Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Wong2024 - Cytotoxicity Prediction from Human Cell Lines

ABSTRACT: The authors use a large dataset (>30k) to train an explainable graph-based model to identify potential antibiotics with low cytotoxicity. The model uses a substructure-based approach to explore the chemical space. Using this method, they were able to screen 283 compounds and identify a candidate active against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci. Model Type: Predictive machine learning model. Model Relevance: Prediction of Human cytotoxicity endpoints. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos42ez

SUBMITTER: Zainab Ashimiyu-Abdusalam

PROVIDER: MODEL2405130002 | BioModels | 2024-05-13

REPOSITORIES: BioModels

ACCESS DATA

Json Xml

Publications

Discovery of a structural class of antibiotics with explainable deep learning.

Wong Felix F Zheng Erica J EJ Valeri Jacqueline A JA Donghia Nina M NM Anahtar Melis N MN Omori Satotaka S Li Alicia A Cubillos-Ruiz Andres A Krishnan Aarti A Jin Wengong W Manson Abigail L AL Friedrichs Jens J Helbig Ralf R Hajian Behnoush B Fiejtek Dawid K DK Wagner Florence F FF Soutter Holly H HH Earl Ashlee M AM Stokes Jonathan M JM Renner Lars D LD Collins James J JJ

Nature 20231220 7997

The discovery of novel structural classes of antibiotics is urgently needed to address the ongoing antibiotic resistance crisis<sup>1-9</sup>. Deep learning approaches have aided in exploring chemical spaces<sup>1,10-15</sup>; these typically use black box models and do not provide chemical insights. Here we reasoned that the chemical substructures associated with antibiotic activity learned by neural network models can be identified and used to predict structural classes of antibiotics. We test ...[more]

PMID: 38123686

Similar Datasets

Wong2024 - Discovery of a structural class of antibiotics with explainable deep learning

Project description:The authors use a large dataset (>30k) to train an explainable graph-based model to identify potential antibiotics with low cytotoxicity. The model uses a substructure-based approach to explore the chemical space. Using this method, they were able to screen 283 compounds and identify a candidate active against methicillin-resistant S. aureus (MRSA) and vancomycin-resistant enterococci. Model Type: Predictive machine learning model. Model Relevance: The model predicts the probability of growth inhibition. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos18ie

2024-05-08 | MODEL2405080002 | BioModels

Potential Mechanism of Action of 3'-Demethoxy-6-O-Demethylisoguaiacin on Methicillin-resistant Staphylococcus aureus

Project description:Methicillin-resistant Staphylococcus aureus is one of the major causative agents associated to infections with a high morbidity and mortality in hospitals worldwide. In previous studies, we reported that lignan 3'-demethoxy-6-O-demethylisoguaiacin isolated and characterized from Larrea tridentata showed the best activity towards methicillin-resistant S. aureus. Understanding of mechanism of action of drugs allows design drugs in a better way. Therefore, we employed microarray to obtain gene expression profile of methicillin-resistant S. aureus after exposure to 3'-demethoxy-6-O-demethylisoguaiacin. The results showed that lignan had an effect on cell membrane affecting proteins of the ATP-binding cassette (ABC) transport system causing bacteria death. This study consisted of comparison of isolated RNA of MRSA not treated and MRSA treated with lignan 3'-demethoxy-6-O-demethylisoguaiacin. Both RNAs samples were differentially dyed with Cy3 and Cy5 during cDNA synthesis and hybridized on DNA chip. Afterwards, the chip was scanned in a GenePix 4000B scanner. The resulting gene expression profile was analyzed in databases for functional annotations to find a potential mechanism of the lignan in MRSA.

2015-06-27 | E-GEOD-70309 | biostudies-arrayexpress

Rahman2022 - High throughput antibacterial screening with machine learning.

Project description:Prediction of antimicrobial potential using a dataset of 29537 compounds screened against the antibiotic resistant pathogen Burkholderia cenocepacia. The model uses the Chemprop Direct Message Passing Neural Network (D-MPNN) and has an AUC score of 0.823 for the test set. It has been used to virtually screen the FDA approved drugs as well as a collection of natural product list (>200k compounds) with hit rates of 26% and 12% respectively. Model Type: Predictive machine learning model. Model Relevance: Probability that a compound inhibits bacterial pathogens with a focus on ESKAPE. Model Encoded by: Sarima Chiorlu (Ersilia) Metadata Submitted in BioModels by: Zainab Ashimiyu-Abdusalam Implementation of this model code by Ersilia is available here: https://github.com/ersilia-os/eos5xng

2024-04-22 | MODEL2404080002 | BioModels

Panton-Valentine Leukocidin Does Not Impact Virulence of Community-associated MRSA

Project description:Panton-valentine leukocidin (PVL) has been linked to worldwide emergence of community-associated methicillin resistant Staphylococcus aureus (CA-MRSA) -- its role in virulence in unclear. Here we show that PVL had no effect on global gene expression of prominent CA-MRSA strains nor did it affect bacterial clearance from lungs, spleen and kidneys in a highly discriminatory rabbit bacteremia model. These findings negate a large body of epidemiological research that implicated PVL in CA-MRSA virulence. Keywords: mutant vs wild type in 2 different growth phases grown in 2 different medias

