Exploring the Chemical Space of CYP17A1 Inhibitors Using Cheminformatics and Machine Learning.

Cytochrome P450 17A1 (CYP17A1) is one of the key enzymes in steroidogenesis that produces dehydroepiandrosterone (DHEA) from cholesterol. Abnormal DHEA production may lead to the progression of severe diseases, such as prostatic and breast cancers. Thus, CYP17A1 is a druggable target for anti-cancer molecule development. In this study, cheminformatic analyses and quantitative structure-activity relationship (QSAR) modeling were applied on a set of 962 CYP17A1 inhibitors (i.e., consisting of 279 steroidal and 683 nonsteroidal inhibitors) compiled from the ChEMBL database. For steroidal inhibitors, a QSAR classification model built using the PubChem fingerprint along with the extra trees algorithm achieved the best performance, reflected by the accuracy values of 0.933, 0.818, and 0.833 for the training, cross-validation, and test sets, respectively. For nonsteroidal inhibitors, a systematic cheminformatic analysis was applied for exploring the chemical space, Murcko scaffolds, and structure-activity relationships (SARs) for visualizing distributions, patterns, and representative scaffolds for drug discoveries. Furthermore, seven total QSAR classification models were established based on the nonsteroidal scaffolds, and two activity cliff (AC) generators were identified. The best performing model out of these seven was model VIII, which is built upon the PubChem fingerprint along with the random forest algorithm. It achieved a robust accuracy across the training set, the cross-validation set, and the test set, i.e., 0.96, 0.92, and 0.913, respectively. It is anticipated that the results presented herein would be instrumental for further CYP17A1 inhibitor drug discovery efforts.

Correction: Shoombuatong, W., et al. iQSP: A Sequence-Based Tool for the Prediction and Analysis of Quorum Sensing Peptides via Chou's 5-Steps Rule and Informative Physicochemical Properties. Int. J. Mol. Sci. 2020, 21, 75.

The authors wish to make the following corrections to this paper: [...].

iQSP: A Sequence-Based Tool for the Prediction and Analysis of Quorum Sensing Peptides via Chou's 5-Steps Rule and Informative Physicochemical Properties.

Understanding of quorum-sensing peptides (QSPs) in their functional mechanism plays an essential role in finding new opportunities to combat bacterial infections by designing drugs. With the avalanche of the newly available peptide sequences in the post-genomic age, it is highly desirable to develop a computational model for efficient, rapid and high-throughput QSP identification purely based on the peptide sequence information alone. Although, few methods have been developed for predicting QSPs, their prediction accuracy and interpretability still requires further improvements. Thus, in this work, we proposed an accurate sequence-based predictor (called iQSP) and a set of interpretable rules (called IR-QSP) for predicting and analyzing QSPs. In iQSP, we utilized a powerful support vector machine (SVM) cooperating with 18 informative features from physicochemical properties (PCPs). Rigorous independent validation test showed that iQSP achieved maximum accuracy and MCC of 93.00% and 0.86, respectively. Furthermore, a set of interpretable rules IR-QSP was extracted by using random forest model and the 18 informative PCPs. Finally, for the convenience of experimental scientists, the iQSP web server was established and made freely available online. It is anticipated that iQSP will become a useful tool or at least as a complementary existing method for predicting and analyzing QSPs.

Machine Learning Approaches to Investigate the Structure-Activity Relationship of Angiotensin-Converting Enzyme Inhibitors.

