Abstract
Bacterial antibiotic resistance is becoming a significant health threat, and rapid identification of antibiotic-resistant bacteria is essential to save lives and reduce the spread of antibiotic resistance. This paper analyzes the ability of machine learning algorithms (MLAs) to process data from a novel spectroscopic diagnostic device to identify antibiotic-resistant genes and bacterial species by comparison to available bacterial DNA sequences. Simulation results show that the algorithms attain from 92% accuracy (for genes) up to 99% accuracy (for species). This novel approach identifies genes and species by optically reading the percentage of A, C, G, T bases in 1000s of short 10-base DNA oligomers instead of relying on conventional DNA sequencing in which the sequence of bases in long oligomers provides genetic information. The identification algorithms are robust in the presence of simulated random genetic mutations and simulated random experimental errors. Thus, these algorithms can be used to identify bacterial species, to reveal antibiotic resistance genes, and to perform other genomic analyses. Some MLAs evaluated here are shown to be better than others at accurate gene identification and avoidance of false negative identification of antibiotic resistance.
Highlights
Novel DNA sequencing technologies have proliferated over the past two decades
This study addressed four main objectives: (1) to determine how many block optical content (BOC) reads are needed for species identification; (2) to determine how many BOC reads are needed for single gene detections; (3) to analyze how accuracy is affected by noise from the detecting instrument and from random gene mutations; (4) to identify which learning algorithms are best at accurately identifying the species and genes
For both bacterial species and antibiotic resistance gene identification, it is noted that the principal component analysis (PCA) produced in all cases contains an arch effect, which indicates that the principal components are not completely independent of each other and are not completely orthogonal to each other (Morton et al, 2017)
Summary
Novel DNA sequencing technologies have proliferated over the past two decades. Continual improvements in “next-generation sequencing” (NGS) and “third-generation sequencing” (TGS) have increased the fidelity and rate of sequencing, but it still takes hours or days to obtain complete sequences (van Dijk et al, 2018). In patients with septic shock from bacterial infections, identification of antibiotic-resistance genes is essential because the mortality rate increases 7.6% per hour of delay in administering correct. Genetic Technique for Identifying Antibiotic Resistance antibiotics (Kumar et al, 2006) It takes more than 24 h to grow up the bacteria recovered from the blood of an infected patient, identify the species, and determine to which antibiotics the organism is resistant, leading to a very high mortality rate for such infections (Kumar et al, 2009). As genome and plasmid sequencing can identify the species and previously identified resistance genes, it would be tremendously useful to perform bacterial sequencing in an hour or less. Current and proposed NGS and TGS techniques still require much more time
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
