Browse
Submit Data
Databases
API
Help

Dataset Information

27 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

A convolutional neural network highlights mutations relevant to antimicrobial resistance in Mycobacterium tuberculosis.

ABSTRACT: Long diagnostic wait times hinder international efforts to address antibiotic resistance in M. tuberculosis. Pathogen whole genome sequencing, coupled with statistical and machine learning models, offers a promising solution. However, generalizability and clinical adoption have been limited by a lack of interpretability, especially in deep learning methods. Here, we present two deep convolutional neural networks that predict antibiotic resistance phenotypes of M. tuberculosis isolates: a multi-drug CNN (MD-CNN), that predicts resistance to 13 antibiotics based on 18 genomic loci, with AUCs 82.6-99.5% and higher sensitivity than state-of-the-art methods; and a set of 13 single-drug CNNs (SD-CNN) with AUCs 80.1-97.1% and higher specificity than the previous state-of-the-art. Using saliency methods to evaluate the contribution of input sequence features to the SD-CNN predictions, we identify 18 sites in the genome not previously associated with resistance. The CNN models permit functional variant discovery, biologically meaningful interpretation, and clinical applicability.

SUBMITTER: Green AG

PROVIDER: S-EPMC9250494 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Diagnostic Performance of a Convolutional Neural Network for Diminutive Colorectal Polyp Recognition

Project description:Interventions: None Primary outcome(s): The primary outcome of the study is the accuracy of the CAD-CNN system for predicting histology of diminutive colorectal polyps (1-5mm) compared with the accuracy of the prediction of the endoscopist. Both the CAD-CNN system and the endoscopist will use NBI for their predictions. Accuracy is defined as the percentage of correctly predicted optical diagnoses of the CAD-CNN system and/or endoscopist compared to the gold standard pathology. For the calculation of the accuracy, adenomas and SSLs will be dichotomised as neoplastic polyps, while HPs and other non-neoplastic histology are considered non-neoplastic. Study Design: N/A: single arm study, Open (masking not used), N/A , unknown, Other

| 2443187 | ecrin-mdr-crc

Molecular analysis of pyrazinamide resistance in Mycobacterium tuberculosis in Vietnam highlights the high rate of pyrazinamide resistance-associated mutations in clinical isolates.

Project description:Pyrazinamide (PZA) is a key antibiotic in current anti-tuberculosis regimens. Although the WHO has stressed the urgent need to obtain data on PZA resistance, in high tuberculosis burden countries, little is known about the level of PZA resistance, the genetic basis of such resistance or its link with Mycobacterium tuberculosis families. In this context, this study assessed PZA resistance through the molecular analysis of 260 Vietnamese M. tuberculosis isolates. First-line drug susceptibility testing, pncA gene sequencing, spoligotyping and mycobacterial interspersed repetitive units-variable number of tandem repeats (MIRU-VNTR) typing were performed. Overall, the pncA mutation frequency was 38.1% (99 out of 260 isolates) but was higher than 72% (89 out of 123 isolates) in multidrug and quadruple-drug resistant isolates. Many different pncA mutations (71 types) were detected, of which 55 have been previously described and 50 were linked to PZA resistance. Among the 16 novel mutations, 14 are likely to be linked to PZA resistance because of their mutation types or codon positions. Genotype analysis revealed that PZA resistance can emerge in any M. tuberculosis cluster or family, although the mutation frequency was the highest in Beijing family isolates (47.7%, 62 out of 130 isolates). These data highlight the high rate of PZA resistance-associated mutations in M. tuberculosis clinical isolates in Vietnam and bring into question the use of PZA for current and future treatment regimens of multidrug-resistant tuberculosis without PZA resistance testing.

| S-EPMC5658769 | biostudies-literature

Emergence of phenotypic and genotypic antimicrobial resistance in Mycobacterium tuberculosis.

Project description:Concentration dependency of phenotypic and genotypic isoniazid-rifampicin resistance emergence was investigated to obtain a mechanistic understanding on how anti-mycobacterial drugs facilitate the emergence of bacterial populations that survive throughout treatment. Using static kill curve experiments, observing two evolution cycles, it was demonstrated that rifampicin resistance was the result of non-specific mechanisms and not associated with accumulation of drug resistance encoding SNPs. Whereas, part of isoniazid resistance could be accounted for by accumulation of specific SNPs, which was concentration dependent. Using a Hollow Fibre Infection Model it was demonstrated that emergence of resistance did not occur at concentration-time profiles mimicking the granuloma. This study showed that disentangling and quantifying concentration dependent emergence of resistance provides an improved rational for drug and dose selection although further work to understand the underlying mechanisms is needed to improve the drug development pipeline.

| S-EPMC9742156 | biostudies-literature

Ethambutol resistance in Mycobacterium tuberculosis: critical role of embB mutations.

