Risk Assessment of Psychotropic Drugs on Mitochondrial Function Using In Vitro Assays.

Mitochondria are potential targets responsible for some drug- and xenobiotic-induced organ toxicities. However, molecular mechanisms of drug-induced mitochondrial toxicities are mostly unknown. Here, multiple in vitro assays were used to investigate the effects of 22 psychotropic drugs on mitochondrial function. The acute extracellular flux assay identified inhibitors of the electron transport chain (ETC), i.e., aripiprazole, phenytoin, and fluoxetine, an uncoupler (reserpine), substrate inhibitors (quetiapine, carbamazepine, buspirone, and tianeptine), and cytotoxic compounds (chlorpromazine and valproic acid) in HepG2 cells. Using permeabilized HepG2 cells revealed minimum effective concentrations of 66.3, 6730, 44.5, and 72.1 µM for the inhibition of complex-I-linked respiration for quetiapine, valproic acid, buspirone, and fluoxetine, respectively. Assessing complex-II-linked respiration in isolated rat liver mitochondria revealed haloperidol is an ETC inhibitor, chlorpromazine is an uncoupler in basal respiration and an ETC inhibitor under uncoupled respiration (IC50 = 135 µM), while olanzapine causes a mild dissipation of the membrane potential at 50 µM. This research elucidates some mechanisms of drug toxicity and provides some insight into their safety profile for clinical drug decisions.

In Vitro Dissolution and Permeability Testing of Inhalation Products: Challenges and Advances.

In vitro dissolution and permeability testing aid the simulation of the in vivo behavior of inhalation drug products. Although the regulatory bodies have specific guidelines for the dissolution of orally administered dosage forms (e.g., tablets and capsules), this is not the case for orally inhaled formulations, as there is no commonly accepted test for assessing their dissolution pattern. Up until a few years ago, there was no consensus that assessing the dissolution of orally inhaled drugs is a key factor in the assessment of orally inhaled products. With the advancement of research in the field of dissolution methods for orally inhaled products and a focus on systemic delivery of new, poorly water-soluble drugs at higher therapeutic doses, an evaluation of dissolution kinetics is proving crucial. Dissolution and permeability testing can determine the differences between the developed formulations and the innovator's formulations and serve as a useful tool in correlating in vitro and in vivo studies. The current review highlights recent advances in the dissolution and permeability testing of inhalation products and their limitations, including recent cell-based technology. Although a few new dissolution and permeability testing methods have been established that have varying degrees of complexity, none have emerged as the standard method of choice. The review discusses the challenges of establishing methods that can closely simulate the in vivo absorption of drugs. It provides practical insights into method development for various dissolution testing scenarios and challenges with dose collection and particle deposition from inhalation devices for dissolution tests. Furthermore, dissolution kinetic models and statistical tests to compare the dissolution profiles of test and reference products are discussed.

Effect of pH, Ionic Strength and Agitation Rate on Dissolution Behaviour of 3D-Printed Tablets, Tablets Prepared from Ground Hot-Melt Extruded Filaments and Physical Mixtures.

