MOTIVATION: Microbial sequences generated from clinical samples are often contaminated with human host sequences that must be removed for ethical and legal reasons. Care must be taken to excise host sequences without inadvertently removing target microbial sequences to the detriment of downstream analyses such as variant calling and de novo assembly. RESULTS: To facilitate accurate host decontamination of both short and long sequencing reads, we developed Hostile, a tool capable of accurate host read removal using a laptop. We demonstrate that our approach removes at least 99.6% of real human reads and retains at least 99.989% of simulated bacterial reads. Using Hostile with a masked reference genome further increases bacterial read retention (≥99.997%) with negligible (≤0.001%) reduction in human read removal performance. Compared with an existing tool, Hostile removes 21%-23% more human short reads and 21-43 times fewer bacterial reads, typically in less time. AVAILABILITY AND IMPLEMENTATION: Hostile is implemented as an MIT-licensed Python package available from https://github.com/bede/hostile together with supplementary material.

Antimicrobial resistance (AMR) poses a threat to global public health. To mitigate the impacts of AMR, it is important to identify the molecular mechanisms of AMR and thereby determine optimal therapy as early as possible. Conventional machine learning-based drug-resistance analyses assume genetic variations to be homogeneous, thus not distinguishing between coding and intergenic sequences. In this study, we represent genetic data from Mycobacterium tuberculosis as a graph, and then adopt a deep graph learning method-heterogeneous graph attention network ('HGAT-AMR')-to predict anti-tuberculosis (TB) drug resistance. The HGAT-AMR model is able to accommodate incomplete phenotypic profiles, as well as provide 'attention scores' of genes and single nucleotide polymorphisms (SNPs) both at a population level and for individual samples. These scores encode the inputs, which the model is 'paying attention to' in making its drug resistance predictions. The results show that the proposed model generated the best area under the receiver operating characteristic (AUROC) for isoniazid and rifampicin (98.53 and 99.10%), the best sensitivity for three first-line drugs (94.91% for isoniazid, 96.60% for ethambutol and 90.63% for pyrazinamide), and maintained performance when the data were associated with incomplete phenotypes (i.e. for those isolates for which phenotypic data for some drugs were missing). We also demonstrate that the model successfully identifies genes and SNPs associated with drug resistance, mitigating the impact of resistance profile while considering particular drug resistance, which is consistent with domain knowledge.

Pathogen genomic data analysis can be extremely bespoke and diverse. This paper presents our plan and progress towards creating a Scalable Pathogen Pipeline Platform (SP3) providing an efficient and unified process of collecting, analysing and comparing genomic data analysis with the benefit of elastic cloud computing. SP3enables container-centric bioinformatic workflows run on personal computers, High-performance computing (HPC) clusters and cloud platforms. We have deployed and tested SP3on local HPC, Google Cloud Platform (GCP), Microsoft Azure and OpenStack Platforms. SP3allows users to fetch genomic sequencing data from European Nucleotide Archive (ENA) and conduct analysis with open-source bioinformatic pipelines. We believe SP3will promote common standards around pathogen genomic data quality, data processing and data analysis, helping answer the challenges of tools divergence and leveraging a pool of public genomic data repository and cloud resources.

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.

We present an open-source Azure solution for running scalable genomics workflows. It benefits from state-of-art distributed workflow framework, container and cloud technologies and allows users to create a cluster that is scaled to suit their workload in minutes. We describe the design decisions, solution testing and automation options to support a variety of users for their genomic data analytics. The solution demonstrates a generic and customizable approach to run genomic data analytics workflows on a cloud environment.

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.

BACKGROUND: Large scale bacterial sequencing has made the determination of genetic relationships within large sequence collections of bacterial genomes derived from the same microbial species an increasingly common task. Solutions to the problem have application to public health (for example, in the detection of possible disease transmission), and as part of divide-and-conquer strategies selecting groups of similar isolates for computationally intensive methods of phylogenetic inference using (for example) maximal likelihood methods. However, the generation and maintenance of distance matrices is computationally intensive, and rapid methods of doing so are needed to allow translation of microbial genomics into public health actions. RESULTS: We developed, tested and deployed three solutions. BugMat is a fast C++ application which generates one-off in-memory distance matrices. FindNeighbour and FindNeighbour2 are server-side applications which build, maintain, and persist either complete (for FindNeighbour) or sparse (for FindNeighbour2) distance matrices given a set of sequences. FindNeighbour and BugMat use a variation model to accelerate computation, while FindNeighbour2 uses reference-based compression. Performance metrics show scalability into tens of thousands of sequences, with options for scaling further. CONCLUSION: Three applications, each with distinct strengths and weaknesses, are available for distance-matrix based analysis of large bacterial collections. Deployed as part of the Public Health England solution for M. tuberculosis genomic processing, they will have wide applicability.

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.