Rapid nanopore sequencing and predictive susceptibility testing of positive blood cultures from intensive care patients with sepsis.

We aimed to evaluate the performance of Oxford Nanopore Technologies (ONT) sequencing from positive blood culture (BC) broths for bacterial identification and antimicrobial susceptibility prediction. Patients with suspected sepsis in four intensive care units were prospectively enrolled. Human-depleted DNA was extracted from positive BC broths and sequenced using ONT (MinION). Species abundance was estimated using Kraken2, and a cloud-based system (AREScloud) provided in silico predictive antimicrobial susceptibility testing (AST) from assembled contigs. Results were compared to conventional identification and phenotypic AST. Species-level agreement between conventional methods and AST predicted from sequencing was 94.2% (49/52), increasing to 100% in monomicrobial infections. In 262 high-quality AREScloud AST predictions across 24 samples, categorical agreement (CA) was 89.3%, with major error (ME) and very major error (VME) rates of 10.5% and 12.1%, respectively. Over 90% CA was achieved for some taxa (e.g., Staphylococcus aureus) but was suboptimal for Pseudomonas aeruginosa. In 470 AST predictions across 42 samples, with both high quality and exploratory-only predictions, overall CA, ME, and VME rates were 87.7%, 8.3%, and 28.4%. VME rates were inflated by false susceptibility calls in a small number of species/antibiotic combinations with few representative resistant isolates. Time to reporting from sequencing could be achieved within 8-16 h from BC positivity. Direct sequencing from positive BC broths is feasible and can provide accurate predictive AST for some species. ONT-based approaches may be faster but significant improvements in accuracy are required before it can be considered for clinical use.IMPORTANCESepsis and bloodstream infections carry a high risk of morbidity and mortality. Rapid identification and susceptibility prediction of causative pathogens, using Nanopore sequencing direct from blood cultures, may offer clinical benefit. We assessed this approach in comparison to conventional phenotypic methods and determined the accuracy of species identification and susceptibility prediction from genomic data. While this workflow holds promise, and performed well for some common bacterial species, improvements in sequencing accuracy and more robust predictive algorithms across a diverse range of organisms are required before this can be considered for clinical use. However, results could be achieved in timeframes that are faster than conventional phenotypic methods.

Metagenomic Antimicrobial Susceptibility Testing from Simulated Native Patient Samples.

Genomic antimicrobial susceptibility testing (AST) has been shown to be accurate for many pathogens and antimicrobials. However, these methods have not been systematically evaluated for clinical metagenomic data. We investigate the performance of in-silico AST from clinical metagenomes (MG-AST). Using isolate sequencing data from a multi-center study on antimicrobial resistance (AMR) as well as shotgun-sequenced septic urine samples, we simulate over 2000 complicated urinary tract infection (cUTI) metagenomes with known resistance phenotype to 5 antimicrobials. Applying rule-based and machine learning-based genomic AST classifiers, we explore the impact of sequencing depth and technology, metagenome complexity, and bioinformatics processing approaches on AST accuracy. By using an optimized metagenomics assembly and binning workflow, MG-AST achieved balanced accuracy within 5.1% of isolate-derived genomic AST. For poly-microbial infections, taxonomic sample complexity and relatedness of taxa in the sample is a key factor influencing metagenomic binning and downstream MG-AST accuracy. We show that the reassignment of putative plasmid contigs by their predicted host range and investigation of whole resistome capabilities improved MG-AST performance on poly-microbial samples. We further demonstrate that machine learning-based methods enable MG-AST with superior accuracy compared to rule-based approaches on simulated native patient samples.

Optimized Method for Bacterial Nucleic Acid Extraction from Positive Blood Culture Broth for Whole-Genome Sequencing, Resistance Phenotype Prediction, and Downstream Molecular Applications.

The application of direct metagenomic sequencing from positive blood culture broth may solve the challenges of sequencing from low-bacterial-load blood samples in patients with sepsis. Forty prospectively collected blood culture broth samples growing Gram-negative bacteria were extracted using commercially available kits to achieve high-quality DNA. Species identification via metagenomic sequencing and susceptibility prediction via a machine-learning algorithm (AREScloud) were compared to conventional methods and other rapid diagnostic platforms (Accelerate Pheno and blood culture identification [BCID] panel). A two-kit method (using MolYsis Basic and Qiagen DNeasy UltraClean kits) resulted in optimal extractions. Taxonomic profiling by direct metagenomic sequencing matched conventional identification in 38/40 (95%) samples. In two polymicrobial samples, a second organism was missed by sequencing. Prediction models were able to accurately infer susceptibility profiles for 6 common pathogens against 17 antibiotics, with an overall categorical agreement (CA) of 95% (increasing to >95% for 5/6 of the most common pathogens, if Klebsiella oxytoca was excluded). The performance of whole-genome sequencing (WGS)-antimicrobial susceptibility testing (AST) was suboptimal for uncommon pathogens (e.g., Elizabethkingia) and some ß-lactamase inhibitor antibiotics (e.g., ticarcillin-clavulanate). The time to pathogen identification was the fastest with BCID (1 h from blood culture positivity). Accelerate Pheno provided a susceptibility result in approximately 8 h. Illumina-based direct sequencing methods provided results in time frames similar to those of conventional culture-based methods. Direct metagenomic sequencing from blood cultures for pathogen detection and susceptibility prediction is feasible. Additional work is required to optimize algorithms for uncommon species and complex resistance genotypes as well as to streamline methods to provide more rapid results.

