase in vitro and in silico

Hops are abundant in natural bioactive compounds. In this work, nine prenylated bitter compounds from hop were evaluated for their inhibitory activity against α-glucosidase. As a result, four flavonoids and one phloroglucinol (lupulone, LP) outperformed acarbose in inhibiting α-glucosidase. Isoxanthohumol (IX) and LP with two types of structures were selected for inhibition mechanism studies by spectroscopic methods and molecular dynamics simulation (MD). Results showed that IX acted as noncompetitive inhibitor and bound to α-glucosidase in allosteric sites via hydrogen bonds, hydrophobic, van der Waals (vdW), and electrostatic force, whereas LP was uncompetitive inhibitor and bound to catalytic sites via hydrophobic and vdW interactions. Notably, the conformation around binding site of α-glucosidase formed stable α-helix and tightened after binding IX and LP, respectively, which helped to elucidate noncompetitive and uncompetitive inhibitory mechanisms. This work demonstrated that two types of prenylated bitter compounds are discrepant in their mechanisms of interaction with α-glucosidase.

In silico formulation prediction of drug/cyclodextrin/polymer ternary complexes by machine learning and molecular modeling techniques

Ternary cyclodextrin (CD) complexes (drug/CD/polymer) can effectively improve the solubility of water-insoluble drugs with large size than binary CD formulations. However, ternary formulations are screened by a trial-and-error approach, which is laborious and material-wasting. Current research aims to develop a prediction model for ternary CD formulations by combined machine learning and molecular modeling. 596 ternary formulations data were collected to build a prediction model by machine learning. The random forest model achieved good performance with R² = 0.887 in S_T prediction and R² = 0.815 in S_T/S_B prediction. Two ternary formulations (Hydrocortisone/β-CD/HPMC and dovitinib/γ-CD/CMC) were used to validate the prediction model. Molecular modeling results showed that HPMC not only warped around hydrocortisone but also prevented CD molecules from self-aggregation to increase solubility. In conclusion, a prediction model for the ternary CD formulations was successfully developed, which will significantly accelerate the formulation screening process to benefit the formulation development of water-insoluble drugs.

Prediction of small-molecule compound solubility in organic solvents by machine learning algorithms

Rapid solvent selection is of great significance in chemistry. However, solubility prediction remains a crucial challenge. This study aimed to develop machine learning models that can accurately predict compound solubility in organic solvents. A dataset containing 5081 experimental temperature and solubility data of compounds in organic solvents was extracted and standardized. Molecular fingerprints were selected to characterize structural features. lightGBM was compared with deep learning and traditional machine learning (PLS, Ridge regression, kNN, DT, ET, RF, SVM) to develop models for predicting solubility in organic solvents at different temperatures. Compared to other models, lightGBM exhibited significantly better overall generalization (logS  ± 0.20). For unseen solutes, our model gave a prediction accuracy (logS  ± 0.59) close to the expected noise level of experimental solubility data. lightGBM revealed the physicochemical relationship between solubility and structural features. Our method enables rapid solvent screening in chemistry and may be applied to solubility prediction in other solvents.

Prediction of lipid nanoparticles for mRNA vaccines by the machine learning algorithm

Lipid nanoparticle (LNP) is commonly used to deliver mRNA vaccines. Currently, LNP optimization primarily relies on screening ionizable lipids by traditional experiments which consumes intensive cost and time. Current study attempts to apply computational methods to accelerate the LNP development for mRNA vaccines. Firstly, 325 data samples of mRNA vaccine LNP formulations with IgG titer were collected. The machine learning algorithm, lightGBM, was used to build a prediction model with good performance (R² > 0.87). More importantly, the critical substructures of ionizable lipids in LNPs were identified by the algorithm, which well agreed with published results. The animal experimental results showed that LNP using DLin-MC3-DMA (MC3) as ionizable lipid with an N/P ratio at 6:1 induced higher efficiency in mice than LNP with SM-102, which was consistent with the model prediction. Molecular dynamic modeling further investigated the molecular mechanism of LNPs used in the experiment. The result showed that the lipid molecules aggregated to form LNPs, and mRNA molecules twined around the LNPs. In summary, the machine learning predictive model for LNP-based mRNA vaccines was first developed, validated by experiments, and further integrated with molecular modeling. The prediction model can be used for virtual screening of LNP formulations in the future.

