In silico prediction of ocular toxicity of compounds using explainable machine learning and deep learning approaches

The accurate identification of chemicals with ocular toxicity is of paramount importance in health hazard assessment. In contemporary chemical toxicology, there is a growing emphasis on refining, reducing, and replacing animal testing in safety evaluations. Therefore, the development of robust computational tools is crucial for regulatory applications. The performance of predictive models is heavily reliant on the quality and quantity of data. In this investigation, we amalgamated the most extensive dataset (4901 compounds) sourced from governmental GHS-compliant databases and literature to develop binary classification models of chemical ocular toxicity. We employed 12 molecular representations in conjunction with six machine learning algorithms and two deep learning algorithms to create a series of binary classification models. The findings indicated that the deep learning method GCN outperformed the machine learning models in cross-validation, achieving an impressive AUC of 0.915. However, the top-performing machine learning model (RF-Descriptor) demonstrated excellent performance with an AUC of 0.869 on the test set and was therefore selected as the best model. To enhance model interpretability, we conducted the SHAP method and attention weights analysis. The two approaches offered visual depictions of the relevance of key descriptors and substructures in predicting ocular toxicity of chemicals. Thus, we successfully struck a delicate balance between data quality and model interpretability, rendering our model valuable for predicting and comprehending potential ocular-toxic compounds in the early stages of drug discovery.

Understanding the Influence of API Conformations on Amorphous Dispersion Formation Potential Predictions using the R3m Molecular Descriptor

The R3m molecular descriptor (R-GETAWAY third-order autocorrelation index weighted by the atomic mass) has previously been shown to encode molecular attributes that appear to be physically and chemically relevant to grouping diverse active pharmaceutical ingredients (API) according to their potential to form persistent amorphous solid dispersions (ASDs) with polyvinylpyrrolidone-vinyl acetate copolymer (PVPVA). The initial R3m dispersibility model was built by using a single three-dimensional (3D) conformation for each drug molecule. Since molecules in the amorphous state will adopt a distribution of conformations, molecular dynamics simulations were performed to sample conformations that are probable in the amorphous form, which resulted in a distribution of R3m values for each API. Although different conformations displayed R3m values that differed by as much as 0.4, the median of each R3m distribution and the value predicted from the single 3D conformation were very similar for most structures studied. The variability in R3m resulting from the distribution of conformations was incorporated into a logistic regression model for the prediction of ASD formation in PVPVA, which resulted in a refinement of the classification boundary relative to the model that only incorporated a single conformation of each API.

Multivariate Approaches in Quantitative Structure-Property Relationships Study for the Photostability Assessment of 1,4-Dihydropyridine Derivatives

1,4-dihydropyridines (1,4-DHPs) are widely recognized as highly effective L-type calcium channel blockers with significant therapeutic benefits in the treatment of cardiovascular disorders. 1,4-DHPs can also target T-type calcium channels, making them promising drug candidates for neurological conditions. When exposed to light, all 1,4-DHPs tend to easily degrade, leading to an oxidation product derived from the aromatization of the dihydropyridine ring. Herein, the elaboration of a quantitative structure-property relationships (QSPR) model was carried out by correlating the light sensitivity of structurally different 1,4-DHPs with theoretical molecular descriptors. Photodegradation experiments were performed by exposing the drugs to a Xenon lamp following the ICH rules. The degradation was monitored by spectrophotometry, and experimental data were elaborated by Multivariate Curve Resolution (MCR) methodologies to assess the kinetic rates. The results were confirmed by the HPLC-DAD method. PaDEL-Descriptor software was used to calculate molecular descriptors and fingerprints related to the chemical structures. Seventeen of the 1875 molecular descriptors were selected and correlated to the photodegradation rate by means of the Ordinary Least Squares (OLS) algorithm. The chemometric model is useful to predict the photosensitivity of other 1,4-DHP derivatives with a very low relative error percentage of 5.03% and represents an effective tool to design new analogs characterized by higher photostability.

GUIDEMOL: A Python graphical user interface for molecular descriptors based on RDKit

GUIDEMOL is a Python computer program based on the RDKit software to process molecular structures and calculate molecular descriptors with a graphical user interface using the tkinter package. It can calculate descriptors already implemented in RDKit as well as grid representations of 3D molecular structures using the electrostatic potential or voxels. The GUIDEMOL app provides easy access to RDKit tools for chemoinformatics users with no programming skills and can be adapted to calculate other descriptors or to trigger other procedures. A command line interface (CLI) is also provided for the calculation of grid representations. The source code is available at https://github.com/jairesdesousa/guidemol.

Application of Machine Learning Methods to Predict the Air Half-Lives of Persistent Organic Pollutants

Persistent organic pollutants (POPs) are ubiquitous and bioaccumulative, posing potential and long-term threats to human health and the ecological environment. Quantitative structure-activity relationship (QSAR) studies play a guiding role in analyzing the toxicity and environmental fate of different organic pollutants. In the current work, five molecular descriptors are utilized to construct QSAR models for predicting the mean and maximum air half-lives of POPs, including specifically the energy of the highest occupied molecular orbital (HOMO_Energy_DMol3), a component of the dipole moment along the z-axis (Dipole_Z), fragment contribution to SAscore (SAscore_Fragments), subgraph counts (SC_3_P), and structural information content (SIC). The QSAR models were achieved through the application of three machine learning methods: partial least squares (PLS), multiple linear regression (MLR), and genetic function approximation (GFA). The determination coefficients (R2) and relative errors (RE) for the mean air half-life of each model are 0.916 and 3.489% (PLS), 0.939 and 5.048% (MLR), 0.938 and 5.131% (GFA), respectively. Similarly, the determination coefficients (R2) and RE for the maximum air half-life of each model are 0.915 and 5.629% (PLS), 0.940 and 10.090% (MLR), 0.939 and 11.172% (GFA), respectively. Furthermore, the mechanisms that elucidate the significant factors impacting the air half-lives of POPs have been explored. The three regression models show good predictive and extrapolation abilities for POPs within the application domain.

Computational Analysis of Some More Rectangular Tessellations of Kekulenes and Their Molecular Characterizations

Cycloarene molecules are benzene-ring-based polycyclic aromatic hydrocarbons that have been fused in a circular manner and are surrounded by carbon-hydrogen bonds that point inward. Due to their magnetic, geometric, and electronic characteristics and superaromaticity, these polycyclic aromatics have received attention in a number of studies. The kekulene molecule is a cyclically organized benzene ring in the shape of a doughnut and is the very first example of such a conjugated macrocyclic compound. Due to its structural characteristics and molecular characterizations, it serves as a great model for theoretical research involving the investigation of π electron conjugation circuits. Therefore, in order to unravel their novel electrical and molecular characteristics and foresee potential applications, the characterization of such components is crucial. In our current research, we describe two unique series of enormous polycyclic molecules made from the extensively studied base kekulene molecule, utilizing the essential graph-theoretical tools to identify their structural characterization via topological quantities. Rectangular kekulene Type-I and rectangular kekulene Type-II structures were obtained from base kekulene molecules arranged in a rectangular fashion. We also employ two subcases for each Type and, for all of these, we derived ten topological indices. We can investigate the physiochemical characteristics of rectangular kekulenes using these topological indices.

Computational Studies on Diverse Characterizations of Molecular Descriptors for Graphyne Nanoribbon Structures

Materials made of graphyne, graphyne oxide, and graphyne quantum dots have drawn a lot of interest due to their potential uses in medicinal nanotechnology. Their remarkable physical, chemical, and mechanical qualities, which make them very desirable for a variety of prospective purposes in this area, are mostly to blame for this. In the subject of mathematical chemistry, molecular topology deals with the algebraic characterization of molecules. Molecular descriptors can examine a compound's properties and describe its molecular topology. By evaluating these indices, researchers can predict a molecule's behavior including its reactivity, solubility, and toxicity. Amidst the captivating realm of carbon allotropes, γ-graphyne has emerged as a mesmerizing tool, with exquisite attention due to its extraordinary electronic, optical, and mechanical attributes. Research into its possible applications across numerous scientific and technological fields has increased due to this motivated attention. The exploration of molecular descriptors for characterizing γ-graphyne is very attractive. As a result, it is crucial to investigate and predict γ-graphyne's molecular topology in order to comprehend its physicochemical characteristics fully. In this regard, various characterizations of γ-graphyne and zigzag γ-graphyne nanoribbons, by computing and comparing distance-degree-based topological indices, leap Zagreb indices, hyper leap Zagreb indices, leap gourava indices, and hyper leap gourava indices, are investigated.

