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

View Article: PubMed Central - PubMed

ABSTRACT

Background: The 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.

Results: 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. 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.

Conclusions: Our 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 material: The online version of this article (doi:10.1186/s12864-016-2889-6) contains supplementary material, which is available to authorized users.

No MeSH data available.


Related in: MedlinePlus

Antibiotic resistance models: Six antibiotic resistance models, which are all disjunctions (logical-OR). The rounded rectangles correspond to antibiotics. The circular nodes correspond to k-mer rules. A single border indicates a presence rule and a double border indicates an absence rule. The numbers in the circles show to the number of equivalent rules. A rule is connected to an antibiotic if it was included in its model. The weight of the edges gives the importance of each rule as defined by Eqs. (3) and (4). The models for all 17 datasets are illustrated in Additional file 4: Figure S1
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC5037627&req=5

Fig2: Antibiotic resistance models: Six antibiotic resistance models, which are all disjunctions (logical-OR). The rounded rectangles correspond to antibiotics. The circular nodes correspond to k-mer rules. A single border indicates a presence rule and a double border indicates an absence rule. The numbers in the circles show to the number of equivalent rules. A rule is connected to an antibiotic if it was included in its model. The weight of the edges gives the importance of each rule as defined by Eqs. (3) and (4). The models for all 17 datasets are illustrated in Additional file 4: Figure S1

Mentions: The annotated models for each dataset are illustrated in Additional file 4: Figure S1. Below, a subset of these models, which is illustrated in Fig. 2, is discussed. For each genomic variation identified by the algorithm, a thorough literature review was performed, with the objective of finding known, and validated, associations to antibiotic resistance.Fig. 2


Predictive computational phenotyping and biomarker discovery using reference-free genome comparisons
Antibiotic resistance models: Six antibiotic resistance models, which are all disjunctions (logical-OR). The rounded rectangles correspond to antibiotics. The circular nodes correspond to k-mer rules. A single border indicates a presence rule and a double border indicates an absence rule. The numbers in the circles show to the number of equivalent rules. A rule is connected to an antibiotic if it was included in its model. The weight of the edges gives the importance of each rule as defined by Eqs. (3) and (4). The models for all 17 datasets are illustrated in Additional file 4: Figure S1
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC5037627&req=5

Fig2: Antibiotic resistance models: Six antibiotic resistance models, which are all disjunctions (logical-OR). The rounded rectangles correspond to antibiotics. The circular nodes correspond to k-mer rules. A single border indicates a presence rule and a double border indicates an absence rule. The numbers in the circles show to the number of equivalent rules. A rule is connected to an antibiotic if it was included in its model. The weight of the edges gives the importance of each rule as defined by Eqs. (3) and (4). The models for all 17 datasets are illustrated in Additional file 4: Figure S1
Mentions: The annotated models for each dataset are illustrated in Additional file 4: Figure S1. Below, a subset of these models, which is illustrated in Fig. 2, is discussed. For each genomic variation identified by the algorithm, a thorough literature review was performed, with the objective of finding known, and validated, associations to antibiotic resistance.Fig. 2

View Article: PubMed Central - PubMed

ABSTRACT

Background: The 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.

Results: 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. 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.

Conclusions: Our 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 material: The online version of this article (doi:10.1186/s12864-016-2889-6) contains supplementary material, which is available to authorized users.

No MeSH data available.


Related in: MedlinePlus