Angiotensin-converting enzyme inhibitors (ACEIs) play a crucial role in treating conditions such as hypertension, heart failure, and kidney diseases. Nevertheless, the ACEIs currently available on the market are linked to a variety of adverse effects including renal insufficiency, which restricts their usage. There is thus an urgent need to optimize the currently available ACEIs. This study represents a structure-activity relationship investigation of ACEIs, employing machine learning to analyze data sets sourced from the ChEMBL database. Exploratory data analysis was performed to visualize the physicochemical properties of compounds by investigating the distributions, patterns, and statistical significance among the different bioactivity groups. Further scaffold analysis has identified 9 representative Murcko scaffolds with frequencies ≥10. Scaffold diversity has revealed that active ACEIs had more scaffold diversity than their intermediate and inactive counterparts, thereby indicating the significance of performing lead optimization on scaffolds of active ACEIs. Scaffolds 1, 3, 6, and 8 are unfavorable in comparison with scaffolds 2, 3, 5, 7, and 9. QSAR investigation of compiled data sets consisting of 549 compounds led to the selection of Mordred descriptor and Random Forest algorithm as the best model, which afforded robust model performance (accuracy: 0.981, 0.77, and 0.745; MCC: 0.972, 0.658, and 0.617 for the training set, 10-fold cross-validation set, and testing set, respectively). To enhance the model's robustness and predictability, we reduced the chemical diversity of the input compounds by using the 9 most prevalent Murcko scaffold-matched compounds (comprising a total of 168) followed by a subsequent QSAR model investigation using Mordred descriptor and extremely gradient boost algorithm (accuracy: 0.973, 0.849, and 0.823; MCC: 0.959, 0.786, and 0.742 for the training set, 10-fold cross-validation set, and testing set, respectively). Further illustration of the structure-activity relationship using SALI plots has enabled the identification of clusters of compounds that create activity cliffs. These findings, as presented in this study, contribute to the advancement of drug discovery and the optimization of ACEIs.

Machine learning approaches to study the structure-activity relationships of LpxC inhibitors.

Antimicrobial resistance (AMR) has emerged as one of the global threats to human health in the 21st century. Drug discovery of inhibitors against novel targets rather than conventional bacterial targets has been considered an inevitable strategy for the growing threat of AMR infections. In this study, we applied quantitative structure-activity relationship (QSAR) modeling to the LpxC inhibitors to predict the inhibitory activity. In addition, we performed various cheminformatics analysis consisting of the exploration of the chemical space, identification of chemotypes, performing structure-activity landscape and activity cliffs as well as construction of the Structure-Activity Similarity (SAS) map. We built a total of 24 QSAR classification models using PubChem and MACCS fingerprint with 12 various machine learning algorithms. The best model with PubChem fingerprint is the Extremely Gradient Boost model (accuracy on the training set: 0.937; accuracy on the 10-fold cross-validation set: 0.795; accuracy on the test set: 0.799). Furthermore, it was found that the best model using the MACCS fingerprint was the Random Forest model (accuracy on the training set: 0.955; accuracy on the 10-fold cross-validation set: 0.803; accuracy on the test set: 0.785). In addition, we have identified eight consensus activity cliff generators that are highly informative for further SAR investigations. It is hoped that findings presented herein can provide guidance for further lead optimization of LpxC inhibitors.

Cheminformatic Analysis and Machine Learning Modeling to Investigate Androgen Receptor Antagonists to Combat Prostate Cancer.

Prostate cancer (PCa) is a major leading cause of mortality of cancer among males. There have been numerous studies to develop antagonists against androgen receptor (AR), a crucial therapeutic target for PCa. This study is a systematic cheminformatic analysis and machine learning modeling to study the chemical space, scaffolds, structure-activity relationship, and landscape of human AR antagonists. There are 1678 molecules as final data sets. Chemical space visualization by physicochemical property visualization has demonstrated that molecules from the potent/active class generally have a mildly smaller molecular weight (MW), octanol-water partition coefficient (log P), number of hydrogen-bond acceptors (nHA), number of rotatable bonds (nRot), and topological polar surface area (TPSA) than molecules from intermediate/inactive class. The chemical space visualization in the principal component analysis (PCA) plot shows significant overlapping distributions between potent/active class molecules and intermediate/inactive class molecules; potent/active class molecules are intensively distributed, while intermediate/inactive class molecules are widely and sparsely distributed. Murcko scaffold analysis has shown low scaffold diversity in general, and scaffold diversity of potent/active class molecules is even lower than intermediate/inactive class molecules, indicating the necessity for developing molecules with novel scaffolds. Furthermore, scaffold visualization has identified 16 representative Murcko scaffolds. Among them, scaffolds 1, 2, 3, 4, 7, 8, 10, 11, 15, and 16 are highly favorable scaffolds due to their high scaffold enrichment factor values. Based on scaffold analysis, their local structure-activity relationships (SARs) were investigated and summarized. In addition, the global SAR landscape was explored by quantitative structure-activity relationship (QSAR) modelings and structure-activity landscape visualization. A QSAR classification model incorporating all of the 1678 molecules stands out as the best model from a total of 12 candidate models for AR antagonists (built on PubChem fingerprint, extra trees algorithm, accuracy for training set: 0.935, 10-fold cross-validation set: 0.735 and test set: 0.756). Deeper insights into the structure-activity landscape highlighted a total of seven significant activity cliff (AC) generators (ChEMBL molecule IDs: 160257, 418198, 4082265, 348918, 390728, 4080698, and 6530), which provide valuable SAR information for medicinal chemistry. The findings in this study provide new insights and guidelines for hit identification and lead optimization for the development of novel AR antagonists.

