Combating antimicrobial resistance through use of genomics and artificial intelligence

Antimicrobial resistance (AMR) is one of the most significant and immediate threats to health in Australia and globally. As an Infectious Diseases physician and researcher, the second supervisor is working on harnessing new technologies such as next-generation sequencing and artificial intelligence to improve the diagnosis, treatment and prevention of AMR infections. The specific aims of this project are:

1.   Rapidly identify AMR and predict treatment responses through use of genomics and machine learning in a clinical context
2.   Detect healthcare-associated transmission of AMR in real-time and transform outbreak response through use of novel long-read sequencing
3.   Use predictive approaches to personalise therapy of patients at-risk or affected by AMR pathogens. This will be achieved by integrating cutting-edge techniques in bacterial genomics, including both short- (Illumina) and long-read sequencing (Oxford Nanopore), data mining of electronic medical records and use of machine learning to predict several outcomes.

Among the approaches used will be the Bayesian information-theoretic Minimum Message Length (MML) principle (Wallace and Boulton, 1968; Wallace and Dowe, 1999a; Wallace, 2005)

References:

  Wallace, C.S. (2005), ``Statistical and Inductive Inference by Minimum Message Length'', Springer  (Link to the preface [and p vi, also here])

  Wallace, C.S. and D.M. Boulton (1968), ``An information measure for classification'', Computer Journal, Vol 11, No 2, August 1968, pp 185-194

  Wallace, C.S. and D.L. Dowe (1999a). Minimum Message Length and Kolmogorov Complexity, Computer Journal (special issue on Kolmogorov complexity), Vol. 42, No. 4, pp270-283.

Keywords:  Machine Learning; Data Science; Artificial intelligence; Machine learning; Antimicrobial resistance; Superbugs; Genomics