Journal: ACS Omega

Article Title: Impact of Applicability Domains to Generative Artificial Intelligence

doi: 10.1021/acsomega.3c00883

Figure Lengend Snippet: Datasets Used for Benchmarking Generative Applicability Domains a

Article Snippet: origin , ChEMBL , Sanofi , Sanofi , ChEMBL.

Techniques:

Journal: Pharmaceutics

Article Title: Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

doi: 10.3390/pharmaceutics15041260

Figure Lengend Snippet: Summary of AI methods to predict CYP subtypes from 2019 to 2022.

Article Snippet: MGAF , ChEMBL, PubChem, OCHEM, literature , 1219 , AUC = 0.822, ACC = 0.744 , [ ] .

Techniques:

Journal: Pharmaceutics

Article Title: Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

doi: 10.3390/pharmaceutics15041260

Figure Lengend Snippet: Summary of AI methods to predict clearance property from 2019 to 2022.

Article Snippet: MGAF , ChEMBL, PubChem, OCHEM, literature , 1219 , AUC = 0.822, ACC = 0.744 , [ ] .

Techniques:

Journal: Pharmaceutics

Article Title: Artificial Intelligence in Drug Metabolism and Excretion Prediction: Recent Advances, Challenges, and Future Perspectives

doi: 10.3390/pharmaceutics15041260

Figure Lengend Snippet: Summary of AI methods to predict half-life property from 2019 to 2022.

Article Snippet: MGAF , ChEMBL, PubChem, OCHEM, literature , 1219 , AUC = 0.822, ACC = 0.744 , [ ] .

Techniques:

Journal: Frontiers in Molecular Biosciences

Article Title: Identification of Potential Binders of Mtb Universal Stress Protein (Rv1636) Through an in silico Approach and Insights Into Compound Selection for Experimental Validation

doi: 10.3389/fmolb.2021.599221

Figure Lengend Snippet: Virtual screening workflow adopted in this study. Approximately 1.9 million compounds were collated from three different libraries (ChEMBL, InterBioScreen-natural, and DrugBank-approved). ChEMBl and InterBioScreen-natural compound libraries were subjected to filtering to discard molecules that are less likely to be good drug candidates. A clean library of ~0.9 million compounds that includes the DrugBank-approved library was then subjected to hierarchical modes of docking simulations (HTVS, SP, XP). Nearly 2,000 hits obtained from this screening step were subjected to analyses to prioritize 22 promising compounds for further investigation as potential Mtb USP (Rv1636) binders. *The DrugBank-approved drugs library was not subjected to this filtering step as discussed in the text.

Article Snippet: It is to be noted that the ChEMBL and InterBioScreen-Natural compound libraries of molecules have been filtered through REOS, PAINS, and Lipinski's rule of five filters as a prescreening step.

Techniques:

Journal: Nucleic Acids Research

Article Title: DrugCentral 2018: an update

doi: 10.1093/nar/gky963

Figure Lengend Snippet: Difference in data content between DrugCentral initial release (2016) and current release (2018)

Article Snippet: DrugCentral mappings to external resources continues to enable integration with other drug information resources including: ChEMBL (through the UniChem service) , ChEBI ontology , PubChem , the Probes & Drugs portal , Pharos , e-Drug3D , MyChem.info ( http://mychem.info/ ) and repoDB ( ).

Techniques: