Application of Random Forest and Multiple Linear Regression Techniques to QSPR Prediction of an Aqueous Solubility for Military Compounds

STOPLIGHT: A Hit Scoring Calculator

We introduce STOPLIGHT, a web portal to assist medicinal chemists in prioritizing hits from screening campaigns and the selection of compounds for optimization. STOPLIGHT incorporates services to assess 6 physiochemical and structural properties, 6 assay liabilities, and 11 pharmacokinetic properties, for any small molecule represented by its SMILES string. We briefly describe each service and illustrate the utility of this portal with a case study. The STOPLIGHT portal provides a user-friendly tool to guide hit selection in early drug discovery campaigns, whereby compounds with unfavorable properties can be quickly recognized and eliminated.

Chemoinformatic regression methods and their applicability domain

The growing interest in chemoinformatic model uncertainty calls for a summary of the most widely used regression techniques and how to estimate their reliability. Regression models learn a mapping from the space of explanatory variables to the space of continuous output values. Among other limitations, the predictive performance of the model is restricted by the training data used for model fitting. Identification of unusual objects by outlier detection methods can improve model performance. Additionally, proper model evaluation necessitates defining the limitations of the model, often called the applicability domain. Comparable to certain classifiers, some regression techniques come with built-in methods or augmentations to quantify their (un)certainty, while others rely on generic procedures. The theoretical background of their working principles and how to deduce specific and general definitions for their domain of applicability shall be explained.

Modeling interactions between Heparan sulfate and proteins based on the Heparan sulfate microarray analysis

Heparan sulfate (HS), a sulfated polysaccharide abundant in the extracellular matrix, plays pivotal roles in various physiological and pathological processes by interacting with proteins. Investigating the binding selectivity of HS oligosaccharides to target proteins is essential, but the exhaustive inclusion of all possible oligosaccharides in microarray experiments is impractical. To address this challenge, we present a hybrid pipeline that integrates microarray and in silico techniques to design oligosaccharides with desired protein affinity. Using fibroblast growth factor 2 (FGF2) as a model protein, we assembled an in-house dataset of HS oligosaccharides on microarrays and developed two structural representations: a standard representation with all atoms explicit and a simplified representation with disaccharide units as "quasi-atoms." Predictive Quantitative Structure-Activity Relationship (QSAR) models for FGF2 affinity were developed using the Random Forest (RF) algorithm. The resulting models, considering the applicability domain, demonstrated high predictivity, with a correct classification rate of 0.81-0.80 and improved positive predictive values (PPV) up to 0.95. Virtual screening of 40 new oligosaccharides using the simplified model identified 15 computational hits, 11 of which were experimentally validated for high FGF2 affinity. This hybrid approach marks a significant step toward the targeted design of oligosaccharides with desired protein interactions, providing a foundation for broader applications in glycobiology.

Pharmacokinetics Profiler (PhaKinPro): Model Development, Validation, and Implementation as a Web Tool for Triaging Compounds with Undesired Pharmacokinetics Profiles

Computational models that predict pharmacokinetic properties are critical to deprioritize drug candidates that emerge as hits in high-throughput screening campaigns. We collected, curated, and integrated a database of compounds tested in 12 major end points comprising over 10,000 unique molecules. We then employed these data to build and validate binary quantitative structure-activity relationship (QSAR) models. All trained models achieved a correct classification rate above 0.60 and a positive predictive value above 0.50. To illustrate their utility in drug discovery, we used these models to predict the pharmacokinetic properties for drugs in the NCATS Inxight Drugs database. In addition, we employed the developed models to predict the pharmacokinetic properties of all compounds in the DrugBank. All models described in this paper have been integrated and made publicly available via the PhaKinPro Web-portal that can be accessed at https://phakinpro.mml.unc.edu/.

