Pharmacoprint -- a combination of pharmacophore fingerprint and artificial intelligence as a tool for computer-aided drug design

TL;DR

Pharmacoprint is a novel high-resolution pharmacophore fingerprint that, when combined with machine learning, enhances the accuracy and efficiency of computer-aided drug design by outperforming existing molecular fingerprints.

Contribution

This paper introduces Pharmacoprint, a new pharmacophore fingerprint that encodes detailed molecular features and improves ML-based classification in drug design tasks.

Findings

Pharmacoprint outperforms other molecular fingerprints in classification accuracy.

Dimensionality reduction improves ML efficiency and performance.

Maximized Matthews Correlation Coefficient up to 0.962 using Pharmacoprint with neural networks.

Abstract

Structural fingerprints and pharmacophore modeling are methodologies that have been used for at least two decades in various fields of cheminformatics: from similarity searching to machine learning (ML). Advances in silico techniques consequently led to combining both these methodologies into a new approach known as pharmacophore fingerprint. Herein, we propose a high-resolution, pharmacophore fingerprint called Pharmacoprint that encodes the presence, types, and relationships between pharmacophore features of a molecule. Pharmacoprint was evaluated in classification experiments by using ML algorithms (logistic regression, support vector machines, linear support vector machines, and neural networks) and outperformed other popular molecular fingerprints (i.e., Estate, MACCS, PubChem, Substructure, Klekotha-Roth, CDK, Extended, and GraphOnly) and ChemAxon Pharmacophoric Features fingerprint. Pharmacoprint consisted of 39973 bits; several methods were applied for dimensionality reduction, and the best algorithm not only reduced the length of bit string but also improved the efficiency of ML tests. Further optimization allowed us to define the best parameter settings for using Pharmacoprint in discrimination tests and for maximizing statistical parameters. Finally, Pharmacoprint generated for 3D structures with defined hydrogens as input data was applied to neural networks with a supervised autoencoder for selecting the most important bits and allowed to maximize Matthews Correlation Coefficient up to 0.962. The results show the potential of Pharmacoprint as a new, perspective tool for computer-aided drug design.