With the current focus on 3D-printing technologies, it is essential to understand the processes involved in such printing methods and approaches to minimize the variability in dissolution behaviour to achieve better quality control outcomes. For this purpose, two formulations of theophylline tablets were prepared using hydroxypropyl cellulose (HPC) and ethyl cellulose (EC). Among the two types of tablets, three different methods (physical mixture (PM), hot-melt extrusion (HME) and 3D-printing fused deposition modelling (FDM)) were applied and their dissolution behaviours were studied under various conditions using a biodissolution tester. This was carried out at pH values of 1.2, 2.2, 5.8, 6.8, 7.2 and 7.5, mimicking the medium in the gastrointestinal tract. Dissolution tests under two dipping rates (10 dpm and 20 dpm) and two ionic strengths (0.2 M and 0.4 M) were conducted to mimic fed and fasting conditions. The dissolution efficiency (DE%), release rate, similarity factor (f2) and difference factor (f1) were calculated. When comparing the DE%, the formulation containing EC showed less sensitivity to changes in the dipping rate and ionic strength compared to the HPC formulation. As for the manufacturing method, 3D-printing FDM could improve the robustness of the dissolution behaviour of both formulations to dipping rate changes. However, for ionic strength changes, the effect of the manufacturing method was dependent on the formulation composition. For example, the 3D-printed tablets of the HPC formulation were more sensitive to changes in ionic strength compared to the EC-containing formulation. The release mechanism also changed after the thermal process, where n values in the Korsmeyer-Peppas model were much higher in the printing and HME methods compared to the PM. Based on the formulation composition, the 3D-printing method could be a good candidate method for tablets with a robust dissolution behaviour in the GI tract. Compared to HPC polymers, using hydrophobic EC polymers in printable formulations can result in a more robust dissolution behaviour in fed and fasting states.

Prediction of drug-induced mitochondrial dysfunction using succinate-cytochrome c reductase activity, QSAR and molecular docking.

There is increasing evidence that links mitochondrial off-target effects with organ toxicities. For this reason, predictive strategies need to be developed to identify mitochondrial dysfunction early in the drug discovery process. In this study, as a major mechanism of mitochondrial toxicity, first, the inhibitory activity of 35 compounds against succinate-cytochrome c reductase (SCR) was investigated. This in vitro study led to the generation of consistent experimental data for a diverse range of compounds, including pharmaceutical drugs and fungicides. Next, molecular docking and protein-ligand interaction fingerprinting (PLIF) analysis were used to identify significant residues and protein-ligand interactions for the Qo site of complex III and Q site of complex II. Finally, this data was used for the development of QSAR models using a regression-based approach to highlight structural and chemical features that might be responsible for SCR inhibition. The statistically validated QSAR models from this work highlighted the importance of low aqueous solubility, low ionisation, fewer 6-membered rings and shorter hydrocarbon alkane chains in the molecular structure for increased inhibition of SCR, hence mitochondrial toxicity. PLIF analysis highlighted two key residues for inhibitory activity of the Qo site of complex III: His 161 as H-bond acceptor and Pro 270 for arene interactions. Currently, there are limited structure-activity models published in the scientific literature for the prediction of mitochondrial toxicity. We believe this study helps shed light on the chemical space for the inhibition of mitochondrial electron transport chain (ETC).

An Insight into the Impact of Thermal Process on Dissolution Profile and Physical Characteristics of Theophylline Tablets Made through 3D Printing Compared to Conventional Methods.

The dissolution profile is of great importance in drug delivery and is affected by the manufacturing method. Thus, it is important to study the influence of the thermal process on drug release in emerging technologies such as 3D printing-fused deposition modeling (FDM). For this purpose, the characteristics of 3D printed tablets were compared to those of tablets prepared by other thermal methods such as hot-melt extrusion (HME) and non-thermal methods such as physical mixture (PM). Theophylline was used as a drug model and blends of ethyl cellulose (EC) and hydroxypropyl cellulose (HPC) were used as a matrix former. The solid state of the drug in all formulations was investigated by differential scanning calorimetry, X-ray powder diffraction, and Fourier-transformed infrared spectroscopy. All studied tablets had the same weight and surface area/volume (SA/V). Dissolution data showed that, for some formulations, printed tablets interestingly had a faster release profile despite having the highest hardness values (>550 N) compared to HME and PM tablets. Porosity investigations showed that 100% infill printed tablets had the highest porosity (~20%) compared to HME (<10%) and PM tablets (≤11%). True density records were the lowest in printed tablets (~1.22 g/m3) compared to tablets made from both HME and PM methods (~1.26 g/m3), reflecting the possible increase in polymer specific volume while printing. This increase in the volume of polymer network may accelerate water and drug diffusion from/within the matrix. Thus, it is a misconception that the 3D printing process will always retard drug release based on increased tablet hardness. Hardness, porosity, density, solid-state of the drug, SA/V, weight, and formulation components are all factors contributing to the release profile where the total balance can either slow down or accelerate the release profile.

