Prediction of drug solubility from molecular structure using a drug-like training set

The Artificial Intelligence-Powered New Era in Pharmaceutical Research and Development: A Review

Currently, artificial intelligence (AI), machine learning (ML), and deep learning (DL) are gaining increased interest in many fields, particularly in pharmaceutical research and development, where they assist in decision-making in complex situations. Numerous research studies and advancements have demonstrated how these computational technologies are used in various pharmaceutical research and development aspects, including drug discovery, personalized medicine, drug formulation, optimization, predictions, drug interactions, pharmacokinetics/ pharmacodynamics, quality control/quality assurance, and manufacturing processes. Using advanced modeling techniques, these computational technologies can enhance efficiency and accuracy, handle complex data, and facilitate novel discoveries within minutes. Furthermore, these technologies offer several advantages over conventional statistics. They allow for pattern recognition from complex datasets, and the models, typically developed from data-driven algorithms, can predict a given outcome (model output) from a set of features (model inputs). Additionally, this review discusses emerging trends and provides perspectives on the application of AI with quality by design (QbD) and the future role of AI in this field. Ethical and regulatory considerations associated with integrating AI into pharmaceutical technology were also examined. This review aims to offer insights to researchers, professionals, and others on the current state of AI applications in pharmaceutical research and development and their potential role in the future of research and the era of pharmaceutical Industry 4.0 and 5.0.

Facile one-pot synthesis and in silico study of new heterocyclic scaffolds with 4-pyridyl moiety: Mechanistic insights and X-ray crystallographic elucidation

4-Acetylpyridine 1 and malononitrile 2 were allowed to react in a 3MCRs with dimedone 3a or cyclohexa-1,3-dione 3b under reflux to afford 4-methyl-4-(pyridin-4-yl)-5,6,7,8-tetrahydro-4H-chromene derivatives 4a,b respectively. The mechanism of the reaction has been studied and the structures elucidated by analytical, spectral as well as X-ray crystallographic data. Heterocyclic compounds find widespread application in pharmaceutical and agrochemical products. Docking analyses were performed on the synthesized compounds to assess their binding modes with various amino acids of the target protein tubulin (PDB Code - 1SA0). The results indicated promising binding scores for compounds 4a and 4b, suggesting a strong affinity for the tubulin binding site. Finally, ADMET for the synthesized compounds 4a, 4b, 5, 8a and 8b were carried out. The drug likeness and pharmacokinetic properties of the prepared compounds were also evaluated. Notably, all of the novel compounds adhered to Lipinski's rule (Ro5) without any violations.

Dual active pyrimidine-based carbocyclic nucleoside derivatives: synthesis, and in silico and in vitro anti-diabetic and anti-microbial studies

Diabetes mellitus (DM) is a chronic metabolic disorder marked by high blood glucose levels, impairing glucose production in the body. Its prevalence has steadily risen over the past decades, leading to compromised immunity and heightened susceptibility to microbial infections. Immune dysfunction associated with diabetes raises vulnerability, while neuropathy dulls sensation in the extremities, reducing injury awareness. Hence, the development of novel chemical compounds for anti-diabetic and anti-infective treatments is imperative to mitigate adverse effects. In this study, we designed and synthesized pyrimidine-based carbocyclic nucleoside derivatives with C-4 substitution to assess their potential in inhibiting α-glucosidase for managing diabetes mellitus (DM) and microbial infections. Compounds 8b and 10a displayed promising IC50 values against α-glucosidase (43.292 nmol and 48.638 nmol, respectively) and noteworthy docking energies (-9.4 kcal mol-1 and -10.3 kcal mol-1, respectively). Additionally, compounds 10a and 10b exhibited better antimicrobial activity against Bacillus cereus, with the zone of inhibition values of 2.2 ± 0.25 mm and 1.4 ± 0.1 mm at a 100 μl concentration, respectively. Compound 10a also exhibited a modest zone of inhibition of 1.2 ± 0.15 mm against Escherichia coli at 100 μl.

Will we ever be able to accurately predict solubility?

