Structural-functional analysis of drug target aspartate semialdehyde dehydrogenase.

Aspartate ß-semialdehyde dehydrogenase (ASADH) is a key enzyme in the biosynthesis of essential amino acids in microorganisms and some plants. Inhibition of ASADHs can be a potential drug target for developing novel antimicrobial and herbicidal compounds. This review covers up-to-date information about sequence diversity, ligand/inhibitor-bound 3D structures, potential inhibitors, and key pharmacophoric features of ASADH useful in designing novel and target-specific inhibitors of ASADH. Most reported ASADH inhibitors have two highly electronegative functional groups that interact with two key arginyl residues present in the active site of ASADHs. The structural information, active site binding modes, and key interactions between the enzyme and inhibitors serve as the basis for designing new and potent inhibitors against the ASADH family.

CRAFT: a web-integrated cavity prediction tool based on flow transfer algorithm.

Numerous computational methods, including evolutionary-based, energy-based, and geometrical-based methods, are utilized to identify cavities inside proteins. Cavity information aids protein function annotation, drug design, poly-pharmacology, and allosteric site investigation. This article introduces "flow transfer algorithm" for rapid and effective identification of diverse protein cavities through multidimensional cavity scan. Initially, it identifies delimiter and susceptible tetrahedra to establish boundary regions and provide seed tetrahedra. Seed tetrahedron faces are precisely scanned using the maximum circle radius to transfer seed flow to neighboring tetrahedra. Seed flow continues until terminated by boundaries or forbidden faces, where a face is forbidden if the estimated maximum circle radius is less or equal to the user-defined maximum circle radius. After a seed scanning, tetrahedra involved in the flow are clustered to locate the cavity. The CRAFT web interface integrates this algorithm for protein cavity identification with enhanced user control. It supports proteins with cofactors, hydrogens, and ligands and provides comprehensive features such as 3D visualization, cavity physicochemical properties, percentage contribution graphs, and highlighted residues for each cavity. CRAFT can be accessed through its web interface at http://pitools.niper.ac.in/CRAFT , complemented by the command version available at https://github.com/PGlab-NIPER/CRAFT/ .Scientific contribution: Flow transfer algorithm is a novel geometric approach for accurate and reliable prediction of diverse protein cavities. This algorithm employs a distinct concept involving maximum circle radius within the 3D Delaunay triangulation to address diverse van der Waals radii while existing methods overlook atom specific van der Waals radii or rely on complex weighted geometric techniques.

Unlocking translational machinery for antitubercular drug development.

Targeting translational factor proteins (TFPs) presents significant promise for the development of innovative antitubercular drugs. Previous insights from antibiotic binding mechanisms and recently solved 3D crystal structures of Mycobacterium tuberculosis (Mtb) elongation factor thermo unstable-GDP (EF-Tu-GDP), elongation factor thermo stable-EF-Tu (EF-Ts-EF-Tu), and elongation factor G-GDP (EF-G-GDP) have opened up new avenues for the design and development of potent antituberculosis (anti-TB) therapies.

Machine Learning Enables Accurate Prediction of Quinone Formation during Drug Metabolism.

Metabolism helps in the elimination of drugs from the human body by making them more hydrophilic. Sometimes, drugs can be bioactivated to highly reactive metabolites or intermediates during metabolism. These reactive metabolites are often responsible for the toxicities associated with the drugs. Identification of reactive metabolites of drug candidates can be very helpful in the initial stages of drug discovery. Quinones are soft electrophiles that are generated as reactive intermediates during metabolism. Quinones make up more than 40% of the reactive metabolites. In this work, a reliable data set of 510 molecules was used to develop machine learning and deep learning-based predictive models to predict the formation of quinone-type metabolites. For representing molecules, two-dimensional (2D) descriptors, PubChem fingerprints, electro-topological state (E-state) fingerprints, and metabolic reactivity-based descriptors were used. Developed models were compared to the existing Xenosite web server using the untouched test set of 102 molecules. The best model achieved an accuracy of 86.27%, while the Xenosite server could achieve an accuracy of only 52.94% on the test set. Descriptor analysis revealed that the presence of greater numbers of polar moieties in a molecule can prevent the formation of quinone-type metabolites. In addition, the presence of a nitrogen atom in an aromatic ring and the presence of metabolophores V51, V52, and V53 (SMARTCyp descriptors) decrease the probability of quinone formation. Finally, a tool based on the best machine learning models was developed, which is accessible at http://14.139.57.41/quinonepred/.

