scholarly journals DeepARG: A deep learning approach for predicting antibiotic resistance genes from metagenomic data

2017 ◽  
Author(s):  
G. A. Arango-Argoty ◽  
E. Garner ◽  
A. Pruden ◽  
L. S. Heath ◽  
P. Vikesland ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Genes ◽  
Agricultural Waste ◽  
Antibiotic Resistance Gene ◽  
False Negative ◽  
Antibiotic Resistance Genes ◽  
Direct Access ◽  
Metagenomic Data ◽  
Community Research

ABSTRACTGrowing concerns regarding increasing rates of antibiotic resistance call for global monitoring efforts. Monitoring of environmental media (e.g., wastewater, agricultural waste, food, and water) is of particular interest as these media can serve as sources of potential novel antibiotic resistance genes (ARGs), as hot spots for ARG exchange, and as pathways for the spread of ARGs and human exposure. Next-generation sequence-based monitoring has recently enabled direct access and profiling of the total metagenomic DNA pool, where ARGs are identified or predicted based on the “best hits” of homology searches against existing databases. Unfortunately, this approach tends to produce high rates of false negatives. To address such limitations, we propose here a deep leaning approach, taking into account a dissimilarity matrix created using all known categories of ARGs. Two models, deepARG-SS and deepARG-LS, were constructed for short read sequences and full gene length sequences, respectively. Performance evaluation of the deep learning models over 30 classes of antibiotics demonstrates that the deepARG models can predict ARGs with both high precision (>0.97) and recall (>0.90) for most of the antibiotic resistance categories. The models show advantage over the traditional best hit approach by having consistently much lower false negative rates and thus higher overall recall (>0.9). As more data become available for under-represented antibiotic resistance categories, the deepARG models’ performance can be expected to be further enhanced due to the nature of the underlying neural networks. The deepARG models are available both in command line version and via a Web server at http://bench.cs.vt.edu/deeparg. Our newly developed ARG database, deepARG-DB, containing predicted ARGs with high confidence and high degree of manual curation, greatly expands the current ARG repository. DeepARG-DB can be downloaded freely to benefit community research and future development of antibiotic resistance-related resources.AbbreviationsARGantibiotic resistance gene

scholarly journals DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data

Microbiome ◽  
2018 ◽  
Vol 6 (1) ◽  
Author(s):  
Gustavo Arango-Argoty ◽  
Emily Garner ◽  
Amy Pruden ◽  
Lenwood S. Heath ◽  
Peter Vikesland ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Genes ◽  
Antibiotic Resistance Genes ◽  
Metagenomic Data ◽  
Learning Approach

scholarly journals Ontology-Aware Deep Learning Enables Novel Antibiotic Resistance Gene Discovery Towards Comprehensive Profiling of ARGs

2021 ◽  
Author(s):  
Yuguo Zha ◽  
Cheng Chen ◽  
Qihong Jiao ◽  
Xiaomei Zeng ◽  
Xuefeng Cui ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Gene ◽  
Resistance Genes ◽  
Antibiotic Resistance Gene ◽  
Antibiotic Resistance Genes ◽  
Oral Microbiome ◽  
Gram Positive Bacteria ◽  
Wet Lab ◽  
Deep Learning Model

Antibiotic resistance genes (ARGs) have emerged in pathogens and spread faster than expected, arousing a worldwide concern. Current methods are suitable mainly for the discovery of close homologous ARGs and have limited utility for discovery of novel ARGs, thus rendering the profiling of ARGs incomprehensive. Here, an ontology-aware deep learning model, ONN4ARG (http://onn4arg.xfcui.com/), is proposed for the discovery of novel ARGs based on multi-level annotations. Experiments based on billions of candidate microbial genes collected from various environments show the superiority of ONN4ARG in comprehensive ARG profiling. Enrichment analyses show that ARGs are both environment-specific and host-specific. For example, resistance genes for rifamycin, which is an important antibacterial agent active against gram-positive bacteria, are enriched in Actinobacteria and in soil environment. Case studies verified ONN4ARG's ability for novel ARG discovery. For example, a novel streptomycin resistance gene was discovered from oral microbiome samples and validated through wet-lab experiments. ONN4ARG provides a complete picture of the prevalence of ARGs in microbial communities as well as guidance for detection and reduction of the spread of resistance genes.

scholarly journals Metagenomics Analysis Reveals the Microbial Communities, Antimicrobial Resistance Gene Diversity and Potential Pathogen Transmission Risk of Two Different Landfills in China

Diversity ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 230
Author(s):  
Shan Wan ◽  
Min Xia ◽  
Jie Tao ◽  
Yanjun Pang ◽  
Fugen Yu ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Microbial Communities ◽  
Resistance Gene ◽  
Resistance Genes ◽  
Gene Diversity ◽  
Antibiotic Resistance Gene ◽  
Antibiotic Resistance Genes ◽  
Pathogen Transmission ◽  
Transmission Risk ◽  
Antimicrobial Resistance Gene

