Abstract
The increasing prevalence of antimicrobial-resistant bacteria drives the need for advanced methods to identify antimicrobial-resistance (AMR) genes in bacterial pathogens. With the availability of whole genome sequences, best-hit methods can be used to identify AMR genes by differentiating unknown sequences with known AMR sequences in existing online repositories. Nevertheless, these methods may not perform well when identifying resistance genes with sequences having low sequence identity with known sequences. We present a machine learning approach that uses protein sequences, with sequence identity ranging between 10% and 90%, as an alternative to conventional DNA sequence alignment-based approaches to identify putative AMR genes in Gram-negative bacteria. By using game theory to choose which protein characteristics to use in our machine learning model, we can predict AMR protein sequences for Gram-negative bacteria with an accuracy ranging from 93% to 99%. In order to obtain similar classification results, identity thresholds as low as 53% were required when using BLASTp.
Highlights
In this paper we introduce a game theoretic dynamic weighting based feature evaluation (GTDWFE) approach in which features are selected one at a time based on relevance and redundancy measurements with dynamic re-weighting of candidate features based on their interdependency with the current selected features
The strength of a machine learning algorithm is that it uses features based on the structural, physicochemical, evolutionary, and compositional properties of protein sequences rather than their sequence similarity
The novel game theory approach we used to determine protein features for our machine learning algorithm has not been used previously for such a purpose and is especially powerful because features are chosen on the basis of how well they work together as a whole to identify putative antimicrobial-resistance genes by taking into account both the relevance and interdependency of features
Summary
The objective of this work was to reduce the dimension of our feature vector in such a way as to produce accurate machine learning predictions for AMR
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