2008-09-12 | GSE8677 | GEO

Global Gene Expression of Methicillin-resistant Staphylococcus aureus USA300 During Human and Mouse Infection

Project description:Little is known about the expression of methicillin-resistant Staphylococcus aureus (MRSA) genes during infection conditions. Here, we described the transcriptome of the clinical MRSA strain USA300 derived from human cutaneous abscesses, and compared it with USA300 bacteria derived from infected kidneys in a mouse model. Remarkable similarity between the transcriptomes allowed us to identify genes encoding multiple proteases and toxins, and iron- and peptide-transporter molecules, which are upregulated in both infections and are likely important for establishment of infection. We also showed that disruption of the global transcriptional regulators agr and sae prevents in vivo upregulation of many toxins and proteases, protecting mice from lethal infection dose, and hinting at the role of these transcriptional regulators in the pathology of MRSA infection.

2015-10-16 | GSE73821 | GEO

RNA-seq of Wildtype Staphylococcus aureus USA300 NRS384

Project description:Methicillin-resistant Staphylococcus aureus (MRSA) infections result in more than 200,000 hospitalizations and 10,000 deaths in the United States each year and remain an important medical challenge. To better understand the transcriptome of Staphylococcus aureus USA300 NRS384, a community-acquired MRSA strain, we have conducted an RNA-Seq experiment on WT samples.

2017-11-15 | GSE102279 | GEO

Proteomic differences in methicillin-sensitive and methicillin-resistant Staphylococcus aureus

Project description:To establish general differences between the protein expression in S. aureus strains, five methicillin sensitive S. aureus (MSSA) strains and five methicillin resistant S. aureus (MRSA) strains were compared both individually and as MSSA and MRSA groups in the absence of antibiotics. Proteins were compared by ultra-performance liquid chromatography-mass spectrometry.

2023-04-25 | PXD021629 | Pride

Proteomic differences between methicillin resistant Staphylococcus aureus showing synergistic effects with cannabinoids

Project description:Methicillin-resistant Staphylococcus aureus (MRSA) is a major human pathogen in both community and health care settings, which causes a wide range of infections. Its resistance to β-lactam antibiotics and methicillin in particular, greatly complicates treatment options and success rate due to the limited number of antibiotics with activity against MRSA. To further the development of alternative therapeutics, the mechanisms that mediate antibiotic resistance in MRSA need to be fully understood. Cannabinoid compounds including cannabidiol (CBD), tetrahydrocannabinol (THC) and cannabinol (CBN) have shown promise as potential antibiotic adjuvants. In the present study, MRSA cells were subjected to antibiotic stress from methicillin in combination with three cannabinoid compounds, and subsequently analysed using metaproteomics to assess the metabolic response. Subjecting MRSA to methicillin made the cells more viable and increased their energy production, as well as upregulation of penicillin-binding protein 2 (PBP2). The cannabinoids all showed antimicrobial activity against MRSA, and inhibited the energy production of the cells as well as PBP2 when used in combination with methicillin. Furthermore, all three cannabinoid compounds inhibited resistance mechanisms in MRSA, resulting in a decrease in the minimum inhibitory concentration (MIC) of methicillin when used in combination.

2022-01-18 | PXD024244 | Pride

Role of the accessory gene regulator agr in community-associated MRSA pathogenesis

Project description:The success of community-associated methicillin-resistant Staphylococcus aureus (CA-MRSA) as pathogens is due to a combination of antibiotic resistance with high virulence. However, evolution of the exceptional virulence potential of CA-MRSA is not understood. Our previous study indicated that differential gene expression contributes substantially to this process. Thus, we here investigated the role of the pivotal virulence gene regulatory system agr in the most prevalent CA-MRSA strain USA300. Using a mouse subcutaneous infection model, we show that agr is essential for the development of CA-MRSA skin infections, the most frequent manifestation of disease caused by CA-MRSA. Furthermore, genome-wide analysis of gene expression revealed significant differences in agr-dependent virulence gene regulation between CA-MRSA, HA-MRSA, and laboratory strains. Our findings demonstrate that agr functionality is critical for CA-MRSA disease and indicate that an adaptation of the agr regulon to optimize expression of a broad set of virulence determinants may have contributed to the evolution of exceptionally pronounced virulence of CA-MRSA strains. Keywords: wild type vs mutant Wild type vs mutant agr strains.

2011-03-29 | E-GEOD-18793 | biostudies-arrayexpress

Loratadine and Compound 8's effects in MRSA USA100

Project description:Methicillin-resistant Staphylococcus aureus (MRSA) is a major threat to human health. Rather than depend on creating new antibiotics (to which bacteria will eventually become resistant), we are employing antibiotic adjuvants that potentiation existing antibiotics. Based on our previous work, loratadine, the FDA-approvide antihistamine, effectively potentiates cell-wall active antibiotics in multiple strains of MRSA. Furthermore, loratadine and oxacillin helped disrupt preformed biofilms and stop them from initially forming in vitro. A structurally related brominated carbazole, compound 8, showed similar antibiotic potentiation. To gain biological insight into these transcriptome disruptors in a more clinically relevant strain of MRSA, we used RNA-seq on treated MRSA USA100 cultures.

2024-05-15 | GSE267020 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data