Integrated in silico formulation design of self-emulsifying drug delivery systems

The drug formulation design of self-emulsifying drug delivery systems (SEDDS) often requires numerous experiments, which are time- and money-consuming. This research aimed to rationally design the SEDDS formulation by the integrated computational and experimental approaches. 4495 SEDDS formulation datasets were collected to predict the pseudo-ternary phase diagram by the machine learning methods. Random forest (RF) showed the best prediction performance with 91.3% for accuracy, 92.0% for sensitivity and 90.7% for specificity in 5-fold cross-validation. The pseudo-ternary phase diagrams of meloxicam SEDDS were experimentally developed to validate the RF prediction model and achieved an excellent prediction accuracy (89.51%). The central composite design (CCD) was used to screen the best ratio of oil-surfactant-cosurfactant. Finally, molecular dynamic (MD) simulation was used to investigate the molecular interaction between excipients and drugs, which revealed the diffusion behavior in water and the role of cosurfactants. In conclusion, this research combined machine learning, central composite design, molecular modeling and experimental approaches for rational SEDDS formulation design. The integrated computer methodology can decrease traditional drug formulation design works and bring new ideas for future drug formulation design.

Integrated computer-aided formulation design: A case study of andrographolide/ cyclodextrin ternary formulation

Current formulation development strongly relies on trial-and-error experiments in the laboratory by pharmaceutical scientists, which is time-consuming, high cost and waste materials. This research aims to integrate various computational tools, including machine learning, molecular dynamic simulation and physiologically based absorption modeling (PBAM), to enhance andrographolide (AG) /cyclodextrins (CDs) formulation design. The lightGBM prediction model we built before was utilized to predict AG/CDs inclusion's binding free energy. AG/γ-CD inclusion complexes showed the strongest binding affinity, which was experimentally validated by the phase solubility study. The molecular dynamic simulation was used to investigate the inclusion mechanism between AG and γ-CD, which was experimentally characterized by DSC, FTIR and NMR techniques. PBAM was applied to simulate the in vivo behavior of the formulations, which were validated by cell and animal experiments. Cell experiments revealed that the presence of D-α-Tocopherol polyethylene glycol succinate (TPGS) significantly increased the intracellular uptake of AG in MDCK-MDR1 cells and the absorptive transport of AG in MDCK-MDR1 monolayers. The relative bioavailability of the AG-CD-TPGS ternary system in rats was increased to 2.6-fold and 1.59-fold compared with crude AG and commercial dropping pills, respectively. In conclusion, this is the first time to integrate various computational tools to develop a new AG-CD-TPGS ternary formulation with significant improvement of aqueous solubility, dissolution rate and bioavailability. The integrated computational tool is a novel and robust methodology to facilitate pharmaceutical formulation 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.

Markov State Models and Molecular Dynamics Simulations Provide Understanding of the Nucleotide-Dependent Dimerization-Based Activation of LRRK2 ROC Domain

Mutations in leucine-rich repeat kinase 2 (LRRK2) are recognized as the most frequent cause of Parkinson's disease (PD). As a multidomain ROCO protein, LRRK2 is characterized by the presence of both a Ras-of-complex (ROC) GTPase domain and a kinase domain connected through the C-terminal of an ROC domain (COR). The bienzymatic ROC-COR-kinase catalytic triad indicated the potential role of GTPase domain in regulating kinase activity. However, as a functional GTPase, the detailed intrinsic regulation of the ROC activation cycle remains poorly understood. Here, combining extensive molecular dynamics simulations and Markov state models, we disclosed the dynamic structural rearrangement of ROC's homodimer during nucleotide turnover. Our study revealed the coupling between dimerization extent and nucleotide-binding state, indicating a nucleotide-dependent dimerization-based activation scheme adopted by ROC GTPase. Furthermore, inspired by the well-known R1441C/G/H PD-relevant mutations within the ROC domain, we illuminated the potential allosteric molecular mechanism for its pathogenetic effects through enabling faster interconversion between inactive and active states, thus trapping ROC in a prolonged activated state, while the implicated allostery could provide further guidance for identification of regulatory allosteric pockets on the ROC complex. Our investigations illuminated the thermodynamics and kinetics of ROC homodimer during nucleotide-dependent activation for the first time and provided guidance for further exploiting ROC as therapeutic targets for controlling LRRK2 functionality in PD treatment.