A machine learning approach for thermodynamic modeling of the statically measured solubility of nilotinib hydrochloride monohydrate (anti-cancer drug) in supercritical CO2

Nilotinib hydrochloride monohydrate (NHM) is an anti-cancer drug whose solubility was statically determined in supercritical carbon dioxide (SC-CO2) for the first time at various temperatures (308-338 K) and pressures (120-270 bar). The mole fraction of the drug dissolved in SC-CO2 ranged from 0.1 × 10-5 to 0.59 × 10-5, corresponding to the solubility range of 0.016-0.094 g/L. Four sets of models were employed to evaluate the correlation of experimental data; (1) ten empirical and semi-empirical models with three to six adjustable parameters, such as Chrastil, Bartle, Sparks, Sodeifian, Mendez-Santiago and Teja (MST), Bian, Jouyban, Garlapati-Madras, Gordillo, and Jafari-Nejad; (2) Peng-Robinson equation of state (Van der Waals mixing rule, had an AARD% of 10.73); (3) expanded liquid theory (modified Wilson model, on average, the AARD of this model was 11.28%); and (4) machine learning (ML) algorithms (random forest, decision trees, multilayer perceptron, and deep neural network with respective R2 values of 0.9933, 0.9799, 0.9724 and 0.9701). All the models showed an acceptable agreement with the experimental data, among them, the Bian model exhibited excellent performance with an AARD% of 8.11. Finally, the vaporization (73.49 kJ/mol) and solvation (- 21.14 kJ/mol) enthalpies were also calculated for the first time.

Molecular dynamics study of the interactions between a hydrophilic polymer brush on graphene and amino acid side chain analogues in water

We perform all-atom molecular dynamics simulations of poly(2-hydroxyethyl methacrylate) (PHEMA) brushes in aqueous solutions of isobutane, propionamide, and sodium propionate. These solutes are side chain analogues to leucine, glutamine, and glutamic acid, respectively. We compute the Gibbs energy profile of the solute's adsorption to the polymer brush and decompose it into the contributions from the steric repulsion, van der Waals interaction, and Coulomb interaction to reveal the energetic origin of repulsion or attraction of the solute by the polymer brush. The Henry adsorption constant is the amount of adsorption normalized by the concentration in aqueous solution. We examine the dependence of this quantity on the grafting density and chain length. Our results suggest that the concurrent primary and ternary adsorption mechanism may be more important than previously expected when the solute is hydrophobic.

Decomposition of 2,4,6-trinitrotoluene (TNT) and 5-nitro-2,4-dihydro-3H-1,2,4-triazol-3-one (NTO) by Fe13O13 nanoparticle: density functional theory study

To obtain more insight into the mechanisms of the decomposition of energetic compounds, we performed a computational study of the interaction of Fe₁₃O₁₃ nanoparticles with two energetic molecules such as 2,4,6-trinitrotoluene (TNT) and 5-nitro-2,4-dihydro-3H-1,2,4-triazol-3-one (NTO). The density functional theory using M06-2X, B3LYP, and BLYP density functionals was applied. We found that the reactivity of these molecules strongly depends on the place of adsorption (so-called top and bottom planes of Fe₁₃O₁₃). Namely, only the interaction with the bottom plane results in the thermodynamic characteristics of the decomposition that provide a medium reaction rate for the studied processes. Several pathways for such decomposition were found. One of them is the inter-complex oxygen transfer of nitro-group oxygen to Fe₁₃O₁₃. This pathway results in the formation of adsorbed nitroso compounds. The second pathway describes a more complex decomposition that includes the transfer of the nitro-group oxygen accompanied by the hydrogen transfer. In all cases, the interaction of energetic molecules with Fe₁₃O₁₃ nanoparticles takes place along with a barrier-less electron transfer from Fe₁₃O₁₃ to TNT or NTO species.

