Convolutional neural network-based quantitative structure-activity relationship and fingerprint analysis against inhibitors of anthrax lethal factor.

Aim: To develop a one-dimensional convolutional neural network-based quantitative structure-activity relationship (1D-CNN-QSAR) model to identify novel anthrax inhibitors and analyze chemical space. Methods: We developed a 1D-CNN-QSAR model to identify novel anthrax inhibitors. Results: The statistical results of the 1D-CNN-QSAR model showed a mean square error of 0.045 and a predicted correlation coefficient of 0.79 for the test set. Further, chemical space analysis showed more than 80% fragment pair similarity, with activity cliffs associated with carboxylic acid, 2-phenylfurans, N-phenyldihydropyrazole, N-phenylpyrrole, furan, 4-methylene-1H-pyrazol-5-one, phenylimidazole, phenylpyrrole and phenylpyrazolidine. Conclusion: These fragments may serve as the basis for developing potent novel drug candidates for anthrax. Finally, we concluded that our proposed 1D-CNN-QSAR model and fingerprint analysis might be used to discover potential anthrax drug candidates.

Discovery of multi-target mur enzymes inhibitors with anti-mycobacterial activity through a Scaffold approach.

In the present study, we generated a ligand-based scaffold model from a known bioactive datasets of mur enzymes of other species to identify multi-targeting inhibitors as antitubercular agents. Compounds in the ChEMBL database were first filtered to screen for substructure molecules ofMtb's multi-target enzymes. 5'-O-(5-Amino-5-deoxy-ß-D-ribofuranosyl)uridine has been identified as scaffold to develop compounds targeting Mtb's mur enzymes. A library of Murcko scaffolds was extracted and evaluated for their in-silico antitubercular activity against Mtb's mur enzymes. The screened compounds were subjected to molecular docking, molecular dynamics simulations, MM/PBSA calculation with Mtb's mur enzymes to evaluate the mechanism of interaction to assess inhibitory activity against the target protein. The results revealed that 15 compounds have higher docking scores and good interactions with multiple mur enzymes of Mtb. From the docking analysis, compound HPT had the best score and binding affinity with the all mur enzymes. Further, protein-ligand interactions were evaluated by molecular dynamics simulations to assess their stability throughout 100 ns period. From the MD trajectory, we calculated RMSD, RMSF, Rg, PCA, DCCM, FEL, hydrogen bonding, and vector motion. Furthermore, the binding free energies of the all nine mur enzymes with compound HPT exhibited good binding affinity might show the anti-mycobacterial activity. The compound HPT revealed from this computational study could act as potent anti-mycobacterial inhibitors and further serve as lead scaffolds to develop more potent pharmaceutical molecules targeting multiple mur enzymes of Mtb based on 5'-O-(5-Amino-5-deoxy-ß-D-ribofuranosyl)uridine in the future.Communicated by Ramaswamy H. Sarma.

Development of a deep learning-based quantitative structure-activity relationship model to identify potential inhibitors against the 3C-like protease of SARS-CoV-2.

Background: In the recent COVID-19 pandemic, SARS-CoV-2 infection spread worldwide. The 3C-like protease (3CLpro) is a promising drug target for SARS-CoV-2. Results: We constructed a deep learning-based convolutional neural network-quantitative structure-activity relationship (CNN-QSAR) model and deployed it on various databases to predict the biological activity of 3CLpro inhibitors. Subsequently, molecular docking analysis, molecular dynamics simulations and binding free energy calculations were performed to validate the predicted inhibitory activity against 3CLpro of SARS-CoV-2. The model showed mean squared error = 0.114, mean absolute error = 0.24 and predicted R2 = 0.84 for the test dataset. Diosmin showed good binding affinity and stability over the course of the simulations. Conclusion: The results suggest that the proposed CNN-QSAR model can be an efficient method for hit prediction and a new way to identify hit compounds against 3CLpro of SARS-CoV-2.

A hybrid resampling algorithms SMOTE and ENN based deep learning models for identification of Marburg virus inhibitors.

Background: Marburg virus (MARV) is a sporadic outbreak of a zoonotic disease that causes lethal hemorrhagic fever in humans. We propose a deep learning model with resampling techniques and predict the inhibitory activity of MARV from unknown compounds in the virtual screening process. Methodology & results: We applied resampling techniques to solve the imbalanced data problem. The classifier model comparisons revealed that the hybrid model of synthetic minority oversampling technique - edited nearest neighbor and artificial neural network (SMOTE-ENN + ANN) achieved better classification performance with 95% overall accuracy. The trained SMOTE-ENN+ANN hybrid model predicted as lead molecules; 25 out of 87,043 from ChemDiv, four out of 340 from ChEMBL anti-viral library, three out of 918 from Phytochemical database, and seven out of 419 from Natural products from NCI divsetIV, and 214 out of 1,12,267 from Natural compounds ZINC database for MARV. Conclusion: Our studies reveal that the proposed SMOTE-ENN + ANN hybrid model can improve overall accuracy more effectively and predict new lead molecules against MARV.