Towards combating antibiotic resistance by exploring the quantitative structure-activity relationship of NDM-1 inhibitors.

The emergence of New Delhi metallo-beta-lactamase-1 (NDM-1) has conferred enteric bacteria resistance to almost all beta-lactam antibiotics. Its capability of horizontal transfer through plasmids, amongst humans, animal reservoirs and the environment, has added up to the totality of antimicrobial resistance control, animal husbandry and food safety. Thus far, there have been no effective drugs for neutralizing NDM-1. This study explores the structure-activity relationship of NDM-1 inhibitors. IC50 values of NDM-1 inhibitors were compiled from both the ChEMBL database and literature. After curation, a final set of 686 inhibitors were used for machine learning model building using the random forest algorithm against 12 sets of molecular fingerprints. Benchmark results indicated that the KlekotaRothCount fingerprint provided the best overall performance with an accuracy of 0.978 and 0.778 for the training and testing set, respectively. Model interpretation revealed that nitrogen-containing features (KRFPC 4080, KRFPC 3882, KRFPC 677, KRFPC 3608, KRFPC 3750, KRFPC 4287 and KRFPC 3943), sulfur-containing substructures (KRFPC 2855 and KRFPC 4843), aromatic features (KRFPC 1566, KRFPC 1564, KRFPC 1642, KRFPC 3608, KRFPC 4287 and KRFPC 3943), carbonyl features (KRFPC 1193 and KRFPC 3025), aliphatic features (KRFPC 2975, KRFPC 297, KRFPC 3224 and KRFPC 669) are features contributing to NDM-1 inhibitory activity. It is anticipated that findings from this study would help facilitate the drug discovery of NDM-1 inhibitors by providing guidelines for further lead optimization.

Synthesis and theoretical study of molecularly imprinted nanospheres for recognition of tocopherols.

Molecular imprinting is a technology that facilitates the production of artificial receptors toward compounds of interest. The molecularly imprinted polymers act as artificial antibodies, artificial receptors, or artificial enzymes with the added benefit over their biological counterparts of being highly durable. In this study, we prepared molecularly imprinted polymers for the purpose of binding specifically to tocopherol (vitamin E) and its derivative, tocopherol acetate. Binding of the imprinted polymers to the template was found to be two times greater than that of the control, non-imprinted polymers, when using only 10 mg of polymers. Optimization of the rebinding solvent indicated that ethanol-water at a molar ratio of 6:4 (v/v) was the best solvent system as it enhanced the rebinding performance of the imprinted polymers toward both tocopherol and tocopherol acetate with a binding capacity of approximately 2 mg/g of polymer. Furthermore, imprinted nanospheres against tocopherol was successfully prepared by precipitation polymerization with ethanol-water at a molar ratio of 8:2 (v/v) as the optimal rebinding solvent. Computer simulation was also performed to provide mechanistic insights on the binding mode of template-monomer complexes. Such polymers show high potential for industrial and medical applications, particularly for selective separation of tocopherol and derivatives.

Computational insights on sulfonamide imprinted polymers.