Solubility Study of Acetylsalicylic Acid in Ethanol + Water Mixtures: Measurement, Mathematical Modeling, and Stability Discussion.

Solubility determination of poorly water-soluble drugs is pivotal for formulation scientists when they want to develop a liquid formulation. Performing such a test with different ratios of cosolvents with water is time-consuming and costly. The scarcity of solubility data for poorly water-soluble drugs increases the importance of developing correlation and prediction equations for these mixtures. Therefore, the aim of the current research is to determine the solubility of acetylsalicylic acid in binary mixtures of ethanol+water at 25 and 37°C. Acetylsalicylic acid is non-stable in aqueous solutions and readily hydrolyze to salicylic acid. So, the solubility of acetylsalicylic acid is measured in ethanolic mixtures by HPLC to follow the concentration of produced salicylic acid as well. Moreover, the solubility of acetylsalicylic acid is modeled using different cosolvency equations. The measured solubility data were also predicted using PC-SAFT EOS model. DSC results ruled out any changes in the polymorphic form of acetylsalicylic acid after the solubility test, whereas XRPD results showed some changes in crystallinity of the precipitated acetylsalicylic acid after the solubility test. Fitting the solubility data to the different cosolvency models showed that the mean relative deviation percentage for the Jouyban-Acree model was less than 10.0% showing that this equation is able to obtain accurate solubility data for acetylsalicylic acid in mixtures of ethanol and water. Also, the predicted data with an average mean relative deviation percentage (MRD%) of less than 29.65% show the capability of the PC-SAFT model for predicting solubility data. A brief comparison of the solubilities of structurally related solutes to acetylsalicylic acid was also provided.

QSAR and molecular docking for the search of AOX inhibitors: a rational drug discovery approach.

The alternative oxidase (AOX) is a monotopic diiron carboxylate protein that catalyses the oxidation of ubiquinol and the reduction of oxygen to water. Although a number of AOX inhibitors have been discovered, little is still known about the ligand-protein interaction and essential chemical characteristics of compounds required for a potent inhibition. Furthermore, owing to the rapidly growing resistance to existing inhibitors, new compounds with improved potency and pharmacokinetic properties are urgently required. In this study we used two computational approaches, ligand-protein docking and Quantitative Structure-Activity Relationships (QSAR) to investigate binding of AOX inhibitors to the enzyme and the molecular characteristics required for inhibition. Docking studies followed by protein-ligand interaction fingerprint (PLIF) analysis using the AOX enzyme and the mutated analogues revealed the importance of the residues Leu 122, Arg 118 and Thr 219 within the hydrophobic cavity. QSAR analysis, using stepwise regression analysis with experimentally obtained IC50 values as the response variable, resulted in a multiple regression model with a good prediction accuracy. The model highlighted the importance of the presence of hydrogen bonding acceptor groups on specific positions of the aromatic ring of ascofuranone derivatives, acidity of the compounds, and a large linker group on the compounds on the inhibitory effect of AOX.

Critical Role of the Maternal Immune System in the Pathogenesis of Autism Spectrum Disorder.