Identification of novel multitarget antitubercular inhibitors against mycobacterial peptidoglycan biosynthetic Mur enzymes by structure-based virtual screening.

Current therapeutic strategies for several diseases, including Mycobacterium tuberculosis infection, have evolved from an initial single-target treatment to a multitarget one. A multitarget antitubercular drugs targeting different mycobacterial proteins are more effective at suppressing bacterial growth. In this study, a high throughput virtual screening was performed to identify hits to the potential antitubercular multitarget: murA, murB, murC, murD, murE, murF, murG and murI from M. tuberculosis that is involved in peptidoglycan biosynthesis. In the virtual screening, we were docked 56,400 compounds of the ChEMBL antimycobacterial library and re-scored and identified the top 10 ranked compounds as antitubercular drug candidates. Further, the best common docked complex CHEMBL446262 was subjected to molecular dynamics simulation to understand the molecule's stability in the presence of an active site environment. After that, we have calculated binding free energy the top-ranked docked complexes using the MM/PBSA method. These ligands exhibited the highest binding affinity; find out novel drug-likeness might show the M. tuberculosis effect's inhibitor by interacting with multitarget Mur enzymes. New antitubercular therapies that include multitarget drugs may have higher efficacy than single-target medicines and provide a more straightforward antitubercular therapy regimen.Communicated by Ramaswamy H. Sarma.

Exploring the interaction mechanism between potential inhibitor and multi-target Mur enzymes of mycobacterium tuberculosis using molecular docking, molecular dynamics simulation, principal component analysis, free energy landscape, dynamic cross-correlation matrices, vector movements, and binding free energy calculation.

Multi-targeting enzyme approaches are considered to be the most significant in suppressing pathogen growth and disease control for MDR and XDR-resistant Mycobacterium tuberculosis. The multiple Mur enzymes involved in peptidoglycan biosynthesis play a key role in a cell's growth. Firstly, homology modeling was employed to construct the 3 D structure of the Mur enzymes. The computational approaches, including molecular docking and molecular dynamics simulations and MM-PBSA methods, were performed to explore the detailed interaction mechanism to evaluate the inhibitory activity against targeted proteins. The computational calculations revealed that the best-docked phytochemical compound (gallomyricitrin) inhibits the selected targets: Mur enzymes by forming stable hydrogen bonds. The analysis of RMSD, RMSF, Rg, PCA, DCCM, cross-correlation network, FEL, H-bond, and vector movement reveal that the docked complex of MurA, MurI, MurG, MurC, and MurE is more stable compared to MurB, MurF, MurD, and MurX docked complexes during MD simulations. Moreover, FEL exposed that gallomyricitrin stabilized to the minimum global energy of Mur Enzymes. The PCA, DCCM, and vector movements and binding free energy results provided further evidence for the stability of gallomyricitrin's interactions inside the binding sites by forming hydrogen bonds. The cross-correlation analysis reveals that Mur enzymes exhibit a positive and negative correlated motion between residues in different protein domains. The computational results contribute in several ways to our understanding of inhibition activity and provide a basic insight into the binding activity of gallomyricitrin as a multi-target drug for tuberculosis. Communicated by Ramaswamy H. Sarma.

Deep learning model for virtual screening of novel 3C-like protease enzyme inhibitors against SARS coronavirus diseases.

In the context of the recently emerging COVID-19 pandemic, we developed a deep learning model that can be used to predict the inhibitory activity of 3CLpro in severe acute respiratory syndrome coronavirus (SARS-CoV) for unknown compounds during the virtual screening process. This paper proposes a novel deep learning-based method to implement virtual screening with convolutional neural network (CNN) architecture. The descriptors represent chemical molecules, and these descriptors are input into the CNN framework to train a model and predict active compounds. When compared to other machine learning methods, including random forest, naive Bayes, decision tree, and support vector machine, the proposed CNN model's evaluation of the test set showed an accuracy of 0.86, a sensitivity of 0.45, a specificity of 0.96, a precision of 0.73, a recall of 0.45, an F-measure of 0.55, and a ROC of 0.71. The CNN model screened 17 out of 918 phytochemical compounds; 60 out of 423 from the natural product NCI divset IV; 17,831 out of 112,267 from the ZINC natural product database; and 315 out of 1556 FDA-approved drugs as anti-SARS-CoV agents. Further, to prioritize drug-like compounds, Lipinski's rule of five was applied to screen anti-SARS-CoV compounds (excluding FDA-approved drugs), resulting in 10, 59, and 14,025 hit molecules. Out of 10 phytochemical compounds, 9 anti-SARS-CoV agents belonged to the flavonoid group. In conclusion, the proposed CNN model can prove useful for developing novel target-specific anti-SARS-CoV compounds.