Project description:Ethambutol [(S,S')-2,2'-(ethylenediimino)di-1-butanol; EMB], is a first-line drug used to treat tuberculosis. To gain insight into the molecular basis of EMB resistance, we characterized the 10-kb embCAB locus in 16 EMB-resistant and 3 EMB-susceptible genetically distinct Mycobacterium tuberculosis strains from diverse localities by automated DNA sequencing and single-stranded conformation polymorphism analysis. All 19 organisms had virtually identical sequences for the entire 10-kb region. Eight EMB-resistant organisms had mutations located in codon 306 of embB that resulted in the replacement of the wild-type Met residue with Ile or Val. Automated sequence analysis of the 5' region (1,892 bp) of embB in an additional 69 EMB-resistant and 30 EMB-susceptible M. tuberculosis isolates from diverse geographic localities and representing 70 distinct IS6110 fingerprints confirmed the unique association of substitutions in amino acid residue 306 of EmbB with EMB resistance. Six other embB nucleotide substitutions resulting in four amino acid replacements were uniquely found in resistant strains. Sixty-nine percent of epidemiologically unassociated EMB-resistant organisms had an amino acid substitution not found in susceptible strains, and most (89%) replacements occurred at amino acid residue 306 of EmbB. For strains with the Met306Leu or Met306Val replacements EMB MICs were generally higher (40 microg/ml) than those for organisms with Met306Ile substitutions (20 microg/ml). The data are consistent with the idea that amino acid substitutions in EmbB alter the drug-protein interaction and thereby cause EMB resistance.

| S-EPMC163984 | biostudies-other

Reconstitution of a Mycobacterium tuberculosis proteostasis network highlights essential cofactor interactions with chaperone DnaK.

Project description:During host infection, Mycobacterium tuberculosis (Mtb) encounters several types of stress that impair protein integrity, including reactive oxygen and nitrogen species and chemotherapy. The resulting protein aggregates can be resolved or degraded by molecular machinery conserved from bacteria to eukaryotes. Eukaryotic Hsp104/Hsp70 and their bacterial homologs ClpB/DnaK are ATP-powered chaperones that restore toxic protein aggregates to a native folded state. DnaK is essential in Mycobacterium smegmatis, and ClpB is involved in asymmetrically distributing damaged proteins during cell division as a mechanism of survival in Mtb, commending both proteins as potential drug targets. However, their molecular partners in protein reactivation have not been characterized in mycobacteria. Here, we reconstituted the activities of the Mtb ClpB/DnaK bichaperone system with the cofactors DnaJ1, DnaJ2, and GrpE and the small heat shock protein Hsp20. We found that DnaJ1 and DnaJ2 activate the ATPase activity of DnaK differently. A point mutation in the highly conserved HPD motif of the DnaJ proteins abrogates their ability to activate DnaK, although the DnaJ2 mutant still binds to DnaK. The purified Mtb ClpB/DnaK system reactivated a heat-denatured model substrate, but the DnaJ HPD mutants inhibited the reaction. Finally, either DnaJ1 or DnaJ2 is required for mycobacterial viability, as is the DnaK-activating activity of a DnaJ protein. These studies lay the groundwork for strategies to target essential chaperone-protein interactions in Mtb, the leading cause of death from a bacterial infection.

| S-EPMC5150378 | biostudies-literature

AtacWorks: A deep convolutional neural network toolkit for epigenomics

Project description:We introduce AtacWorks (https://github.com/clara-genomics/AtacWorks), a method to denoise and identify accessible chromatin regions from low-coverage or low-quality ATAC-seq data. AtacWorks uses a deep neural network to learn a mapping between noisy ATAC-seq data and corresponding higher-coverage or higher-quality data. We apply this approach to as few as 50 hematopoietic stem cells to identify regulatory elements that are differentially-accessible between rare lineage-primed cell subpopulations.

2021-01-11 | GSE147113 | GEO

Two Novel katG Mutations Conferring Isoniazid Resistance in Mycobacterium tuberculosis.