Estimating the hydrophobicity extent of molecular fragments using reversed-phase liquid chromatography

A fast HPLC method was developed to study the hydrophobicity extent of pharmaceutically relevant molecular fragments. By this strategy, the reduced amount of sample available for physico-chemical evaluations in early-phase drug discovery programs does not represent a limiting factor. The sixteen acid fragments investigated were previously synthesized also determining potentiometrically their experimental log D values. For four fragments it was not possible to determine such property since their values were outside of the instrumental working range (2 < pKa  < 12). An RP-HPLC method was therefore optimized. For each scrutinized method, some derived chromatographic indices were calculated, and Pearson's correlation coefficient (r) allowed to select the so-called "φ0 index" as the best correlating with the log D. Thew s p H ${}_w^spH$ was fixed at 3.5 and a modification of some variables [organic modifier (methanol vs. ACN), stationary phase (octyl vs. octadecyl), presence/absence of the additives n-octanol, n-butylamine, and n-octylamine], allowed to select the best correlation conditions, producing a r = 0.94 (p < 0.001). Importantly, the φ0 index enabled the estimation of log D values for four fragments which were unattainable by potentiometric titration. Moreover, a series of molecular descriptors were calculated to identify the chemical characteristics of the fragments explaining the obtained φ0 . The number of hydrogen bond donors and the index of cohesive interaction correlated with the experimental data.

Chemoinformatic modelling of the antioxidant activity of phenolic compounds

BACKGROUND

Antioxidants are chemicals used to protect foods from deterioration by neutralizing free radicals and inhibiting the oxidative process. One approach to investigate the antioxidant activity is to develop quantitative structure-activity relationships (QSARs).

RESULTS

A curated database of 165 structurally heterogeneous phenolic compounds with the Trolox equivalent antioxidant capacity (TEAC) was developed. Molecular geometries were optimized by means of the GFN2-xTB semiempirical method and diverse molecular descriptors were obtained afterwards. For model development, V-WSP unsupervised variable reduction was used before performing the genetic algorithms-variable subset selection (GAs-VSS) to construct the best five-descriptor multiple linear regression model. The coefficient of determination and the root mean square error were used to measure the performance in calibration (R²  = 0.789 and RMSEC = 0.381), and test set prediction (Q²  = 0.748 and RMSEP = 0.416), along several cross-validation criteria. To thoroughly understand the TEAC prediction, a fully explained mechanism of action of the descriptors is provided. In addition, the applicability domain of the model defined a theoretical chemical space for reliable predictions of new phenolic compounds.

CONCLUSION

This in silico model conforms to the five principles stated by the Organisation for Economic Co-operation and Development. The model might be useful for virtual screening of the antioxidant chemical space and for identifying the most potent molecules related to an experimental measurement of TEAC activity. In addition, the model could assist chemists working on computer-aided drug design for the synthesis of new targets with improved activity and potential uses in food science. © 2023 Society of Chemical Industry.

Molecular Motifs in Vascular Morphogenesis: Vascular Endothelial Growth Factor A (VEGFA) as the Leading Promoter of Angiogenesis

Tissular hypoxia stimulates vascular morphogenesis. Vascular morphogenesis shapes the cell and, consecutively, tissue growth. The development of new blood vessels is intermediated substantially through the tyrosine kinase pathway. There are several types of receptors inferred to be located in the blood vessel structures. Vascular endothelial growth factor A (VEGF-A) is the leading protagonist of angiogenesis. VEGF-A's interactions with its receptors VEGFR1, VEGFR2, and VEGFR3, together with disintegrin and metalloproteinase with thrombospondin motifs 1 (ADAMTS1), connective tissue growth factor (CTGF), and neuropilin-1 (NRP1), independently, are studied computationally. Peripheral artery disease (PAD), which results in tissue ischemia, is more prevalent in the senior population. Presently, medical curatives used to treat cases of PAD-antiplatelet and antithrombotic agents, statins, antihypertensive remedies with ACE (angiotensin-converting enzyme) impediments, angiotensin receptor blockers (ARB) or β- blockers, blood glucose control, and smoking cessation-are not effective. These curatives were largely established from the treatment of complaint cases of coronary disease. However, these medical curatives do not ameliorate lower limb perfusion in cases of PAD. Likewise, surgical or endovascular procedures may be ineffective in relieving symptoms. Eventually, after successful large vessel revascularization, the residual microvascular circulation may well limit the effectiveness of curatives in cases of PAD. It would thus feel rational to attempt to ameliorate perfusion in PAD by enhancing vascular rejuvenescence and function. Likewise, stimulating specific angiogenesis in these cases (PAD) can ameliorate the patient's symptomatology. Also, the quality of life of PAD patients can be improved by developing new vasodilative and angiogenetic molecules that stimulate the tyrosine kinase pathway. In this respect, the VEGFA angiogenetic pathway was explored computationally. Docking methodologies, molecular dynamics, and computational molecular design methodologies were used. VEGFA's interaction with its target was primarily studied. Common motifs in the vascular morphogenesis pathway are suggested using conformational energy and Riemann spaces. The results show that interaction with VEGFR2 and ADAMTS1 is pivotal in the angiogenetic process. Also, the informational content of two VEGFA complexes, VEGFR2 and ADAMTS1, is crucial in the angiogenesis process.

Effect of Storage Time on the Physical, Chemical, and Rheological Properties of Blueberry Jam: Experimental Measurements and Artificial Neural Network Simulation

Reversible data hiding (RDH) is crucial in modern data security, ensuring confidentiality and tamper-proofness in various industries like copyright protection, medical imaging, and digital forensics. As technology advances, RDH techniques become essential, but the trade-off between embedding capacity and visual quality must be heeded. In this paper, the relative correlation between the pixel's local complexity and its directional prediction error is employed to enhance an efficient RDH without using a location map. An embedding process based on multiple cumulative peak region localization (MCPRL) is proposed to hide information in the 3D-directional prediction error histogram with a lower local complexity value and avoid the underflow/overflow problems. The carrier image is divided into three color channels, and then each channel is split into two non-overlapping sets: blank and shadow. Two half-directional prediction errors (the blank set and the shadow set) are constructed to generate a full-directional prediction error for each color channel belonging to the host image. The local complexity value and directional prediction error are critical metrics in the proposed embedding process to improve security and robustness. By utilizing these metrics to construct a 3D stego-Blank Set, the 3D stego-shadow Set will be subsequently constructed using the 3D blank set. The proposed technique outperforms other state-of-the-art techniques in terms of embedding capacity, image quality, and robustness against attacks without an extra location map. The experimental results illustrate the effectiveness of the proposed method for various 3D RDH techniques.

Recent Advances in Machine-Learning-Based Chemoinformatics: A Comprehensive Review

In modern drug discovery, the combination of chemoinformatics and quantitative structure-activity relationship (QSAR) modeling has emerged as a formidable alliance, enabling researchers to harness the vast potential of machine learning (ML) techniques for predictive molecular design and analysis. This review delves into the fundamental aspects of chemoinformatics, elucidating the intricate nature of chemical data and the crucial role of molecular descriptors in unveiling the underlying molecular properties. Molecular descriptors, including 2D fingerprints and topological indices, in conjunction with the structure-activity relationships (SARs), are pivotal in unlocking the pathway to small-molecule drug discovery. Technical intricacies of developing robust ML-QSAR models, including feature selection, model validation, and performance evaluation, are discussed herewith. Various ML algorithms, such as regression analysis and support vector machines, are showcased in the text for their ability to predict and comprehend the relationships between molecular structures and biological activities. This review serves as a comprehensive guide for researchers, providing an understanding of the synergy between chemoinformatics, QSAR, and ML. Due to embracing these cutting-edge technologies, predictive molecular analysis holds promise for expediting the discovery of novel therapeutic agents in the pharmaceutical sciences.