Autism spectrum disorders (ASD) are a group of neurodevelopmental disorders characterised by impairments in communication, social interaction, and the presence of restrictive and repetitive behaviours. Over the past decade, most of the research in ASD has focused on the contribution of genetics, with the identification of a variety of different genes and mutations. However, the vast heterogeneity in clinical presentations associated with this disorder suggests that environmental factors may be involved, acting as a "second hit" in already genetically susceptible individuals. To this regard, emerging evidence points towards a role for maternal immune system dysfunctions. This literature review considered evidence from epidemiological studies and aimed to discuss the pathological relevance of the maternal immune system in ASD by looking at the proposed mechanisms by which it alters the prenatal environment. In particular, this review focuses on the effects of maternal immune activation (MIA) by looking at foetal brain-reactive antibodies, cytokines and the microbiome. Despite the arguments presented here that strongly implicate MIA in the pathophysiology of ASD, further research is needed to fully understand the precise mechanisms by which they alter brain structure and behaviour. Overall, this review has not only shown the importance of the maternal immune system as a risk factor for ASD, but more importantly, has highlighted new promising pathways to target for the discovery of novel therapeutic interventions for the treatment of such a life-changing disorder.

Investigation of water vapour sorption mechanism of starch-based pharmaceutical excipients.

Starch-based excipients are commonly used in oral solid dosage forms. The effect of particle size and pregelatinisation level of starch-based excipients on their water absorption behaviour have been evaluated. The results showed that starch-based excipients have type ii isotherms, indicating that the principal mechanism of sorption is the formation of monolayer coverage and multilayer water molecules (10-80 RH %). It was found that the particle size of starch-based excipients did not have any influence on the rate of water sorption, whereas the level of pregelatinisation changed the kinetics of water sorption-desorption. Results showed that the higher the degree of pregelatinisation, the higher the rate of water absorption, which is irrespective of particle size. SEM images showed that a partially gelatinised starch had a firm granular structure with small pores and channels on the surface while a fully gelatinised starch had more irregular and spongy like surface with a degree of fractured particles.

Liquisolid System and Liqui-Mass System Are Not the Same.

This commentary is written in response to Pezzini's research group commentary, which claimed Liqui-Pellet and liquisolid pellet are not different. Despite some similarities, there are crucial differences separating these two technologies. Liqui-Pellet uses liqui-mass system (wet mass/paste admixture), and liquisolid pellet uses liquisolid system (flowable powder admixture). The understanding of the well-defined term 'liquisolid system' is crucial to understand what is and is not liquisolid formulation. Spireas, who is the inventor of liquisolid technology, clearly defined liquisolid system in his patent document and publications. Since his first publication in 1998, there are around 200 articles about liquisolid formulations (extracted from Scopus), and with no exception, every single one of them followed the original definition of liquisolid system. Liqui-Pellet does not use liquisolid system and so calling it the same as liquisolid pellet, which uses liquisolid system, is incorrect and misleading. The purpose of this commentary is to resolve misunderstanding and support furthering knowledge.

Optimising the release rate of naproxen liqui-pellet: a new technology for emerging novel oral dosage form.

Liqui-pellet is a new dosage form stemming from pelletisation technology and concept from liquisolid technology. In spite of liqui-pellet overcoming a major hurdle in liquisolid technology through achieving excellent flow property with high liquid load factor, the formulation requires to be optimised in order to improve drug release rate. Liqui-pellets of naproxen containing Tween 80, Primojel, Avicel and Aerosil were extruded and spheronised. Flowability test confirmed that all liqui-pellet formulations have excellent-good flow property (Carr's index between 3.9-11.17%), including liqui-pellets with a high liquid load factor of 1.52, where 38% of the total mass is co-solvent. This shows a relatively high liquid load factor can be achieved in liqui-pellet without compromising the flowability, which is one of the key novelty of this work. It was found that the improved drug release rate was due to the remarkably improved disintegration of the supposedly non-disintegrating microcrystalline-based pellet; the optimised liqui-pellet seems to explode into fragments in the dissolution medium. At pH 1.2, the optimised formulation had ~ 10% more drug release than non-optimised formulation after 2 h, and at pH 7.4, the drug release of the optimised pellet was nearing 100% at ~ 15 min, whereas the none-optimised pellet only achieved ~ 79% drug release after 2 h. DSC and XRPD indicated an increase in the dissolution rate could be due to molecularly dispersion of naproxen in the pellets. Overall results showed that liqui-pellet exhibited an enhanced drug release and the capacity for high liquid load factor whilst maintaining excellent flowability, rendering it a potentially commercially feasible drug delivery system.

