“Tracking antibiotic resistance gene pollution from different sources using machine-learning classification”
“Antimicrobial resistance (AMR) has been a worldwide public health concern. Current widespread AMR pollution has posed a big challenge in accurately disentangling source-sink relationship, which has been further confounded by point and non-point sources, as well as endogenous and exogenous cross-reactivity under complicated environmental conditions. Because of insufficient capability in identifying source-sink relationship within a quantitative framework, traditional antibiotic resistance gene (ARG) signatures-based source-tracking methods would hardly be a practical solution.
By combining broad-spectrum ARG profiling with machine-learning classification SourceTracker, here we present a novel way to address the question in the era of high-throughput sequencing. Its potential in extensive application was firstly validated by 656 global-scale samples covering diverse environmental types (e.g., human/animal gut, wastewater, soil, ocean) and broad geographical regions (e.g., China, USA, Europe, Peru). Its potential and limitations in source prediction as well as effect of parameter adjustment were then rigorously evaluated by artificial configurations with representative source proportions. When applying SourceTracker in region-specific analysis, excellent performance was achieved by ARG profiles in two sample types with obvious different source compositions, i.e., influent and effluent of wastewater treatment plant. Two environmental metagenomic datasets of anthropogenic interference gradient further supported its potential in practical application. To complement general-profile-based source tracking in distinguishing continuous gradient pollution, a few generalist and specialist indicator ARGs across ecotypes were identified in this study.
We demonstrated for the first time that the developed source-tracking platform when coupling with proper experiment design and efficient metagenomic analysis tools will have significant implications for assessing AMR pollution. Following predicted source contribution status, risk ranking of different sources in ARG dissemination will be possible, thereby paving the way for establishing priority in mitigating ARG spread and designing effective control strategies.
Altogether, by combining comprehensive metagenomic ARG profiling with machine-learning classification SourceTracker, we here presented a novel quantitative framework to address ARG pollution source tracking. Although sequencing expense and computational complexity might impede the platform application as a routine ARG pollution monitor tool, continued reduction in
sequencing costs and increase in public accessible computational resources (e.g., online ARG annotation platform ARGs-OAP [54]) may soon make this approach feasible. Following predicted source contribution status, risk ranking of different sources in ARG dissemination will be possible, thereby paving the way for establishing priority in mitigating further ARG spread. Particularly,
differentiation of sources will shed light on areas where intervention can be most effective in reducing ARG spread in the environment. Thus, the presented source-tracking platform will have far-reaching significance for both science community and public authorities in AMR control.”
Source: Microbiome Journal