Machine Learning Analysis of Essential Oils from Cuban Plants: Potential Activity against Protozoa Parasites

Essential oils (EOs) are a mixture of chemical compounds with a long history of use in food, cosmetics, perfumes, agricultural and pharmaceuticals industries. The main object of this study was to find chemical patterns between 45 EOs and antiprotozoal activity (antiplasmodial, antileishmanial and antitrypanosomal), using different machine learning algorithms. In the analyses, 45 samples of EOs were included, using unsupervised Self-Organizing Maps (SOM) and supervised Random Forest (RF) methodologies. In the generated map, the hit rate was higher than 70% and the results demonstrate that it is possible find chemical patterns using a supervised and unsupervised machine learning approach. A total of 20 compounds were identified (19 are terpenes and one sulfur-containing compound), which was compared with literature reports. These models can be used to investigate and screen for bioactivity of EOs that have antiprotozoal activity more effectively and with less time and financial cost.

Computer-Assisted Discovery of Alkaloids with Schistosomicidal Activity

Schistosomiasis is a chronic parasitic disease caused by trematodes of the genus Schistosoma; it is commonly caused by Schistosoma mansoni, which is transmitted by Bioamphalaria snails. Studies show that more than 200 million people are infected and that more than 90% of them live in Africa. Treatment with praziquantel has the best cost–benefit result on the market. However, hypersensitivity, allergy, and drug resistance are frequently presented after administration. From this perspective, ligand-based and structure-based virtual screening (VS) techniques were combined to select potentially active alkaloids against S. mansoni from an internal dataset (SistematX). A set of molecules with known activity against S. mansoni was selected from the ChEMBL database to create two different models with accuracy greater than 84%, enabling ligand-based VS of the alkaloid bank. Subsequently, structure-based VS was performed through molecular docking using four targets of the parasite. Finally, five consensus hits (i.e., five alkaloids with schistosomicidal potential), were selected. In addition, in silico evaluations of the metabolism, toxicity, and drug-like profile of these five selected alkaloids were carried out. Two of them, namely, 11,12-methylethylenedioxypropoxy and methyl-3-oxo-12-methoxy-n(1)-decarbomethoxy-14,15-didehydrochanofruticosinate, had plausible toxicity, metabolomics, and toxicity profiles. These two alkaloids could serve as starting points for the development of new schistosomicidal compounds based on natural products.

Summary of 17 chemicals evaluated by OECD TG229 using Japanese Medaka, Oryzias latipes in EXTEND 2016

In June 2016, the Ministry of the Environment of Japan announced a program "EXTEND2016" on the implementation of testing and assessment for endocrine active chemicals, consisting of a two-tiered strategy. The aim of the Tier 1 screening and the Tier 2 testing is to identify the impacts on the endocrine system and to characterize the adverse effects to aquatic animals by endocrine disrupting chemicals detected in the aquatic environment in Japan. For the consistent assessment of the effects on reproduction associated with estrogenic, anti-estrogenic, androgenic, and/or anti-androgenic activities of chemicals throughout Tier 1 screening to Tier 2 testing, a unified test species, Japanese medaka (Oryzias latipes), has been used. For Tier 1 screening, the in vivo Fish Short-Term Reproduction Assay (OECD test guideline No. 229) was conducted for 17 chemicals that were nominated based on the results of environmental monitoring, existing knowledge obtained from a literature survey, and positive results in reporter gene assays using the estrogen receptor of Japanese medaka. In the 17 assays using Japanese medaka, adverse effects on reproduction (i.e., reduction in fecundity and/or fertility) were suggested for 10 chemicals, and a significant increase of hepatic vitellogenin in males, indicating estrogenic (estrogen receptor agonistic) potency, was found for eight chemicals at the concentrations in which no overt toxicity was observed. Based on these results, and the frequency and the concentrations detected in the Japanese environment, estrone, 4-nonylphenol (branched isomers), 4-tert-octylphenol, triphenyl phosphate, and bisphenol A were considered as high priority candidate substances for the Tier 2 testing.