Sulfonated β-cyclodextrins: efficient supramolecular organocatalysts for diverse organic transformations

The present review summarizes various organic transformations carried out by using sulfonated β-cyclodextrins such as β-cyclodextrin sulfonic acid, β-cyclodextrin propyl sulfonic acid, and β-cyclodextrin butyl sulfonic acid as an efficient, supramolecular reusable catalyst under diverse reaction conditions.

Nanoparticulation of Prodrug into Medicines for Cancer Therapy

This article provides a broad spectrum about the nanoprodrug fabrication advances co-driven by prodrug and nanotechnology development to potentiate cancer treatment. The nanoprodrug inherits the features of both prodrug concept and nanomedicine know-how, attempts to solve underexploited challenge in cancer treatment cooperatively. Prodrugs can release bioactive drugs on-demand at specific sites to reduce systemic toxicity, this is done by using the special properties of the tumor microenvironment, such as pH value, glutathione concentration, and specific overexpressed enzymes; or by using exogenous stimulation, such as light, heat, and ultrasound. The nanotechnology, manipulating the matter within nanoscale, has high relevance to certain biological conditions, and has been widely utilized in cancer therapy. Together, the marriage of prodrug strategy which shield the side effects of parent drug and nanotechnology with pinpoint delivery capability has conceived highly camouflaged Trojan horse to maneuver cancerous threats.

Development of Arteannuin B Sustained-Release Microspheres for Anti-Tumor Therapy by Integrated Experimental and Molecular Modeling Approaches

Arteannuin B (AB) has been found to demonstrate obvious anti-tumor activity. However, AB is not available for clinical use due to its very low solubility and very short half-life. This study aimed to develop AB long sustained-release microspheres (ABMs) to improve the feasibility of clinical applications. Firstly, AB-polylactic-co-glycolic acid (PLGA) microspheres were prepared by a single emulsification method. In vitro characterization studies showed that ABMs had a low burst release and stable in vitro release for up to one week. The particle size of microspheres was 69.10 μm (D50). The drug loading is 37.8%, and the encapsulation rate is 85%. Moreover, molecular dynamics modeling was firstly used to simulate the preparation process of microspheres, which clearly indicated the molecular image of microspheres and provided in-depth insights for understanding several key preparation parameters. Next, in vivo pharmacokinetics (PK) study was carried out to evaluate its sustained release effect in Sprague-Dawley (SD) rats. Subsequently, the methyl thiazolyl tetrazolium (MTT) method with human lung cancer cells (A549) was used to evaluate the in vitro efficacy of ABMs, which showed the IC50 of ABMs (3.82 μM) to be lower than that of AB (16.03 μM) at day four. Finally, in vivo anti-tumor activity and basic toxicity studies were performed on BALB/c nude mice by subcutaneous injection once a week, four times in total. The relative tumor proliferation rate T/C of AMBs was lower than 40% and lasted for 21 days after administration. The organ index, organ staining, and tumor cell staining indicated the excellent safety of ABMs than Cis-platinum. In summary, the ABMs were successfully developed and evaluated with a low burst release and a stable release within a week. Molecular dynamics modeling was firstly applied to investigate the molecular mechanism of the microsphere preparation. Moreover, the ABMs possess excellent in vitro and in vivo anti-tumor activity and low toxicity, showing great potential for clinical applications.

Machine learning directed drug formulation development

Machine learning (ML) has enabled ground-breaking advances in the healthcare and pharmaceutical sectors, from improvements in cancer diagnosis, to the identification of novel drugs and drug targets as well as protein structure prediction. Drug formulation is an essential stage in the discovery and development of new medicines. Through the design of drug formulations, pharmaceutical scientists can engineer important properties of new medicines, such as improved bioavailability and targeted delivery. The traditional approach to drug formulation development relies on iterative trial-and-error, requiring a large number of resource-intensive and time-consuming in vitro and in vivo experiments. This review introduces the basic concepts of ML-directed workflows and discusses how these tools can be used to aid in the development of various types of drug formulations. ML-directed drug formulation development offers unparalleled opportunities to fast-track development efforts, uncover new materials, innovative formulations, and generate new knowledge in drug formulation science. The review also highlights the latest artificial intelligence (AI) technologies, such as generative models, Bayesian deep learning, reinforcement learning, and self-driving laboratories, which have been gaining momentum in drug discovery and chemistry and have potential in drug formulation development.

