Biology subjects

Olson, R.

Publications and source records attributed to Olson, R..

3 recordsLinked to original sources

bioRxiv2018

Using machine learning to predict antimicrobial minimum inhibitory concentrations and associated genomic features for nontyphoidal Salmonella

Nontyphoidal Salmonella species are the leading bacterial cause of food-borne disease in the United States. Whole genome sequences and paired antimicrobial susceptibility data are available for Salmonella strains because of surveillance efforts from public health agencies. In this study, a collection of 5,278 nontyphoidal Salmonella genomes, collected over 15 years in the United States, were used to generate XGBoost-based machine learning models for predicting minimum inhibitory concentrations (MICs) for 15 antibiotics. The MIC prediction models have average accuracies between 95-96% within {+/-} 1 two-fold dilution factor and can predict MICs with no a priori information about the underlying gene content or resistance phenotypes of the strains. By selecting diverse genomes for training sets, we show that highly accurate MIC prediction models can be generated with fewer than 500 genomes. We also show that our approach for predicting MICs is stable over time despite annual fluctuations in antimicrobial resistance gene content in the sampled genomes. Finally, using feature selection, we explore the important genomic regions identified by the models for predicting MICs. To date, this is one of the largest MIC modeling studies to be published. Our strategy for developing whole genome sequence-based models for surveillance and clinical diagnostics can be readily applied to other important human pathogens.

bioinformatics↗

bioRxiv2017

Developing an in silico minimum inhibitory concentration panel test for Klebsiella pneumoniae

Antimicrobial resistant infections are a serious public health threat worldwide. Whole genome sequencing approaches to apidly identify pathogens and predict antibiotic resistance phenotypes are becoming more feasible and may offer a way to reduce clinical test turnaround times compared to conventional culture-based methods, and in turn, improve patient outcomes. In this study, we use whole genome sequence data from 1668 clinical isolates of Klebsiella pneumoniae to develop a XGBoost-based machine learning model that accurately predicts minimum inhibitory concentrations (MICs) for 20 antibiotics. The overall accuracy of the model, within {+/-}1 two-fold dilution factor, is 92%. Individual accuracies are[≥]90% for 15/20 antibiotics. We show that the MICs predicted by the model correlate with known antimicrobial resistance genes. Importantly, the genome-wide approach described in this study offers a way to predict MICs for isolates without knowledge of the underlying gene content. This study shows that machine learning can be used to build a complete in silico MIC prediction panel for K. pneumoniae and provides a framework for building MIC prediction models for other pathogenic bacteria.

bioinformatics↗

bioRxiv2017

Spatial resource heterogeneity increases diversity and evolutionary potential

Spatial heterogeneity is believed to be an evolutionary driver of biodiversity. Variability in the distribution of resource patches can allow an environment to support a wider variety of phenotypes for selection to act upon at the ecosystem level, which may lead to more species. However, the generality of this principle has not been thoroughly tested, as the relevant adaptive dynamics occur on evolutionary timescales. We overcame this challenge by performing experiments on populations of digital organisms in the Avida Digital Evolution Platform, in which we investigated the impact of spatial resource heterogeneity on phenotypic diversity. Since an important benefit of diversity may be increased evolutionary potential, we also tracked the probability of a complex trait evolving in the context of various levels of spatial heterogeneity. We found that spatial entropy and phenotypic diversity have a strong positive correlation and this relationship is consistent across various spatial configurations. Diversity also increases evolutionary potential, but has a much smaller impact than other components of environmental composition. The most important of these components was the mean number of resources present in locations across the environment, likely owing to the importance of building blocks for the evolution of complex features. These results suggest that a general relationship exists between spatial heterogeneity and diversity, beyond the specific ecosystems and timescales in which it has previously been studied. By examining this relationship in the context of phenotypic evolution, we advance a mechanistic understanding of the resulting dynamics. Moreover, our results suggest that the likelihood of evolving various traits can be impacted by the spatial configuration of patches in which these traits are advantageous. These findings have implications for both evolutionary biology and evolutionary computation, as generating and maintaining diversity is critical to all forms of evolution.

ecology↗