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.     

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.     

A Practical Framework Toward Prediction of Breaking Force and Disintegration of Tablet Formulations Using Machine Learning Tools

Enabling the paradigm of quality by design requires the ability to quantitatively correlate material properties and process variables to measureable product performance attributes. Conventional, quality-by-test methods for determining tablet breaking force and disintegration time usually involve destructive tests, which consume significant amount of time and labor and provide limited information. Recent advances in material characterization, statistical analysis, and machine learning have provided multiple tools that have the potential to develop nondestructive, fast, and accurate approaches in drug product development. In this work, a methodology to predict the breaking force and disintegration time of tablet formulations using nondestructive ultrasonics and machine learning tools was developed. The input variables to the model include intrinsic properties of formulation and extrinsic process variables influencing the tablet during manufacturing. The model has been applied to predict breaking force and disintegration time using small quantities of active pharmaceutical ingredient and prototype formulation designs. The novel approach presented is a step forward toward rational design of a robust drug product based on insight into the performance of common materials during formulation and process development. It may also help expedite drug product development timeline and reduce active pharmaceutical ingredient usage while improving efficiency of the overall process.     

Efficient Prediction of In Vitro Piroxicam Release and Diffusion From Topical Films Based on Biopolymers Using Deep Learning Models and Generative Adversarial Networks

The purpose of this study was to simultaneously predict the drug release and skin permeation of Piroxicam (PX) topical films based on Chitosan (CTS), Xanthan gum (XG) and its Carboxymethyl derivatives (CMXs) as matrix systems. These films were prepared by the solvent casting method, using Tween 80 (T80) as a permeation enhancer. All of the prepared films were assessed for their physicochemical parameters, their in vitro drug release and ex vivo skin permeation studies. Moreover, deep learning models and machine learning models were applied to predict the drug release and permeation rates. The results indicated that all of the films exhibited good consistency and physicochemical properties. Furthermore, it was noticed that when T80 was used in the optimal formulation (F8) based on CTS-CMX3, a satisfactory drug release pattern was found where 99.97% of PX was released and an amount of 1.18 mg/cm² was permeated after 48 h. Moreover, Generative Adversarial Network (GAN) efficiently enhanced the performance of deep learning models and DNN was chosen as the best predictive approach with MSE values equal to 0.00098 and 0.00182 for the drug release and permeation kinetics, respectively. DNN precisely predicted PX dissolution profiles with f₂ values equal to 99.99 for all the formulations.     

Predicting liposome formulations by the integrated machine learning and molecular modeling approaches

Liposome is one of the most widely used carriers for drug delivery because of the great biocompatibility and biodegradability. Due to the complex formulation components and preparation process, formulation screening mostly relies on trial-and-error process with low efficiency. Here liposome formulation prediction models have been built by machine learning (ML) approaches. The important parameters of liposomes, including size, polydispersity index (PDI), zeta potential and encapsulation, are predicted individually by optimal ML algorithm, while the formulation features are also ranked to provide important guidance for formulation design. The analysis of key parameter reveals that drug molecules with logS [-3, -6], molecular complexity [500, 1000] and XLogP3 (≥2) are priority for preparing liposome with higher encapsulation. In addition, naproxen (NAP) and palmatine HCl (PAL) represented the insoluble and water-soluble molecules are prepared as liposome formulations to validate prediction ability. The consistency between predicted and experimental value verifies the satisfied accuracy of ML models. As the drug properties are critical for liposome particles, the molecular interactions and dynamics of NAP and PAL liposome are further investigated by coarse-grained molecular dynamics simulations. The modeling structure reveals that NAP molecules could distribute into lipid layer, while most PAL molecules aggregate in the inner aqueous phase of liposome. The completely different physical state of NAP and PAL confirms the importance of drug properties for liposome formulations. In summary, the general prediction models are built to predict liposome formulations, and the impacts of key factors are analyzed by combing ML with molecular modeling. The availability and rationality of these intelligent prediction systems have been proved in this study, which could be applied for liposome formulation development in the future.     