PharmDE: A new expert system for drug-excipient compatibility evaluation

Drug-excipient compatibility study is the essential basis for excipient selection at the pre-formulation stage. According to the pharmaceutical Quality by Design (QbD) principles, a comprehensive understanding of the ingredients' physicochemical properties and a theoretical evaluation of the interaction risk between the drugs and excipients are required for conducting rational compatibility experimental design. Currently, there is an urgent need to establish an artificial intelligence system for researchers to easily get through the problem because it is very inconvenient and hard to utilize those drug-excipient incompatibility data scattered in scientific literature. Here, we designed a knowledge-driven expert system named PharmDE for drug-excipient incompatibility risk evaluation. PharmDE firstly developed an information-rich database to store incompatibility data, covering 532 data items from 228 selected articles. Then, 60 drug-excipient interaction rules were created based on our knowledge and formulation research experiences. Finally, the expert system was developed by organically integrating the database searching and rule-based incompatibility risk prediction, which resulted in four main functionalities: basic search of incompatibility database, data matching by similarity search, drug incompatibility risk evaluation, and formulation incompatibility risk evaluation. PharmDE is expected to be a useful tool for drug-excipient compatibility study and accelerate drug formulation design. It is now freely available at https://pharmde.computpharm.org.

Prediction of Free Drug Absorption in Cyclodextrin Formulation by a Modified Physiologically Based Pharmacokinetic Model and Phase Solubility 3-D Surface Graph

PURPOSE

Cyclodextrin (CD) is commonly used to enhance the solubility of oral drugs. However, with the increase of CD concentrations, the fraction of free drug molecules decreases, which may potentially impede drug absorption. This study aims to predict the optimal ratio between drug and CD to achieve the best absorption efficiency by computational simulation.

METHODS

First, a physiologically based pharmacokinetic (PBPK) model was developed. This model can continuously adjust absorption according to free drug fraction and was validated against two model drugs, progesterone (PG) and andrographolide (AG). The further analysis involves 3-D surface graphs to investigate the relationship between free drug amount, theoretically absorbable concentration, and contents of drug and CD in the formulation.

RESULTS

The PBPK model predicted the PK behavior of two drugs well. The concentration ratio of drug to CD, leading to maximal free drug amount and the best absorption efficiency, is nearly the same as the slope determined in the phase solubility test. The new modified PBPK model and 3-D surface graph can easily predict the absorption difference of formulations with various drug/CD ratios.

CONCLUSION

This PBPK model and 3-D surface graph can predict the absorption and determine the optimal concentration ratio of CD formulation, which could accelerate the R&D of CD formulation.

New machine learning and physics-based scoring functions for drug discovery

Scoring functions are essential for modern in silico drug discovery. However, the accurate prediction of binding affinity by scoring functions remains a challenging task. The performance of scoring functions is very heterogeneous across different target classes. Scoring functions based on precise physics-based descriptors better representing protein–ligand recognition process are strongly needed. We developed a set of new empirical scoring functions, named DockTScore, by explicitly accounting for physics-based terms combined with machine learning. Target-specific scoring functions were developed for two important drug targets, proteases and protein–protein interactions, representing an original class of molecules for drug discovery. Multiple linear regression (MLR), support vector machine and random forest algorithms were employed to derive general and target-specific scoring functions involving optimized MMFF94S force-field terms, solvation and lipophilic interactions terms, and an improved term accounting for ligand torsional entropy contribution to ligand binding. DockTScore scoring functions demonstrated to be competitive with the current best-evaluated scoring functions in terms of binding energy prediction and ranking on four DUD-E datasets and will be useful for in silico drug design for diverse proteins as well as for specific targets such as proteases and protein–protein interactions. Currently, the MLR DockTScore is available at www.dockthor.lncc.br.