Probing the Effect of Photovoltaic Material on Voc in Ternary Polymer Solar Cells with Non-Fullerene Acceptors by Machine Learning

The power conversion efficiency (PCE) of ternary polymer solar cells (PSCs) with non-fullerene has a phenomenal increase in recent years. However, improving the open circuit voltage (V_oc) of ternary PSCs with non-fullerene still remains a challenge. Therefore, in this work, machine learning (ML) algorithms are employed, including eXtreme gradient boosting, K-nearest neighbor and random forest, to quantitatively analyze the impact mechanism of V_oc in ternary PSCs with the double acceptors from the two aspects of photovoltaic materials. In one aspect of photovoltaic materials, the doping concentration has the greatest impact on V_oc in ternary PSCs. Furthermore, the addition of the third component affects the energy offset between the donor and acceptor for increasing V_oc in ternary PSCs. More importantly, to obtain the maximum V_oc in ternary PSCs with the double acceptors, the HOMO and LUMO energy levels of the third component should be around (-5.7 ± 0.1) eV and (-3.6 ± 0.1) eV, respectively. In the other aspect of molecular descriptors and molecular fingerprints in the third component of ternary PSCs with the double acceptors, the hydrogen bond strength and aromatic ring structure of the third component have high impact on the V_oc of ternary PSCs. In partial dependence plot, it is clear that when the number of methyl groups is four and the number of carbonyl groups is two in the third component of acceptor, the V_oc of ternary PSCs with the double acceptors can be maximized. All of these findings provide valuable insights into the development of materials with high V_oc in ternary PSCs for saving time and cost.

Quantitative structure activity relationship (QSAR) modeling study of some novel thiazolidine 4-one derivatives as potent anti-tubercular agents

This study aims to develop a QSAR model for Antitubercular activity. The quantitative structure-activity relationship (QSAR) approach predicted the thiazolidine-4-ones derivative's Antitubercular activity. For the QSAR study, 53 molecules with Antitubercular activity on H37Rv were collected from the literature. Compound structures were drawn by ACD/Labs ChemSketch. The energy minimization of the 2D structure was done using the MM2 force field in Chem3D pro. PaDEL Descriptor software was used to construct the molecular descriptors. QSARINS software was used in this work to develop the 2D QSAR model. A series of thiazolidine 4-one with MIC data were taken from the literature to develop the QSAR model. These compounds were split into a training set (43 compounds) and a test set (10 compounds). The PaDEL software calculated 2300 descriptors for this series of thiazolidine 4-one derivatives. The best predictive Model 4, which has R2 of 0.9092, R2adj of 0.8950 and LOF parameter of 0.0289 identify a preferred fit. The QSAR study resulted in a stable, predictive, and robust model representing the original dataset. In the QSAR equation, the molecular descriptor of MLFER_S, GATSe2, Shal, and EstateVSA 6 positively correlated with Antitubercular activity. While the SpMAD_Dzs 6 is negatively correlated with Antitubercular activity. The high polarizability, Electronegativities, Surface area contributions and number of Halogen atoms in the thiazolidine 4-one derivatives will increase the Antitubercular activity.

Quantitative structure-activity relationship(QSAR) models for color and COD removal for some dyes subjected to electrochemical oxidation

Electrochemical oxidation is an efficient method for the destruction of dyes in wastewater streams. The experimental conditions during electrochemical oxidation (EO) and molecular structure of a dye greatly influence the extent of degradation. The extent of degradation for a variety of dyes by EO can be predicted conveniently by the use of Quantitative structure-activity Relationship (QSAR) models. An abundant amount of published data on dye degradation by EO using highly variable experimental conditions lies unutilized to prepare QSAR models. In this study, an effort is made to use published experimental data on EO of aqueous dyes after applying an easy method of normalization, to prepare QSAR models for percent color and COD removal. Normalized color and COD removal were obtained by multiplying the reported removal by volume of reactor and concentration of dye; and divided by total current passed and the time of electrolysis. More than 15 molecular descriptors were computed using Schrodinger-suit 2018-3. The multiple linear regression (MLR) approach was used to develop normalized color and COD removal models. The quantum chemical descriptors: highest occupied molecular orbital energy (HOMO) and lowest unoccupied molecular orbital energy (LUMO), polar surface area (PSA), hydrogen bond donor count (HBD), and number of atoms were found significant. The statistical indices: goodness-of-fit, R² > 0.75, and internal and external validations, Q²_LOOCV and Q²_ext, > 0.5, satisfied the criteria for predictive models and indicated that the method of normalization used in this study is adequate. Developed QSAR models are quite simple, interpretable, and transparent.

Discovery of New 2-Phenylamino-3-acyl-1,4-naphthoquinones as Inhibitors of Cancer Cells Proliferation: Searching for Intra-Cellular Targets Playing a Role in Cancer Cells Survival

A series of 2-phenylamino-3-acyl-1,4-naphtoquinones were evaluated regarding their in vitro antiproliferative activities using DU-145, MCF-7 and T24 cancer cells. Such activities were discussed in terms of molecular descriptors such as half-wave potentials, hydrophobicity and molar refractivity. Compounds 4 and 11 displayed the highest antiproliferative activity against the three cancer cells and were therefore further investigated. The in silico prediction of drug likeness, using pkCSM and SwissADME explorer online, shows that compound 11 is a suitable lead molecule to be developed. Moreover, the expressions of key genes were studied in DU-145 cancer cells. They include genes involved in apoptosis (Bcl-2), tumor metabolism regulation (mTOR), redox homeostasis (GSR), cell cycle regulation (CDC25A), cell cycle progression (TP53), epigenetic (HDAC4), cell-cell communication (CCN2) and inflammatory pathways (TNF). Compound 11 displays an interesting profile because among these genes, mTOR was significantly less expressed as compared to control conditions. Molecular docking shows that compound 11 has good affinity with mTOR, unraveling a potential inhibitory effect on this protein. Due to the key role of mTOR on tumor metabolism, we suggest that impaired DU-145 cells proliferation by compound 11 is caused by a reduced mTOR expression (less mTOR protein) and inhibitory activity on mTOR protein.

Subclass Effects on Self-Association and Viscosity of Monoclonal Antibodies at High Concentrations

The effects of a subclass of monoclonal antibodies (mAbs) on protein-protein interactions, formation of reversible oligomers (clusters), and viscosity (η) are not well understood at high concentrations. Herein, we quantify a short-range anisotropic attraction between the complementarity-determining region (CDR) and CH3 domains (K_CDR-CH3) for vedolizumab IgG1, IgG2, or IgG4 subclasses by fitting small-angle X-ray scattering (SAXS) structure factor S_eff(q) data with an extensive library of 12-bead coarse-grained (CG) molecular dynamics simulations. The K_CDR-CH3 bead attraction strength was isolated from the strength of long-range electrostatic repulsion for the full mAb, which was determined from the theoretical net charge and a scaling parameter ψ to account for solvent accessibility and ion pairing. At low ionic strength (IS), the strongest short-range attraction (K_CDR-CH3) and consequently the largest clusters and highest η were observed with IgG1, the subclass with the most positively charged CH3 domain. Furthermore, the trend in K_CDR-CH3 with the subclass followed the electrostatic interaction energy between the CDR and CH3 regions calculated with the BioLuminate software using the 3D mAb structure and molecular interaction potentials. Whereas the equilibrium cluster size distributions and fractal dimensions were determined from fits of SAXS with the MD simulations, the degree of cluster rigidity under flow was estimated from the experimental η with a phenomenological model. For the systems with the largest clusters, especially IgG1, the inefficient packing of mAbs in the clusters played the largest role in increasing η, whereas for other systems, the relative contribution from stress produced by the clusters was more significant. The ability to relate η to short-range attraction from SAXS measurements at high concentrations and to theoretical characterization of electrostatic patches on the 3D surface is not only of fundamental interest but also of practical value for mAb discovery, processing, formulation, and subcutaneous delivery.

Drug Potency Prediction of SARS-CoV-2 Main Protease Inhibitors Based on a Graph Generative Model

The prediction of a ligand potency to inhibit SARS-CoV-2 main protease (M-pro) would be a highly helpful addition to a virtual screening process. The most potent compounds might then be the focus of further efforts to experimentally validate their potency and improve them. A computational method to predict drug potency, which is based on three main steps, is defined: (1) defining the drug and protein in only one 3D structure; (2) applying graph autoencoder techniques with the aim of generating a latent vector; and (3) using a classical fitting model to the latent vector to predict the potency of the drug. Experiments in a database of 160 drug-M-pro pairs, from which the pIC50 is known, show the ability of our method to predict their drug potency with high accuracy. Moreover, the time spent to compute the pIC50 of the whole database is only some seconds, using a current personal computer. Thus, it can be concluded that a computational tool that predicts, with high reliability, the pIC50 in a cheap and fast way is achieved. This tool, which can be used to prioritize which virtual screening hits, will be further examined in vitro.

