Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors

Developing effective antibiotics against Gram-negative bacteria remains challenging due to their protective outer membrane. With this study, we investigated the relationship between antibiotic permeation through the OmpF porin of <i>Escherichia coli</i> and antimicrobial efficacy. We mea...

Full description

Saved in:
Bibliographic Details
Main Authors: Sara Boi, Silvia Puxeddu, Ilenia Delogu, Domenica Farci, Dario Piano, Aldo Manzin, Matteo Ceccarelli, Fabrizio Angius, Mariano Andrea Scorciapino, Stefan Milenkovic
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Molecules
Subjects:
Online Access:https://www.mdpi.com/1420-3049/30/6/1224
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091572188676096
author Sara Boi
Silvia Puxeddu
Ilenia Delogu
Domenica Farci
Dario Piano
Aldo Manzin
Matteo Ceccarelli
Fabrizio Angius
Mariano Andrea Scorciapino
Stefan Milenkovic
author_facet Sara Boi
Silvia Puxeddu
Ilenia Delogu
Domenica Farci
Dario Piano
Aldo Manzin
Matteo Ceccarelli
Fabrizio Angius
Mariano Andrea Scorciapino
Stefan Milenkovic
author_sort Sara Boi
collection DOAJ
description Developing effective antibiotics against Gram-negative bacteria remains challenging due to their protective outer membrane. With this study, we investigated the relationship between antibiotic permeation through the OmpF porin of <i>Escherichia coli</i> and antimicrobial efficacy. We measured the relative permeability coefficients (RPCs) through the bacterial porin by liposome swelling assays, including non-antibacterial molecules, and the minimum inhibitory concentrations (MICs) against <i>E. coli</i>. We developed a machine learning (ML) approach by combining classification and regression models to correlate these data sets. Our strategy allowed us to quantify the negative correlation between RPC and MIC values, clearly indicating that increased permeability through OmpF generally leads to improved antimicrobial activity. Moreover, the correlation was remarkable only for compounds with significant permeability coefficients. Conversely, when permeation ability is low, other factors play the most significant role in antimicrobial potency. Importantly, the proposed ML-based approach was set by exploiting the available seminal information from previous investigations in order to keep the number of molecular descriptors to the minimum for greater interpretability. This provided valuable insights into the complex interplay between different molecular properties in defining the overall outer membrane permeation and, consequently, the antimicrobial efficacy. From a practical perspective, the presented approach does not aim at identifying the “golden rule” for boosting antibiotic potency. The automated protocol presented here could be used to inspect, in silico, many alternatives of a given molecular structure, with the output being the list of the best candidates to be then synthesized and tested. This could be a valuable in silico tool for researchers in both academia and industry to rapidly evaluate novel potential compounds and reduce costs and time during the early drug discovery stage.
format Article
id doaj-art-564a9c2dd8ed4a00a57e2a8f0fcbcb35
institution DOAJ
issn 1420-3049
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Molecules
spelling doaj-art-564a9c2dd8ed4a00a57e2a8f0fcbcb352025-08-20T02:42:22ZengMDPI AGMolecules1420-30492025-03-01306122410.3390/molecules30061224Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular DescriptorsSara Boi0Silvia Puxeddu1Ilenia Delogu2Domenica Farci3Dario Piano4Aldo Manzin5Matteo Ceccarelli6Fabrizio Angius7Mariano Andrea Scorciapino8Stefan Milenkovic9Department of Chemical and Geological Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Biomedical Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Biomedical Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Life and Environmental Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Life and Environmental Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Biomedical Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Physics, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Biomedical Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Chemical and Geological Sciences, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDepartment of Physics, University of Cagliari, S.P. 8 km 0,700, I-09042 Monserrato, CA, ItalyDeveloping effective antibiotics against Gram-negative bacteria remains challenging due to their protective outer membrane. With this study, we investigated the relationship between antibiotic permeation through the OmpF porin of <i>Escherichia coli</i> and antimicrobial efficacy. We measured the relative permeability coefficients (RPCs) through the bacterial porin by liposome swelling assays, including non-antibacterial molecules, and the minimum inhibitory concentrations (MICs) against <i>E. coli</i>. We developed a machine learning (ML) approach by combining classification and regression models to correlate these data sets. Our strategy allowed us to quantify the negative correlation between RPC and MIC values, clearly indicating that increased permeability through OmpF generally leads to improved antimicrobial activity. Moreover, the correlation was remarkable only for compounds with significant permeability coefficients. Conversely, when permeation ability is low, other factors play the most significant role in antimicrobial potency. Importantly, the proposed ML-based approach was set by exploiting the available seminal information from previous investigations in order to keep the number of molecular descriptors to the minimum for greater interpretability. This provided valuable insights into the complex interplay between different molecular properties in defining the overall outer membrane permeation and, consequently, the antimicrobial efficacy. From a practical perspective, the presented approach does not aim at identifying the “golden rule” for boosting antibiotic potency. The automated protocol presented here could be used to inspect, in silico, many alternatives of a given molecular structure, with the output being the list of the best candidates to be then synthesized and tested. This could be a valuable in silico tool for researchers in both academia and industry to rapidly evaluate novel potential compounds and reduce costs and time during the early drug discovery stage.https://www.mdpi.com/1420-3049/30/6/1224antibioticsdrug designartificial intelligenceinfectious diseasesin silico screeningliposomes
spellingShingle Sara Boi
Silvia Puxeddu
Ilenia Delogu
Domenica Farci
Dario Piano
Aldo Manzin
Matteo Ceccarelli
Fabrizio Angius
Mariano Andrea Scorciapino
Stefan Milenkovic
Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
Molecules
antibiotics
drug design
artificial intelligence
infectious diseases
in silico screening
liposomes
title Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
title_full Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
title_fullStr Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
title_full_unstemmed Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
title_short Seeking Correlation Among Porin Permeabilities and Minimum Inhibitory Concentrations Through Machine Learning: A Promising Route to the Essential Molecular Descriptors
title_sort seeking correlation among porin permeabilities and minimum inhibitory concentrations through machine learning a promising route to the essential molecular descriptors
topic antibiotics
drug design
artificial intelligence
infectious diseases
in silico screening
liposomes
url https://www.mdpi.com/1420-3049/30/6/1224
work_keys_str_mv AT saraboi seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT silviapuxeddu seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT ileniadelogu seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT domenicafarci seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT dariopiano seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT aldomanzin seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT matteoceccarelli seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT fabrizioangius seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT marianoandreascorciapino seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors
AT stefanmilenkovic seekingcorrelationamongporinpermeabilitiesandminimuminhibitoryconcentrationsthroughmachinelearningapromisingroutetotheessentialmoleculardescriptors