A genetic programming-based approach to identify potential inhibitors of serine protease of Mycobacterium tuberculosis.

Aim: We applied genetic programming approaches to understand the impact of descriptors on inhibitory effects of serine protease inhibitors of Mycobacterium tuberculosis (Mtb) and the discovery of new inhibitors as drug candidates. Materials & methods: The experimental dataset of serine protease inhibitors of Mtb descriptors was optimized by genetic algorithm (GA) along with the correlation-based feature selection (CFS) in order to develop predictive models using machine-learning algorithms. The best model was deployed on a library of 918 phytochemical compounds to screen potential serine protease inhibitors of Mtb. Quality and performance of the predictive models were evaluated using various standard statistical parameters. Result: The best random forest model with CFS-GA screened 126 anti-tubercular agents out of 918 phytochemical compounds. Also, genetic programing symbolic classification method is optimized descriptors and developed an equation for mathematical models. Conclusion: The use of CFS-GA with random forest-enhanced classification accuracy and predicted new serine protease inhibitors of Mtb, which can be used for better drug development against tuberculosis.

Virtual screening to identify novel potential inhibitors for Glutamine synthetase of Mycobacterium tuberculosis.

Glutamine synthetase (GS) of Mycobacterium tuberculosis (Mtb) is an essential enzyme which is involved in nitrogen metabolism and cell wall synthesis. It is involved in the inhibition of phagosome-lysosome fusion by preventing acidification. Targeting GS can be helpful to control the infection of Mtb. In order to identify potential inhibitors, we screened chemical libraries (56,400 compounds of ChEMBL anti-mycobacterial, 1596 FDA approved drugs, 419 Natural product and 916 phytochemical) against this target using the virtual screening approach. Screening by molecular docking identified ten top-ranked compounds as GSMtb inhibitors and they were compared with known inhibitors (as control). Since GS enzyme (GSHs) is also present in human. We have compared the protein sequence of GS from Mtb and human using the P-BLAST in NCBI. We found ∼27% identity in between these two sequences, so we also compared the binding affinity of inhibitor between Mtb and human. Finally, we identified top two compounds namely CHEMBL387509, CHEMBL226198 from ChEMBL anti-mycobacterial dataset, and Eriocitrin and Malvidin from phytochemical dataset which showed lees binding affinity towards GSHs whereas Pamidronate, and Phentermine from FDA approved drugs and (-)-Quinic Acid, Hexopyranuronic acid, Quebrachit, and Castanospermine from natural product showed protein-ligand interaction with Mtb protein while no interaction with GSHs. The top two docked complexes were subjected to molecular dynamic simulation to understand the stability of the molecule. Further, we calculated the binding free energy of the docked complex and analyzed hydrogen bond, salt bridge, pie stacking, and hydrophobic interaction in the docking region. These ligands exhibited very good binding affinity GSMtb enzymes. Therefore, these ligands are novel and drug-likeness compounds, and they may be potential inhibitors of M tuberculosis.Communicated by Ramaswamy H. Sarma.

High Throughput Virtual Screening to Identify Novel natural product Inhibitors for MethionyltRNA-Synthetase of Brucella melitensis.

The Brucella melitensis methionyl-tRNA-synthetase (MetRSBm) is a promising target for brucellosis drug development. The virtual screening of large libraries of a drug like molecules against a protein target is a common strategy used to identify novel inhibitors. A High throughput virtual screening was performed to identify hits to the potential antibrucellosis drug target, MetRSBm. The best inhibitor identified from the literature survey was 1312, 1415, and 1430. In the virtual screening 56,400 compounds of ChEMBL antimycobacterial library, 1596 approved drugs, 419 Natural product IV library, and 2396 methionine analogous were docked and rescoring, identified top 10 ranked compounds as anti-mycobacterial leads showing G-scores -10.27 to -8.42 (in kcal/mol), approved drugs G-scores -9.08 to -6.60 (in kcal/mol), Natural product IV library G-scores -10.55 to -6.02 (in kcal/mol), methionine analogous Gscores -11.20 to -8.51 (in kcal/mol), and compared with all three known inhibitors (as control) G-scores -3.88 to -3.17 (in kcal/mol). This result indicates these novel compounds have the best binding affinity for MetRSBm. In this study, we extrapolate that the analogous of methionine for find novel drug likeness has been identified [4-(L-histidyl)-2-phenylbenzoyl] methionine hydrochloride, might show the inhibitor of Brucella melitensis effect by interacting with MetRS enzyme. We suggests that Prumycin as a natural product is the novel drugs for brucellosis.