Liqui-Pellet: the Emerging Next-Generation Oral Dosage Form Which Stems from Liquisolid Concept in Combination with Pelletization Technology.

In spite of the major advantages that the liquisolid technology offers, particularly in tackling poor bioavailability of poorly water-soluble drugs (i.e., BCS Class II drugs), there are a few critical drawbacks. The inability of a high liquid load factor, poor flowability, poor compactibility, and an inability to produce a high dose dosage form of a reasonable size for swallowing are major hurdles, hampering this technology from being commercially feasible. An attempt was therefore made to overcome these drawbacks whilst maintaining the liquisolid inherent advantages. This resulted in the emerging next generation of oral dosage forms called the liqui-pellet. All formulations were incorporated into capsules as the final product. Solubility studies of naproxen were conducted in different liquid vehicles, namely polyethylene glycol 200, propylene glycol, Tween 80, Labrafil, Labrasol, and Kolliphor EL. The scanning electron microscopy studies indicated that the liquid vehicle tends to reduce the surface roughness of the pellet. X-ray powder diffraction (XRPD) indicated no significant differences in the crystalline structure or amorphous content between the physical mixture and the liqui-pellet formulation. This was due to the presence of a high concentration of amorphous Avicel in the formulation which overshadowed the crystalline structure of naproxen in the physical mixtures. Flowability and dissolution tests confirmed that this next-generation oral dosage form has excellent flowability, whilst maintaining the typical liquisolid enhanced drug release performance in comparison to its physical mixture counterpart. The liqui-pellet also had a high liquid load factor of 1, where ~ 29% of the total mass was the liquid vehicle. This shows that a high liquid load factor can be achieved in a liqui-pellet without compromising flowability. Overall, the results showed that the poor flowability of a liquisolid formulation could be overcomed with the liqui-pellet, which is believed to be a major advancement into the commercial feasibility of the liquisolid concept.

Machine learning for predicting lifespan-extending chemical compounds.

Increasing age is a risk factor for many diseases; therefore developing pharmacological interventions that slow down ageing and consequently postpone the onset of many age-related diseases is highly desirable. In this work we analyse data from the DrugAge database, which contains chemical compounds and their effect on the lifespan of model organisms. Predictive models were built using the machine learning method random forests to predict whether or not a chemical compound will increase Caenorhabditis elegans' lifespan, using as features Gene Ontology (GO) terms annotated for proteins targeted by the compounds and chemical descriptors calculated from each compound's chemical structure. The model with the best predictive accuracy used both biological and chemical features, achieving a prediction accuracy of 80%. The top 20 most important GO terms include those related to mitochondrial processes, to enzymatic and immunological processes, and terms related to metabolic and transport processes. We applied our best model to predict compounds which are more likely to increase C. elegans' lifespan in the DGIdb database, where the effect of the compounds on an organism's lifespan is unknown. The top hit compounds can be broadly divided into four groups: compounds affecting mitochondria, compounds for cancer treatment, anti-inflammatories, and compounds for gonadotropin-releasing hormone therapies.

Effect of OATP-binding on the prediction of biliary excretion.

1. Biliary excretion of compounds is dependant on several transporter proteins for the active uptake of compounds from the blood into the hepatocytes. Organic anion-transporting polypeptides (OATPs) are some of the most abundant transporter proteins in the sinusoidal membrane and have been shown to have substrate specificity similar to the structural characteristics of cholephilic compounds. 2. In this study, we sought to use measures of OATP binding as predictors of biliary excretion in conjunction with molecular descriptors in a quantitative structure-activity relationship (QSAR) study. Percentage inhibitions of three subtypes of OATPs were used as surrogate indicators of OATP substrates. Several statistical modelling techniques were incorporated including classification and regression trees, boosted trees, random forest and multivariate adaptive regression splines (MARS) in order to first develop QSARs for the prediction of OATP inhibition of compounds. The predicted OATP percentage inhibition using selected models were then used as features of the QSAR models for the prediction of biliary excretion of compounds in rat. 3. The results indicated that incorporation of predicted OATP inhibition improves accuracy of biliary excretion models. The best result was obtained from a simple regression tree that used predicted OATP1B1 percentage inhibition at the root node of the tree.