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

Indolyl-4H-Chromene Derivatives as Antibacterial Agents: Synthesis, in Vitro and in Silico Studies

In this study, indolyl-4H-chromene derivatives are designed and synthesised using an eco-friendly multicomponent one-pot synthesis using benzaldehydes, nitroketene N, S-acetals, and indoles combine with InCl3 , a Lewis acid catalyst, and ethanol, an environmentally acceptable solvent. Due to antibiotic resistance, assessed these Indolyl-4H-chromene derivatives for their in vitro antibacterial activity against Gram-positive and Gram-negative bacteria, including Streptococcus pyogenes, Staphylococcus aureus, Clostridium pyrogenes, Bacillus subtilis, Escherichia coli, and Pseudomonas aeruginosa, using the agar well diffusion method and Minimum Inhibition Concentration (MIC) assay. Three compounds, 4-(1H-indol-3-yl)-6-methoxy-N-methyl-3-nitro-4H-chromen-2-amine, 4-(1H-indol-3-yl)-3-nitro-N-phenyl-4H-chromen-2-amine and 4-(6-Fluoro-1H-Indol-3-yl)-N-methyl-3-nitro-4H-chromen-2-amine showed better zone of inhibition (mm) and Minimum Inhibition Concentration (MIC) values of 10 μg/mL to 25 μg/mL against all bacterial types. The Ki values of 278.60 nM and 2.21 nM for compound 4-(1H-indol-3-yl)-3-nitro-N-phenyl-4H-chromen-2-amine showed improved interactions with DNA gyrase B and topoIV ParE's ATP binding sites in in silico studies.

Fragment-pair based drug molecule solubility prediction through attention mechanism

The purpose of drug discovery is to identify new drugs, and the solubility of drug molecules is an important physicochemical property in medicinal chemistry, that plays a crucial role in drug discovery. In solubility prediction, high-precision computational methods can significantly reduce the experimental costs and time associated with drug development. Therefore, artificial intelligence technologies have been widely used for solubility prediction. This study utilized the attention layer in mechanism in the deep learning model to consider the atomic-level features of the molecules, and used gated recurrent neural networks to aggregate vectors between layers. It also utilized molecular fragment technology to divide the complete molecule into pairs of fragments, extracted characteristics from each fragment pair, and finally fused the characteristics to predict the solubility of drug molecules. We compared and evaluated our method with five existing models using two performance evaluation indicators, demonstrating that our method has better performance and greater robustness.

Molecular Hybrids of Pyazolo[3,4-b]pyridine and Triazole: Design, Synthesis and In Vitro Antibacterial Studies

Antimicrobial resistance is on the rise, and there aren't enough new treatments to combat it. This might send the modern world back to the pre-antibiotic age. The molecular hybrids of pyrazolo[3,4-b]pyridine and triazole have been designed, synthesized, and analyzed for their drug-like molecule nature and in vitro analyses for their inhibition potentials against S. aureus and K. pneumoniae. The compounds 24 and 27 have been identified as the high potential molecules in this series based on in vitro experiments. Compound 24 has zone of inhibition values of 15 ± 0.82 mm and 14 ± 0.7 mm, whilst compound 27 has zone of inhibition values of 18 ± 0.95 mm and 16 ± 0.82 mm against S. aureus and K. pneumoniae, respectively. MIC and MIB values for compounds 24 and 27 against S. aureus and K. pneumoniae are 0.25 and 0.5, respectively.

Xanthenylacetic Acid Derivatives Effectively Target Lysophosphatidic Acid Receptor 6 to Inhibit Hepatocellular Carcinoma Cell Growth

Despite the increasing incidence of hepatocellular carcinoma (HCC) worldwide, current pharmacological treatments are still unsatisfactory. We have previously shown that lysophosphatidic acid receptor 6 (LPAR6) supports HCC growth and that 9-xanthenylacetic acid (XAA) acts as an LPAR6 antagonist inhibiting HCC growth without toxicity. Here, we synthesized four novel XAA derivatives, (±)-2-(9H-xanthen-9-yl)propanoic acid (compound 4 - MC9), (±)-2-(9H-xanthen-9-yl)butanoic acid (compound 5 - MC6), (±)-2-(9H-xanthen-9-yl)hexanoic acid (compound 7 - MC11), and (±)-2-(9H-xanthen-9-yl)octanoic acid (compound 8 - MC12, sodium salt) by introducing alkyl groups of increasing length at the acetic α-carbon atom. Two of these compounds were characterized by X-ray powder diffraction and quantum mechanical calculations, while molecular docking simulations suggested their enantioselectivity for LPAR6. Biological data showed anti-HCC activity for all XAA derivatives, with the maximum effect observed for MC11. Our findings support the view that increasing the length of the alkyl group improves the inhibitory action of XAA and that enantioselectivity can be exploited for designing novel and more effective XAA-based LPAR6 antagonists.

Pruned Machine Learning Models to Predict Aqueous Solubility

Solubility is a key metric for therapeutic compounds. Conversely, insoluble compounds cloud the accuracy of assays at all stages of chemical biology and drug discovery. Herein, we disclose naïve Bayesian classifier models to predict aqueous solubility. Publicly accessible aqueous solubility data were used to create two full, or nonpruned, training sets. These two sets were also combined to create a full fused set, and a training set comprised of a literature collation of solubility data was also considered as a reference. We tested different extents of data pruning on the training sets and constructed machine learning models that were evaluated with two independent, external test sets that contained compounds that were different from the training sets. The best pruned and fused model was significantly more accurate, in comparison to either the full model or the full fused model, with the prediction of these external test sets. By carefully removing data from the training set, less information can be used to create more accurate machine learning models for aqueous solubility. This knowledge and the curated training sets should prove useful to future machine learning approaches.

