Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons

Abstract

BackgroundThe identification of genomic biomarkers is a key step towards improving diagnostic tests and therapies. We present a reference-free method for this task that relies on a k-mer representation of genomes and a machine learning algorithm that produces intelligible models. The method is computationally scalable and well-suited for whole genome sequencing studies.ResultsThe method was validated by generating models that predict the antibiotic resistance of C. difficile, M. tuberculosis, P. aeruginosa, and S. pneumoniae for 17 antibiotics. The obtained models are accurate, faithful to the biological pathways targeted by the antibiotics, and they provide insight into the process of resistance acquisition. Moreover, a theoretical analysis of the method revealed tight statistical guarantees on the accuracy of the obtained models, supporting its relevance for genomic biomarker discovery.ConclusionsOur method allows the generation of accurate and interpretable predictive models of phenotypes, which rely on a small set of genomic variations. The method is not limited to predicting antibiotic resistance in bacteria and is applicable to a variety of organisms and phenotypes. Kover, an efficient implementation of our method, is open-source and should guide biological efforts to understand a plethora of phenotypes (http://github.com/aldro61/kover/).Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-016-2889-6) contains supplementary material, which is available to authorized users.

Genomics of antibiotic‐resistance prediction in Pseudomonas aeruginosa

“…Remarkably, as depicted in Figure , AMR genes or mutants were found for the major families of antibiotics used, including aminoglycosides, β‐lactams, fluoroquinolones, fosfomycin, macrolides, polymyxin, rifampin, sulfonamide, and tetracycline. On the basis of our own work, as well as machine learning attempts from another team, the only single gene that can be directly associated with a resistance phenotype is gyrA , for which specific variants are associated with quinolone resistance . This highlights the complex nature of the molecular basis of AMR in P. aeruginosa and the challenge that is AMR prediction for this organism.…”

“…This is why machine learning is such a promising approach for predicting AMR. To date, however, machine learning applied to P. aeruginosa AMR has had mitigated success and will need to be better adapted to the genomic complexity of the species. Currently, there are two major approaches that could be amenable to AMR prediction: rules‐based methods and machine learning methods.…”

Evaluation of Machine Learning Models for Predicting Antimicrobial Resistance of Actinobacillus pleuropneumoniae From Whole Genome Sequences

“…A conjunction model assigns the positive class to a genome if all the rules output true, whereas a disjunction model does the same if at least one rule outputs true. The method was validated by generating models that predict the antibiotic resistance of C. difficile, M. tuberculosis, P. aeruginosa, and S. pneumoniae for 17 antibiotics (Drouin et al, 2016). The obtained models, implemented in Kover, were proven to be accurate, faithful to the biological pathways targeted by the antibiotics, and they provide insight into the process of resistance acquisition.…”

“…But this method relies mainly on the database and therefore cannot be used for predictions where resistance mechanisms have yet to be identified. The SCM model should need enough proportion of true phenotype data against false phenotype data as input to form a "training set" to train the model, but it provides a unique approach for deciphering, de novo, new biological mechanisms without the need for prior information (Drouin et al, 2016).…”

Unique k-mers as Strain-Specific Barcodes for Phylogenetic Analysis and Natural Microbiome Profiling

“…They were adapted for evaluating sequencing data, including quality control [22,23], SNP identification [24,25], and even for virtual sequence error correction [25][26][27][28]. Furthermore, a combination of k-mer analysis with machine learning algorithms allows predicting some phenotypes, for instance, antibiotic resistance [29][30][31][32]. The intensive use of k-mers as taxonomic markers started very recently (for a review, see [33]), but they have already been applied in several computer algorithms.Thus, in 2013, a strategy was developed to search for strain/species-specific 50-mers to identify microbes with diagnostic microarrays [34].…”