DeepADRA2A: predicting adrenergic α2a inhibitors using deep learning.

Adrenergic α2a (ADRA2A) receptors play a crucial role in modulating various physiological actions, thereby influencing the proper functioning of different systems in the body. ADRA2A regulation is associated with a wide range of effects, including alterations in blood pressure, hypertension, heightened heart rate, etc. Inhibition of these receptors results in the release of noradrenaline, leading to heightened physiological activity, improved alertness, reduced blood pressure, and alleviation of hypertension. Conventional approaches for identifying ADRA2A inhibitors are burdened with high costs, labor-intensive procedures, and time-consuming processes. In light of these challenges, leveraging the power of artificial intelligence offers a promising solution for drug discovery and development. This study endeavors to harness the potential of artificial intelligence to develop robust models capable of accurately predicting ADRA2A inhibitors and non-inhibitors. By doing so, we aim to streamline and expedite the identification of potential drug candidates in this domain. In this study, we employed four different machine learning (ML) and deep learning (DL) algorithms to develop prediction models based on various molecular descriptors (1D, 2D, and molecular fingerprints). Among these models, the DL-based prediction model demonstrated superior performance, achieving accuracies of 98.25% and 97.23% on the training and test datasets, respectively. These results underscore the efficacy of DL-based model, as a highly effective tool for predicting ADRA2A inhibitors. The model is made available at https://github.com/PGlab-NIPER/DeepADRA2A.git.Communicated by Ramaswamy H. Sarma.

Carbamate as a potential anti-Alzheimer's pharmacophore: A review.

Alzheimer's disease (AD) is a progressive age-related neurodegenerative brain disorder, which leads to loss of memory and other cognitive dysfunction. The underlying mechanisms of AD pathogenesis are very complex and still not fully explored. Cholinergic neuronal loss, accumulation of amyloid plaque, metal ions dyshomeostasis, tau hyperphosphorylation, oxidative stress, neuroinflammation, and mitochondrial dysfunction are major hallmarks of AD. The current treatment options for AD are acetylcholinesterase inhibitors (donepezil, rivastigmine, and galantamine) and NMDA receptor antagonists (memantine). These FDA-approved drugs mainly provide symptomatic relief without addressing the pathological aspects of disease progression. So, there is an urgent need for novel drug development that not only addresses the basic mechanisms of the disease but also shows the neuroprotective property. Various research groups across the globe are working on the development of multifunctional agents for AD amelioration using different core scaffolds for their design, and carbamate is among them. Rivastigmine was the first carbamate drug investigated for AD management. The carbamate fragment, a core scaffold of rivastigmine, act as a potential inhibitor of acetylcholinesterase. In this review, we summarize the last 10 years of research conducted on the modification of carbamate with different substituents which primarily target ChE inhibition, reduce oxidative stress, and modulate Aß aggregation.

Rationally Designed Naringenin-Conjugated Polyester Nanoparticles Enable Folate Receptor-Mediated Peroral Delivery of Insulin.

Receptor-mediated transcytosis of nanoparticles is paramount for the effective delivery of various drugs. Here, we report the design and synthesis of highly functional nanoparticles with specific targeting toward the folate receptor (FR) for the peroral delivery of insulin. In doing so, we demonstrate naringenin (NAR), a citrous flavonoid, as a targeting ligand to FR, with a similar affinity as folic acid. The NAR-decorated nanoparticles indicated a 4-fold increase in FR colocalization compared to unfunctionalized nanoparticles. The NAR-conjugated precision polyester allows for high insulin loading and entrapment efficiencies. As a result, insulin-laden NAR-functional nanoparticles offered a 3-fold higher bioavailability in comparison to unfunctionalized nanoparticles. This work generated a promising contribution to folate-receptor-mediated peroral delivery of insulin, utilizing polymeric nanoparticles decorated with a natural ligand, NAR.