Simultaneous Prediction of four ATP-binding Cassette Transporters' Substrates Using Multi-label QSAR.

Efflux by the ATP-binding cassette (ABC) transporters affects the pharmacokinetic profile of drugs and it has been implicated in drug-drug interactions as well as its major role in multi-drug resistance in cancer. It is therefore important for the pharmaceutical industry to be able to understand what phenomena rule ABC substrate recognition. Considering a high degree of substrate overlap between various members of ABC transporter family, it is advantageous to employ a multi-label classification approach where predictions made for one transporter can be used for modeling of the other ABC transporters. Here, we present decision tree-based QSAR classification models able to simultaneously predict substrates and non-substrates for BCRP1, P-gp/MDR1 and MRP1 and MRP2, using a dataset of 1493 compounds. To this end, two multi-label classification QSAR modelling approaches were adopted: Binary Relevance (BR) and Classifier Chain (CC). Even though both multi-label models yielded similar predictive performances in terms of overall accuracies (close to 70 %), the CC model overcame the problem of skewed performance towards identifying substrates compared with non-substrates, which is a common problem in the literature. The models were thoroughly validated by using external testing, applicability domain and activity cliffs characterization. In conclusion, a multi-label classification approach is an appropriate alternative for the prediction of ABC efflux.

Substrate-specific effects of pirinixic acid derivatives on ABCB1-mediated drug transport.

Pirinixic acid derivatives, a new class of drug candidates for a range of diseases, interfere with targets including PPARα, PPARγ, 5-lipoxygenase (5-LO), and microsomal prostaglandin and E2 synthase-1 (mPGES1). Since 5-LO, mPGES1, PPARα, and PPARγ represent potential anti-cancer drug targets, we here investigated the effects of 39 pirinixic acid derivatives on prostate cancer (PC-3) and neuroblastoma (UKF-NB-3) cell viability and, subsequently, the effects of selected compounds on drug-resistant neuroblastoma cells. Few compounds affected cancer cell viability in low micromolar concentrations but there was no correlation between the anti-cancer effects and the effects on 5-LO, mPGES1, PPARα, or PPARγ. Most strikingly, pirinixic acid derivatives interfered with drug transport by the ATP-binding cassette (ABC) transporter ABCB1 in a drug-specific fashion. LP117, the compound that exerted the strongest effect on ABCB1, interfered in the investigated concentrations of up to 2µM with the ABCB1-mediated transport of vincristine, vinorelbine, actinomycin D, paclitaxel, and calcein-AM but not of doxorubicin, rhodamine 123, or JC-1. In silico docking studies identified differences in the interaction profiles of the investigated ABCB1 substrates with the known ABCB1 binding sites that may explain the substrate-specific effects of LP117. Thus, pirinixic acid derivatives may offer potential as drug-specific modulators of ABCB1-mediated drug transport.

Enzastaurin inhibits ABCB1-mediated drug efflux independently of effects on protein kinase C signalling and the cellular p53 status.