Potential of Raman spectroscopy in facilitating pharmaceutical formulations development - An AI perspective

Drug development is time-consuming and inherently possesses a high failure rate. Pharmaceutical formulation development is the bridge that links a new chemical entity (NCE) to pre-clinical and clinical trials, and has a high impact on the efficacy and safety of the final drug product. Further, the time required for this process is escalating as formulation techniques are becoming more complicated due to the rising demands for drug products with better efficacy and patient compliance, as well as the inherent difficulties of addressing the unfavorable properties of NCEs such as low water solubility. The advent of artificial intelligence (AI) provides possibilities to accelerate the drug development process. In this review, we first examine applications of AI methods in different types of pharmaceutical formulations and formulation techniques. Moreover, as availability of data is the engine for the advancement of AI, we then suggest a potential way (i.e. applying Raman spectroscopy) for faster high-quality data gathering from formulations. Raman techniques have the capability of analyzing the composition and distribution of components and the physicochemical properties thereof within formulations, which are prominent factors governing drug dissolution profiles and subsequently bioavailability. Thus, useful information can be obtained bridging formulation development to the final product quality.

How Parkinson's disease-related mutations disrupt the dimerization of WD40 domain in LRRK2: a comparative molecular dynamics simulation study

The multidomain kinase enzyme leucine-rich-repeat kinase 2 (LRRK2), activated through a homodimerization manner, has been identified as an important pathogenic factor in Parkinson's disease (PD), the second most common neurodegenerative disease wordwide. The Trp-Asp-40 (WD40) domain, located in the C-terminal LRRK2, harbours one of the most frequent PD-related variants, G2385R. However, the detailed dynamics of WD40 during LRRK2 dimerization and the underlying mechanism through which the pathogenic mutations disrupt the formation of the WD40 dimer have remained elusive. Here, microsecond-scale molecular dynamics simulations were employed to provide a mechanistic view underlying the WD40 dimerization and unveil the structural basis by which the interface-based mutations G2385R, H2391D and R2394E compromise the corresponding process. The simulation results identified important residues, D2351, R2394, E2395, R2413, and R2443, involved in establishing the complex binding network along the dimerization interface, which was significantly weakened in the presence of interfacial mutations. A "sag-bulge" model was proposed to explain the unfavorable dimer formation in the mutant systems. In addition, mutations altered the community configuration in the wild-type system in which inter-monomeric interplay is prominent, leading to the destabilization of the WD40 dimer under mutation.

Investigation of supramolecular interaction of quercetin with N,N-dimethylamine-functionalized p-sulfonated calix[4,8]arenes using molecular modeling and their in vitro cytotoxic response towards selected cancer cells

Although quercetin is an effective bioactive compound preventing the progress of several human cancers, its impact is reduced due to low bioavailability.

Review of machine learning algorithms' application in pharmaceutical technology

Machine learning algorithms, and artificial intelligence in general, have a wide range of applications in the field of pharmaceutical technology. Starting from the formulation development, through a great potential for integration within the Quality by design framework, these data science tools provide a better understanding of the pharmaceutical formulations and respective processing. Machine learning algorithms can be especially helpful with the analysis of the large volume of data generated by the Process analytical technologies. This paper provides a brief explanation of the artificial neural networks, as one of the most frequently used machine learning algorithms. The process of the network training and testing is described and accompanied with illustrative examples of machine learning tools applied in the context of pharmaceutical formulation development and related technologies, as well as an overview of the future trends. Recently published studies on more sophisticated methods, such as deep neural networks and light gradient boosting machine algorithm, have been described. The interested reader is also referred to several official documents (guidelines) that pave the way for a more structured representation of the machine learning models in their prospective submissions to the regulatory bodies.

Mechanism and optimization of supramolecular complexation-enhanced fluorescence spectroscopy for the determination of SN-38 in plasma and cells

Quantitative detection of two different forms of SN-38 in biological samples is, currently, cumbersome and difficult. A revisit to the mechanism of supramolecular complexation-enhanced fluorescence spectroscopy helps to optimize the determination of SN-38 in plasma and the cellular pharmacokinetics in A549 cells based on the supramolecular complexation. Firstly, the inclusion mechanism dominated by thermodynamic constants was determined by measuring kinetic/thermodynamic parameters (k_on , k_off , ΔG, ΔH, ΔS). On this basis, the best effect of fluorescence sensitization was optimized through screening the interaction conditions (cyclodextrin species and concentrations, drug levels, temperature, pH of the buffer, and reaction time). Furthermore, the proportional relationship between the concentration of the inclusion complex and the fluorescence intensity was confirmed. Finally, a highly sensitive, selective spectrofluorimetric method was established and validated for quantitative analysis of the lactone and carboxylate molecular states of SN-38 plasma levels in rats and cell membrane transfer kinetics in A549 cell lines. The limits of detection for the lactone and carboxylate forms in plasma were found to be 0.44 ng·ml^-1 and 0.28 ng·ml^-1 , respectively. Precision and accuracy met the requirements of biological samples analysis. The proposed detection method provided a reference for elucidating the biodistribution of SN-38.