Target validation and structure-based virtual screening to Discover potential lead molecules against the oncogenic NSD1 histone methyltransferase.

The aim of the study was to validate Nuclear receptor-binding SET Domain NSD1 as a cancer drug target followed by the design of lead molecules against NSD1. TCGA clinical data, molecular expression techniques were used to validate the target and structure-based virtual screening was performed to design hits against NSD1. Clinical data analysis suggests the role of NSD1 in metastasis, prognosis and influence on overall survival in various malignancies. Furthermore, the mRNA and protein expression profile of NSD1 was evaluated in various cell lines. NSD1 was exploited as a target protein for in silico design of inhibitors using two major databases including ZINC15 and ChemDiv by structure-based virtual screening approach. Virtual screening was performed using the pharmacophore hypothesis designed with a protein complex S-adenosyl-l-methionine (SAM) as an endogenous ligand. Subsequently, a combined score was used to distinguish the top 10 compounds from the docking screened compounds having high performance in all four scores (docking score, XP, Gscore, PhaseScreenScore, and MMGBSA delta G Bind). Finally, the top three Zinc compounds were subjected to molecular dynamic simulation. The binding MMGBSA data suggests that ZINC000257261703 and ZINC000012405780 can be taken for in vitro and in vivo studies as they have lesser MMGBSA energy towards the cofactor binding site of NSD1 than the sinefungin. Our data validates NSD1 as a cancer drug target and provides promising structures that can be utilized for further lead optimization and rational drug design to open new gateways in the field of cancer therapeutics. Supplementary Information: The online version contains supplementary material available at 10.1007/s40203-023-00158-0.

FGFR1Pred: an artificial intelligence-based model for predicting fibroblast growth factor receptor 1 inhibitor.

Fibroblast growth factor receptors (FGFRs) are a family of cell surface receptors that bind to fibroblast growth factor (FGF) and mediate various cellular functions (translocating proteins, tissue repair, cell proliferation, development, and differentiation) through complex signaling pathways. The FGFR1 growth receptor is essential in the pathogenesis of numerous malignancies, including but not limited to breast cancer, bladder cancer, hepatocellular carcinoma (HCC), and cholangiocarcinoma. The higher levels of FGFR1 expression on the surface of cancer cells cause overly active signaling, which leads to rapid cell proliferation, resulting in a high spread of cancer cells. The kinases that FGFR1 activates migrate across the cell nucleus, activating genes and kinase proteins necessary for the growth and survival of cancerous cells. Therefore, FGFR1 targeting shows therapeutic promise in some diseases, including cancer. Inhibitors of FGFR1s are being developed and studied for their potential to block aberrant FGFR1 signaling and inhibit cancer growth. Since the discovery of new FGFR1 inhibitors in the laboratory is difficult, expensive, time-consuming, and labor-intensive, only a small number of FGFR1 inhibitors have been approved by the FDA for use in the treatment of cancer. To accelerate drug discovery by efficiently exploring the vast chemical space, and identifying potential candidates with higher accuracy and reduced cost, we developed artificial intelligence (AI)-based prediction models for FGFR1 inhibitors using a dataset of 2356 chemical compounds. Four machine learning (ML) algorithms (SVM, RF, k-NN, and ANN) were used to train different prediction models based on molecular descriptors (1D and 2D, with and without molecular fingerprints). Among all trained models, the random forest (RF)-based prediction model achieved the highest accuracy on the training (98.9%), test (89.8%), and external test (90.3%) datasets. The developed inhibitor prediction model (FGFR1Pred) provides a valuable tool for identifying potential FGFR1 inhibitors, expediting the drug discovery process and ultimately facilitating the development of new therapeutics. The model is made available at https://github.com/PGlab-NIPER/FGFR1Pred.git.