The PKCß inhibitor enzastaurin was tested in parental neuroblastoma and rhabdomyosarcoma cell lines, their vincristine-resistant sub-lines, primary neuroblastoma cells, ABCB1-transduced, ABCG2-transduced, and p53-depleted cells. Enzastaurin IC50s ranged from 3.3 to 9.5 µM in cell lines and primary cells independently of the ABCB1, ABCG2, or p53 status. Enzastaurin 0.3125 µM interfered with ABCB1-mediated drug transport. PKCα and PKCß may phosphorylate and activate ABCB1 under the control of p53. However, enzastaurin exerted similar effects on ABCB1 in the presence or absence of functional p53. Also, enzastaurin inhibited PKC signalling only in concentrations ≥ 1.25 µM. The investigated cell lines did not express PKCß. PKCα depletion reduced PKC signalling but did not affect ABCB1 activity. Intracellular levels of the fluorescent ABCB1 substrate rhodamine 123 rapidly decreased after wash-out of extracellular enzastaurin, and enzastaurin induced ABCB1 ATPase activity resembling the ABCB1 substrate verapamil. Computational docking experiments detected a direct interaction of enzastaurin and ABCB1. These data suggest that enzastaurin directly interferes with ABCB1 function. Enzastaurin further inhibited ABCG2-mediated drug transport but by a different mechanism since it reduced ABCG2 ATPase activity. These findings are important for the further development of therapies combining enzastaurin with ABC transporter substrates.

Predicting volume of distribution with decision tree-based regression methods using predicted tissue:plasma partition coefficients.

BACKGROUND: Volume of distribution is an important pharmacokinetic property that indicates the extent of a drug's distribution in the body tissues. This paper addresses the problem of how to estimate the apparent volume of distribution at steady state (Vss) of chemical compounds in the human body using decision tree-based regression methods from the area of data mining (or machine learning). Hence, the pros and cons of several different types of decision tree-based regression methods have been discussed. The regression methods predict Vss using, as predictive features, both the compounds' molecular descriptors and the compounds' tissue:plasma partition coefficients (Kt:p) - often used in physiologically-based pharmacokinetics. Therefore, this work has assessed whether the data mining-based prediction of Vss can be made more accurate by using as input not only the compounds' molecular descriptors but also (a subset of) their predicted Kt:p values. RESULTS: Comparison of the models that used only molecular descriptors, in particular, the Bagging decision tree (mean fold error of 2.33), with those employing predicted Kt:p values in addition to the molecular descriptors, such as the Bagging decision tree using adipose Kt:p (mean fold error of 2.29), indicated that the use of predicted Kt:p values as descriptors may be beneficial for accurate prediction of Vss using decision trees if prior feature selection is applied. CONCLUSIONS: Decision tree based models presented in this work have an accuracy that is reasonable and similar to the accuracy of reported Vss inter-species extrapolations in the literature. The estimation of Vss for new compounds in drug discovery will benefit from methods that are able to integrate large and varied sources of data and flexible non-linear data mining methods such as decision trees, which can produce interpretable models. Graphical AbstractDecision trees for the prediction of tissue partition coefficient and volume of distribution of drugs.

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.

Decision trees to characterise the roles of permeability and solubility on the prediction of oral absorption.

Oral absorption of compounds depends on many physiological, physiochemical and formulation factors. Two important properties that govern oral absorption are in vitro permeability and solubility, which are commonly used as indicators of human intestinal absorption. Despite this, the nature and exact characteristics of the relationship between these parameters are not well understood. In this study a large dataset of human intestinal absorption was collated along with in vitro permeability, aqueous solubility, melting point, and maximum dose for the same compounds. The dataset allowed a permeability threshold to be established objectively to predict high or low intestinal absorption. Using this permeability threshold, classification decision trees incorporating a solubility-related parameter such as experimental or predicted solubility, or the melting point based absorption potential (MPbAP), along with structural molecular descriptors were developed and validated to predict oral absorption class. The decision trees were able to determine the individual roles of permeability and solubility in oral absorption process. Poorly permeable compounds with high solubility show low intestinal absorption, whereas poorly water soluble compounds with high or low permeability may have high intestinal absorption provided that they have certain molecular characteristics such as a small polar surface or specific topology.