Identification of New Potent Acetylcholinesterase Inhibitors Using Virtual Screening and <i>in vitro</i> Approaches

Mokrani, El Hassen; Bensegueni, Abderrahmane; Chaput, Ludovic; Beauvineau, Claire; Djeghim, Hanène; Mouawad, Liliane

doi:10.1002/minf.201800118

Cited by 15 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is certainly the case that virtual screening hit rates against GPCRs are often much higher those obtained for other target classes ( 12 ). Indeed, careful examination of the literature showed that some of the studies reporting virtual screens against AChE ( 79 – 83 ) do indeed find considerably higher hit rates and more potent compounds than the median values we quote across all target classes. In light of these other results, then, a degree of caution must be exercised before extrapolating the performance of vScreenML in this prospective AChE benchmark to other target classes; further evaluation will be needed to explicitly determine whether vScreenML affords similarly outstanding results in future screening experiments.…”

Section: Discussionmentioning

confidence: 76%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Proc. Natl. Acad. Sci. U.S.A.

126

111

View full text Add to dashboard Cite

With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery’s search for active chemical matter. In typical virtual screens, however, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays. We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because studies reporting new scoring methods have not validated their models prospectively within the same study. Here, we report a strategy for building a training dataset (D-COID) that aims to generate highly compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework. In retrospective benchmarks, our classifier shows outstanding performance relative to other scoring functions. In a prospective context, nearly all candidate inhibitors from a screen against acetylcholinesterase show detectable activity; beyond this, 10 of 23 compounds have IC50 better than 50 μM. Without any medicinal chemistry optimization, the most potent hit has IC50 280 nM, corresponding to Ki of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

show abstract

Section: Discussionmentioning

confidence: 76%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Proc. Natl. Acad. Sci. U.S.A.

126

111

View full text Add to dashboard Cite

show abstract

“…It is certainly the case that virtual screening hit rates against GPCRs are often much higher those obtained for other target classes [12]. Indeed, careful examination of the literature showed that some of the studies reporting virtual screens against AChE [81][82][83][84][85] do indeed find considerably higher hit rates and more potent compounds than the median values we quote across all target classes. In light of these other results, then, a degree of caution must be exercised before extrapolating the performance of vScreenML in this prospective AChE benchmark to other target classes;…”

Section: Compound Identified As a Top-scoring Hitmentioning

confidence: 72%

Machine learning classification can reduce false positives in structure-based virtual screening

Adeshina

Deeds

Karanicolas

2020

Preprint

View full text Add to dashboard Cite

With the recent explosion in the size of libraries available for screening, virtual screening is positioned to assume a more prominent role in early drug discovery's search for active chemical matter.Modern virtual screening methods are still, however, plagued with high false positive rates: typically, only about 12% of the top-scoring compounds actually show activity when tested in biochemical assays.We argue that most scoring functions used for this task have been developed with insufficient thoughtfulness into the datasets on which they are trained and tested, leading to overly simplistic models and/or overtraining. These problems are compounded in the literature because none of the studies reporting new scoring methods have validated their model prospectively within the same study. Here, we report a new strategy for building a training dataset (D-COID) that aims to generate highly-compelling decoy complexes that are individually matched to available active complexes. Using this dataset, we train a general-purpose classifier for virtual screening (vScreenML) that is built on the XGBoost framework of gradient-boosted decision trees. In retrospective benchmarks, our new classifier shows outstanding performance relative to other scoring functions. We additionally evaluate the classifier in a prospective context, by screening for new acetylcholinesterase inhibitors. Remarkably, we find that nearly all compounds selected by vScreenML show detectable activity at 50 µM, with 10 of 23 providing greater than 50% inhibition at this concentration. Without any medicinal chemistry optimization, the most potent hit from this initial screen has an IC50 of 280 nM, corresponding to a Ki value of 173 nM. These results support using the D-COID strategy for training classifiers in other computational biology tasks, and for vScreenML in virtual screening campaigns against other protein targets. Both D-COID and vScreenML are freely distributed to facilitate such efforts.

show abstract

“…Finally, the intramolecular energy was lowered, and a mol2 file was saved. Enzyme ligand interactions were visualized using Maestro software version 11.1 [29].…”

Section: Molecular Dockingmentioning

confidence: 99%

Evaluation of In Vitro and In Silico Anti-Alzheimer Potential of Nonpolar Extracts and Essential Oil from Mentha piperita

Srief

Bani

Mokrani

et al. 2023

Foods

Self Cite

View full text Add to dashboard Cite

The anticholinesterase and antioxidant activities with chemical composition and molecular docking of essential oil and nonpolar extracts of Mentha piperita were evaluated using enzymatic and chemical methods. Molecular docking tools were used to explain the interaction of the major chemical constituents with the enzymes. GC/MS analyses revealed that the main compounds in M. piperita essential oil were l-menthone (43.601%) followed by pulegone (21.610%), linolenic acid (25.628%), and l-menthone (10.957%), representing the major compounds of the petroleum ether extract. Imidazoquinoline (7.767%) and 17-N-acetyl-oroidine (5.363%) were the major constituents of the chloroform extract. Linolenic acid (19.397%) and l-menthone (6.336%) were the most abundant compounds in the hexane extract. The M. piperita essential oil and nonpolar extracts showed moderate antioxidant activity. The essential oil showed the most promising anticholinesterase activity with IC50 = 10.66 ± 0.12 µg/mL and IC50 = 16.33 ± 0.03 µg/mL against acetylcholinesterase (AChE) and butyrylcholinesterase (BChE), respectively, close to galantamine in AChE and more active in BChE, followed by the interesting activity in the petroleum ether extract with IC50 = 23.42 ± 3.06 µg/mL in AChE and IC50 = 62.00 ± 3.22 µg/mL in BChE. The docking experiments showed that among the seven major identified compounds, N-acetyl-17-oroidine showed the highest binding score (63.01 in AChE and 63.68 in BChE). This compound was found to bind the catalytic and peripheral sites, resulting in more potent inhibitory activity than galantamine, which only binds to the catalytic site. These findings suggested the possible use of M. piperita essential oil and nonpolar extracts as a potential source of alternative natural anti-Alzheimer compounds.

show abstract

Identification of New Potent Acetylcholinesterase Inhibitors Using Virtual Screening and in vitro Approaches

Cited by 15 publications

References 34 publications

Machine learning classification can reduce false positives in structure-based virtual screening

Machine learning classification can reduce false positives in structure-based virtual screening

Machine learning classification can reduce false positives in structure-based virtual screening

Evaluation of In Vitro and In Silico Anti-Alzheimer Potential of Nonpolar Extracts and Essential Oil from Mentha piperita

Contact Info

Product

Resources

About