Machine Learning Algorithm Identifies an Antibiotic Vocabulary for Permeating Gram-Negative Bacteria

  title={Machine Learning Algorithm Identifies an Antibiotic Vocabulary for Permeating Gram-Negative Bacteria},
  author={Rachael Alexandra Mansbach and Inga V. Leus and Jitender Mehla and Cesar A. L{\'o}pez and John K Walker and Valentin V. Rybenkov and Nicolas W. Hengartner and Helen I. Zgurskaya and Sandrasegaram Gnanakaran},
  journal={Journal of chemical information and modeling},
Drug discovery faces a crisis. The industry has used up the "obvious" space in which to find novel drugs for biomedical applications, and productivity is declining. One strategy to combat this is rational approaches to expand the search space without relying on chemical intuition, to avoid rediscovery of similar spaces. In this work, we present proof-of-concept of an approach to rationally identify a "chemical vocabulary" related to a specific drug activity of interest without employing known… 

Figures and Tables from this paper

Data-Driven Derivation of Molecular Substructures That Enhance Drug Activity in Gram-Negative Bacteria

Recurring chemical moieties are found, of a wider range than previously known, that consistently improve activity and it is suggested that this insight can be used to optimize compounds for increased Gram-negative uptake.

Accelerating antibiotic discovery through artificial intelligence

This review describes AI-facilitated advances in the discovery of both small molecule antibiotics and antimicrobial peptides and analyzes uptake of open science best practices in AI-driven antibiotic discovery and argues for openness and reproducibility as a means of accelerating preclinical research.

Property space mapping of Pseudomonas aeruginosa permeability to small molecules

This study developed an approach to analyze the permeation of compounds into Gram-negative bacteria and applied it to Pseudomonas aeruginosa, an important human pathogen notorious for resistance to multiple antibiotics.

Machine Learning in Antibacterial Drug Design

This review focuses on the latest machine learning approaches used in the discovery of new antibacterial agents and targets, covering both small molecules and antibacterial peptides.

Challenges in Drug Discovery for Intracellular Bacteria

It is believed drug discovery against intracellular bacterial pathogens can be advanced significantly by overcoming the above hurdles.

Artificial Intelligence and Antibiotic Discovery

Cheaper and faster research can be achieved through algorithms that identify hit compounds, thereby further accelerating the development of new antibiotics, which represents a vital step in solving the current antibiotic crisis.

Predictive Rules of Efflux Inhibition and Avoidance in Pseudomonas aeruginosa

The identified predictors of efflux avoidance and inhibition will enable the discovery and optimization of antibacterial agents suitable for treatment of P. aeruginosa infections and pave the way for development of compounds with the desired efflux interface properties.

Application of Artificial Intelligence and Machine Learning in Drug Discovery.

  • R. Gupta
  • Biology, Computer Science
    Methods in molecular biology
  • 2022
This chapter would provide an overview of these methods and how they have been applied across various work streams, e.g., generative chemistry, ADMET prediction, retrosynthetic analysis, etc within drug discovery process and attempt to provide caution and pit falls in utilizing these methods blindly while summarizing challenges and limitations.

Outer membrane permeability: Antimicrobials and diverse nutrients bypass porins in Pseudomonas aeruginosa

Porin-independent permeation of antibiotics through the outer-membrane lipid bilayer was hampered by carboxylate groups, consistent with nutrient data, and challenge common assumptions about the role of porins.

The Whole Is Bigger than the Sum of Its Parts: Drug Transport in the Context of Two Membranes with Active Efflux.

This review surveys key experimental and computational approaches to the investigation of transport by individual translocators and in whole cells, summarizes key findings from these studies and outlines implications for antibiotic discovery.



Predictive compound accumulation rules yield a broad-spectrum antibiotic

These guidelines were then applied to convert deoxynybomycin, a natural product that is active only against Gram-positive organisms, into an antibiotic with activity against a diverse panel of multi-drug-resistant Gram-negative pathogens.

Chemoinformatics for medicinal chemistry: in silico model to enable the discovery of potent and safer anti-cocci agents.

A chemoinformatic model for simultaneous prediction of anti-cocci activities, and profiles involving absorption, distribution, metabolism, elimination and toxicity (ADMET) can be used as powerful tool for virtual screening of promising anti- cocci agents.

Identification of Novel Antibacterials Using Machine Learning Techniques

An efficient in silico model able to find compounds that have plenty of chances to exhibit antibacterial activity is developed and several compounds showed an outstanding antibacterial potency and were identified as translation machinery inhibitors in vitro and in vivo.

A Gestalt approach to Gram-negative entry.

  • L. Silver
  • Biology
    Bioorganic & medicinal chemistry
  • 2016

The challenge of converting Gram‐positive‐only compounds into broad‐spectrum antibiotics

Looking back through 50+ years of antibacterial research and 1000s of derivatives is looked at, suggesting that the eNTRy rules may provide an actionable and general roadmap for the conversion of Gram‐positive‐only compounds into broad‐spectrum antibiotics.

Molecular Properties That Define the Activities of Antibiotics in Escherichia coli and Pseudomonas aeruginosa.

This study used Pseudomonas aeruginosa and Escherichia coli strains with controllable permeability barriers, achieved through hyperporination of the OMs and varied efflux capacities, to evaluate the contributions of each of the barriers to protection from antibacterials.

Fragments: where are we now?

An overview of current progress in fragment library design, fragment to lead optimisation, on the advancement in techniques used for screening and on the future opportunities and challenges in this field are given.

Speeding up Early Drug Discovery in Antiviral Research: A Fragment-Based in Silico Approach for the Design of Virtual Anti-Hepatitis C Leads.

This work reports the first multitasking model for quantitative structure-biological effect relationships (mtk-QSBER), focused on the simultaneous exploration of anti-HCV activity and in vitro safety profiles related to the absorption, distribution, metabolism, elimination, and toxicity (ADMET).

De novo computational design of compounds virtually displaying potent antibacterial activity and desirable in vitro ADMET profiles

In this work, we introduce the first multitasking model for quantitative structure-biological effect relationships focused on the simultaneous exploration of antibacterial activity against