Facts, Patterns, and Principles in Drug Discovery: Appraising the Rule of 5 with Measured Physicochemical Data

The rule of 5 was designed to estimate the likelihood of poor absorption or permeation, noting the impact of poor solubility. This Perspective explores the impact of various physicochemical descriptors and contemporary lipophilicity measurements on permeability and solubility, showing that the distribution coefficient log D_7.4 (rather than log P) is the most impactful parameter. Molecular weight, almost invariably the defining characteristic of "beyond the rule of 5" compounds, has little impact on solubility when log D_7.4 measurements and aromaticity are considered. Predicting permeation is more complex, given passive and carrier transport mechanisms; however, notable patterns of behavior are apparent, giving insight even "beyond the rule of 5". Recommended best practices should involve using the facts (measurements) and the patterns they reveal to establish informative principles rather than fastidious rules.

Thiosemicarbazone derivatives: Design, synthesis and in vitro antimalarial activity studies

Different types of thiosemicarbazone derivatives were designed and tested for their Drug-Like Molecular (DLM) nature by using Lipinski and Veber rules. Subsequently, compounds with DLM properties were synthesized and characterized by spectral methods. In vitro antimalarial activity studies of the synthesized thiosemicarbazone derivatives have been carried out against Plasmodium falciparum, 3D7 strain using fluorescence assay method and found that the compounds, (E)-2-(1-(4-fluorophenyl)ethylidene)hydrazine-1-carbothioamide (6), (E)-2-(1-(3-bromophenyl) ethylidene) hydrazine-1-carbothioamide (15) and (E)-2-(3,4,5-trimethoxybenzylidene) hydrazine-1-carbothioamide (29) showed notable antimalarial activity with EC₅₀ values of 13.54 μM, 15.83 μM and 14.52 μM respectively.

Anticancer potential of aminomethylidene-diazinanes I. Synthesis of arylaminomethylidene of diazinetriones and its cytotoxic effects tested in glioblastoma cells

Diazinane and aryl moieties with vinylamine linkers were synthesized to investigate the importance of their structural variations as potential anti-glioblastoma agents. Structural variations incorporated on to the diazinane moiety included oxa and thio derivatives, each with a variety of nitrogen-bound substituents. The size and shape of the aromatic moiety was varied, with the final variation introducing two carbonyl groups, yielding a substituted anthraquinone. Readily available diazinanes and aryl amines were used asan advantageous foundation. Several parameters were calculated whilst engineering these compounds, including: ClogP, molecular polarizability, polar surface area, minimal molecular projected area, and pK_a. In addition, a simple and efficient procedure was developed to synthesize these compounds. It was demonstrated that a vinylamine with 1,3-diazinane-2,4,6-trione and 1-anthraquinone moiety is the most promising drug candidate causing almost 70% of LN229 tumor cell death at 1µg/ml. In addition, its molecular polarizability, polar surface area and minimal molecular projected area indicate a possible potential of this molecule for crossing BBB.

Hydration Free Energy as a Molecular Descriptor in Drug Design: A Feasibility Study

In this work the idea was investigated whether calculated hydration energy (ΔGhyd ) can be used as a molecular descriptor in defining promising regions of chemical space for drug design. Calculating ΔGhyd using the Density Solvation Model (SMD) in conjunction with the density functional theory (DFT) gave an excellent correlation with experimental values. Furthermore, calculated ΔGhyd correlates reasonably well with experimental water solubility (r(2) =0.545) and also log P (r(2) =0.530). Three compound collections were used: Known drugs (n=150), drug-like compounds (n=100) and simple organic compounds (n=140). As an approximation only molecules, which do not de/protonate at physiological pH were considered. A relatively broad distribution was seen for the known drugs with an average at -15.3 kcal/mol and a standard deviation of 7.5 kcal/mol. Interestingly, much lower averages were found for the drug-like compounds (-7.5 kcal/mol) and the simple organic compounds (-3.1 kcal/mol) with tighter distributions; 4.3 and 3.2 kcal/mol, respectively. This trend was not observed for these collections when calculated log P and log S values were used. The considerable greater exothermic ΔGhyd average for the known drugs clearly indicates in order to develop a successful drug candidate value of ΔGhyd <-5 kcal/mol or less is preferable.