Simplex representation of molecular structure as universal QSAR/QSPR tool

We review the development and application of the Simplex approach for the solution of various QSAR/QSPR problems. The general concept of the simplex method and its varieties are described. The advantages of utilizing this methodology, especially for the interpretation of QSAR/QSPR models, are presented in comparison to other fragmentary methods of molecular structure representation. The utility of SiRMS is demonstrated not only in the standard QSAR/QSPR applications, but also for mixtures, polymers, materials, and other complex systems. In addition to many different types of biological activity (antiviral, antimicrobial, antitumor, psychotropic, analgesic, etc.), toxicity and bioavailability, the review examines the simulation of important properties, such as water solubility, lipophilicity, as well as luminescence, and thermodynamic properties (melting and boiling temperatures, critical parameters, etc.). This review focuses on the stereochemical description of molecules within the simplex approach and details the possibilities of universal molecular stereo-analysis and stereochemical configuration description, along with stereo-isomerization mechanism and molecular fragment "topography" identification.

Artificial intelligence in drug design: algorithms, applications, challenges and ethics

The discovery paradigm of drugs is rapidly growing due to advances in machine learning (ML) and artificial intelligence (AI). This review covers myriad faces of AI and ML in drug design. There is a plethora of AI algorithms, the most common of which are summarized in this review. In addition, AI is fraught with challenges that are highlighted along with plausible solutions to them. Examples are provided to illustrate the use of AI and ML in drug discovery and in predicting drug properties such as binding affinities and interactions, solubility, toxicology, blood–brain barrier permeability and chemical properties. The review also includes examples depicting the implementation of AI and ML in tackling intractable diseases such as COVID-19, cancer and Alzheimer’s disease. Ethical considerations and future perspectives of AI are also covered in this review.

Computer-assisted discovery of compounds with insecticidal activity against Musca domestica and Mythimna separata

Pesticides are used to control and combat insects and pests in the agricultural sector, households, and public health programs. The frequent and disorderly use of these pesticides may lead to variety of undesired effects. Therefore, natural products have many advantages over to synthetic compounds to be used as insecticides. The goal of this study was to find natural products with insecticidal potential against Musca domestica and Mythimna separata. To achieve this goal, we developed predictive QSAR models using MuDRA, PLS, and RF approaches and performed virtual screening of 117 natural products. As a result of QSAR modeling, we formulated the recommendations regarding physico-chemical characteristics for promising compounds active against Musca domestica and Mythimna separata. Homology models were successfully built for both species and molecular docking of QSAR hits vs known insecticides allowed us to prioritize twenty-two compounds against Musca domestica and six against Mythimna separata. Our results suggest that pimarane diterpenes, abietanes diterpenes, dimeric diterpenes and scopadulane diterpenes obtained from aerial parts of species of the genus Calceolaria (Calceolariaceae: Scrophulariaceae) can be considered as potential insecticidal.

QSAR without borders

Prediction of chemical bioactivity and physical properties has been one of the most important applications of statistical and more recently, machine learning and artificial intelligence methods in chemical sciences. This field of research, broadly known as quantitative structure-activity relationships (QSAR) modeling, has developed many important algorithms and has found a broad range of applications in physical organic and medicinal chemistry in the past 55+ years. This Perspective summarizes recent technological advances in QSAR modeling but it also highlights the applicability of algorithms, modeling methods, and validation practices developed in QSAR to a wide range of research areas outside of traditional QSAR boundaries including synthesis planning, nanotechnology, materials science, biomaterials, and clinical informatics. As modern research methods generate rapidly increasing amounts of data, the knowledge of robust data-driven modelling methods professed within the QSAR field can become essential for scientists working both within and outside of chemical research. We hope that this contribution highlighting the generalizable components of QSAR modeling will serve to address this challenge.