Project description:Tuberculosis (TB), an infectious disease caused by Mycobacterium tuberculosis, is among the top 10 leading causes of death worldwide. The treatment course for TB is challenging; it requires antibiotic administration for at least 6 months, and bacterial drug resistance makes treatment even more difficult. Understanding the mechanisms of resistance is important for improving treatment. To investigate new mechanisms of isoniazid (INH) resistance, we obtained three INH-resistant (INH-R) M. tuberculosis clinical isolates collected by the Taiwan Centers for Disease Control (TCDC) and sequenced genes known to harbor INH resistance-conferring mutations. Then, the relationship between the mutations and INH resistance of these three INH-R isolates was investigated. Sequencing of the INH-R isolates identified three novel katG mutations resulting in R146P, W341R, and L398P KatG proteins, respectively. To investigate the correlation between the observed INH-R phenotypes of the clinical isolates and these katG mutations, wild-type katG from H37Rv was expressed on a plasmid (pMN437-katG) in the isolates, and their susceptibilities to INH were determined. The plasmid expressing H37Rv katG restored INH susceptibility in the two INH-R isolates encoding the W341R KatG and L398P KatG proteins. In contrast, no phenotypic change was observed in the KatG R146P isolate harboring pMN437-katG. H37Rv isogenic mutant with W341R KatG or L398P KatG was further generated. Both showed resistant to INH. In conclusion, W341R KatG and L398P KatG conferred resistance to INH in M. tuberculosis, whereas R146P KatG did not affect the INH susceptibility of M. tuberculosis.

| S-EPMC7374161 | biostudies-literature

Neural encoding with unsupervised spiking convolutional neural network.

Project description:Accurately predicting the brain responses to various stimuli poses a significant challenge in neuroscience. Despite recent breakthroughs in neural encoding using convolutional neural networks (CNNs) in fMRI studies, there remain critical gaps between the computational rules of traditional artificial neurons and real biological neurons. To address this issue, a spiking CNN (SCNN)-based framework is presented in this study to achieve neural encoding in a more biologically plausible manner. The framework utilizes unsupervised SCNN to extract visual features of image stimuli and employs a receptive field-based regression algorithm to predict fMRI responses from the SCNN features. Experimental results on handwritten characters, handwritten digits and natural images demonstrate that the proposed approach can achieve remarkably good encoding performance and can be utilized for "brain reading" tasks such as image reconstruction and identification. This work suggests that SNN can serve as a promising tool for neural encoding.

| S-EPMC10462614 | biostudies-literature

Mutations associated with pyrazinamide resistance in pncA of Mycobacterium tuberculosis complex organisms.

Project description:A gene (pncA) with mutations associated with pyrazinamide resistance in Mycobacterium tuberculosis complex members was characterized in 67 pyrazinamide-resistant and 51 pyrazinamide-susceptible isolates recovered from diverse geographic localities and anatomic sites and typed by IS6110 profiling. All pyrazinamide-susceptible organisms had identical pncA alleles. In striking contrast, 72% of the 67 resistant organisms had pncA mutations that altered the primary amino acid sequence of pyrazinamidase. A total of 17 previously undescribed mutations were found, including upstream mutations, missense changes, nucleotide insertions and deletions, and termination mutations. The mutations were arrayed along virtually the entire length of the gene. These data are further evidence that most drug resistance in M. tuberculosis is due to simple mutations occurring in chromosomally encoded genes rather than to acquisition of resistance genes by horizontal transfer events.

| S-EPMC163764 | biostudies-other

Identification of novel mutations associated with clofazimine resistance in Mycobacterium tuberculosis.

Project description:Although clofazimine has been traditionally used to treat leprosy, there is recent interest in using clofazimine for the treatment of MDR-TB and drug-susceptible TB. However, the mechanisms of resistance to clofazimine are poorly understood. Here, we investigated the molecular basis of clofazimine resistance using resistant mutants isolated in vitro.We isolated 96 mutants of Mycobacterium tuberculosis resistant to clofazimine and performed WGS and Sanger sequencing to identify possible mutations associated with clofazimine resistance.We found that 97% (93/96) of clofazimine-resistant mutants had a mutation in rv0678 encoding a transcription repressor for efflux pump MmpL5. Two mutational hot spots at nucleotide positions 193 and 466 in rv0678 accounted for 43.8% (42/96) and 11.5% (11/96) of the mutations, respectively. The previously reported A202G mutation (S68G) in rv0678 occurred less frequently, in 5 of 96 mutants. The remaining 34 mutations were scattered along the entire rv0678 gene. We discovered two new genes (rv1979c and rv2535c) associated with clofazimine resistance in mutants without rv0678 mutations.Mutations in rv0678 are a major mechanism of clofazimine resistance. Our findings provide useful information for the design of new molecular tests for rapid detection of clofazimine resistance. Further studies are needed to address the role of rv1979c and rv2535c in clofazimine resistance and mechanisms of action.

| S-EPMC4539095 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

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