Predictive QSAR models development and validation for human ether-a-go-go related gene (hERG) blockers using newer tools

Do AutoML-Based QSAR Models Fulfill OECD Principles for Regulatory Assessment? A 5-HT1A Receptor Case

The drug discovery and development process requires a lot of time, financial, and workforce resources. Any reduction in these burdens might benefit all stakeholders in the healthcare domain, including patients, government, and companies. One of the critical stages in drug discovery is a selection of molecular structures with a strong affinity to a particular molecular target. The possible solution is the development of predictive models and their application in the screening process, but due to the complexity of the problem, simple and statistical models might not be sufficient for practical application. The manuscript presents the best-in-class predictive model for the serotonin 1A receptor affinity and its validation according to the Organization for Economic Co-operation and Development guidelines for regulatory purposes. The model was developed based on a database with close to 9500 molecules by using an automatic machine learning tool (AutoML). The model selection was conducted based on the Akaike information criterion value and 10-fold cross-validation routine, and later good predictive ability was confirmed with an additional external validation dataset with over 700 molecules. Moreover, the multi-start technique was applied to test if an automatic model development procedure results in reliable results.

In Silico Based Structural and Fingerprint Analysis of Structurally Diverse AT1 inhibitors

Background and Objective:

The development of pharmacologically active molecules for the treatment of hypertension and other cardiovascular diseases are important nowadays. In the present investigation, computational techniques have been implemented on Angiotensin II Type 1 (AT1) antagonists to develop better predictive models.

Methods:

Quantitative Structure Activity Relationship (QSAR) and structural patterns/fragments analyses were performed using physicochemical descriptors and MACCS Fingerprints calculaced from AT1 inhibitors collected from the literature.

Results:

The significant models developed have been validated by Leave One Out (LOO) and test set methods, which exhibit considerable Q2 values (>0.65 for the training set and >0.5 for the test set) and the R2pred values for the models are also >0.5. The applicability of the contributed descriptors in these models revealed that the chlorine atom, dipole moment, hydrogen bond donor atoms and electrostatic potential are negatively contributing, and the presence of bond between heavy atoms and the carbon atom connected with small side chain and topological polar vdW surface area are favorable for the AT1 antagonistic activity. The MACCS Fingerprints showed that the presence of atoms (kind of heavy atoms), such as N, O, and S, connected with other heteroatoms or carbon or any other atoms, through single or double bonds are predominantly present in highly active molecules. The presence of halogens, long chain alkanes, halogenated alkanes, and sulfur atoms attached with nitrogen through any atoms are responsible for decreased AT1 antagonistic activity.

Conclusion:

The results have provided additional information on the structural patterns of the compounds based on its MACCS Fingerprints, which may be used for further characterization and design of novel AT1 inhibitors.

In silico prediction of hERG inhibition

The voltage-gated potassium channel encoded by hERG carries a delayed rectifying potassium current (IKr) underlying repolarization of the cardiac action potential. Pharmacological blockade of the hERG channel results in slowed repolarization and therefore prolongation of action potential duration and an increase in the QT interval as measured on an electrocardiogram. Those are possible to cause sudden death, leading to the withdrawals of many drugs, which is the reason for hERG screening. Computational in silico prediction models provide a rapid, economic way to screen compounds during early drug discovery. In this review, hERG prediction models are classified as 2D and 3D quantitative structure–activity relationship models, pharmacophore models, classification models, and structure based models (using homology models of hERG).

Early identification of hERG liability in drug discovery programs by automated patch clamp

Blockade of the cardiac ion channel coded by human ether-à-gogo-related gene (hERG) can lead to cardiac arrhythmia, which has become a major concern in drug discovery and development. Automated electrophysiological patch clamp allows assessment of hERG channel effects early in drug development to aid medicinal chemistry programs and has become routine in pharmaceutical companies. However, a number of potential sources of errors in setting up hERG channel assays by automated patch clamp can lead to misinterpretation of data or false effects being reported. This article describes protocols for automated electrophysiology screening of compound effects on the hERG channel current. Protocol details and the translation of criteria known from manual patch clamp experiments to automated patch clamp experiments to achieve good quality data are emphasized. Typical pitfalls and artifacts that may lead to misinterpretation of data are discussed. While this article focuses on hERG channel recordings using the QPatch (Sophion A/S, Copenhagen, Denmark) technology, many of the assay and protocol details given in this article can be transferred for setting up different ion channel assays by automated patch clamp and are similar on other planar patch clamp platforms.