Investigating Key Molecular Descriptors Affecting Particle Size: A Predictive Exemplary Approach for Self-Emulsifying System

The self-nano/microemulsifying drug delivery system is one of the well-established techniques for enhancing the solubility of poorly water-soluble drug molecules. The ratio of oil:surfactant:cosolvent plays a key role in globule size on dispersion into water, but there is very limited information on how a drug molecule affects the size. The rationale of this project was to illustrate the correlation between the particle size of nanoemulsion droplets and molecular descriptors of a drug. In the study, a self-nanoemulsifying preconcentrate containing drug with medium chain triglycerides (oil), dimethylacetamide (DMA, cosolvent), and Kolliphor EL (surfactant) was prepared for 40 drug molecules with diverse physicochemical properties. The self-nanoemulsifying preconcentrate was dispersed in water, and dynamic light scattering particle size was analyzed. A majority of drugs showed a significant increase in globule size compared to blank formulation, while few drugs showed a stark reduction in globule size. It is interesting to understand the attributes of molecules driving the self-emulsification and the diameter of nanoglobules. A systematic correlation of resultant particle size with 1D, 2D, and 3D molecular descriptors (overall more than 700 descriptors) was carried out for the data set using the PaDEL tool kit. The data compilation, curation, and analysis were performed using the SIMCA14 software. In the process of molecular descriptors screening, thereafter curation, 50 descriptors were selected using the genetic algorithm screening. The PLS-DA statistical method was employed for conversion of data into binomial systems. Final group of 5 descriptors: SpMiSpMin2_Bhe, RNCS, TDB9i, JG17, and ETA_Shape showed the correlation with particle size and classifying the drug molecules facilitating increase or decrease in particle size.

Artificial intelligence for drug discovery: Resources, methods, and applications

Conventional wet laboratory testing, validations, and synthetic procedures are costly and time-consuming for drug discovery. Advancements in artificial intelligence (AI) techniques have revolutionized their applications to drug discovery. Combined with accessible data resources, AI techniques are changing the landscape of drug discovery. In the past decades, a series of AI-based models have been developed for various steps of drug discovery. These models have been used as complements of conventional experiments and have accelerated the drug discovery process. In this review, we first introduced the widely used data resources in drug discovery, such as ChEMBL and DrugBank, followed by the molecular representation schemes that convert data into computer-readable formats. Meanwhile, we summarized the algorithms used to develop AI-based models for drug discovery. Subsequently, we discussed the applications of AI techniques in pharmaceutical analysis including predicting drug toxicity, drug bioactivity, and drug physicochemical property. Furthermore, we introduced the AI-based models for de novo drug design, drug-target structure prediction, drug-target interaction, and binding affinity prediction. Moreover, we also highlighted the advanced applications of AI in drug synergism/antagonism prediction and nanomedicine design. Finally, we discussed the challenges and future perspectives on the applications of AI to drug discovery.

Overproduce and select, or Determine Optimal Molecular Descriptor Subset via Configuration Space Optimization? Application to the Prediction of Ecotoxicological Endpoints

Predicting the likely biological activity (or property) of compounds is a fundamental and challenging task in the drug discovery process. Current computational methodologies aim to improve their predictive accuracies by using deep learning (DL) approaches. However, shallow learning-based methodologies for small- and medium-sized chemical datasets have demonstrated to be most suitable for. The latter start with a universe of molecular descriptors (MDs), then apply different feature selection algorithms, and finally construct a predictive model for the intended learning task. We demonstrate here that this approach may miss relevant information by assuming that the initial universe of MDs codifies, when it does not, all relevant aspects for the respective learning task. We argue that the limitation is mainly because of the constrained intervals of the parameters used in the algorithms that compute MDs, parameters that define the Descriptor Configuration Space (DCS). We propose to relax these constraints in an open CDS approach, so that a larger universe of MDs can initially be considered. We model the generation of MDs as a multicriteria optimization problem and tackle it with a variant of the standard genetic algorithm. As a novel component, the individual fitness function is computed by aggregating four criteria via the Choquet integral using a fuzzy (non-additive) measure. Experimental results on benchmarking chemical datasets show that the proposed approach generates a meaningful DCS by improving state-of-the-art approaches in most of the datasets.

Data-Driven Prediction of the Formation of Co-Amorphous Systems

Co-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS. While some models exist to predict the potential formation of COAMS, they often focus on a limited group of compounds. Here, four classes of combinations of an active pharmaceutical ingredient (API) with (1) another API, (2) an amino acid, (3) an organic acid, or (4) another substance were considered. A model using gradient boosting methods was developed to predict the successful formation of COAMS for all four classes. The model was tested on data not seen during training and predicted 15 out of 19 examples correctly. In addition, the model was used to screen for new COAMS in binary systems of two APIs for inhalation therapy, as diseases such as tuberculosis, asthma, and COPD usually require complex multidrug-therapy. Three of these new API-API combinations were selected for experimental testing and co-processed via milling. The experiments confirmed the predictions of the model in all three cases. This data-driven model will facilitate and expedite the screening phase for new binary COAMS.

Modeling structure-activity relationships with machine learning to identify GSK3-targeted small molecules as potential COVID-19 therapeutics

Coronaviruses induce severe upper respiratory tract infections, which can spread to the lungs. The nucleocapsid protein (N protein) plays an important role in genome replication, transcription, and virion assembly in SARS-CoV-2, the virus causing COVID-19, and in other coronaviruses. Glycogen synthase kinase 3 (GSK3) activation phosphorylates the viral N protein. To combat COVID-19 and future coronavirus outbreaks, interference with the dependence of N protein on GSK3 may be a viable strategy. Toward this end, this study aimed to construct robust machine learning models to identify GSK3 inhibitors from Food and Drug Administration-approved and investigational drug libraries using the quantitative structure-activity relationship approach. A non-redundant dataset consisting of 495 and 3070 compounds for GSK3α and GSK3β, respectively, was acquired from the ChEMBL database. Twelve sets of molecular descriptors were used to define these inhibitors, and machine learning algorithms were selected using the LazyPredict package. Histogram-based gradient boosting and light gradient boosting machine algorithms were used to develop predictive models that were evaluated based on the root mean square error and R-squared value. Finally, the top two drugs (selinexor and ruboxistaurin) were selected for molecular dynamics simulation based on the highest predicted activity (negative log of the half-maximal inhibitory concentration, pIC₅₀ value) to further investigate the structural stability of the protein-ligand complexes. This artificial intelligence-based virtual high-throughput screening approach is an effective strategy for accelerating drug discovery and finding novel pharmacological targets while reducing the cost and time.

Antiproliferative Activity Predictor: A New Reliable In Silico Tool for Drug Response Prediction against NCI60 Panel

In vitro antiproliferative assays still represent one of the most important tools in the anticancer drug discovery field, especially to gain insights into the mechanisms of action of anticancer small molecules. The NCI-DTP (National Cancer Institute Developmental Therapeutics Program) undoubtedly represents the most famous project aimed at rapidly testing thousands of compounds against multiple tumor cell lines (NCI60). The large amount of biological data stored in the National Cancer Institute (NCI) database and many other databases has led researchers in the fields of computational biology and medicinal chemistry to develop tools to predict the anticancer properties of new agents in advance. In this work, based on the available antiproliferative data collected by the NCI and the manipulation of molecular descriptors, we propose the new in silico Antiproliferative Activity Predictor (AAP) tool to calculate the GI₅₀ values of input structures against the NCI60 panel. This ligand-based protocol, validated by both internal and external sets of structures, has proven to be highly reliable and robust. The obtained GI₅₀ values of a test set of 99 structures present an error of less than ±1 unit. The AAP is more powerful for GI₅₀ calculation in the range of 4-6, showing that the results strictly correlate with the experimental data. The encouraging results were further supported by the examination of an in-house database of curcumin analogues that have already been studied as antiproliferative agents. The AAP tool identified several potentially active compounds, and a subsequent evaluation of a set of molecules selected by the NCI for the one-dose/five-dose antiproliferative assays confirmed the great potential of our protocol for the development of new anticancer small molecules. The integration of the AAP tool in the free web service DRUDIT provides an interesting device for the discovery and/or optimization of anticancer drugs to the medicinal chemistry community. The training set will be updated with new NCI-tested compounds to cover more chemical spaces, activities, and cell lines. Currently, the same protocol is being developed for predicting the TGI (total growth inhibition) and LC₅₀ (median lethal concentration) parameters to estimate toxicity profiles of small molecules.