Molecular imprinting is one of the most efficient methods for preparing synthetic receptors that possess user defined recognition properties. Despite general success of non-covalent imprinting for a large variety of templates, some groups of compounds remain difficult to tackle due to their structural complexity. In this study we investigate preparation of molecularly imprinted polymers that can bind sulfonamide compounds, which represent important drug candidates. Compared to the biological system that utilizes metal coordinated interaction, the imprinted polymer provided pronounced selectivity when hydrogen bond interaction was employed in an organic solvent. Computer simulation of the interaction between the sulfonamide template and functional monomers pointed out that although methacrylic acid had strong interaction energy with the template, it also possessed high non-specific interaction with the solvent molecules of tetrahydrofuran as well as being prone to self-complexation. On the other hand, 1-vinyl-imidazole was suitable for imprinting sulfonamides as it did not cross-react with the solvent molecules or engage in self-complexation structures.

Copper complexes of nicotinic-aromatic carboxylic acids as superoxide dismutase mimetics.

Nicotinic acid (also known as vitamin B3) is a dietary element essential for physiological and antihyperlipidemic functions. This study reports the synthesis of novel mixed ligand complexes of copper with nicotinic and other select carboxylic acids (phthalic, salicylic and anthranilic acids). The tested copper complexes exhibited superoxide dismutase (SOD) mimetic activity and antimicrobial activity against Bacillus subtilis ATCC 6633, with a minimum inhibition concentration of 256 microg/mL. Copper complex of nicotinic-phthalic acids (CuNA/Ph) was the most potent with a SOD mimetic activity of IC(50) 34.42 microM. The SOD activities were observed to correlate well with the theoretical parameters as calculated using density functional theory (DFT) at the B3LYP/LANL2DZ level of theory. Interestingly, the SOD activity of the copper complex CuNA/Ph was positively correlated with the electron affinity (EA) value. The two quantum chemical parameters, highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO), were shown to be appropriate for understanding the mechanism of the metal complexes as their calculated energies show good correlation with the SOD activity. Moreover, copper complex with the highest SOD activity were shown to possess the lowest HOMO energy. These findings demonstrate a great potential for the development of value-added metallovitamin-based therapeutics.

Molecularly imprinted polymer for human viral pathogen detection.

Molecular imprinting has become an attractive synthetic approach for the fabrication of novel functional polymers with pre-designed molecular target selectivity. Such molecularly imprinted polymers (MIPs) have been applied in wide range of areas such as chemical and biological sensors, solid phase extraction and drug assays owing to their inherent robustness, reusability and reproducibility. Furthermore, MIPs can also be used as tools for studies concerning antibody/receptor binding site mimicry as well as being used as antibody substitutes for biomedical applications. Viral detection is a rapidly growing field owing to its increasing prevalence and ongoing evolution of viral variants and drug resistance. Therefore, this calls for effective detection, surveillance and control. Herein, we highlight and summarize the literature on the utilization of MIPs for human virus detection. Particularly, MIPs afford great potential for rapid virus detection as well as other recognition-based viral studies.

Quercetin-imprinted polymer for anthocyanin extraction from mangosteen pericarp.

Molecular imprinting is a facilitative technology for the production of artificial receptors possessing great endurance with high specificity toward target molecules of interest. The polymers are commonly applied for separation or analysis of substances of interest. In this study, we prepared molecularly imprinted polymers for the purpose of binding specifically to quercetin and related compounds. Quercetin was used as the template molecule, 4-vinylpyridine (4-VP) as the functional monomer, ethylene glycol dimethacrylate (EDMA) as the cross-linking monomer, azobisisobutyronitrile (AIBN) as the polymerization initiator and ethanol as the porogenic solvent. Such 4-VP-based imprinted polymer was found to bind the template molecule greater than that of the control polymer with an approximate 2 folds higher binding using 20mg of polymer in the optimal solvent, ethanol:water (4:1v/v). Quercetin-imprinted polymer (QIP) was found to bind well against its template; approximately 1mg/g polymer. In addition, QIP was applied to bind anthocyanin from the crude extract of mangosteen pericarp. The binding capacity of quercetin-MIP toward anthocyanin was approximately 0.875mg per gram of polymer. This result indicated that quercetin-MIP showed its specific binding to quercetin and related compound particularly anthocyanin. In conclusion, we have demonstrated the successful preparation and utilization of molecularly imprinted polymer for the specific recognition of quercetin as well as structurally related anthocyanins from the mangosteen pericarp with enhanced and robust performance.

A polymer supported manganese catalyst useful as a superoxide dismutase mimic.