Nilotinib based pharmacophore models for BCRABL

Tyrosine kinase inhibitors have revolutionized the treatment of several malignancies, converting lethal diseases in a manageable aspect. Imitanib, a small molecule ABL kinase inhibitor is a highly effective therapy for early phase chronic myeloid leukemia (CML), which has constitutively active ABL kinase activity owing to the over expression of the BCR-ABL fusion protein. But some patients develop imatinib resistance, particularly in the advanced phases of CML.The discovery of resistance mechanisms of imitanib; urge forward the development of second generation drugs. Nilotinib, a second generation drug is more potent inhibitor of BCR-ABL than imatinib. But nilotinib also develops dermatologic events and headache in patients. Large information about BCR-ABL structure and its inhibitors are now available. Based on the pharmacophore modeling approaches, it is possible to decipher the molecular determinants to inhibit BCR-ABL. We conducted a structure based and ligand based study to identify potent natural compounds as BCR-ABL inhibitor. First kinase inhibitors were docked with the receptor (BCR-ABL) and nilotinib was selected as a pharmacophore due its high binding efficiency. Eleven compounds were selected out of 1457 substances which have mutual pharmacopohre features with nilotinib. These eleven compounds were validated and used for docking study to find the drug like molecules. The best molecules from the final set of screening candidates can be evaluated in cell lines and may represent a novel class of BCR-ABL inhibitors.

ABBREVIATIONS

CML - Chronic myeloid leukemia, PDGFR - Platelet derived growth factor receptor, TKI - Tyrosine kinase inhibitors.

The Structure, Thermodynamics and Solubility of Organic Crystals from Simulation with a Polarizable Force Field

An important unsolved problem in materials science is prediction of the thermodynamic stability of organic crystals and their solubility from first principles. Solubility can be defined as the saturating concentration of a molecule within a liquid solvent, where the physical picture is of solvated molecules in equilibrium with their solid phase. Despite the importance of solubility in determining the oral bioavailability of pharmaceuticals, prediction tools are currently limited to quantitative structure-property relationships that are fit to experimental solubility measurements. For the first time, we describe a consistent procedure for the prediction of the structure, thermodynamic stability and solubility of organic crystals from molecular dynamics simulations using the polarizable multipole AMOEBA force field. Our approach is based on a thermodynamic cycle that decomposes standard state solubility into the sum of solid-vapor sublimation and vapor-liquid solvation free energies [Formula: see text], which are computed via the orthogonal space random walk (OSRW) sampling strategy. Application to the n-alkylamides series from aeetamide through octanamide was selected due to the dependence of their solubility on both amide hydrogen bonding and the hydrophobic effect, which are each fundamental to protein structure and solubility. On average, the calculated absolute standard state solubility free energies are accurate to within 1.1 kcal/mol. The experimental trend of decreasing solubility as a function of n-alkylamide chain length is recapitulated by the increasing stability of the crystalline state and to a lesser degree by decreasing favorability of solvation (i.e. the hydrophobic effect). Our results suggest that coupling the polarizable AMOEBA force field with an orthogonal space based free energy algorithm, as implemented in the program Force Field X, is a consistent procedure for predicting the structure, thermodynamic stability and solubility of organic crystals.

Prediction of physicochemical properties

Physicochemical properties are key factors in controlling the interactions of xenobiotics with living organisms. Computational approaches to toxicity prediction therefore generally rely to a very large extent on the physicochemical properties of the query compounds. Consequently it is important that reliable in silico methods are available for the rapid calculation of physicochemical properties. The key properties are partition coefficient, aqueous solubility, and pKa and, to a lesser extent, melting point, boiling point, vapor pressure, and Henry's law constant (air-water partition coefficient). The calculation of each of these properties from quantitative structure-property relationships (QSPRs) and from available software is discussed in detail, and recommendations made. Finally, detailed consideration is given of guidelines for the development of QSPRs and QSARs.

Insolubility classification with accurate prediction probabilities using a MetaClassifier

Insolubility is a crucial issue in drug design because insoluble compounds are often measured to be inactive although they might be active if they were soluble. We provide and analyze various insolubility classification models based on a recently published data set and compounds measured in-house at Boehringer-Ingelheim. The 2D descriptor sets from pharmacophore fingerprints and MOE and the 3D descriptor sets from ParaSurf and VolSurf were examined in conjunction with support vector machines, Bayesian regularized neural networks, and random forests. We introduce a classifier-fusion strategy, called metaclassifier, which improves upon the best single prediction and at the same time avoids descriptor selection, a potential source of overfitting. The metaclassifier strategy is compared to the simpler fusion strategies of maximum vote and highest probability picking. A prediction accuracy of 72.6% on a three class model is achieved with the metaclassifier, with nearly perfect separation of soluble and insoluble compounds and prediction as good as our calculated maximum possible agreement with experiment.