A Closer Look at the "Right" Format for Clinical Decision Support: Methods for Evaluating a Storyboard BestPractice Advisory

(1) Background: The five rights of clinical decision support (CDS) are a well-known framework for planning the nuances of CDS, but recent advancements have given us more options to modify the format of the alert. One-size-fits-all assessments fail to capture the nuance of different BestPractice Advisory (BPA) formats. To demonstrate a tailored evaluation methodology, we assessed a BPA after implementation of Storyboard for changes in alert fatigue, behavior influence, and task completion; (2) Methods: Data from 19 weeks before and after implementation were used to evaluate differences in each domain. Individual clinics were evaluated for task completion and compared for changes pre- and post-redesign; (3) Results: The change in format was correlated with an increase in alert fatigue, a decrease in erroneous free text answers, and worsened task completion at a system level. At a local level, however, 14% of clinics had improved task completion; (4) Conclusions: While the change in BPA format was correlated with decreased performance, the changes may have been driven primarily by the COVID-19 pandemic. The framework and metrics proposed can be used in future studies to assess the impact of new CDS formats. Although the changes in this study seemed undesirable in aggregate, some positive changes were observed at the level of individual clinics. Personalized implementations of CDS tools based on local need should be considered.

Identifying sarcopenia in advanced non-small cell lung cancer patients using skeletal muscle CT radiomics and machine learning

Background

Sarcopenia has been confirmed as a poor prognostic indicator of lung cancer. However, the lack of abdominal computed tomography (CT) hindered the application to assess the status of sarcopenia. The purpose of this study was to assess the ability of chest CT radiomics combined with machine learning classifiers to identify sarcopenia in advanced non‐small cell lung cancer (NSCLC) patients.

Methods

This study retrospectively analyzed CT images of 99 patients with NSCLC. Skeletal muscle radiomics were extracted from a single axial slice of the chest CT scan at the 12th thoracic vertebrae level. In total, 854 radiomic and clinical features were obtained from each patient. Feature selection was conducted with FeatureSelector module, optimal key features were fed into the lightGBM classifier for model construction, and Bayesian optimization was adopted to tune hyperparameters. The model's performance was evaluated by specificity, sensitivity, accuracy, precision, F1‐score, Matthew's correlation coefficient (MCC), Cohen's kappa coefficient (Kappa), and AUC.

Results

A total of 40 patients were found to have sarcopenia. Five optimal features were selected. In the base lightGBM model, the specificity, sensitivity, accuracy, precision, F1‐score, AUC, MCC, Kappa of validation set were 0.889, 0.750, 0.833, 0.818, 0.783, 0.819, 0.649, 0.648, respectively. After Bayesian hyperparameter tuning, the optimized lightGBM model achieved better prediction performance, and the corresponding values were 0.944, 0.833, 0.900, 0.909, 0.870, 0.889, 0.791, 0.789, respectively.

Conclusions

Chest CT‐based radiomics has the potential to identify sarcopenia in NSCLC patients with the lightGBM classifier, and the optimal lightGBM model via Bayesian hyperparameter tuning demonstrated better performance.

Key points

Significant findings of the study

Our study demonstrates that chest CT‐based radiomics combined with lightGBM classifier has the ability to identify sarcopenia in NSCLC patients.

What this study adds

Skeletal muscle radiomics would be a potential biomarker for sarcopenia identity in NSCLC patients.

