Fitting stochastic transmission models to electronic patient data can offer detailed insights into the transmission of healthcare-associated infections and improve infection control. Pathogen whole-genome sequencing may improve the precision of model inferences, but computational constraints have limited modelling applications predominantly to small datasets and specific outbreaks, whereas large-scale sequencing studies have mostly relied on simple rules for identifying/excluding plausible transmission. We present a novel approach for integrating detailed epidemiological data on patient contact networks in hospitals with large-scale pathogen sequencing data. We apply our approach to study Clostridioides difficile transmission using a dataset of 1223 infections in Oxfordshire, UK, 2007-2011. 262 (21% [95% credibility interval 20-22%]) infections were estimated to have been acquired from another known case. There was heterogeneity by sequence type (ST) in the proportion of cases acquired from another case with the highest rates in ST1 (ribotype-027), ST42 (ribotype-106) and ST3 (ribotype-001). These same STs also had higher rates of transmission mediated via environmental contamination/spores persisting after patient discharge/recovery; for ST1 these persisted longer than for most other STs except ST3 and ST42. We also identified variation in transmission between hospitals, medical specialties and over time; by 2011 nearly all transmission from known cases had ceased in our hospitals. Our findings support previous work suggesting only a minority of C. difficile infections are acquired from known cases but highlight a greater role for environmental contamination than previously thought. Our approach is applicable to other healthcare-associated infections. Our findings have important implications for effective control of C. difficile.

MOTIVATION: Timely identification of Mycobacterium tuberculosis (MTB) resistance to existing drugs is vital to decrease mortality and prevent the amplification of existing antibiotic resistance. Machine learning methods have been widely applied for timely predicting resistance of MTB given a specific drug and identifying resistance markers. However, they have been not validated on a large cohort of MTB samples from multi-centers across the world in terms of resistance prediction and resistance marker identification. Several machine learning classifiers and linear dimension reduction techniques were developed and compared for a cohort of 13 402 isolates collected from 16 countries across 6 continents and tested 11 drugs. RESULTS: Compared to conventional molecular diagnostic test, area under curve of the best machine learning classifier increased for all drugs especially by 23.11%, 15.22% and 10.14% for pyrazinamide, ciprofloxacin and ofloxacin, respectively (P < 0.01). Logistic regression and gradient tree boosting found to perform better than other techniques. Moreover, logistic regression/gradient tree boosting with a sparse principal component analysis/non-negative matrix factorization step compared with the classifier alone enhanced the best performance in terms of F1-score by 12.54%, 4.61%, 7.45% and 9.58% for amikacin, moxifloxacin, ofloxacin and capreomycin, respectively, as well increasing area under curve for amikacin and capreomycin. Results provided a comprehensive comparison of various techniques and confirmed the application of machine learning for better prediction of the large diverse tuberculosis data. Furthermore, mutation ranking showed the possibility of finding new resistance/susceptible markers. AVAILABILITY AND IMPLEMENTATION: The source code can be found at http://www.robots.ox.ac.uk/ davidc/code.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Resistance co-occurrence within first-line anti-tuberculosis (TB) drugs is a common phenomenon. Existing methods based on genetic data analysis of Mycobacterium tuberculosis (MTB) have been able to predict resistance of MTB to individual drugs, but have not considered the resistance co-occurrence and cannot capture latent structure of genomic data that corresponds to lineages. RESULTS: We used a large cohort of TB patients from 16 countries across six continents where whole-genome sequences for each isolate and associated phenotype to anti-TB drugs were obtained using drug susceptibility testing recommended by the World Health Organization. We then proposed an end-to-end multi-task model with deep denoising auto-encoder (DeepAMR) for multiple drug classification and developed DeepAMR_cluster, a clustering variant based on DeepAMR, for learning clusters in latent space of the data. The results showed that DeepAMR outperformed baseline model and four machine learning models with mean AUROC from 94.4% to 98.7% for predicting resistance to four first-line drugs [i.e. isoniazid (INH), ethambutol (EMB), rifampicin (RIF), pyrazinamide (PZA)], multi-drug resistant TB (MDR-TB) and pan-susceptible TB (PANS-TB: MTB that is susceptible to all four first-line anti-TB drugs). In the case of INH, EMB, PZA and MDR-TB, DeepAMR achieved its best mean sensitivity of 94.3%, 91.5%, 87.3% and 96.3%, respectively. While in the case of RIF and PANS-TB, it generated 94.2% and 92.2% sensitivity, which were lower than baseline model by 0.7% and 1.9%, respectively. t-SNE visualization shows that DeepAMR_cluster captures lineage-related clusters in the latent space. AVAILABILITY AND IMPLEMENTATION: The details of source code are provided at http://www.robots.ox.ac.uk/∼davidc/code.php. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Correct and rapid determination of Mycobacterium tuberculosis (MTB) resistance against available tuberculosis (TB) drugs is essential for the control and management of TB. Conventional molecular diagnostic test assumes that the presence of any well-studied single nucleotide polymorphisms is sufficient to cause resistance, which yields low sensitivity for resistance classification. Summary: Given the availability of DNA sequencing data from MTB, we developed machine learning models for a cohort of 1839 UK bacterial isolates to classify MTB resistance against eight anti-TB drugs (isoniazid, rifampicin, ethambutol, pyrazinamide, ciprofloxacin, moxifloxacin, ofloxacin, streptomycin) and to classify multi-drug resistance. Results: Compared to previous rules-based approach, the sensitivities from the best-performing models increased by 2-4% for isoniazid, rifampicin and ethambutol to 97% (P < 0.01), respectively; for ciprofloxacin and multi-drug resistant TB, they increased to 96%. For moxifloxacin and ofloxacin, sensitivities increased by 12 and 15% from 83 and 81% based on existing known resistance alleles to 95% and 96% (P < 0.01), respectively. Particularly, our models improved sensitivities compared to the previous rules-based approach by 15 and 24% to 84 and 87% for pyrazinamide and streptomycin (P < 0.01), respectively. The best-performing models increase the area-under-the-ROC curve by 10% for pyrazinamide and streptomycin (P < 0.01), and 4-8% for other drugs (P < 0.01). Availability and implementation: The details of source code are provided at http://www.robots.ox.ac.uk/~davidc/code.php. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

