Pharmacoprint: A Combination of a Pharmacophore Fingerprint and Artificial Intelligence as a Tool for Computer-Aided Drug Design

Abstract

Structural fingerprints and pharmacophore modeling are methodologies that have been used for at least 2 decades in various fields of cheminformatics, from similarity searching to machine learning (ML). Advances in in silico techniques consequently led to combining both these methodologies into a new approach known as the 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., ECFP4, Estate, MACCS, PubChem, Substructure, Klekota–Roth, CDK, Extended, and GraphOnly) and the ChemAxon pharmacophoric features fingerprint. Pharmacoprint consisted of 39 973 bits; several methods were applied for dimensionality reduction, and the best algorithm not only reduced the length of the bit string but also improved the efficiency of the 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 three-dimensional (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 us to maximize the Matthews correlation coefficient up to 0.962. The results show the potential of Pharmacoprint as a new, perspective tool for computer-aided drug design.

An Algorithm Framework for Drug-Induced Liver Injury Prediction Based on Genetic Algorithm and Ensemble Learning

“…These results indicate that molecular fingerprints based on substructure and pharmacophores can better represent the toxic fingerprints for DILI prediction. Meanwhile, pharmacophore-based fingerprints named Pharmcoprint show that pharmacophore fingerprints are superior to other molecular fingerprints for protein targets prediction [ 70 ]. In the pre-experiment, we also found that the fingerprint based on pharmacophores had the highest accuracy in the single fingerprint experiment, but the prediction accuracy was higher when it was combined with other fingerprints by using R-E-GA.…”

ELIXIR-A: An Interactive Visualization Tool for Multi-Target Pharmacophore Refinement

“… 23 A 2D pharmacophore fingerprint is a form of a binary code that contains pharmacophore properties. 24 − 27 These pharmacophore fingerprints containing molecular fragments have been applied with multiple artificial intelligence-related models such as PTML, 28 , 29 Pharmacoprint, 27 and Pharm-IF. 30 …”

Proteome-Informed Machine Learning Studies of Cocaine Addiction

“…In the benchmark classification tasks, the authors dropped the compounds between active and inactive to define a distinct boundary: for the DAT and hERG data sets, the compounds with pK i or pIC 50 values between 5 and 6 were excluded; 65 for the D 2 R data set, the compounds with pK i or pIC 50 values between 6 and 7 were removed. 66 Therefore, to fairly compare our results to theirs, we also followed the same preprocessing strategies so that the data sets can be directly compared.…”

“…This work studied 36 data sets for 32 different protein targets. The data were collected from refs and and the ChEMBL database . These data sets are summarized in Table S1.…”

“…Some benchmark data sets related to cocaine addiction were already studied in terms of regression or classification tasks. , On these benchmark data sets, our predictors, especially consensus ones, exhibit high prediction power (see Figure ). On regression tasks, we can achieve R values of >0.8 ( R 2 > 0.64) on all of the data sets except extended hERG.…”