In this study, we used a metagenomic approach to analyze microbial communities, antibiotic resistance gene diversity, and human pathogenic bacterium composition in two typical landfills in China. Results showed that the phyla Proteobacteria, Bacteroidetes, and Actinobacteria were predominant in the two landfills, and archaea and fungi were also detected. The genera Methanoculleus, Lysobacter, and Pseudomonas were predominantly present in all samples. sul2, sul1, tetX, and adeF were the four most abundant antibiotic resistance genes. Sixty-nine bacterial pathogens were identified from the two landfills, with Klebsiella pneumoniae, Bordetella pertussis, Pseudomonas aeruginosa, and Bacillus cereus as the major pathogenic microorganisms, indicating the existence of potential environmental risk in landfills. In addition, KEGG pathway analysis indicated the presence of antibiotic resistance genes typically associated with human antibiotic resistance bacterial strains. These results provide insights into the risk of pathogens in landfills, which is important for controlling the potential secondary transmission of pathogens and reducing workers’ health risk during landfill excavation.

scholarly journals HMD-ARG: hierarchical multi-task deep learning for annotating antibiotic resistance genes

Microbiome ◽  
2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Yu Li ◽  
Zeling Xu ◽  
Wenkai Han ◽  
Huiluo Cao ◽  
Ramzan Umarov ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Genes ◽  
Antibiotic Resistance Genes ◽  
Third Party ◽  
Superior Performance ◽  
Beta Lactamase ◽  
Learning Framework ◽  
Sequence Encoding ◽  
Global Threat

Abstract Background The spread of antibiotic resistance has become one of the most urgent threats to global health, which is estimated to cause 700,000 deaths each year globally. Its surrogates, antibiotic resistance genes (ARGs), are highly transmittable between food, water, animal, and human to mitigate the efficacy of antibiotics. Accurately identifying ARGs is thus an indispensable step to understanding the ecology, and transmission of ARGs between environmental and human-associated reservoirs. Unfortunately, the previous computational methods for identifying ARGs are mostly based on sequence alignment, which cannot identify novel ARGs, and their applications are limited by currently incomplete knowledge about ARGs. Results Here, we propose an end-to-end Hierarchical Multi-task Deep learning framework for ARG annotation (HMD-ARG). Taking raw sequence encoding as input, HMD-ARG can identify, without querying against existing sequence databases, multiple ARG properties simultaneously, including if the input protein sequence is an ARG, and if so, what antibiotic family it is resistant to, what resistant mechanism the ARG takes, and if the ARG is an intrinsic one or acquired one. In addition, if the predicted antibiotic family is beta-lactamase, HMD-ARG further predicts the subclass of beta-lactamase that the ARG is resistant to. Comprehensive experiments, including cross-fold validation, third-party dataset validation in human gut microbiota, wet-experimental functional validation, and structural investigation of predicted conserved sites, demonstrate not only the superior performance of our method over the state-of-art methods, but also the effectiveness and robustness of the proposed method. Conclusions We propose a hierarchical multi-task method, HMD-ARG, which is based on deep learning and can provide detailed annotations of ARGs from three important aspects: resistant antibiotic class, resistant mechanism, and gene mobility. We believe that HMD-ARG can serve as a powerful tool to identify antibiotic resistance genes and, therefore mitigate their global threat. Our method and the constructed database are available at http://www.cbrc.kaust.edu.sa/HMDARG/.

scholarly journals Antimicrobial Resistance and CRISPR Typing Among Salmonella Isolates From Poultry Farms in China

2021 ◽  
Vol 12 ◽  
Author(s):  
Cui Li ◽  
Yulong Wang ◽  
Yufeng Gao ◽  
Chao Li ◽  
Boheng Ma ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Resistance Genes ◽  
Antibiotic Resistance Gene ◽  
Antibiotic Resistance Genes ◽  
Direct Repeat ◽  
Epidemiological Data ◽  
Multidrug Resistant ◽  
Typing Method ◽  
Crispr Locus ◽  
Research Areas

Although knowledge of the clustered regularly interspaced short palindromic repeat (CRISPR)-Cas system has been applied in many research areas, comprehensive studies of this system in Salmonella, particularly in analysis of antibiotic resistance, have not been reported. In this work, 75 Salmonella isolates obtained from broilers or broilers products were characterized to determine their antimicrobial susceptibilities, antibiotic resistance gene profiles, and CRISPR array diversities, and genotyping was explored. In total, 80.00% (60/75) of the strains were multidrug resistant, and the main pattern observed in the isolates was CN-AZM-AMP-AMC-CAZ-CIP-ATM-TE-SXT-FOS-C. The resistance genes of streptomycin (aadA), phenicol (floR-like and catB3-like), β-lactams (blaTEM, blaOXA, and blaCTX), tetracycline [tet(A)-like], and sulfonamides (sul1 and sul2) appeared at higher frequencies among the corresponding resistant isolates. Subsequently, we analyzed the CRISPR arrays and found 517 unique spacer sequences and 31 unique direct repeat sequences. Based on the CRISPR spacer sequences, we developed a novel typing method, CRISPR locus three spacer sequences typing (CLTSST), to help identify sources of Salmonella outbreaks especially correlated with epidemiological data. Compared with multi-locus sequence typing (MLST), conventional CRISPR typing (CCT), and CRISPR locus spacer pair typing (CLSPT), discrimination using CLTSST was weaker than that using CCT but stronger than that using MLST and CLSPT. In addition, we also found that there were no close correlations between CRISPR loci and antibiotics but had close correlations between CRISPR loci and antibiotic resistance genes in Salmonella isolates.