Transforming Lipid-Based Oral Drug Delivery Systems into Solid Dosage Forms: An Overview of Solid Carriers, Physicochemical Properties, and Biopharmaceutical Performance

The diversity of lipid excipients available commercially has enabled versatile formulation design of lipid-based drug delivery systems for enhancing the oral absorption of poorly water-soluble drugs, such as emulsions, microemulsions, micelles, liposomes, niosomes and various self-emulsifying systems. The transformation of liquid lipid-based systems into solid dosage forms has been investigated for several decades, and has recently become a core subject of pharmaceutical research as solidification is regarded as viable means for stabilising lipid colloidal systems while eliminating stringent processing requirements associated with liquid systems. This review describes the types of pharmaceutical grade excipients (silica nanoparticle/microparticle, polysaccharide, polymer and protein-based materials) used as solid carriers and the current state of knowledge on the liquid-to-solid conversion approaches. Details are primarily focused on the solid-state physicochemical properties and redispersion capacity of various dry lipid-based formulations, and how these relate to the in vitro drug release and solubilisation, lipid carrier digestion and cell permeation performances. Numerous in vivo proof-of-concept studies are presented to highlight the viability of these dry lipid-based formulations. This review is significant in directing future research work in fostering translation of dry lipid-based formulations into clinical applications.     

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.     

Cyclodextrins: structure,physicochemical properties and pharmaceutical applications

Since their discovery over 100 years ago cyclodextrins (CDs) have been the subject of numerous scientific publications. In 2016 alone CDs were the subject of over 2200 research articles published in peer-reviewed journals and mentioned in over 2300 patents and patent applications, many of which were on pharmaceutical applications. Natural CDs and their derivatives are used as enabling pharmaceutical excipients that enhance aqueous solubility of poorly soluble drugs, increase drug permeability through biological membranes and improve drug bioavailability. Unlike conventional penetration enhancers, their hydrophilic structure and high molecular weight prevents them from penetrate into lipophilic membranes leaving biological membranes intact. The natural CDs and some of their derivatives have monographs in pharmacopeias and are also commonly used as food additives and in toiletry products. CDs form inclusion complexes with lipophilic moieties of hydrophobic drugs. Furthermore, CDs are able to form non-inclusion complexes and self-assembled aggregates; small and large complex aggregates with micellar-like structures that can enhance drug solubility. Excipients commonly used in pharmaceutical formulations may have additive or inhibiting effect on the CD solubilization. Here various methods used to investigate CD aggregate formation are reviewed as well as techniques that are used to increase the solubilizing effects of CDs; methods that enhance the apparent intrinsic solubility of drugs and/or the complexation efficacy and decrease the amount of CD needed to develop CD-containing pharmaceutical formulations. It will be explained how too much or too little CD can hamper drug bioavailability, and the role of CDs in solid dosage forms and parenteral formulations, and examples given on how CDs can enhance drug delivery after ocular, nasal and pulmonary administration.     

人工智能在药物发现中的应用与挑战

新药研发存在周期长、费用高和成功率低等特点。人工智能技术是近些年来的热点技术之一,在很多领域都有非常广泛的应用,多种人工智能方法已经成功应用于药物的发现过程。综述总结了常用机器学习方法和深度学习方法在药物研发领域中的应用,同时也提出了人工智能存在的问题和面临的挑战。整体而言,人工智能技术在药物研发领域发展潜力巨大,将为医药发展带来新的机遇和希望。     

Relationships between the modulus of elasticity and tensile strength for pharmaceutical drugs and excipients.

The relationship between the modulus of elasticity and tensile strength for a variety of pharmaceutical drugs and excipients has been explored as a means of generating algorithms for use in computer simulations and expert systems. From literature data two equations have been developed to enable the formulator, from knowledge of one property, to predict the other with a reasonable degree of accuracy. Such relationships are invaluable for use in computer simulation programs or formulation expert systems, enabling formulators to screen potential formulations quickly without the need for extensive experimental work.     

The Next Era: Deep Learning in Pharmaceutical Research

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule’s properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique.     

