Predicting Antibiotic Resistance Through the Utilization and Comparison of Machine Learning Algorithms
Authors: Meris Johnson-Hagler; Jameel Ali; Faye Orcales; John Matt Suntay; Kristiene Recto ; Lucy Mocteczuma; Feyeeza Shaikh; Pleuni Pennings
Affiliation: San Francisco State University
Keywords: Phylogenetics, Macroevolution, and Biogeography
Antibiotic resistance has become a global public health concern. Bacteria are evolving resistance to the current arsenal of prescribed antibiotics resulting in strains that are developing multi-drug resistance. Currently, clinics are often performing traditional culture-based assays to determine antibiotic resistance in bacterial strains. However, this method is time-consuming and may be phenotypically inaccurate. To determine antibiotic resistance with a greater degree of accuracy and efficiency than traditional methods, we will be utilizing machine learning algorithms. The machine learning algorithms will process publically available whole genome sequences of E. coli strains to produce Decision Trees, Random Forest, and Gradient Boosted Trees models. We want to compare the machine learning models to determine which one has the best accuracy when using population structure, isolation year, and gene content as features. Through comparative analysis, we want to identify which features can predict antibiotic resistance.We aim to use what we have learned from this study to contribute to a future where machine learning can be used as a diagnostic tool to accurately predict antibiotic resistance from whole genome sequencing data.