HATS5m as an Example of GETAWAY Molecular Descriptor in Assessing the Similarity/Diversity of the Structural Features of 4-Thiazolidinone

Among the various methods for drug design, the approach using molecular descriptors for quantitative structure–activity relationships (QSAR) bears promise for the prediction of innovative molecular structures with bespoke pharmacological activity. Despite the growing number of successful potential applications, the QSAR models often remain hard to interpret. The difficulty arises from the use of advanced chemometric or machine learning methods on the one hand, and the complexity of molecular descriptors on the other hand. Thus, there is a need to interpret molecular descriptors for identifying the features of molecules crucial for desirable activity. For example, the development of structure–activity modeling of different molecule endpoints confirmed the usefulness of H-GETAWAY (H-GEometry, Topology, and Atom-Weights AssemblY) descriptors in molecular sciences. However, compared with other 3D molecular descriptors, H-GETAWAY interpretation is much more complicated. The present study provides insights into the interpretation of the HATS5m descriptor (H-GETAWAY) concerning the molecular structures of the 4-thiazolidinone derivatives with antitrypanosomal activity. According to the published study, an increase in antitrypanosomal activity is associated with both a decrease and an increase in HATS5m (leverage-weighted autocorrelation with lag 5, weighted by atomic masses) values. The substructure-based method explored how the changes in molecular features affect the HATS5m value. Based on this approach, we proposed substituents that translate into low and high HATS5m. The detailed interpretation of H-GETAWAY descriptors requires the consideration of three elements: weighting scheme, leverages, and the Dirac delta function. Particular attention should be paid to the impact of chemical compounds’ size and shape and the leverage values of individual atoms.

Statistical Methods in the Study of Protein Binding and Its Relationship to Drug Bioavailability in Breast Milk

Protein binding (PB) is indicated as the factor most severely limiting distribution in the organism, reducing the bioavailability of the drug, but also minimizing the penetration of xenobiotics into the fetus or the body of a breastfed child. Therefore, PB is an important aspect to be analyzed and monitored in the design of new drug substances. In this paper, several statistical analyses have been introduced to find the relationship between protein binding and the amount of drug in breast milk and to select molecular descriptors responsible for both pharmacokinetic phenomena. Along with descriptors related to the physicochemical properties of drugs, chromatographic descriptors from TLC and HPLC experiments were also used. Both methods used modification of the stationary phase, using bovine serum albumin (BSA) in TLC and human serum albumin (HSA) in HPLC. The use of the chromatographic data in the protein binding study was found to be positive -the most effective application of normal-phase TLC and HPLC_HSA data was found. Statistical analyses also confirmed the prognostic value of affinity chromatography data and protein binding itself as the most important parameters in predicting drug excretion into breast milk.

Combined machine learning and pharmacophore based virtual screening approaches to screen for antibiofilm inhibitors targeting LasR of Pseudomonas aeruginosa

Pseudomonas aeruginosa, a virulent pathogen affects patients with cystic fibrosis and nosocomial infections. Quorum sensing (QS) mechanism plays a crucial role in causing these ailments by mediating biofilm formation and expressing virulent genes. A novel approach to circumvent this bacterial infection is by hindering its QS network. Targeting LasR of las system serves beneficial as it holds the top position in QS system cascade. Here, we have integrated machine learning, pharmacophore based virtual screening, molecular docking and simulation studies to look for new leads as inhibitors for LasR. Support vector machine (SVM) learning algorithm was used to generate QSAR models from 66 antagonist dataset. The top three models resulted in correlation coefficient (R²) values of 0.67, 0.86, and 0.91, respectively. The correlation coefficient (R²_test) values on external test set were found to be 0.62, 0.57, and 0.55, respectively. A four-point pharmacophore model was developed. The pharmacophore hypothesis AAAD_1 was used to screen for potential leads against MolPort database in ZincPharmer. The leads which showed predicted pIC50 value of >8.00 by SVM models were subjected to docking analysis that reranked the compounds based on docking scores. Four top leads namely ZINC3851967 N-[3,5-bis(trifluoromethyl)phenyl]-5-tert-butyl-6-chloropyrazine-2-carboxamide, ZINC4024175 4-Amino-1-[(2R,3S,4S,5S)-3,4-dihydroxy-5-(hydroxymethyl)oxolan-2-yl]-2-oxopyrimidine-5-carbonitrile, ZINC2125703 N-[(5-Methoxy-4,7-dimethyl-2-oxo-2H-chromen-3-yl)acetyl]-beta-alanine, and ZINC3851966 N-[3,5-Bis(trifluoromethyl)phenyl]5-tert-butylpyrazine-2-carboxamide were selected. These compounds were checked for its stability by performing a molecular dynamics simulation for a period of 100 ns. The ADME properties of the leads were also determined. Hence, the compounds identified in this study can be used as possible leads for developing a novel inhibitor for LasR.Communicated by Ramaswamy H. Sarma.

Molecular Descriptors as a Facile Tool toward Designing Surface-Functionalized Nanoparticles for Drug Delivery

Modulating the surface chemistry of nanoparticles, often by grafting hydrophilic polymer brushes (e.g., polyethylene glycol) to prepare nanoformulations that can resist opsonization in a hematic environment and negotiate with the mucus barrier, is a popular strategy toward developing biocompatible and effective nano-drug delivery systems. However, there is a need for tools that can screen multiple surface ligands and cluster them based on both structural similarity and physicochemical attributes. Molecular descriptors offer numerical readouts based on molecular properties and provide a fertile ground for developing quick screening platforms. Thus, a study was conducted with 14 monomers/repeating blocks of polymeric chains, namely, oxazoline, acrylamide, vinylpyrrolidone, glycerol, acryloyl morpholine, dimethyl acrylamide, hydroxypropyl methacrylamide, hydroxyethyl methacrylamide, sialic acid, carboxybetaine acrylamide, carboxybetaine methacrylate, sulfobetaine methacrylate, methacryloyloxyethyl phosphorylcholine, and vinyl-pyridinio propanesulfonate, capable of imparting hydrophilicity to a surface when assembled as polymeric brushes. Employing free, Web-based, and user-friendly platforms, such as SwissADME and ChemMine tools, a series of molecular descriptors and Tanimoto coefficient of molecular pairs were determined, followed by hierarchical clustering analyses. Molecular pairs of oxazoline/dimethyl acrylamide, hydroxypropyl methacrylamide/hydroxyethyl methacrylamide, acrylamide/glycerol, carboxybetaine acrylamide/vinyl-pyridinio propanesulfonate, and sulfobetaine methacrylate/methacryloyloxyethyl phosphorylcholine were clustered together. Similarly, the molecular pair of hydroxypropyl methacrylamide/hydroxyethyl methacrylamide demonstrated a high Tanimoto coefficient of >0.9, whereas the pairs oxazoline/vinylpyrrolidone, acrylamide/dimethyl acrylamide, acryloyl morpholine/dimethyl acrylamide, acryloyl morpholine/hydroxypropyl methacrylamide, acryloyl morpholine/hydroxyethyl methacrylamide, carboxybetaine methacrylate/sulfobetaine methacrylate, and glycerol/hydroxypropyl methacrylamide had a Tanimoto coefficient of >0.8. The analyzed data not only demonstrated the ability of such in silico tools as a facile technique in clustering molecules of interest based on their structure and physicochemical characteristics but also provided vital information on their behavior within biological systems, including the ability to engage an array of possible molecular targets when the monomers are self-assembled on nanoparticulate surfaces.