Discovery of new potent hits against intracellular Trypanosoma cruzi by QSAR-based virtual screening

Chagas disease is a neglected tropical disease (NTD) caused by the protozoan parasite Trypanosoma cruzi and is primarily transmitted to humans by the feces of infected Triatominae insects during their blood meal. The disease affects 6-8 million people, mostly in Latin America countries, and kills more people in the region each year than any other parasite-born disease, including malaria. Moreover, patient numbers are currently increasing in non-endemic, developed countries, such as Australia, Japan, Canada, and the United States. The treatment is limited to one drug, benznidazole, which is only effective in the acute phase of the disease and is very toxic. Thus, there is an urgent need to develop new, safer, and effective drugs against the chronic phase of Chagas disease. Using a QSAR-based virtual screening followed by in vitro experimental evaluation, we report herein the identification of novel potent and selective hits against T. cruzi intracellular stage. We developed and validated binary QSAR models for prediction of anti-trypanosomal activity and cytotoxicity against mammalian cells using the best practices for QSAR modeling. These models were then used for virtual screening of a commercial database, leading to the identification of 39 virtual hits. Further in vitro assays showed that seven compounds were potent against intracellular T. cruzi at submicromolar concentrations (EC₅₀ < 1 μM) and were very selective (SI > 30). Furthermore, other six compounds were also inside the hit criteria for Chagas disease, which presented activity at low micromolar concentrations (EC₅₀ < 10 μM) against intracellular T. cruzi and were also selective (SI > 15). Moreover, we performed a multi-parameter analysis for the comparison of tested compounds regarding their balance between potency, selectivity, and predicted ADMET properties. In the next studies, the most promising compounds will be submitted to additional in vitro and in vivo assays in acute model of Chagas disease, and can be further optimized for the development of new promising drug candidates against this important yet neglected disease.

Maternal-fetal transfer rates of PCBs, OCPs, PBDEs, and dioxin-like compounds predicted through quantitative structure-activity relationship modeling

The present study aims to predict the maternal-fetal transfer rates of the polychlorinated biphenyls (PCBs), organochlorine pesticides (OCPs), and polybrominated diphenyl ethers (PBDEs), and dioxin-like compounds using a quantitative structure-activity relationship model. The relation between the maternal-fetal transfer rate and the contaminants' physicochemical properties was investigated by multiple linear regression (MLR), partial least square regression (PLS), and random forest regression (RF). The 10-fold cross-validation technique estimated low predictive performances for both MLR and PLS models (R ²_CV = 0.425 ± 0.0964 for MLR and R ²_CV = 0.492 ± 0.115 for PLS) and is in agreement with an external test (R ²_pred = 0.129 for MLR and R ²_pred = 0.123 for PLS). In contrast, the RF model exhibits good predictive performance, estimated through 10-fold cross-validation (R ²_CV = 0.566 ± 0.0885) and an external test set (R ²_pred = 0.519). Molecular weight and polarity were selected in all models as important parameters that may predict the ability of a molecule to cross the placenta to the fetus.

Computer-Assisted Decision Support for Student Admissions Based on Their Predicted Academic Performance

Objective. To develop predictive computational models forecasting the academic performance of students in the didactic-rich portion of a doctor of pharmacy (PharmD) curriculum as admission-assisting tools. Methods. All PharmD candidates over three admission cycles were divided into two groups: those who completed the PharmD program with a GPA ≥ 3; and the remaining candidates. Random Forest machine learning technique was used to develop a binary classification model based on 11 pre-admission parameters. Results. Robust and externally predictive models were developed that had particularly high overall accuracy of 77% for candidates with high or low academic performance. These multivariate models were highly accurate in predicting these groups to those obtained using undergraduate GPA and composite PCAT scores only. Conclusion. The models developed in this study can be used to improve the admission process as preliminary filters and thus quickly identify candidates who are likely to be successful in the PharmD curriculum.

