Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

Muller, Christophe; Rabal, Obdulia; Gonzalez, Constantino Diaz

doi:10.1007/978-1-0716-1787-8_16

Cited by 18 publications

(12 citation statements)

References 157 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The docking study was validated using ROC curve analysis [39 -41]. The ROC testing sets were composed of experimentally validated active and inactive CaMKIIα and CaMKIIβ inhibitors extracted from the ChEMBL database [23]. The ROC set of CaMKIIα includes 20 active compounds (Ki < 800 nM) and 110 inactive compounds (Ki > 3,900 nM).…”

Section: Receiver Operating Characteristic (Roc) Curve Analysismentioning

confidence: 99%

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Daoud¹,

Abutayeh²,

Alabed³

et al. 2023

TOMCJ

View full text Add to dashboard Cite

Aim The aim of this study is to investigated the potential inhibitory activity of asenapine against central nervous system CaMKII isozymes as a potential repurposing study using docking experiments and enzymatic assay. Background The Ca2+/calmodulin-dependent protein kinase II (CaMKII) is a multifunctional protein kinase ubiquitously expressed throughout the brain. Emerging biological data have indicated that inhibiting central nervous system CaMKII isoforms, namely, CaMKIIα and CaMKIIβ, may be a promising therapeutic strategy for the potential treatment of many neurological diseases including schizophrenia, depression, epilepsy, and learning deficit. Objective 1- Study the possible attractive interactions of asenapine within the binding sites of the central CaMKII isozymes. 2- Evaluate the inhibitory activities of asenapine against central CaMKII isozymes. Method Docking experiments of asenapine and other known CaMKII inhibitors were performed. Docking settings were validated using ROC analysis. After that, the inhibitory activities of asenapine against central CaMKII alpha and beta were evaluated by enzymatic assay. Result Docking and scoring experiments of asenapine showed several binding interactions anchoring asenapine within CaMKIIα and CaMKIIβ catalytic sites while enzymatic assay results revealed that asenapine can inhibit CaMKIIα and CaMKIIβ in the micromolar range. Conclusion Our study provides evidence that asenapine can serve as a promising lead for the development of new CaMKIIα and CaMKIIβ inhibitors. Moreover, this study reinforces how the investment in drug repurposing could boost the drug discovery process.

show abstract

Section: Receiver Operating Characteristic (Roc) Curve Analysismentioning

confidence: 99%

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Daoud¹,

Abutayeh²,

Alabed³

et al. 2023

TOMCJ

View full text Add to dashboard Cite

show abstract

“…Moreover, deep learning is utilized to predict other structural aspects of proteins, such as contacts [94] , secondary structure [95] and torsional angles [96] . DNNs are also successfully applied to predict protein function [97] , [98] , [99] , protein-drug interactions [100] , [101] , and functional sites [102] , [103] , [104] .…”

Section: Prediction Of Intrinsic Disorder Using Deep Learningmentioning

confidence: 99%

Deep learning in prediction of intrinsic disorder in proteins

Zhao

Kurgan

2022

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

“…To address this demand, several recent studies have demonstrated the successful integration of quantum mechanical (QM) calculations and machine learning (ML) techniques for highly accurate physicochemical property prediction. The adaptation of ML as a viable tool in the quantum chemist’s toolbox has led to numerous applications in materials discovery, catalysis, drug design, etc. − When it comes to p K a prediction, one QM/ML model by Hunt et al used semiempirical features along with radial basis functions to obtain commendable performance on the SAMPL6 and Jensen data sets . Similarly, Lawler et al used features derived from DFT with a kernel ridge regression model to achieve a low mean absolute error (MAE) of 0.60 on oxoacids.…”

Section: Introductionmentioning

confidence: 99%

Leveraging DFT and Molecular Fragmentation for Chemically Accurate pK_a Prediction Using Machine Learning

Sanchez,

Maier,

Raghavachari

2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

We present a quantum mechanical/machine learning (ML) framework based on random forest to accurately predict the pK a s of complex organic molecules using inexpensive density functional theory (DFT) calculations. By including physics-based features from low-level DFT calculations and structural features from our connectivity-based hierarchy (CBH) fragmentation protocol, we can correct the systematic error associated with DFT. The generalizability and performance of our model are evaluated on two benchmark sets (SAMPL6 and Novartis). We believe the carefully curated input of physics-based features lessens the model's data dependence and need for complex deep learning architectures, without compromising the accuracy of the test sets. As a point of novelty, our work extends the applicability of CBH, employing it for the generation of viable molecular descriptors for ML.

show abstract

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

Cited by 18 publications

References 157 publications

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Deep learning in prediction of intrinsic disorder in proteins

Leveraging DFT and Molecular Fragmentation for Chemically Accurate pK_a Prediction Using Machine Learning

Contact Info

Product

Resources

About

Artificial Intelligence, Machine Learning, and Deep Learning in Real-Life Drug Design Cases

Cited by 18 publications

References 157 publications

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Asenapine as a Potential Lead Inhibitor against Central Ca2+/Calmodulin-Dependent Protein Kinase II: Investigation by Docking Simulation and Experimental Validation

Deep learning in prediction of intrinsic disorder in proteins

Leveraging DFT and Molecular Fragmentation for Chemically Accurate pKa Prediction Using Machine Learning

Contact Info

Product

Resources

About

Leveraging DFT and Molecular Fragmentation for Chemically Accurate pK_a Prediction Using Machine Learning