GitHub - madhubioinformatics/G6PD-activators-Machine-learning: Glucose-6-Phosphate Dehydrogenase (G6PD) is a ubiquitous cytoplasmic enzyme converting glucose-6-phosphate into 6-phosphogluconate in the pentose phosphate pathway (PPP). The G6PD deficiency renders the inability to regenerate glutathione due to lack of NADPH and produces the oxidative injury in retina that accelerate the dystrophic conditions to photoreceptor cells and damage the retinal blood barrier function. In this study, we constructed pharmacophore-based models based on the compound complex of G6PD with AG1 (G6PD activator) followed by virtual screening. 53 hit molecules were mapped with core pharmacophore features. We calculated molecular descriptors, clustering, principle component analysis (PCA) to pharmacophore hit molecules and further applied statistical machine learning methods . Results showed that the all model performed best and classified as drug-like (18) and nondrug-like (35) compounds. The drug-like compounds were further evaluated our established cheminformatics pipeline (molecular docking and in silico ADMET analysis). Finally, five hits with different scaffolds were picked out for docking studies and in silico ADMET analysis. This study proposes that the combination of machine learning methods with traditional structure-based virtual screening can effectively strengthen the ability in finding potential G6PD activators designing for G6PD deficiency diseases. Moreover, these compounds can be considered as safe agents for further validation studies at cell level, animal model, and even clinic setting.

madhubioinformatics / G6PD-activators-Machine-learning Public

Notifications You must be signed in to change notification settings
Fork 0
Star 2

Glucose-6-Phosphate Dehydrogenase (G6PD) is a ubiquitous cytoplasmic enzyme converting glucose-6-phosphate into 6-phosphogluconate in the pentose phosphate pathway (PPP). The G6PD deficiency renders the inability to regenerate glutathione due to lack of NADPH and produces the oxidative injury in retina that accelerate the dystrophic conditions t…

2 stars 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 6 Commits
AMDET_properites of 53 compounds_Table3.xlsx		AMDET_properites of 53 compounds_Table3.xlsx
Activesite_castp.tif		Activesite_castp.tif
Alignment1.tif		Alignment1.tif
Fig. 4.tif		Fig. 4.tif
Fig. 5.tif		Fig. 5.tif
Fig.1.tif		Fig.1.tif
Fig.2.tif		Fig.2.tif
Fig.3.tif		Fig.3.tif
Fig.6.tif		Fig.6.tif
Fig.7.tif		Fig.7.tif
Fig.8.tif		Fig.8.tif
Fig4.tif		Fig4.tif
Fig5.tif		Fig5.tif
Graphical abstract.tif		Graphical abstract.tif
Heatmap_descriptors.xlsx		Heatmap_descriptors.xlsx
ML_results.xlsx		ML_results.xlsx
Pharmacophore1.tif		Pharmacophore1.tif
Pharmacophore2.tif		Pharmacophore2.tif
Pharmacophore_53 hits_1.tif		Pharmacophore_53 hits_1.tif
Pharmacophore_complex.pdb		Pharmacophore_complex.pdb
Pharmacopore_hits_1-9.tif		Pharmacopore_hits_1-9.tif
Pharmacopore_hits_10-18.tif		Pharmacopore_hits_10-18.tif
Pharmacopore_hits_19-27.tif		Pharmacopore_hits_19-27.tif
Pharmacopore_hits_28-36.tif		Pharmacopore_hits_28-36.tif
Pharmacopore_hits_37-45.tif		Pharmacopore_hits_37-45.tif
Pharmacopore_hits_46-53.tif		Pharmacopore_hits_46-53.tif
R-program.txt		R-program.txt
README.md		README.md
SWISS-ADMET of top 5 compounds_Table2.xlsx		SWISS-ADMET of top 5 compounds_Table2.xlsx
Taining set_S2_Table.docx		Taining set_S2_Table.docx
Test set_S1_Table.docx		Test set_S1_Table.docx