Polymer supported manganese was synthesized via a template polymerization involving functional monomers to afford a catalyst with superoxide dismutase activity.

One-step purification of chimeric green fluorescent protein providing metal-binding avidity and protease recognition sequence.

Gene fusion technique was successfully applied as a potential approach to create a metal-binding site to assist one-step purification of green fluorescent protein (GFP). The chimeric GFP carrying hexapolyhistidine (H6GFPuv) was purified to homogeneous protein via the Immobilized Metal Affinity Chromatography charged with zinc ions. Removal of metal tagger could readily be performed by using enterokinase enzyme. Engineering of the hexahistidine and enterokinase cleavage sites (DDDDK) onto the chimeric protein did not significantly affect the fluorescent property and the binding avidity to Burkholderia pseudomallei protease of a chimeric protease-binding GFP (H6PBGFPuv). This concludes that engineering of repetitive histidine regions onto interested target protein along with the enterokinase cleavage sites will ease the complication of protein purification.

Synthesis and computational investigation of molecularly imprinted nanospheres for selective recognition of alpha-tocopherol succinate.

Molecularly imprinted polymers (MIPs) are macromolecular matrices that can mimic the functional properties of antibodies, receptors and enzymes while possessing higher durability. As such, these polymers are interesting materials for applications in biomimetic sensor, drug synthesis, drug delivery and separation. In this study, we prepared MIPs and molecularly imprinted nanospheres (MINs) as receptors with specific recognition properties toward tocopherol succinate (TPS) in comparison to tocopherol (TP) and tocopherol nicotinate (TPN). MIPs were synthesized using methacrylic acid (MAA) as functional monomer, ethylene glycol dimethacrylate (EGDMA) as crosslinking agent and dichloromethane or acetronitrile as porogenic solvent under thermal-induced polymerization condition. Results indicated that imprinted polymers of TPS-MIP, TP-MIP and TPN-MIP all bound specifically to their template molecules at 2 folds greater than the non-imprinted polymers. The calculated binding capacity of all MIP was approximately 2 mg per gram of polymer when using the optimal rebinding solvent EtOH:H2O (3:2, v/v). Furthermore, the MINs toward TPS and TP were prepared by precipitation polymerization that yielded particles that are 200-400 nm in size. The binding capacities of MINs to their templates were greater than that of the non-imprinted nanospheres when using the optimal rebinding solvent EtOH:H2O (4:1, v/v). Computer simulation was performed to provide mechanistic insights on the binding modalities of template-monomer complexes. In conclusion, we had successful prepared MIPs and MINs for binding specifically to TP and TPS. Such MIPs and MINs have great potential for industrial and medical applications, particularly for the selective separation of TP and TPS.

Metalloantibiotic Mn(II)-bacitracin complex mimicking manganese superoxide dismutase.

Superoxide dismutase (SOD) activities of various metallobacitracin complexes were evaluated using the riboflavin-methionine-nitro blue tetrazolium assay. The radical scavenging activity of various metallobacitracin complexes was shown to be higher than those of the negative controls, e.g., free transition metal ions and metal-free bacitracin. The SOD activity of the complex was found to be in the order of Mn(II)>Cu(II)>Co(II)>Ni(II). Furthermore, the effect of bacitracin and their complexation to metals on various microorganisms was assessed by antibiotic susceptibility testing. Moreover, molecular modeling and quantum chemical calculation of the metallobacitracin complex was performed to evaluate the correlation of electrostatic charge of transition metal ions on the SOD activity.

Molecularly imprinted nanoreactors for regioselective huisgen 1,3-dipolar cycloaddition reaction.

A molecularly imprinted polymer has been successfully utilized as nanoreactors for Huisgen 1,3-dipolar cycloaddition of azides and alkynes, leading to high product regioselectivity and kinetic acceleration. The MIP nanoreactors also showed remarkable selectivity toward the reactant structures, so that the "best fit" product was mostly amplified during the reaction. In contrast to previously reported regioselective MIPs, the present imprinted cavities bind reactants by means of only noncovalent molecular interactions, the same as that normally involved in biological systems. The results support the concept of drug "cloning" that further extends both the anti-idiotypic imprinting and in-cavity synthesis approaches into the modern drug discovery area.