Hospital networks, formed by patients visiting multiple hospitals, affect the spread of hospital-associated infections, resulting in differences in risks for hospitals depending on their network position. These networks are increasingly used to inform strategies to prevent and control the spread of hospital-associated pathogens. However, many studies only consider patients that are received directly from the initial hospital, without considering the effect of indirect trajectories through the network. We determine the optimal way to measure the distance between hospitals within the network, by reconstructing the English hospital network based on shared patients in 2014-2015, and simulating the spread of a hospital-associated pathogen between hospitals, taking into consideration that each intermediate hospital conveys a delay in the further spread of the pathogen. While the risk of transferring a hospital-associated pathogen between directly neighbouring hospitals is a direct reflection of the number of shared patients, the distance between two hospitals far-away in the network is determined largely by the number of intermediate hospitals in the network. Because the network is dense, most long distance transmission chains in fact involve only few intermediate steps, spreading along the many weak links. The dense connectivity of hospital networks, together with a strong regional structure, causes hospital-associated pathogens to spread from the initial outbreak in a two-step process: first, the directly surrounding hospitals are affected through the strong connections, second all other hospitals receive introductions through the multitude of weaker links. Although the strong connections matter for local spread, weak links in the network can offer ideal routes for hospital-associated pathogens to travel further faster. This hold important implications for infection prevention and control efforts: if a local outbreak is not controlled in time, colonised patients will appear in other regions, irrespective of the distance to the initial outbreak, making import screening ever more difficult.

Bacterial whole genome sequencing offers the prospect of rapid and high precision investigation of infectious disease outbreaks. Close genetic relationships between microorganisms isolated from different infected cases suggest transmission is a strong possibility, whereas transmission between cases with genetically distinct bacterial isolates can be excluded. However, undetected mixed infections-infection with ≥2 unrelated strains of the same species where only one is sequenced-potentially impairs exclusion of transmission with certainty, and may therefore limit the utility of this technique. We investigated the problem by developing a computationally efficient method for detecting mixed infection without the need for resource-intensive independent sequencing of multiple bacterial colonies. Given the relatively low density of single nucleotide polymorphisms within bacterial sequence data, direct reconstruction of mixed infection haplotypes from current short-read sequence data is not consistently possible. We therefore use a two-step maximum likelihood-based approach, assuming each sample contains up to two infecting strains. We jointly estimate the proportion of the infection arising from the dominant and minor strains, and the sequence divergence between these strains. In cases where mixed infection is confirmed, the dominant and minor haplotypes are then matched to a database of previously sequenced local isolates. We demonstrate the performance of our algorithm with in silico and in vitro mixed infection experiments, and apply it to transmission of an important healthcare-associated pathogen, Clostridium difficile. Using hospital ward movement data in a previously described stochastic transmission model, 15 pairs of cases enriched for likely transmission events associated with mixed infection were selected. Our method identified four previously undetected mixed infections, and a previously undetected transmission event, but no direct transmission between the pairs of cases under investigation. These results demonstrate that mixed infections can be detected without additional sequencing effort, and this will be important in assessing the extent of cryptic transmission in our hospitals.