Potential Effects of Romanian Propolis Extracts against Pathogen Strains

The impact of globalization on beekeeping brings new economic, scientific, ecological and social dimensions to this field The present study aimed to evaluate the chemical compositions of eight propolis extracts from Romania, and their antioxidant action and antimicrobial activity against seven species of bacteria, including pathogenic ones: Staphylococcus aureus, Bacillus cereus, Bacillus subtilis, Pseudomonas aeruginosa, Escherichia coli, Listeria monocytogenes and Salmonella enterica serovar Typhimurium. The phenolic compounds, flavonoids and antioxidant activity of propolis extracts were quantified; the presence of flavones and aromatic acids was determined. Quercetin and rutin were identified by HPLC analysis and characterized using molecular descriptors. All propolis samples exhibited antibacterial effects, especially against P. aeruginosa and L. monocytogenes. A two-way analysis of variance was used to evaluate correlations among the diameters of the inhibition zones, the bacteria used and propolis extracts used. Statistical analysis demonstrated that the diameter of the inhibition zone was influenced by the strain type, but no association between the propolis origin and the microbial activity was found.

Bioactive Marine Xanthones: A Review

The marine environment is an important source of specialized metabolites with valuable biological activities. Xanthones are a relevant chemical class of specialized metabolites found in this environment due to their structural variety and their biological activities. In this work, a comprehensive literature review of marine xanthones reported up to now was performed. A large number of bioactive xanthone derivatives (169) were identified, and their structures, biological activities, and natural sources were described. To characterize the chemical space occupied by marine-derived xanthones, molecular descriptors were calculated. For the analysis of the molecular descriptors, the xanthone derivatives were grouped into five structural categories (simple, prenylated, O-heterocyclic, complex, and hydroxanthones) and six biological activities (antitumor, antibacterial, antidiabetic, antifungal, antiviral, and miscellaneous). Moreover, the natural product-likeness and the drug-likeness of marine xanthones were also assessed. Marine xanthone derivatives are rewarding bioactive compounds and constitute a promising starting point for the design of other novel bioactive molecules.

Interpreting the Physicochemical Meaning of a Molecular Descriptor Which Is Predictive of Amorphous Solid Dispersion Formation in Polyvinylpyrrolidone Vinyl Acetate

A molecular descriptor known as R3m (the R-GETAWAY third-order autocorrelation index weighted by the atomic mass) was previously identified as capable of grouping members of an 18-compound library of organic molecules that successfully formed amorphous solid dispersions (ASDs) when co-solidified with the co-polymer polyvinylpyrrolidone vinyl acetate (PVPva) at two concentrations using two preparation methods. To clarify the physical meaning of this descriptor, the R3m calculation is examined in the context of the physicochemical mechanisms of dispersion formation. The R3m equation explicitly captures information about molecular topology, atomic leverage, and molecular geometry, features which might be expected to affect the formation of stabilizing non-covalent interactions with a carrier polymer, as well as the molecular mobility of the active pharmaceutical ingredient (API) molecule. Molecules with larger R3m values tend to have more atoms, especially the heavier ones that form stronger non-covalent interactions, generally, more irregular shapes, and more complicated topology. Accordingly, these molecules are more likely to remain dispersed within PVPva. Furthermore, multiple linear regression modeling of R3m and more interpretable descriptors supported these conclusions. Finally, the utility of the R3m descriptor for predicting the formation of ASDs in PVPva was tested by analyzing the commercially available products that contain amorphous APIs dispersed in the same polymer. All of these analyses support the conclusion that the information about the API geometry, size, shape, and topological connectivity captured by R3m relates to the ability of a molecule to interact with and remain dispersed within an amorphous PVPva matrix.

Combining machine learning and quantum mechanics yields more chemically aware molecular descriptors for medicinal chemistry applications

Molecular interaction fields (MIFs), describing molecules in terms of their ability to interact with any chemical entity, are one of the most established and versatile concepts in drug discovery. Improvement of this molecular description is highly desirable for in silico drug discovery and medicinal chemistry applications. In this work, we revised a well‐established molecular mechanics' force field and applied a hybrid quantum mechanics and machine learning approach to parametrize the hydrogen‐bonding (HB) potentials of small molecules, improving this aspect of the molecular description. Approximately 66,000 molecules were chosen from available drug databases and subjected to density functional theory calculations (DFT). For each atom, the molecular electrostatic potential (EP) was extracted and used to derive new HB energy contributions; this was subsequently combined with a fingerprint‐based description of the structural environment via partial least squares modeling, enabling the new potentials to be used for molecules outside of the training set. We demonstrate that parameter prediction for molecules outside of the training set correlates with their DFT‐derived EP, and that there is correlation of the new potentials with hydrogen‐bond acidity and basicity scales. We show the newly derived MIFs vary in strength for various ring substitution in accordance with chemical intuition. Finally, we report that this derived parameter, when extended to non‐HB atoms, can also be used to estimate sites of reaction.

Machine Learning Assisted Approach for Finding Novel High Activity Agonists of Human Ectopic Olfactory Receptors

Olfactory receptors (ORs) constitute the largest superfamily of G protein-coupled receptors (GPCRs). ORs are involved in sensing odorants as well as in other ectopic roles in non-nasal tissues. Matching of an enormous number of the olfactory stimulation repertoire to its counterpart OR through machine learning (ML) will enable understanding of olfactory system, receptor characterization, and exploitation of their therapeutic potential. In the current study, we have selected two broadly tuned ectopic human OR proteins, OR1A1 and OR2W1, for expanding their known chemical space by using molecular descriptors. We present a scheme for selecting the optimal features required to train an ML-based model, based on which we selected the random forest (RF) as the best performer. High activity agonist prediction involved screening five databases comprising ~23 M compounds, using the trained RF classifier. To evaluate the effectiveness of the machine learning based virtual screening and check receptor binding site compatibility, we used docking of the top target ligands to carefully develop receptor model structures. Finally, experimental validation of selected compounds with significant docking scores through in vitro assays revealed two high activity novel agonists for OR1A1 and one for OR2W1.

Water Activity Prediction in Sugar and Polyol Systems Using Theoretical Molecular Descriptors

Water activity is a key factor in the development of pharmaceutical, cosmetic, and food products. In aqueous solutions of nonelectrolytes, the Norrish model provides a simple and effective way to evaluate this quantity. However, it contains a parameter, known as the Norrish constant, that must be estimated from experimental data. In this study, a new strategy is proposed for the prediction of water activity in the absence of experimental information, based on the use of theoretical molecular descriptors for characterizing the effects of a solute. This approach was applied to the evaluation of water activity in the presence of sugars (glucose, fructose, xylose, sucrose) and polyols (sorbitol, xylitol, glycerol, erythritol). The use of two descriptors related to the constitutional and connectivity properties of the solutes was first investigated. Subsequently, a new theoretical descriptor, named the global information index (G), was developed. By using this index, the water activity curves in the binary systems were reconstructed. The positive results obtained support the proposed strategy, as well as the possibility of including, in a single information index, the main molecular features of a solute that determine its effects on water activity.

Chemoinformatics Analyses of Tau Ligands Reveal Key Molecular Requirements for the Identification of Potential Drug Candidates against Tauopathies

Tau is a highly soluble protein mainly localized at a cytoplasmic level in the neuronal cells, which plays a crucial role in the regulation of microtubule dynamic stability. Recent studies have demonstrated that several factors, such as hyperphosphorylation or alterations of Tau metabolism, may contribute to the pathological accumulation of protein aggregates, which can result in neuronal death and the onset of a number of neurological disorders called Tauopathies. At present, there are no available therapeutic remedies able to reduce Tau aggregation, nor are there any structural clues or guidelines for the rational identification of compounds preventing the accumulation of protein aggregates. To help identify the structural properties required for anti-Tau aggregation activity, we performed extensive chemoinformatics analyses on a dataset of Tau ligands reported in ChEMBL. The performed analyses allowed us to identify a set of molecular properties that are in common between known active ligands. Moreover, extensive analyses of the fragment composition of reported ligands led to the identification of chemical moieties and fragment combinations prevalent in the more active compounds. Interestingly, many of these fragments were arranged in recurring frameworks, some of which were clearly present in compounds currently under clinical investigation. This work represents the first in-depth chemoinformatics study of the molecular properties, constituting fragments and similarity profiles, of known Tau aggregation inhibitors. The datasets of compounds employed for the analyses, the identified molecular fragments and their combinations are made publicly available as supplementary material.

