Machine learning driven web-based app platform for the discovery of monoamine oxidase B inhibitors.

Monoamine oxidases (MAOs), specifically MAO-A and MAO-B, play important roles in the breakdown of monoamine neurotransmitters. Therefore, MAO inhibitors are crucial for treating various neurodegenerative disorders, including Parkinson's disease (PD), Alzheimer's disease (AD), and amyotrophic lateral sclerosis (ALS). In this study, we developed a novel cheminformatics pipeline by generating three diverse molecular feature-based machine learning-assisted quantitative structural activity relationship (ML-QSAR) models concerning MAO-B inhibition. PubChem fingerprints, substructure fingerprints, and one-dimensional (1D) and two-dimensional (2D) molecular descriptors were implemented to unravel the structural insights responsible for decoding the origin of MAO-B inhibition in 249 non-reductant molecules. Based on a random forest ML algorithm, the final PubChem fingerprint, substructure fingerprint, and 1D and 2D molecular descriptor prediction models demonstrated significant robustness, with correlation coefficients of 0.9863, 0.9796, and 0.9852, respectively. The significant features of each predictive model responsible for MAO-B inhibition were extracted using a comprehensive variance importance plot (VIP) and correlation matrix analysis. The final predictive models were further developed as a web application, MAO-B-pred ( https://mao-b-pred.streamlit.app/ ), to allow users to predict the bioactivity of molecules against MAO-B. Molecular docking and dynamics studies were conducted to gain insight into the atomic-level molecular interactions between the ligand-receptor complexes. These findings were compared with the structural features obtained from the ML-QSAR models, which supported the mechanistic understanding of the binding phenomena. The presented models have the potential to serve as tools for identifying crucial molecular characteristics for the rational design of MAO-B target inhibitors, which may be used to develop effective drugs for neurodegenerative disorders.

Navigating bioactivity space in anti-tubercular drug discovery through the deployment of advanced machine learning models and cheminformatics tools: a molecular modeling based retrospective study.

Mycobacterium tuberculosis is the bacterial strain that causes tuberculosis (TB). However, multidrug-resistant and extensively drug-resistant tuberculosis are significant obstacles to effective treatment. As a result, novel therapies against various strains of M. tuberculosis have been developed. Drug development is a lengthy procedure that includes identifying target protein and isolation, preclinical testing of the drug, and various phases of a clinical trial, etc., can take decades for a molecule to reach the market. Computational approaches such as QSAR, molecular docking techniques, and pharmacophore modeling have aided drug development. In this review article, we have discussed the various techniques in tuberculosis drug discovery by briefly introducing them and their importance. Also, the different databases, methods, approaches, and software used in conducting QSAR, pharmacophore modeling, and molecular docking have been discussed. The other targets targeted by these techniques in tuberculosis drug discovery have also been discussed, with important molecules discovered using these computational approaches. This review article also presents the list of drugs in a clinical trial for tuberculosis found drugs. Finally, we concluded with the challenges and future perspectives of these techniques in drug discovery.

Predicting the molecular mechanism-driven progression of breast cancer through comprehensive network pharmacology and molecular docking approach.

Identification of key regulators is a critical step toward discovering biomarker that participate in BC. A gene expression dataset of breast cancer patients was used to construct a network identifying key regulators in breast cancer. Overexpressed genes were identified with BioXpress, and then curated genes were used to construct the BC interactome network. As a result of selecting the genes with the highest degree from the BC network and tracing them, three of them were identified as novel key regulators, since they were involved at all network levels, thus serving as the backbone. There is some evidence in the literature that these genes are associated with BC. In order to treat BC, drugs that can simultaneously interact with multiple targets are promising. When compared with single-target drugs, multi-target drugs have higher efficacy, improved safety profile, and are easier to administer. The haplotype and LD studies of the FN1 gene revealed that the identified variations rs6707530 and rs1250248 may both cause TB, and endometriosis respectively. Interethnic differences in SNP and haplotype frequencies might explain the unpredictability in association studies and may contribute to predicting the pharmacokinetics and pharmacodynamics of drugs using FN1.

Probing the origins of programmed death ligand-1 inhibition by implementing machine learning-assisted sequential virtual screening techniques.

PD-L1 is a key immunotarget involved in binding to its receptor PD-1. PD-L1/PD-1 interface blocking using antibodies (or small molecules) is the central area of interest for tumor suppression in various cancers. Blocking the PD-L1/PD-1 pathway in the tumor cells results in its immune activation and destruction, and thereby restoring the T-cell proliferation and cytokine production. The active binding site interface residues of PD-L1/PD-1 were experimentally known and proven by structural biology and site-directed mutagenesis studies. Structure-based molecular design technique was employed to identify the inhibitors for blocking the PD-L1/PD-1 interface. Nine hits to leads were identified from the SPECS small molecule database by machine learning, molecular docking, and molecular dynamics simulation techniques. Following this, a machine learning-assisted QSAR modeling approach was implemented using ChEMBL database to gain insights into the inhibitory potential of PD-L1 inhibitors and predict the activity of our previously screened nine hit molecules. The best leads identified in the present study bind strongly with the active sites of PD-L1/PD-1 interface residues, which include A121, M115, I116, S117, I54, Y56, D122, and Y123. These computational leads are considered promising molecules for further in vitro and in vivo analysis to be developed as potential PD-L1 checkpoint inhibitors to cure different types of cancers.

Corrigendum: Navigating bioactivity space in anti-tubercular drug discovery through the deployment of advanced machine learning models and cheminformatics tools: a molecular modeling based retrospective study.

[This corrects the article DOI: 10.3389/fphar.2023.1265573.].

Identification, analysis of deleterious SNPs of the human GSR gene and their effects on the structure and functions of associated proteins and other diseases.

Hereditary glutathione reductase deficiency, caused by mutations of the GSR gene, is an autosomal recessive disorder characterized by decreased glutathione disulfide (GSSG) reduction activity and increased thermal instability. This study implemented computational analysis to screen the most likely mutation that might be associated with hereditary glutathione reductase deficiency and other diseases. Using ten online computational tools, the study revealed four nsSNPs among the 17 nsSNPs identified as most deleterious and disease associated. Structural analyses and evolutionary confirmation study of native and mutant GSR proteins using the HOPE project and ConSruf. HOPE revealed more flexibility in the native GSR structure than in the mutant structure. The mutation in GSR might be responsible for changes in the structural conformation and function of the GSR protein and might also play a significant role in inducing hereditary glutathione reductase deficiency. LD and haplotype studies of the gene revealed that the identified variations rs2978663 and rs8190955 may be responsible for obstructive heart defects (OHDs) and hereditary anemia, respectively. These interethnic differences in the frequencies of SNPs and haplotypes might help explain the unpredictability that has been reported in association studies and can contribute to predicting the pharmacokinetics and pharmacodynamics of drugs that make use of GSR.