scholarly journals Removal of Antibiotic Resistance Gene-Carrying Plasmids from Lactobacillus reuteri ATCC 55730 and Characterization of the Resulting Daughter Strain, L. reuteri DSM 17938

2008 ◽  
Vol 74 (19) ◽  
pp. 6032-6040 ◽  
Author(s):  
Anna Rosander ◽  
Eamonn Connolly ◽  
Stefan Roos
Keyword(s):  
Antibiotic Resistance ◽  
Resistance Genes ◽  
Lactobacillus Reuteri ◽  
Antibiotic Resistance Gene ◽  
Genetically Modify ◽  
Antibiotic Resistance Genes ◽  
Probiotic Strain ◽  
Probiotic Properties ◽  
Food Borne

ABSTRACT The spread of antibiotic resistance in pathogens is primarily a consequence of the indiscriminate use of antibiotics, but there is concern that food-borne lactic acid bacteria may act as reservoirs of antibiotic resistance genes when distributed in large doses to the gastrointestinal tract. Lactobacillus reuteri ATCC 55730 is a commercially available probiotic strain which has been found to harbor potentially transferable resistance genes. The aims of this study were to define the location and nature of β-lactam, tetracycline, and lincosamide resistance determinants and, if they were found to be acquired, attempt to remove them from the strain by methods that do not genetically modify the organism before subsequently testing whether the probiotic characteristics were retained. No known β-lactam resistance genes was found, but penicillin-binding proteins from ATCC 55730, two additional resistant strains, and three sensitive strains of L. reuteri were sequenced and comparatively analyzed. The β-lactam resistance in ATCC 55730 is probably caused by a number of alterations in the corresponding genes and can be regarded as not transferable. The strain was found to harbor two plasmids carrying tet(W) tetracycline and lnu(A) lincosamide resistance genes, respectively. A new daughter strain, L. reuteri DSM 17938, was derived from ATCC 55730 by removal of the two plasmids, and it was shown to have lost the resistances associated with them. Direct comparison of the parent and daughter strains for a series of in vitro properties and in a human clinical trial confirmed the retained probiotic properties of the daughter strain.

scholarly journals Genomic and Functional Analyses of SXT, an Integrating Antibiotic Resistance Gene Transfer Element Derived from Vibrio cholerae

2002 ◽  
Vol 184 (15) ◽  
pp. 4259-4269 ◽  
Author(s):  
John W. Beaber ◽  
Bianca Hochhut ◽  
Matthew K. Waldor
Keyword(s):  
Antibiotic Resistance ◽  
Vibrio Cholerae ◽  
Resistance Genes ◽  
Antibiotic Resistance Gene ◽  
Antibiotic Resistance Genes ◽  
Amino Acid Sequences ◽  
Conjugation System ◽  
Conjugative Transposons ◽  
The One ◽  
Functional Analyses

ABSTRACT SXT is representative of a family of conjugative-transposon-like mobile genetic elements that encode multiple antibiotic resistance genes. In recent years, SXT-related conjugative, self-transmissible integrating elements have become widespread in Asian Vibrio cholerae. We have determined the 100-kb DNA sequence of SXT. This element appears to be a chimera composed of transposon-associated antibiotic resistance genes linked to a variety of plasmid- and phage-related genes, as well as to many genes from unknown sources. We constructed a nearly comprehensive set of deletions through the use of the one-step chromosomal gene inactivation technique to identify SXT genes involved in conjugative transfer and chromosomal excision. SXT, unlike other conjugative transposons, utilizes a conjugation system related to that encoded by the F plasmid. More than half of the SXT genome, including the composite transposon-like structure that contains its antibiotic resistance genes, was not required for its mobility. Two SXT loci, designated setC and setD, whose predicted amino acid sequences were similar to those of the flagellar regulators FlhC and FlhD, were found to encode regulators that activate the transcription of genes required for SXT excision and transfer. Another locus, designated setR, whose gene product bears similarity to lambdoid phage CI repressors, also appears to regulate SXT gene expression.

scholarly journals Prediction of antibiotic-resistance genes occurrence at a recreational beach with deep learning models

2021 ◽  
pp. 117001
Author(s):  
Jiyi Jang ◽  
Ather Abbas ◽  
Minjeong Kim ◽  
Jingyeong Shin ◽  
Young Mo Kim ◽  
...  
Keyword(s):  
Antibiotic Resistance ◽  
Deep Learning ◽  
Resistance Genes ◽  
Antibiotic Resistance Genes ◽  
Learning Models ◽  
Recreational Beach
Sign in / Sign up

Export Citation Format

Share Document