TNFipred: a classification model to predict TNF-α inhibitors.

Rheumatoid arthritis (RA), characterized by severe inflammation in the joint lining, is a progressive, chronic, autoimmune disorder with high morbidity and mortality rates. There are several mechanisms responsible for joint damage, but overproduction of TNF-α is a significant mechanism that results in excess swelling and pain. Drugs acting on TNF-α are known to significantly reduce the disease progression and improve the quality of life in many RA patients. Hence, inhibiting TNF-α is considered one of the most effective treatments for RA. Currently, there are only a few FDA-approved TNF-α inhibitors, which are mainly monoclonal antibodies, fusion proteins, or biosimilars with disadvantages such as poor stability, difficulty in route of administration (often given as injection or infusion), cost-prohibitive large-scale production, and increased side effects. There are just a handful of small compounds known to have TNF- inhibitory capabilities. Thus, there is a dire need for new drugs, especially small molecules in the market, such as TNF-α inhibitors. The conventional method of identifying TNF-α inhibitors is expensive, labor, and time intensive. Machine learning (ML) can be used to solve existing drug discovery and development problems. In this study, four classification algorithms-naïve Bayes (NB), random forest (RF), k-nearest neighbor (kNN), and support vector machine (SVM)-were used to train ML models for classifying TNF-α inhibitors based on three sets of features. The performance of the RF model was found to be best when using 1D, 2D, and fingerprints as features, with an accuracy of 87.96 and a sensitivity of 86.17. To our knowledge, this is the first ML model for TNF-α inhibitor prediction. The model is available at http://14.139.57.41/tnfipred/.

Deep learning-based prediction model for diagnosing gastrointestinal diseases using endoscopy images.

BACKGROUND: Gastrointestinal (GI) infections are quite common today around the world. Colonoscopy or wireless capsule endoscopy (WCE) are noninvasive methods for examining the whole GI tract for abnormalities. Nevertheless, it requires a great deal of time and effort for doctors to visualize a large number of images, and diagnosis is prone to human error. As a result, developing automated artificial intelligence (AI) based GI disease diagnosis methods is a crucial and emerging research area. AI-based prediction models may lead to improvements in the early diagnosis of gastrointestinal disorders, assessing severity, and healthcare systems for the benefit of patients as well as clinicians. The focus of this research is on the early diagnosis of gastrointestinal diseases using a convolution neural network (CNN) to enhance diagnosis accuracy. METHODS: Various CNN models (baseline model and using transfer learning (VGG16, InceptionV3, and ResNet50)) were trained on a benchmark image dataset, KVASIR, containing images from inside the GI tract using n-fold cross-validation. The dataset comprises images of three disease states-polyps, ulcerative colitis, and esophagitis-as well as images of the healthy colon. Data augmentation strategies together with statistical measures were used to improve and evaluate the model's performance. Additionally, the test set comprising 1200 images was used to evaluate the model's accuracy and robustness. RESULTS: The CNN model using the weights of the ResNet50 pre-trained model achieved the highest average accuracy of approximately 99.80% on the training set (100% precision and approximately 99% recall) and accuracies of 99.50% and 99.16% on the validation and additional test set, respectively, while diagnosing GI diseases. When compared to other existing systems, the proposed ResNet50 model outperforms them all. CONCLUSION: The findings of this study indicate that AI-based prediction models using CNNs, specifically ResNet50, can improve diagnostic accuracy for detecting gastrointestinal polyps, ulcerative colitis, and esophagitis. The prediction model is available at https://github.com/anjus02/GI-disease-classification.git.

AndroPred: an artificial intelligence-based model for predicting androgen receptor inhibitors.