3D QSAR, pharmacophore and molecular docking studies of known inhibitors and designing of novel inhibitors for M18 aspartyl aminopeptidase of Plasmodium falciparum.

BACKGROUND: The Plasmodium falciparum M18 Aspartyl Aminopeptidase (PfM18AAP) is only aspartyl aminopeptidase which is found in the genome of P. falciparum and is essential for its survival. The PfM18AAP enzyme performs various functions in the parasite and the erythrocytic host such as hemoglobin digestion, erythrocyte invasion, parasite growth and parasite escape from the host cell. It is a valid target to develop antimalarial drugs. In the present work, we employed 3D QSAR modeling, pharmacophore modeling, and molecular docking to identify novel potent inhibitors that bind with M18AAP of P. falciparum. RESULTS: The PLSR QSAR model showed highest value for correlation coefficient r(2) (88 %) and predictive correlation coefficient (pred_r2) =0.6101 for external test set among all QSAR models. The pharmacophore modeling identified DHRR (one hydrogen donor, one hydrophobic group, and two aromatic rings) as an essential feature of PfM18AAP inhibitors. The combined approach of 3D QSAR, pharmacophore, and structure-based molecular docking yielded 10 novel PfM18AAP inhibitors from ChEMBL antimalarial library, 2 novel inhibitors from each derivative of quinine, chloroquine, 8-aminoquinoline and 10 novel inhibitors from WHO antimalarial drugs. Additionally, high throughput virtual screening identified top 10 compounds as antimalarial leads showing G-scores -12.50 to -10.45 (in kcal/mol), compared with control compounds(G-scores -7.80 to -4.70) which are known antimalarial M18AAP inhibitors (AID743024). This result indicates these novel compounds have the best binding affinity for PfM18AAP. CONCLUSION: The 3D QSAR models of PfM18AAP inhibitors provided useful information about the structural characteristics of inhibitors which are contributors of the inhibitory potency. Interestingly, In this studies, we extrapolate that the derivatives of quinine, chloroquine, and 8-aminoquinoline, for which there is no specific target has been identified till date, might show the antimalarial effect by interacting with PfM18AAP.

Virtual screening of natural compounds as inhibitors of EGFR 696-1022 T790M associated with non-small cell lung cancer.

Non-small cell lung cancer (NSCLC) is the most dominating and lethal type of lung cancer triggering more than 1.3 million deaths per year. The most effective line of treatment against NSCLC is to target epidermal growth factor receptor (EGFR) activating mutation. The present study aims to identify the novel anti-lung cancer compounds form nature against EGFR 696-1022 T790M by using in silico approaches. A library of 419 compounds from several natural resources was subjected to pre-screen through machine learning model using Random Forest classifier resulting 63 screened molecules with active potential. These molecules were further screened by molecular docking against the active site of EGFR 696-1022 T790M protein using AutoDock Vina followed by rescoring using X-Score. As a result 4 compounds were finally screened namely Granulatimide, Danorubicin, Penicinoline and Austocystin D with lowest binding energy which were -6.5 kcal/mol, -6.1 kcal/mol, -6.3 kcal/mol and -7.1 kcal/mol respectively. The drug likeness of the screened compounds was evaluated using FaF-Drug3 server. Finally toxicity of the hit compounds was predicted in cell line using the CLC-Pred server where their cytotoxic ability against various lung cancer cell lines was confirmed. We have shown 4 potential compounds, which could be further exploited as efficient drug candidates against lung cancer.

In silico prediction of anti-malarial hit molecules based on machine learning methods.

Machine learning techniques have been widely used in drug discovery and development in the areas of cheminformatics. Aspartyl aminopeptidase (M18AAP) of Plasmodium falciparum is crucial for survival of malaria parasite. We have created predictive models using weka and evaluated their performance based on various statistical parameters. Random Forest based model was found to be the most specificity (97.94%), with best accuracy (97.3%), MCC (0.306) as well as ROC (86.1%). The accuracy and MCC of these models indicated that they could be used to classify huge dataset of unknown compounds to predict their antimalarial compounds to develop effective drugs. Further, we deployed best predictive model on NCI diversity set IV. As result we found 59 bioactive anti-malarial molecules inhibiting M18AAP. Further, we obtained 18 non-toxic hit molecules out of 59 bioactive compounds. We suggest that such machine learning approaches could be applied to reduce the cost and length of time of drug discovery.