Novel enhanced applications of QSPR models: Temperature dependence of aqueous solubility

A model developed to predict aqueous solubility at different temperatures has been proposed based on quantitative structure-property relationships (QSPR) methodology. The prediction consists of two steps. The first one predicts the value of k parameter in the linear equation lgSw=kT+c, where Sw is the value of solubility and T is the value of temperature. The second step uses Random Forest technique to create high-efficiency QSPR model. The performance of the model is assessed using cross-validation and external test set prediction. Predictive capacity of developed model is compared with COSMO-RS approximation, which has quantum chemical and thermodynamic foundations. The comparison shows slightly better prediction ability for the QSPR model presented in this publication. © 2016 Wiley Periodicals, Inc.

Design, Virtual Screening, and Synthesis of Antagonists of αIIbβ3 as Antiplatelet Agents

This article describes design, virtual screening, synthesis, and biological tests of novel αIIbβ3 antagonists, which inhibit platelet aggregation. Two types of αIIbβ3 antagonists were developed: those binding either closed or open form of the protein. At the first step, available experimental data were used to build QSAR models and ligand- and structure-based pharmacophore models and to select the most appropriate tool for ligand-to-protein docking. Virtual screening of publicly available databases (BioinfoDB, ZINC, Enamine data sets) with developed models resulted in no hits. Therefore, small focused libraries for two types of ligands were prepared on the basis of pharmacophore models. Their screening resulted in four potential ligands for open form of αIIbβ3 and four ligands for its closed form followed by their synthesis and in vitro tests. Experimental measurements of affinity for αIIbβ3 and ability to inhibit ADP-induced platelet aggregation (IC50) showed that two designed ligands for the open form 4c and 4d (IC50 = 6.2 nM and 25 nM, respectively) and one for the closed form 12b (IC50 = 11 nM) were more potent than commercial antithrombotic Tirofiban (IC50 = 32 nM).

Amino substituted nitrogen heterocycle ureas as kinase insert domain containing receptor (KDR) inhibitors: Performance of structure–activity relationship approaches

A quantitative structure–activity relationship (QSAR) study was performed on a set of amino-substituted nitrogen heterocyclic urea derivatives. Two novel approaches were applied: (1) the simplified molecular input-line entry systems (SMILES) based optimal descriptors approach; and (2) the fragment-based simplex representation of molecular structure (SiRMS) approach. Comparison with the classic scheme of building up the model and balance of correlation (BC) for optimal descriptors approach shows that the BC scheme provides more robust predictions than the classic scheme for the considered pIC₅₀ of the heterocyclic urea derivatives. Comparison of the SMILES-based optimal descriptors and SiRMS approaches has confirmed good performance of both techniques in prediction of kinase insert domain containing receptor (KDR) inhibitory activity, expressed as a logarithm of inhibitory concentration (pIC50) of studied compounds.

A metabonomics investigation of multiple sclerosis by nuclear magnetic resonance

Multiple sclerosis (MS) is a nervous system disease that affects the fatty myelin sheaths around the axons of the brain and spinal cord, leading to demyelination and a broad range of signs and symptoms. MS can be difficult to diagnose because its signs and symptoms may be similar to other medical problems. To find out which metabolites in serum are effective for the diagnosis of MS, we utilized metabolic profiling using proton nuclear magnetic resonance spectroscopy ((1)H-NMR). Random forest (RF) was used to classify the MS patients and healthy subjects. Atomic absorption spectroscopy was used to measure the serum levels of selenium. The results showed that the levels of selenium were lower in the MS group, when compared with the control group. RF was used to identify the metabolites that caused selenium changes in people with MS by building a correlation model between these metabolites and serum levels of selenium. For the external test set, the obtained classification model showed a 93% correct classification of MS and healthy subjects. The regression model of levels of selenium and metabolites showed the correlation (R(2)) value of 0.88 for the external test set. The results indicate the suitability of NMR as a screen for identifying MS patients and healthy subjects. A novel model with good prediction outcomes was constructed between serum levels of selenium and NMR data.