Androgen receptor (AR), a steroid receptor, plays a pivotal role in the pathogenesis of prostate cancer (PCa). AR controls the transcription of genes that help cells avoid apoptosis and proliferate, thereby contributing to the development of PCa. Understanding AR molecular mechanisms has led to the development of newer drugs that inhibit androgen production enzymes or block ARs. The FDA has approved a small number of AR-inhibiting drugs for use in PCa thus far, as the identification of novel AR inhibitors is difficult, expensive, time-consuming, and labor-intensive. To accelerate the process, artificial intelligence (AI) algorithms were employed to predict AR inhibitors using a dataset of 2242 compounds. Four machine learning (ML) and deep learning (DL) algorithms were used to train different prediction models based on molecular descriptors (1D, 2D, and molecular fingerprints). The DL-based prediction model outperformed the other trained models with accuracies of 92.18% and 93.05% on the training and test datasets, respectively. Our findings highlight the potential of DL, particularly the DNN model, as an effective approach for predicting AR inhibitors, which could significantly streamline the process of identifying novel AR inhibitors in PCa drug discovery. Further validation of these models using experimental assays and prospective testing of newly designed compounds would be valuable to confirm their predictive power and applicability in practical drug discovery settings.Communicated by Ramaswamy H. Sarma.

Artificial intelligence in intestinal polyp and colorectal cancer prediction.

Artificial intelligence (AI) algorithms and their application to disease detection and decision support for healthcare professions have greatly evolved in the recent decade. AI has been widely applied and explored in gastroenterology for endoscopic analysis to diagnose intestinal cancers, premalignant polyps, gastrointestinal inflammatory lesions, and bleeding. Patients' responses to treatments and prognoses have both been predicted using AI by combining multiple algorithms. In this review, we explored the recent applications of AI algorithms in the identification and characterization of intestinal polyps and colorectal cancer predictions. AI-based prediction models have the potential to help medical practitioners diagnose, establish prognoses, and find accurate conclusions for the treatment of patients. With the understanding that rigorous validation of AI approaches using randomized controlled studies is solicited before widespread clinical use by health authorities, the article also discusses the limitations and challenges associated with deploying AI systems to diagnose intestinal malignancies and premalignant lesions.

Characterization of the enzymatic and multifunctional properties of Acinetobacter baumannii erythrose-4-phosphate dehydrogenase (E4PDH).

Infections due to Acinetobacter baumannii (A. baumannii) are rapidly increasing worldwide and consequently therapeutic options for treatment are limited. The emergence of multi drug resistant (MDR) strains has rendered available antibiotics ineffective, necessitating the urgent discovery of new drugs and drug targets. The vitamin B6 biosynthetic pathway has been considered as a potential antibacterial drug target but it is as yet uncharacterized for A. baumannii. In the current work, we have carried out in silico and biochemical characterization of Erythrose-4-phosphate dehydrogenase (E4PDH) (EC 1.2.1.72). This enzyme catalyzes the first step in the deoxyxylulose-5-phosphate (DXP) dependent Vitamin B6 biosynthetic pathway i.e. the conversion of d-erythrose-4-phosphate (E4P) to 4-Phosphoerythronate. E4PDH also possesses an additional activity whereby it can catalyze the conversion of Glyceraldehyde-3-phosphate (G3P) to 1,3 bisphosphoglycerate (1,3BPG). Our studies have revealed that this enzyme exhibits an alternate moonlighting function as a cell surface receptor for the human iron transport proteins transferrin (Tf) and lactoferrin (Lf). The present work reports the internalization of Tf and consequent iron acquisition as an alternate strategy for iron acquisition. Given its essential role in two crucial pathways i.e. metabolism and iron acquisition, A. baumannii E4PDH may play a vital role in bacterial pathogenesis.

Molecular explorations of the Leishmania donovani 6-phosphogluconolactonase enzyme, a key player in the pentose phosphate pathway.

