Machine learning-powered antibiotics phenotypic drug discovery

@article{Zoffmann2019MachineLA,
  title={Machine learning-powered antibiotics phenotypic drug discovery},
  author={Sannah Zoffmann and Maarten Vercruysse and Fethallah Benmansour and Andreas Maunz and Luise Wolf and Rita Blum Marti and Tobias Heckel and Haiyuan Ding and Hoa Hue Truong and Michael Prummer and Roland Schmucki and Clive Mason and Kenneth Bradley and Asha Ivy Jacob and Christian D. Lerner and Andrea Araujo Del Rosario and Mark M. Burcin and Kurt E. Amrein and Marco Prunotto},
  journal={Scientific Reports},
  year={2019},
  volume={9}
}
Identification of novel antibiotics remains a major challenge for drug discovery. The present study explores use of phenotypic readouts beyond classical antibacterial growth inhibition adopting a combined multiparametric high content screening and genomic approach. Deployment of the semi-automated bacterial phenotypic fingerprint (BPF) profiling platform in conjunction with a machine learning-powered dataset analysis, effectively allowed us to narrow down, compare and predict compound mode of… 

Expanding the search for small-molecule antibacterials by multidimensional profiling

TLDR
How multidimensional small-molecule profiling and the ever-increasing computing power are accelerating the discovery of unconventional antibacterials capable of bypassing resistance and exploiting synergies with established antibacterial treatments and with protective host mechanisms is discussed.

Technologies for High-Throughput Identification of Antibiotic Mechanism of Action

TLDR
Techniques with throughput suitable to screen large libraries and sufficient sensitivity to distinguish MOA were reviewed, and new and reinvigorated phenotypic assays bring renewed hope in the discovery of a new generation of antibiotics.

The application of machine learning techniques to innovative antibacterial discovery and development

TLDR
This review covers some of the applications of MLT in medicinal chemistry, focusing on the development of new antibiotics, the prediction of resistance and its mechanisms, and the main advantages and disadvantages and the major trends from studies over the past 5 years.

Machine learning in mass spectrometry: A MALDI-TOF MS approach to phenotypic antibacterial screening.

TLDR
It is shown that antibacterial effects can be identified and classified in a label-free, high-throughput manner using wild-type Escherichia coli and Staphylococcus aureus cells at variable levels of target engagement.

Simultaneous elucidation of antibiotic mechanism of action and potency with high-throughput Fourier-transform infrared (FTIR) spectroscopy and machine learning.

TLDR
High-throughput Fourier-transform infrared spectroscopy was used to discriminate the MOA of 14 antibiotics at pathway, class, and individual antibiotic level, and sub-inhibitory MOA identification suggests ability to explore grey chemical matter.

Accelerating antibiotic discovery through artificial intelligence

TLDR
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.

Screening of antibacterial compounds with novel structure from the FDA approved drugs using machine learning methods

TLDR
An antibacterial compound predictor was constructed using the support vector machines and random forest methods and the data of the active and inactive antibacterial compounds from the ChEMBL database and showed that both models have excellent prediction performance.

Fast identification of off‐target liabilities in early antibiotic discovery with Fourier‐transform infrared spectroscopy

TLDR
FTIRS mechanism‐based screening assays can be applied for hit discovery and to guide lead optimization during the early stages of antibiotic discovery, and are highly effective at predicting MOA and off‐target liabilities.

A Machine Learning-Based Prediction Platform for P-Glycoprotein Modulators and Its Validation by Molecular Docking

TLDR
The machine-learning approach introduced in this investigation may serve as a tool for the rapid detection of P-gp substrates and inhibitors in large chemical libraries.

Natural products discovery and potential for new antibiotics.

References

SHOWING 1-10 OF 38 REFERENCES

Bacterial cytological profiling rapidly identifies the cellular pathways targeted by antibacterial molecules

TLDR
BCP is shown to be a rapid and powerful approach for identifying the cellular pathway affected by antibacterial molecules and it is demonstrated that spirohexenolide A, a spirotetronate that is active against methicillin-resistant Staphylococcus aureus, rapidly collapses the proton motive force.

Challenges of Antibacterial Discovery

  • L. Silver
  • Biology
    Clinical Microbiology Reviews
  • 2011
TLDR
The purpose of this review is to underscore and illustrate those scientific problems unique to the discovery and optimization of novel antibacterial agents that have adversely affected the output of the effort.

Modern approaches in the search for new lead antiparasitic compounds from higher plants.

Higher plants represent a rich source of new molecules with pharmacological properties, which are lead compounds for the development of new drugs. During the last decades, the renewed interest in

Tricyclic GyrB/ParE (TriBE) Inhibitors: A New Class of Broad-Spectrum Dual-Targeting Antibacterial Agents

TLDR
A novel dual-targeting pyrimidoindole inhibitor series with exquisite potency against GyrB and ParE enzymes from a broad range of clinically important pathogens, demonstrating potent, broad-spectrum antibacterial activity against Gram-positive and Gram-negative pathogens of clinical importance.

Antibacterial drug discovery in the resistance era

The looming antibiotic-resistance crisis has penetrated the consciousness of clinicians, researchers, policymakers, politicians and the public at large. The evolution and widespread distribution of

A Diarylquinoline Drug Active on the ATP Synthase of Mycobacterium tuberculosis

TLDR
A diarylquinoline, R207910, is identified that potently inhibits both drug-sensitive and drug-resistant Mycobacterium tuberculosis in vitro and mutants selected in vitro suggest that the drug targets the proton pump of adenosine triphosphate (ATP) synthase.

Incentivising innovation in antibiotic drug discovery and development: progress, challenges and next steps

TLDR
This study finds that incentive programmes are overly committed to early-stage push funding of basic science and preclinical research, while there is limited late-stagePush funding of clinical development and antibiotic sustainability and patient access requirements are poorly integrated into the array of incentive mechanisms.

The chemical space project.

  • J. Reymond
  • Chemistry
    Accounts of chemical research
  • 2015
TLDR
Beyond enumeration, understanding and exploiting GDBs (generated databases) led us to develop methods for virtual screening and visualization of very large databases in the form of a "periodic system of molecules" comprising six different fingerprint spaces, and the MQN- and SMIfp-Mapplet application for exploring color-coded principal component maps of GDB and other large databases.

Regulated Expression of the Escherichia coli lepB Gene as a Tool for Cellular Testing of Antimicrobial Compounds That Inhibit Signal Peptidase I In Vitro

TLDR
The cell-based assay was used to test cellular inhibition of SPase by compounds that inhibit the enzyme in vitro, finding that MD1, MD2, and MD3 are SPase inhibitors with antimicrobial activity against Staphylococcus aureus, although they do not inhibit growth of E. coli.