Genome-Wide Mutation Scoring for Machine-Learning-Based Antimicrobial Resistance Prediction.

The prediction of antimicrobial resistance (AMR) based on genomic information can improve patient outcomes. Genetic mechanisms have been shown to explain AMR with accuracies in line with standard microbiology laboratory testing. To translate genetic mechanisms into phenotypic AMR, machine learning has been successfully applied. AMR machine learning models typically use nucleotide k-mer counts to represent genomic sequences. While k-mer representation efficiently captures sequence variation, it also results in high-dimensional and sparse data. With limited training data available, achieving acceptable model performance or model interpretability is challenging. In this study, we explore the utility of feature engineering with several biologically relevant signals. We propose to predict the functional impact of observed mutations with PROVEAN to use the predicted impact as a new feature for each protein in an organism's proteome. The addition of the new features was tested on a total of 19,521 isolates across nine clinically relevant pathogens and 30 different antibiotics. The new features significantly improved the predictive performance of trained AMR models for Pseudomonas aeruginosa, Citrobacter freundii, and Escherichia coli. The balanced accuracy of the respective models of those three pathogens improved by 6.0% on average.

Predictive Antibiotic Susceptibility Testing by Next-Generation Sequencing for Periprosthetic Joint Infections: Potential and Limitations.

Joint replacement surgeries are one of the most frequent medical interventions globally. Infections of prosthetic joints are a major health challenge and typically require prolonged or even indefinite antibiotic treatment. As multidrug-resistant pathogens continue to rise globally, novel diagnostics are critical to ensure appropriate treatment and help with prosthetic joint infections (PJI) management. To this end, recent studies have shown the potential of molecular methods such as next-generation sequencing to complement established phenotypic, culture-based methods. Together with advanced bioinformatics approaches, next-generation sequencing can provide comprehensive information on pathogen identity as well as antimicrobial susceptibility, potentially enabling rapid diagnosis and targeted therapy of PJIs. In this review, we summarize current developments in next generation sequencing based predictive antibiotic susceptibility testing and discuss potential and limitations for common PJI pathogens.

Learning From Limited Data: Towards Best Practice Techniques for Antimicrobial Resistance Prediction From Whole Genome Sequencing Data.

Antimicrobial resistance prediction from whole genome sequencing data (WGS) is an emerging application of machine learning, promising to improve antimicrobial resistance surveillance and outbreak monitoring. Despite significant reductions in sequencing cost, the availability and sampling diversity of WGS data with matched antimicrobial susceptibility testing (AST) profiles required for training of WGS-AST prediction models remains limited. Best practice machine learning techniques are required to ensure trained models generalize to independent data for optimal predictive performance. Limited data restricts the choice of machine learning training and evaluation methods and can result in overestimation of model performance. We demonstrate that the widely used random k-fold cross-validation method is ill-suited for application to small bacterial genomics datasets and offer an alternative cross-validation method based on genomic distance. We benchmarked three machine learning architectures previously applied to the WGS-AST problem on a set of 8,704 genome assemblies from five clinically relevant pathogens across 77 species-compound combinations collated from public databases. We show that individual models can be effectively ensembled to improve model performance. By combining models via stacked generalization with cross-validation, a model ensembling technique suitable for small datasets, we improved average sensitivity and specificity of individual models by 1.77% and 3.20%, respectively. Furthermore, stacked models exhibited improved robustness and were thus less prone to outlier performance drops than individual component models. In this study, we highlight best practice techniques for antimicrobial resistance prediction from WGS data and introduce the combination of genome distance aware cross-validation and stacked generalization for robust and accurate WGS-AST.

DeepNOG: fast and accurate protein orthologous group assignment.

MOTIVATION: Protein orthologous group databases are powerful tools for evolutionary analysis, functional annotation or metabolic pathway modeling across lineages. Sequences are typically assigned to orthologous groups with alignment-based methods, such as profile hidden Markov models, which have become a computational bottleneck. RESULTS: We present DeepNOG, an extremely fast and accurate, alignment-free orthology assignment method based on deep convolutional networks. We compare DeepNOG against state-of-the-art alignment-based (HMMER, DIAMOND) and alignment-free methods (DeepFam) on two orthology databases (COG, eggNOG 5). DeepNOG can be scaled to large orthology databases like eggNOG, for which it outperforms DeepFam in terms of precision and recall by large margins. While alignment-based methods still provide the most accurate assignments among the investigated methods, computing time of DeepNOG is an order of magnitude lower on CPUs. Optional GPU usage further increases throughput massively. A command-line tool enables rapid adoption by users. AVAILABILITYAND IMPLEMENTATION: Source code and packages are freely available at https://github.com/univieCUBE/deepnog. Install the platform-independent Python program with $pip install deepnog. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.