The enzymes of the pentose phosphate pathway are vital to survival in kinetoplastids. The second step of the pentose phosphate pathway involves hydrolytic cleavage of 6-phosphogluconolactone to 6-phosphogluconic acid by 6- phosphogluconolactonase (6PGL). In the present study, Leishmania donovani 6PGL (Ld6PGL) was cloned and overexpressed in bacterial expression system. Comparative sequence analysis revealed the conserved sequence motifs, functionally and structurally important residues in 6PGL family. In silico amino acid substitution study and interacting partners of 6PGL were predicted. The Ld6PGL enzyme was found to be active in the assay and in the parasites. Specificity was confirmed by Western blot analysis. The ∼30 kDa protein was found to be a dimer in MALDI, glutaraldehyde crosslinking and size exclusion chromatography studies. Kinetic analysis and structural stability studies of Ld6PGL were performed with denaturants and at varied temperature. Computational 3D Structural modelling of Ld6PGL elucidates that it has a similar α/ß hydrolase fold structural topology as in other members of 6PGL family. The three loops are found in extended form when the structure is compared with the human 6PGL (Hs6PGL). Further, enzyme substrate binding mode and its mechanism were investigated using the molecular docking and molecular simulation studies. Interesting dynamics action of substrate 6-phosphogluconolactone was observed into active site during MD simulation. Interesting differences were observed between host and parasite enzyme which pointed towards its potential to be explored as an antileishmanial drug target. This study forms the basis for further analysis of the role of Ld6PGL in combating oxidative stress in Leishmania.

Pyrazole based Furanone Hybrids as Novel Antimalarial: A Combined Experimental, Pharmacological and Computational Study.

BACKGROUND: Malaria parasite strains are resistant to the therapeutic effect of prophylactics medicines presently available. This resistance now poses a significant challenge to researchers to beat malaria parasitic infections. Strategies such as investigating newer hybrid chemical entities and specified drug targets may help us spot new efficient derivatives that bind to the parasites in a more specific manner and inhibit their growth. OBJECTIVE: To scientifically perform the experimental, pharmacological, and computational studies of pyrazole-based furanone hybrids as novel antimalarial agents. METHODS: A series of new furanone-based pyrazole derivatives were synthesized and investigated as potential antimalarial agents by performing in vitro antimalarial activity. To get further optimization, these synthesized derivatives were virtually screened based on ADME-T filters, and molecular docking studies were also accomplished on the crystal structures of Plasmodium falciparum lactate dehydrogenase (PfLDH). Furthermore, the in-silico prediction was supported by performing an LDH assay. RESULTS: The docking data suggested that the designed hybrid of furanone-pyrazole may act as PfLDH inhibitors. It was found that the results of experimental in vitro antimalarial activity and in silico analysis correlate well to each other to a good extent. The compounds (7d), (7g), and (8e) were found to be the most potent derivatives with IC50 values of 1.968, 1.983, and 2.069 µg/ml, respectively. CONCLUSION: From the results, it may be concluded that compounds that are active in low doses might be adopted as a lead compound for the development of more active antimalarial agents. The synthesized compounds (7d), (7g), and (8e) exhibited good antimalarial activity with PfLDH inhibition. The best compounds can be explored further in the future for designing the potent inhibitors of PfLDH as new potent antimalarial agents.

Probing the Molecular Basis of Cofactor Affinity and Conformational Dynamics of Mycobacterium tuberculosis Elongation Factor Tu: An Integrated Approach Employing Steered Molecular Dynamics and Umbrella Sampling Simulations.