Digital Pharmaceutical Sciences

Artificial intelligence (AI) and machine learning, in particular, have gained significant interest in many fields, including pharmaceutical sciences. The enormous growth of data from several sources, the recent advances in various analytical tools, and the continuous developments in machine learning algorithms have resulted in a rapid increase in new machine learning applications in different areas of pharmaceutical sciences. This review summarizes the past, present, and potential future impacts of machine learning technologies on different areas of pharmaceutical sciences, including drug design and discovery, preformulation, and formulation. The machine learning methods commonly used in pharmaceutical sciences are discussed, with a specific emphasis on artificial neural networks due to their capability to model the nonlinear relationships that are commonly encountered in pharmaceutical research. AI and machine learning technologies in common day-to-day pharma needs as well as industrial and regulatory insights are reviewed. Beyond traditional potentials of implementing digital technologies using machine learning in the development of more efficient, fast, and economical solutions in pharmaceutical sciences are also discussed.

Computer-Aided Discovery of New Solubility-Enhancing Drug Delivery System

The poor aqueous solubility of active pharmaceutical ingredients (APIs) places a limit on their therapeutic potential. Cyclodextrins (CDs) have been shown to improve the solubility of APIs, but the magnitude of the improvement depends on the structure of both the CDs and APIs. We have developed quantitative structure-property relationship (QSPR) models that predict the stability of the complexes formed by a popular poorly soluble antibiotic, cefuroxime axetil (CA) and different CDs. We applied this model to five CA-CD systems not included in the modeling set. Two out of three systems predicted to have poor stability and poor CA solubility, and both CA-CD systems predicted to have high stability and high CA solubility were confirmed experimentally. One of the CDs that significantly improved CA solubility, methyl-βCD, is described here for the first time, and we propose this CD as a novel promising excipient. Computational approaches and models developed and validated in this study could help accelerate the development of multifunctional CDs-based formulations.

Can machine learning predict drug nanocrystals?

Nanocrystals have exhibited great advantage for enhancing the dissolution rate of water insoluble drugs due to the reduced size to nanoscale. However, current pharmaceutical approaches for nanocrystals formulation development highly depend on the expert experience and trial-and-error attempts which remain time and resource consuming. In this research, we utilized machine learning techniques to predict the particle size and polydispersity index (PDI) of nanocrystals. Firstly, 910 nanocrystal size data and 341 PDI data by three preparation methods (ball wet milling (BWM) method, high-pressure homogenization (HPH) method and antisolvent precipitation (ASP) method) were collected for the construction of the prediction models. The results demonstrated that light gradient boosting machine (LightGBM) exhibited well performance for the nanocrystals size and PDI prediction with BWM and HPH methods, but relatively poor predictions for ASP method. The possible reasons for the poor prediction refer to low quality of data because of the poor reproducibility and instability of nanocrystals by ASP method, which also confirm that current commercialized products were mainly manufactured by BWM and HPH approaches. Notably, the contribution of the influence factors was ranked by the LightGBM, which demonstrated that milling time, cycle index and concentration of stabilizer are crucial factors for nanocrystals prepared by BWM, HPH and ASP, respectively. Furthermore, the model generalizations and prediction accuracies of LightGBM were confirmed experimentally by the newly prepared nanocrystals. In conclusion, the machine learning techniques can be successfully utilized for the predictions of nanocrystals prepared by BWM and HPH methods. Our research also reveals a new way for nanotechnology manufacture.

Predicting physical stability of solid dispersions by machine learning techniques

Amorphous solid dispersion (SD) is an effective solubilization technique for water-insoluble drugs. However, physical stability issue of solid dispersions still heavily hindered the development of this technique. Traditional stability experiments need to be tested at least three to six months, which is time-consuming and unpredictable. In this research, a novel prediction model for physical stability of solid dispersion formulations was developed by machine learning techniques. 646 stability data points were collected and described by over 20 molecular descriptors. All data was classified into the training set (60%), validation set (20%), and testing set (20%) by the improved maximum dissimilarity algorithm (MD-FIS). Eight machine learning approaches were compared and random forest (RF) model achieved the best prediction accuracy (82.5%). Moreover, the RF models revealed the contribution of each input parameter, which provided us the theoretical guidance for solid dispersion formulations. Furthermore, the prediction model was confirmed by physical stability experiments of 17β-estradiol (ED)-PVP solid dispersions and the molecular mechanism was investigated by molecular modeling technique. In conclusion, an intelligent model was developed for the prediction of physical stability of solid dispersions, which benefit the rational formulation design of this technique. The integrated experimental, theoretical, modeling and data-driven AI methodology is also able to be used for future formulation development of other dosage forms.