Prediction of Drug-Induced Liver Toxicity Using SVM and Optimal Descriptor Sets

Drug-induced liver toxicity is one of the significant safety challenges for the patient's health and the pharmaceutical industry. It causes termination of drug candidates in clinical trials and also the retractions of approved drugs from the market. Thus, it is essential to identify hepatotoxic compounds in the initial stages of drug development process. The purpose of this study is to construct quantitative structure activity relationship models using machine learning algorithms and systematical feature selection methods for molecular descriptor sets. The models were built from a large and diverse set of 1253 drug compounds and were validated internally with 10-fold cross-validation. In this study, we applied a variety of feature selection techniques to extract the optimal subset of descriptors as modeling features to improve the prediction performance. Experimental results suggested that the support vector machine-based classifier had achieved a better classification accuracy with reduced molecular descriptors. The final optimal model provides an accuracy of 0.811, a sensitivity of 0.840, a specificity of 0.783 and Mathew's correlation coefficient of 0.623 with an internal validation set. Furthermore, this model outperformed the prior studies while evaluated in both the internal and external test sets. The utilization of distinct optimal molecular descriptors as modeling features produce an in silico model with a superior performance.

Structure-Activity Relationships of the Imidazolium Compounds as Antibacterials of Staphylococcus aureus and Pseudomonas aeruginosa

This paper presents the results of structure-activity relationship (SAR) studies of 140 3,3'-(α,ω-dioxaalkan)bis(1-alkylimidazolium) chlorides. In the SAR analysis, the dominance-based rough set approach (DRSA) was used. For analyzed compounds, minimum inhibitory concentration (MIC) against strains of Staphylococcus aureus and Pseudomonas aeruginosa was determined. In order to perform the SAR analysis, a tabular information system was formed, in which tested compounds were described by means of condition attributes, characterizing the structure (substructure parameters and molecular descriptors) and their surface properties, and a decision attribute, classifying compounds with respect to values of MIC. DRSA allows to induce decision rules from data describing the compounds in terms of condition and decision attributes, and to rank condition attributes with respect to relevance using a Bayesian confirmation measure. Decision rules present the most important relationships between structure and surface properties of the compounds on one hand, and their antibacterial activity on the other hand. They also indicate directions of synthesizing more efficient antibacterial compounds. Moreover, the analysis showed differences in the application of various parameters for Gram-positive and Gram-negative strains, respectively.

ADMET Profiling in Drug Discovery and Development: Perspectives of in silico, in vitro and integrated approaches

In the drug discovery setting, undesirable ADMET properties of a pharmacophore with good predictive power obtained after a tedious drug discovery and development process may lead to late-stage attrition. The early-stage ADMET profiling has introduced a new dimension to leading development. Although several high-throughput in vitro models are available for ADMET profiling, however, the in silico methods are gaining more importance because of their economic and faster prediction ability without the requirements of tedious and expensive laboratory resources. Nonetheless, in silico ADMET tools alone are not accurate and, therefore, ideally adopted along with in vitro and or in vivo methods in order to enhance predictability power. This review summarizes the significance and challenges associated with the application of in silico tools as well as the possible scope of in vitro models for integration to improve the ADMET predictability power of these tools.

Off-Target-Based Design of Selective HIV-1 PROTEASE Inhibitors

The approval of the first HIV-1 protease inhibitors (HIV-1 PRIs) marked a fundamental step in the control of AIDS, and this class of agents still represents the mainstay therapy for this illness. Despite the undisputed benefits, the necessary lifelong treatment led to numerous severe side-effects (metabolic syndrome, hepatotoxicity, diabetes, etc.). The HIV-1 PRIs are capable of interacting with "secondary" targets (off-targets) characterized by different biological activities from that of HIV-1 protease. In this scenario, the in-silico techniques undoubtedly contributed to the design of new small molecules with well-fitting selectivity against the main target, analyzing possible undesirable interactions that are already in the early stages of the research process. The present work is focused on a new mixed-hierarchical, ligand-structure-based protocol, which is centered on an on/off-target approach, to identify the new selective inhibitors of HIV-1 PR. The use of the well-established, ligand-based tools available in the DRUDIT web platform, in combination with a conventional, structure-based molecular docking process, permitted to fast screen a large database of active molecules and to select a set of structure with optimal on/off-target profiles. Therefore, the method exposed herein, could represent a reliable help in the research of new selective targeted small molecules, permitting to design new agents without undesirable interactions.

Novel Pyran-Linked Phthalazinone-Pyrazole Hybrids: Synthesis, Cytotoxicity Evaluation, Molecular Modeling, and Descriptor Studies

A series of novel pyran-linked phthalazinone-pyrazole hybrids were designed and synthesized by a facile one-pot three-component reaction employing substituted phthalazinone, 1H-pyrazole-5-carbaldehyde, and active methylene compounds. Optimization studies led to the identification of L-proline and ethanol as efficient catalyst and solvent, respectively. This was followed by evaluation of anticancer activity against solid tumor cell lines of lung and cervical carcinoma that displayed IC₅₀ values in the range of 9.8–41.6 µM. Molecular modeling studies were performed, and crucial interactions with the target protein were identified. The drug likeliness nature of the compounds and molecular descriptors such as molecular flexibility, complexity, and shape index were also calculated to understand the potential of the synthesized molecules to act as lead-like molecule upon further detailed biological investigations as well as 3D-QSAR studies.

Distance based and bond additive topological indices of certain repurposed antiviral drug compounds tested for treating COVID-19

The entire world is struggling to control the spread of coronavirus (COVID-19) as there are no proper drugs for treating the disease. Under clinical trials, some of the repurposed antiviral drugs have been applied to COVID-19 patients and reported the efficacy of the drugs with the diverse inferences. Molecular topology has been developed in recent years as an influential approach for drug design and discovery in which molecules that are structurally related show similar pharmacological properties. It permits a purely mathematical description of the molecular structure so that in the development of identification of new drugs can be found through adequate topological indices. In this paper, we study the structural properties of the several antiviral drugs such as chloroquine, hydroxychloroquine, lopinavir, ritonavir, remdesivir, theaflavin, nafamostat, camostat, umifenovir and bevacizumab by considering the distance and bond measures of chemical compounds. Our quantitative values of the topological indices are extremely useful in the recent development of designing new drugs for COVID-19.

QSAR models for insecticidal properties of plant essential oils on the housefly (Musca domestica L.)

The fumigant and topical activities exhibited by 27 plant-derived essentials oils (EOs) on adult M. domestica housefly are predicted through the Quantitative Structure-Activity Relationship (QSAR) theory. These molecular structure based calculations are performed on 253 structurally diverse compounds from the EOs, where the number of constituents in each essential oil mixture varies between 2 to 24. A large number of 86,048 non-conformational mixture descriptors are derived as linear combinations of the molecular descriptors of the EO components. Two strategies are compared for the mixture descriptor formulation, which consider or avoid the use of the chemical composition. The multivariable linear regression QSAR models of the present work are useful for fumigant and topical applications, describing predictive parallelisms for the insecticidal activity of the analysed complex mixtures.

Physicochemical and Structural Parameters Contributing to the Antibacterial Activity and Efflux Susceptibility of Small-Molecule Inhibitors of Escherichia coli

Discovering new Gram-negative antibiotics has been a challenge for decades. This has been largely attributed to a limited understanding of the molecular descriptors governing Gram-negative permeation and efflux evasion. Herein, we address the contribution of efflux using a novel approach that applies multivariate analysis, machine learning, and structure-based clustering to some 4,500 molecules (actives) from a small-molecule screen in efflux-compromised Escherichia coli We employed principal-component analysis and trained two decision tree-based machine learning models to investigate descriptors contributing to the antibacterial activity and efflux susceptibility of these actives. This approach revealed that the Gram-negative activity of hydrophobic and planar small molecules with low molecular stability is limited to efflux-compromised E. coli Furthermore, molecules with reduced branching and compactness showed increased susceptibility to efflux. Given these distinct properties that govern efflux, we developed the first efflux susceptibility machine learning model, called Susceptibility to Efflux Random Forest (SERF), as a tool to analyze the molecular descriptors of small molecules and predict those that could be susceptible to efflux pumps in silico Here, SERF demonstrated high accuracy in identifying such molecules. Furthermore, we clustered all 4,500 actives based on their core structures and identified distinct clusters highlighting side-chain moieties that cause marked changes in efflux susceptibility. In all, our work reveals a role for physicochemical and structural parameters in governing efflux, presents a machine learning tool for rapid in silico analysis of efflux susceptibility, and provides a proof of principle for the potential of exploiting side-chain modification to design novel antimicrobials evading efflux pumps.