The emergence of multidrug-resistant and extensively drug-resistant tuberculosis strains is the reason that the infectious tuberculosis pathogen is still the most common cause of death. The quest for new antitubercular drugs that can fit into multidrug regimens, function swiftly, and overcome the ever-increasing prevalence of drug resistance continues. The crucial role of MtbEF-Tu in translation and trans-translation processes makes it an excellent target for antitubercular drug design. In this study, the primary sequence of MtbEF-Tu was used to model the three-dimensional structures of MtbEF-Tu in the presence of GDP ("off" state) and GTP ("on" state). The binding free energy computed using both the molecular mechanics/Poisson-Boltzmann surface area and umbrella sampling approaches shows that GDP binds to MtbEF-Tu with an ∼2-fold affinity compared to GTP. The steered molecular dynamics (SMD) and umbrella sampling simulation also shows that the dissociation of GDP from MtbEF-Tu in the presence of Mg2+ is a thermodynamically intensive process, while in the absence of Mg2+, the destabilized GDP dissociates very easily from the MtbEF-Tu. Naturally, the dissociation of Mg2+ from the MtbEF-Tu is facilitated by the nucleotide exchange factor EF-Ts, and this prior release of magnesium makes the dissociation process of destabilized GDP easy, similar to that observed in the umbrella sampling and SMD study. The MD simulations of MtbEF-Tu's "on" state conformation in the presence of GTP reveal that the secondary structure of switch-I and Mg2+ coordination network remains similar to its template despite the absence of identity in the conserved region of switch-I. On the other hand, the secondary structure in the conserved region of the switch-I of MtbEF-Tu unwinds from a helix to a loop in the presence of GDP. The major conformational changes observed in switch-I and the movement of Thr64 away from Mg2+ mainly reflect essential conformational changes to make the shift of MtbEF-Tu's "on" state to the "off" state in the presence of GDP. These obtained structural and functional insights into MtbEF-Tu are pivotal for a better understanding of structural-functional linkages of MtbEF-Tu, and these findings may serve as a basis for the design and development of MtbEF-Tu-specific inhibitors.

Exploration of Neuroprotective Properties of a Naturally Inspired Multifunctional Molecule (F24) against Oxidative Stress and Amyloid ß Induced Neurotoxicity in Alzheimer's Disease Models.

The pathological hallmarks of Alzheimer's disease (AD) are manifested as an increase in the level of oxidative stress and aggregation of the amyloid-ß protein. In vitro, in vivo, and in silico experiments were designed and carried out with multifunctional cholinergic inhibitor, F24 (EJMC-7a) to explore its neuroprotective effects in AD models. The neuroprotection ability of F24 was tested in SH-SY5Y cells, a widely used neuronal cell line. The pretreatment and subsequent co-treatment of SH-SY5Y cells with different doses of F24 was effective in rescuing the cells from H2O2 induced neurotoxicity. F24 treated cells were found to be effective in the reduction of cellular reactive oxygen species, DNA damage, and Aß1-42 induced neurotoxicity, which validated its neuroprotective effectiveness. F24 exhibited efficacy in an in vivoDrosophila model by rescuing eye phenotypes from degeneration caused by Aß toxicity. Further, computational studies were carried out to monitor the interaction between F24 and Aß1-42 aggregates. The computational studies corroborated our in vitro and in vivo studies suggesting Aß1-42 aggregation modulation ability of F24. The brain entry ability of F24 was studied in the parallel artificial membrane permeability assay. Finally, F24 was tested at doses of 1 and 2.5 mg/kg in the Morris water maze AD model. The neuroprotective properties shown by F24 strongly suggest that multifunctional features of this molecule provide symptomatic relief and act as a disease-modifying agent in the treatment of AD. The results from our experiments strongly indicated that natural template-based F24 could serve as a lead molecule for further investigation to explore multifunctional therapeutic agents for AD management.

Machine learning-based modeling to predict inhibitors of acetylcholinesterase.

Acetylcholinesterase enzyme is responsible for the degradation of acetylcholine and is an important drug target for the treatment of Alzheimer's disease. When this enzyme is inhibited, more acetylcholine is available in the synaptic cleft for the use, which leads to enhanced memory and cognitive ability. The aim of the present work is to create machine learning models for distinguishing between AChE inhibitors and non-inhibitors using algorithms like support vector machine (SVM), k-nearest neighbor (k-NN) and random forest (RF). The developed models were evaluated by 10-fold cross-validation and external dataset. Descriptor analysis was performed to identify most important features for the activity of molecules. Descriptors which were identified as important include maxssCH2, minHssNH, SaasC, minssCH2, bit 128 MACCS key, bit 104 MACCS key, bit 24 estate fingerprint and bit 18 estate fingerprints. The model developed using fingerprints based on random forest algorithm produced better results compared to other models. The overall accuracy of best model on test set was 85.38 percent. The developed model is available at http://14.139.57.41/achepredictor/ .