Machine Learning-based Analysis of Electronic Properties as Predictors of Anticholinesterase Activity in Chalcone Derivatives

TL;DR

This paper employs machine learning to analyze electronic properties of chalcone derivatives, successfully predicting their anticholinesterase activity and identifying key electronic descriptors for activity classification.

Contribution

It introduces a machine learning approach using electronic structure parameters to predict biological activity in chalcone derivatives, highlighting the most relevant electronic descriptors.

Findings

Electronic populations and orbital energies are key predictors.

Machine learning models effectively distinguish active from inactive compounds.

The approach can streamline drug development by focusing on relevant electronic properties.

Abstract

In this study, we investigated the correlation between the electronic properties of anticholinesterase compounds and their biological activity. While the methodology of such correlation is well-established and has been effectively utilized in previous studies, we employed a more sophisticated approach: machine learning. Initially, we focused on a set of $22$ molecules sharing a common chalcone skeleton and categorized them into two groups based on their IC50 indices: active and inactive. Utilizing the open-source software Orca, we conducted calculations to determine the geometries and electronic structures of these molecules. Over a hundred parameters were collected from these calculations, serving as the foundation for the features used in machine learning. These parameters included the Mulliken and Lowdin electronic populations of each atom within the skeleton, molecular orbital energies, and Mayer's free valences. Through our analysis, we developed numerous models and identified several successful candidates for effectively distinguishing between the two groups. Notably, the most informative descriptor for this separation relied solely on electronic populations and orbital energies. By understanding which computationally calculated properties are most relevant to specific biological activities, we can significantly enhance the efficiency of drug development processes, saving both time and resources.