Inhibition of organic cation transporter 3 activity by tyrosine kinase inhibitors

Organic cation transporter (OCT) 3 (SLC22A3) is a widely expressed drug transporter, handling notably metformin and platinum derivatives, as well as endogenous compounds like monoamine neurotransmitters. OCT3 has been shown to be inhibited by a few marketed tyrosine kinase inhibitors (TKIs). The present study was designed to determine whether additional TKIs may interact with OCT3. For this purpose, the effects of 25 TKIs toward OCT3 activity were analyzed using OCT3-overexpressing HEK293 cells. 13/25 TKIs, each used at 10 µM, were found to behave as moderate or strong inhibitors of OCT3 activity, that is, they decreased OCT3-mediated uptake of the fluorescent dye 4-(4-(dimethylamino)styryl)-N-methylpyridinium iodide by at least 50% or 80%, respectively. This OCT3 inhibition was correlated to some molecular descriptors of TKIs, such as the percentage of H atoms and that of cationic forms at pH = 7.4. It was concentration-dependent, notably for brigatinib, ceritinib, and crizotinib, which exhibited low half maximal inhibitory concentration (IC₅₀ ) values in the 28-106 nM range. Clinical concentrations of these three marketed TKIs, as well as those of pacritinib, were next predicted to inhibit in vivo OCT3 activity according to regulatory criteria. Cellular TKI accumulation experiments as well as trans-stimulation assays, however, demonstrated that OCT3 does not transport brigatinib, ceritinib, crizotinib, and pacritinib, thus discarding any implication of OCT3 in the pharmacokinetics of these TKIs. Taken together, these data suggest that some TKIs may act as potent inhibitors of OCT3 activity, which may have consequences in terms of drug-drug interactions and toxicity.

Computing Analysis of Degree and Connection Based Irregular Indices of Polycyclic Aromatic Hydrocarbons

INTRODUCTION

A graph is supposed to be regular if all vertices have equal degree, otherwise irregular.

MATERIALS AND METHODS

Polycyclic aromatic hydrocarbons are important combusting material and considered as class of carcinogens. These polycyclic aromatic hydrocarbons play an important role in graphitisation of medical science. A topological index is a function that assigns a numerical value to a (molecular) graph which predicts various physical, chemical, biological, thermodynamical and structural properties of (molecular) graphs. An irregular index is a topological index that measures the irregularity of atoms with respect to their bonding for the chemical compounds which are involved in the under studying graphs.

RESULTS AND DISCUSSION

In this paper, we will compute an analysis of distance based irregular indices of polycyclic aromatic hydrocarbons. A comparison among the obtained indices with the help of their numerical values and the 3D presentations is also included. The efficient and steady indices of polycyclic aromatic hydrocarbons are addressed in the form of their irregularities.

CONCLUSION

Connection based study of the molecular graphs is more suitable than the degree based irregularity indices.

Improvement of Prediction Performance With Conjoint Molecular Fingerprint in Deep Learning

The accurate predicting of physical properties and bioactivity of drug molecules in deep learning depends on how molecules are represented. Many types of molecular descriptors have been developed for quantitative structure-activity/property relationships quantitative structure-activity relationships (QSPR). However, each molecular descriptor is optimized for a specific application with encoding preference. Considering that standalone featurization methods may only cover parts of information of the chemical molecules, we proposed to build the conjoint fingerprint by combining two supplementary fingerprints. The impact of conjoint fingerprint and each standalone fingerprint on predicting performance was systematically evaluated in predicting the logarithm of the partition coefficient (logP) and binding affinity of protein-ligand by using machine learning/deep learning (ML/DL) methods, including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost), long short-term memory network (LSTM), and deep neural network (DNN). The results demonstrated that the conjoint fingerprint yielded improved predictive performance, even outperforming the consensus model using two standalone fingerprints among four out of five examined methods. Given that the conjoint fingerprint scheme shows easy extensibility and high applicability, we expect that the proposed conjoint scheme would create new opportunities for continuously improving predictive performance of deep learning by harnessing the complementarity of various types of fingerprints.

Mathematical Models Generated for the Prediction of Corrosion Inhibition Using Different Theoretical Chemistry Simulations

The use of corrosion inhibitors is an important method to retard the process of metallic attack by corrosion. The construction of mathematical models from theoretical-computational and experimental data obtained for different molecules is one of the most attractive alternatives in the analysis of corrosion prevention, whose objective is to define those molecular characteristics that are common in high-performance corrosion inhibitors. This review includes data of corrosion inhibitors evaluated in different media, the most commonly studied molecular descriptors, and some examples of mathematical models generated by different researchers.

Two- and Three-dimensional Quantitative Structure-activity Relationship Models Based on Conformer Structures

In three-dimensional (3D)-quantitative structure-activity relationship (QSAR) analysis, the chemical structure of a studied molecule is typically optimized assuming its presence in a vacuum environment. However, in practical scenarios, the environment of even the most stable molecules contains water, proteins, and other species; therefore, their actual structures significantly differ from those in vacuum and have multiple structures. Herein, both two-dimensional and 3D molecular descriptors, which accepted the existence of multiple conformers, were calculated, and a conformer-based 3D-QSAR model (C3D-QSAR) that considered the chemical structures of conformers was developed. The prediction accuracy of the C3D-QSAR method determined by analyzing the data sets obtained for the angiotensin-converting enzyme and dihydrofolate reductase inhibitors was found to be higher than those of the existing QSAR models.

An Integrative Informatics Approach to Explain the Mechanism of Action of Novel N1-(Anthraquinon-2-yl) Amidrazones as BCR/ABL Inhibitors

BACKGROUND

Drugs incorporating heterocyclic chemical skeletons possess a plethora of therapeutic activities such as anticancer, antimicrobial, antihypertensive, and antipsychiatric effects. It is becoming routine, nowadays, to use cheminformatics and bioinformatics methods to elucidate the mechanism(s) of action of such drugs.

OBJECTIVE

To probe the activity of a recently published series of N1-(anthraquinon-2-yl) amidrazone piperazine derivatives employing computational strategies[1], identify their structural basis of binding to BCR/ABL kinase domain, and explain their anticancer activities in human breast adenocarcinoma (MCF-7) and chronic myelogenous leukemia (K562) cell lines.

METHODS

We applied an in silico integrative informatics approach integrating molecular descriptors, docking studies, cheminformatics, and network analysis.

RESULTS

Our results highlighted the possible involvement of the BCR/ABL and DRD2 pathways in the anticancer activity of the studied compounds, and induced fit docking (IFD) indicated that the BCR/ABL kinase domain is a putative drug target. Additionally, high-scoring docking poses identified a unique network of hydrogen bonding with amino acids Y253, K271, E286, V299, L301, T315, M318, I360, R362, V379, and D3810.

CONCLUSION

Using an integrative informatics approach to characterize our anticancer compounds, we were able to explain the biological differences between synthesized and biologically validated amidrazone piperazine anticancer agents. We were also able to postulate a mechanism of action of this novel group of anticancer agents.

Quantitative Structure-Property Relationship study for Prediction of boiling point and enthalpy of vaporization of alkenes

INTRODUCTION

Quantitative structure- property relationships (QSPRs) models have been widely developed to derive correlation between chemical structures of molecules to their known properties. In this study, QSPR models have been carried out on 91 alkenes to develop a robust model for the prediction of enthalpy of vaporization at standard condition (∆H°vap/kJ.mol-1) and normal temperature of boiling points (T˚bp /K) of alkenes.

METHODS

A training set of 81 structurally diverse alkenes was randomly selected and used to construct QSPR models. These models were optimized using backward -multiple linear regression (MLR) analysis. The Genetic algorithm and multiple linear regression analysis (GA-MLR) were used to select the suitable descriptors derived from the Dragon software.

RESULTS

The multicollinearity properties of the descriptors contributed in the QSPR models were tested and several method were used for testing the predictive models power such as Leave-One-Out (LOO) crossvalidation(Q2 LOO), the five-fold cross-validation techniques, external validation parameters (Q2F1, Q2F2, Q2F3), the concordance correlation coefficient (CCC) and the predictive parameter R2m .

CONCLUSION

The predictive ability of the models were found to be satisfactory, and the five descriptors in three blocks namely connectivity, edge adjacency indices and 2D matrix-based descriptors could be used to predict the mentioned properties of alkenes.