Modeling Antibacterial Activity with Machine Learning and Fusion of Chemical Structure Information with Microorganism Metabolic Networks

Abstract

Predicting the activity of new chemical compounds over pathogenic microorganisms with different metabolic reaction networks (MRN s ) is an important goal due to the different susceptibility to antibiotics. The ChEMBL database contains >160 000 outcomes of preclinical assays of antimicrobial activity for 55 931 compounds with >365 parameters of activity (MIC, IC50, etc.) and >90 bacteria strains of >25 bacterial species. In addition, the Leong and Barabàsi data set includes >40 MRNs of microorganisms. However, there are no models able to predict antibacterial activity for multiple assays considering both drug and MRN structures at the same time. In this work, we combined perturbation theory, machine learning, and information fusion techniques to develop the first PTMLIF model. The best linear model found presented values of specificity = 90.31/90.40 and sensitivity = 88.14/88.07 in training/validation series. We carried out a comparison to nonlinear artificial neural network (ANN) techniques and previous models from the literature. Next, we illustrated the practical use of the model with an experimental case of study. We reported for the first time the isolation and characterization of terpenes from the plant Cissus incisa. The antibacterial activity of the terpenes was experimentally determined. The more active compounds were phytol and α-amyrin, with MIC = 100 μg/mL for Vancomycin-resistant Enterococcus faecium and Acinetobacter baumannii resistant to carbapenems. These compounds are already known from other sources. However, they have been isolated and evaluated for the first time here against several strains of multidrug-resistant bacteria including World Health Organization (WHO) priority pathogens. Last, we used the model to predict the activity of these compounds versus other microorganisms with different MRNs in order to find other potential targets.

Applications of Virtual Screening in Bioprospecting: Facts, Shifts, and Perspectives to Explore the Chemo-Structural Diversity of Natural Products

“…Despite the majority of the computational screening approaches using ML algorithms lacking experimental validations, we have some interesting successful studies that aimed to find and characterize novel natural products with experimentally validated biological activity (Rupp et al, 2010 ; Zhang et al, 2017 ; Nocedo-Mena et al, 2019 ; Patsilinakos et al, 2019 ; Lee et al, 2020 ; Liu et al, 2020 ). Recently, Reher et al reported on the SMART 2.0, an NMR-based machine learning tool designed for the discovery and characterization of natural products.…”

“…ML algorithms have been successfully applied to predict the bioactivity of compounds. Recently, Nocedo-Mena et al ( 2019 ) combined machine learning, perturbation theory, and information fusion techniques to investigate the antibacterial activity of terpenes from the Cissus incisa plant, and the authors found that phytol and α-amyrin showed minimum inhibitory concentrations equal to 100 μg/ml against the carbapenem-resistant Acinetobacter baumannii and the vancomycin-resistant Enterococcus faecium . In another study, Liu et al applied deep learning algorithms to find natural products with anti-osteoporosis activity.…”

The Urgent Need for pan-antiviral Agents: From Multitarget Discovery to Multiscale Design

“…The first approach focuses on models combining perturbation theory and machine learning (PTML) [ 8 , 9 ] which, through the application of Box–Jenkins operators, can integrate in vitro screening data containing multiple viral proteins from different viruses. This enables the screening of FDA-approved drugs, and those predicted as versatile inhibitors of the viral proteins can be experimentally validated as potential treatments against SARS-CoV-2 and other viral pathogens.…”

Computational Health Engineering Applied to Model Infectious Diseases and Antimicrobial Resistance Spread

“…The stochastic models are the most suitable, when considering variables such as cross-transmission or temporary nursery staff, in the study of outbreaks [117] (Table A1). Machine learning combined with algorithms and in vitro experiments can help to develop new antimicrobial peptides [118] to predict their activity over different pathogenic microorganisms [119], and at the laboratory level, they can rapidly determine identification and antimicrobial susceptibility [120].…”