Solid dispersions, part I: recent evolutions and future opportunities in manufacturing methods for dissolution rate enhancement of poorly water-soluble drugs

INTRODUCTION: In recent years, the number of active pharmaceutical ingredients with high therapeutic impact, but very low water solubility, has increased significantly. Thus, a great challenge for pharmaceutical technology is to create new formulations and efficient drug-delivery systems to overcome these dissolution problems. AREAS COVERED: Drug formulation in solid dispersions (SDs) is one of the most commonly used techniques for the dissolution rate enhancement of poorly water-soluble drugs. Generally, SDs can be defined as a dispersion of active ingredients in molecular, amorphous and/or microcrystalline forms into an inert carrier. This review covers literature which states that the dissolution enhancement of SDs is based on the fact that drugs in the nanoscale range, or in amorphous phase, dissolve faster and to a greater extent than micronized drug particles. This is in accordance to the Noyes-Whitney equation, while the wetting properties of the used polymer may also play an important role. EXPERT OPINION: The main factors why SD-based pharmaceutical products on the market are steadily increasing over the last few years are: the recent progress in various methods used for the preparation of SDs, the effect of evolved interactions in physical state of the drug and formulation stability during storage, the characterization of the physical state of the drug and the mechanism of dissolution rate enhancement.     

Prediction Machines: Applied Machine Learning for Therapeutic Protein Design and Development

The rapid growth in technological advances and quantity of scientific data over the past decade has led to several challenges including data storage and analysis. Accurate models of complex datasets were previously difficult to develop and interpret. However, improvements in machine learning algorithms have since enabled unparalleled classification and prediction capabilities. The application of machine learning can be seen throughout diverse industries due to their ease of use and interpretability. In this review, we describe popular machine learning algorithms and highlight their application in pharmaceutical protein development. Machine learning models have now been applied to better understand the nonlinear concentration dependent viscosity of protein solutions, predict protein oxidation and deamidation rates, classify sub-visible particles and compare the physical stability of proteins. We also applied several machine learning algorithms using previously published data and describe models with improved predictions and classification. The authors hope that this review can be used as a resource to others and encourage continued application of machine learning algorithms to problems in pharmaceutical protein development.     

In silico prediction of drug‐induced rhabdomyolysis with machine‐learning models and structural alerts

Drug‐induced rhabdomyolysis (DIR) is a serious adverse reaction and can be fatal. In the present study, we focused on the modeling and understanding of the molecular basis of DIR of small molecule drugs. A series of machine‐learning models were developed using an Online Chemical Modeling Environment platform with a diverse dataset. A total of 80 machine‐learning models were generated. Based on the top‐performing individual models, a consensus model was also developed. The consensus model was available at https://ochem.eu/model/32214665 , and the individual models can be accessed with the corresponding model IDs on the website. Furthermore, we also analyzed the difference of distributions of eight key physicochemical properties between rhabdomyolysis‐inducing drugs and non‐rhabdomyolysis‐inducing drugs. Finally, structural alerts responsible for DIR were identified from fragments of the Klekota‐Roth fingerprints.     

Rational Selection of Bio-Enabling Oral Drug Formulations – A PEARRL Commentary

New drug candidates often require bio-enabling formation technologies such as lipid-based formulations, solid dispersions, or nanosized drug formulations. Development of such more sophisticated delivery systems generally requires higher resource investment compared to a conventional oral dosage form, which might slow down clinical development. To achieve the biopharmaceutical objectives while enabling rapid cost effective development, it is imperative to identify a suitable formulation technique for a given drug candidate as early as possible. Hence many companies have developed internal decision trees based mostly on prior organizational experience, though they also contain some arbitrary elements. As part of the EU funded PEARRL project, a number of new decision trees are here proposed that reflect both the current scientific state of the art and a consensus among the industrial project partners. This commentary presents and discusses these, while also going beyond this classical expert approach with a pilot study using emerging machine learning, where the computer suggests formulation strategy based on the physicochemical and biopharmaceutical properties of a molecule. Current limitations are discussed and an outlook is provided for likely future developments in this emerging field of pharmaceutics.