Related Experiment Video
Updated: Jul 21, 2026
Identification of Mediators of T-cell Receptor Signaling via the Screening of Chemical Inhibitor Libraries
Published on: January 22, 2019
QSAR analysis on a large and diverse set of potent phosphoinositide 3-kinase gamma (PI3Kγ) inhibitors using MLR and
Fereydoun Sadeghi1, Abbas Afkhami2,3, Tayyebeh Madrakian1,4
1Faculty of Chemistry, Bu-Ali Sina University, Hamedan, Iran.
Abstract:
Phosphorylation of PI3Kγ as a member of lipid kinases-enzymes, plays a crucial role in regulating immune cells through the generation of intracellular signals. Deregulation of this pathway is involved in several tumors. In this research, diverse sets of potent and selective isoform-specific PI3Kγ inhibitors whose drug-likeness was confirmed based on Lipinski's rule of five were used in the modeling process. Genetic algorithm (GA)-based multivariate analysis was employed on the half-maximal inhibitory concentration (IC50) of them. In this way, multiple linear regression (MLR) and artificial neural network (ANN) algorithm, were used to QSAR models construction on 245 compounds with a wide range of pIC50 (5.23-9.32). The stability and robustness of the models have been evaluated by external and internal validation methods (R2 0.623-0.642, RMSE 0.464-0.473, F 40.114, Q2LOO 0.600, and R2y-random 0.011). External verification using a wide variety of structures out of the training and test sets show that ANN is superior to MLR. The descriptors entered into the model are in good agreement with the X-ray structures of target-ligand complexes; so the model is interpretable. Finally, Williams plot-based analysis was applied to simultaneously compare the inhibitory activity and structural similarity of training, test and validation sets.
Insights
This study developed quantitative structure-activity relationship (QSAR) models to predict the inhibitory activity of phosphoinositide 3-kinase gamma (PI3Kγ) inhibitors. The artificial neural network (ANN) model demonstrated superior predictive performance for designing novel PI3Kγ-targeting cancer therapeutics.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Pharmacology
Background:
- Phosphorylation of phosphoinositide 3-kinase gamma (PI3Kγ), a lipid kinase, is vital for immune cell regulation and intracellular signaling.
- Aberrant PI3Kγ pathway activity is implicated in the development of various cancers.
Purpose of the Study:
- To develop and validate quantitative structure-activity relationship (QSAR) models for predicting the inhibitory activity of PI3Kγ inhibitors.
- To identify key molecular descriptors influencing PI3Kγ inhibitory potency.
Main Methods:
- Utilized a dataset of 245 diverse PI3Kγ inhibitors with confirmed drug-likeness.
- Employed genetic algorithm (GA)-based multivariate analysis, multiple linear regression (MLR), and artificial neural network (ANN) for QSAR model construction.
- Validated models using internal and external validation techniques, including R², RMSE, F, Q²LOO, and Ry-random.
Main Results:
- Developed robust QSAR models with good predictive accuracy (R² 0.623-0.642, Q²LOO 0.600).
- Artificial neural network (ANN) model outperformed multiple linear regression (MLR) in external validation.
- Identified descriptors consistent with X-ray crystallography data, ensuring model interpretability.
Conclusions:
- The developed ANN-based QSAR model is a reliable tool for predicting PI3Kγ inhibitory activity.
- This research facilitates the design of novel, potent, and selective PI3Kγ inhibitors for potential cancer therapy.
