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.

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.

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.

Preeclampsia, which is a leading cause of maternal and perinatal mortality and morbidity, represents a biologically heterogeneous syndrome. First-trimester screening with the Fetal Medicine Foundation (FMF) competing-risks model for preterm preeclampsia enables earlier identification of at-risk pregnancies, allowing risk reduction through aspirin prophylaxis, but depends on Doppler velocimetry and biochemical measurements that limit scalability and offer limited discrimination for term disease. A unified, molecular first-trimester test capable of stratifying risk across the full clinical spectrum of preeclampsia has not been established. To determine whether multi-modal, tissue-resolved analysis of first-trimester circulating cell-free DNA (cfDNA), obtained during routine noninvasive prenatal testing (NIPT), enables early prediction of both preterm and term preeclampsia. This nested case-control study included 125 singleton pregnancies sampled at 11 to 14 weeks’ gestation after quality control (48 controls, 30 preterm preeclampsia, 47 term preeclampsia). For 80 pregnancies, matched placental villi and maternal buffy coat samples were available to derive tissue reference profiles. Plasma cfDNA underwent multi-modal sequencing using Oxford Nanopore Technologies, enabling tissue-resolved analysis of fragmentomic and epigenetic signatures. Separate ensemble machine-learning classifiers were developed to capture distinct disease pathways for preterm (<37 weeks) and term (≥37 weeks) preeclampsia using stratified 10-fold cross-validation. Model discrimination was evaluated using area under the receiver operating characteristic curve (AUROC), sensitivity at predefined specificity thresholds, and comparison with the FMF first-trimester risk score. A population-level simulation of 100,000 pregnancies, applying incidence point estimates of 2.5% for preterm and 7.5% for term PE, was used to derive predictive values and likelihood ratios. The multi-modal cfDNA classifier achieved an AUROC (95% CI) of 0.85 (0.77–0.91) for preterm preeclampsia and 0.84 (0.76–0.91) for term preeclampsia. The FMF score yielded an AUROC of 0.80 (0.70–0.89) for preterm and 0.53 (0.43–0.63) for term PE. At 80% specificity, cfDNA sensitivity was 70.5% for preterm and 72.1% for term preeclampsia, demonstrating improved discrimination for term disease compared with FMF screening. In simulated population-level analysis, positive likelihood ratios were 4.25 (preterm) and 3.83 (term), with negative likelihood ratios of 0.21 and 0.34, respectively, supporting meaningful post-test risk stratification and strong rule-out performance. First-trimester multi-modal, tissue-resolved cfDNA analysis enables early risk stratification across the full clinical spectrum of preeclampsia from a single routine blood sample. Compared with FMF screening, this approach can potentially improve discrimination for term preeclampsia while providing incremental improvement for preterm disease. The potential for integration into existing NIPT workflows offers a scalable pathway toward unified precision prevention, supporting timely aspirin prophylaxis for preterm preeclampsia and risk-adapted surveillance strategies for term disease.

Background: A prerequisite to rapid molecular detection of pathogens causing bloodstream infections is an efficient, cost effective and robust DNA extraction solution. We describe methods for microbial DNA extraction direct from positive blood culture broths, suitable for metagenomic sequencing and the application of machine-learning based tools to predict antimicrobial susceptibility. Methods: Prospectively collected culture-positive blood culture broths with Gram-negative bacteria, were directly extracted using various commercially available kits. We compared methods for efficient inhibitor removal, avoidance of DNA shearing or degradation, to achieve DNA of high quality and purity. Bacterial species identified via whole-genome metagenomic sequencing (Illumina, MiniSeq) from blood culture extracts were compared to conventional methods from cultured isolates (Vitek MS). A machine-learning algorithm (AREScloud) was used to predict susceptibility against commercially available antibiotics, compared to susceptibility testing (Vitek 2) and other commercially available rapid diagnostic instruments (Accelerate Pheno and BCID). Results: A two-kit method using a modified MolYsis Basic kit (for host DNA depletion) and extraction using Qiagen DNeasy UltraClean microbial kits resulted in optimal extractions appropriate for multiple molecular applications, including PCR, short-read and long-read sequencing. DNA extracts from 40 blood culture broths were included. Taxonomic profiling by direct metagenomic sequencing matched species identification by conventional methods in 38/40 (95%) of samples, with two showing agreement to genus level. In two polymicrobial samples, a second organism was missed by sequencing. Whole genome sequencing antimicrobial susceptibility testing (WGS-AST) models were able to accurately infer profiles for 6 common pathogens against 17 antibiotics. Overall categorical agreement (CA) was 95%, with 11% very major errors (VME) and 3.9% major errors (ME). CA for WGS-AST was >95% for 5/6 of the most common pathogens ( E. coli, K. pneumoniae, P. mirabilis, P. aeruginosa and C. jejuni ) while it was lower for K. oxytoca (66.7%), likely due to the presence of inducible cephalosporinases. Performance of WGS-AST was sub-optimal for uncommon pathogens (e.g. Elizabethkingia ) and some combination antibiotic compounds (e.g. ticarcillin-clavulanate). Time to pathogen identification and resistance gene detection was fastest with BCID (1 h from blood culture positivity). Accelerate Pheno provided a rapid MIC result in approximately 8 h. While Illumina based direct metagenomic sequencing did not result in faster turn-around times compared conventional methods, use of real-time nanopore sequencing may allow faster data acquisition. Conclusions: The application of direct metagenomic sequencing from positive blood culture broths is a feasible approach and solves some of the challenges of sequencing from low-bacterial load samples. Machine-learning based algorithms are also accurate for common pathogen / drug combinations, although additional work is required to optimise algorithms for uncommon species and more complex resistance genotypes, as well as streamlining methods to provide more rapid sequencing results.