skip to main content
Back to Project Search

Predicting Bacterial Antimicrobial Resistance Phenotypes from Genomic Biomarkers

Project

Project Details

Program
BioScience
Field of Study
Microbial genomics
Division
Biological and Environmental Sciences and Engineering
Faculty Lab Link
https://www.kaust.edu.sa/en/study/faculty/danesh-moradigaravand
Center Affiliation
Computational Bioscience Research Center

Project Description

The Infectious Disease Epidemiology lab of Prof. Danesh Moradigaravand is looking for student interns to work on a range of projects on the intersection of machine learning and microbial genomics. We are interested in understanding the evolution and epidemiology of antimicrobial resistance strains recovered from natural sources, including clinical and environmental sites. Antimicrobial resistance is a global health threat, expected to become a leading cause of deaths worldwide within the next three decades. This is predominately due to the rapid emergence of novel genetic variants, which lead to new resistance mechanisms. The understanding of the genetic repertoire of resistance is henceforth important to design new antimicrobial strategies and develop new compounds. In this project, the student will develop a machine learning-based predictive model to systematically identify resistance determinants in bacterial genomes. The projects involves integration of genomic and phenomic data, generated by high throughput phenotypic assays using an off-the-shelf machine learning method. The student will implement an entire predictive pipeline and deploy the model as a data science solution. The project helps student gain hands-on experience of programming, next generation sequencing data analysis and machine learning

About the Researcher

Danesh Moradigaravand
Assistant Professor, Bioscience
Biological and Environmental Science and Engineering Division

Affiliations

Education Profile

  • Research Associate, Wellcome Sanger Institute, Hinxton 2018
  • PhD in Theoretical and Computational Biology, ETH Zurich 2014
  • MSc in Molecular Biology, International Max Planck Research School Goettingen 2011

Research Interests

a€‹Professor Moradigaravand's research is on the evolution and epidemiology of infectious diseases, especially in the context of antimicrobial resistance. He utilises a broad range of genomic, phenomic and machine learning approaches to understand the dissemination of pathogens within and between environmental and clinical settings and to pinpoint genetic factors driving the evolution of pathogens. Moreover, he employs machine learning approaches for predicting bacterial complex phenotypic features, e.g. bacterial growth, antimicrobial resistance, and horizontal gene transfer, from genomic variants

Selected Publications

  • Danesh Moradigaravand, Sandra Reuter, Veronique Martin, Sharon J Peacock, Julian Parkhill, The dissemination of multidrug-resistant Enterobacter cloacae throughout the UK and Ireland. Nat Microbiol, 2016. 1: p. 16173.
  • Danesh Moradigaravand, Martin Palm, Anne Farewell, Ville Mustonen, Jonas Warringer, Leopold Parts, Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data. PLoS Comput Biol, 2018. 14(12): p. e1006258
  • Danesh Moradigaravand, Veronique Martin, Sharon J Peacock, Julian Parkhill, Evolution and Epidemiology of Multidrug-Resistant Klebsiella pneumoniae in the United Kingdom and Ireland. mBio, 2017. 8(1)
  • Danesh Moradigaravand, Christine J Boinett, Veronique Martin, Sharon J Peacock, Julian Parkhill, Recent independent emergence of multiple multidrug-resistant Serratia marcescens clones within the United Kingdom and Ireland. Genome Res, 2016. 26(8): p. 1101-9.
  • Sam Benkwitz-Bedford, Martin Palm, Talip Yasir Demirtas, Ville Mustonen, Anne Farewell, Jonas Warringer, Leopold Parts, Danesh Moradigaravand, Machine Learning Prediction of Resistance to Subinhibitory Antimicrobial Concentrations from Escherichia coli Genomes. mSystems, 2021. 6(4): p. e0034621.

Desired Project Deliverables

Develop and deploy a machine learning pipeline Disclose a database of predictive biomarkers for antimicrobial resistance Contribute to relevant publications

Recommended Student Background

Prior hands-on experience of writing high quality codes in R and Python
Familiarity with bash programing and running computational tasks on clouds
Familiarity with next generation sequencing technologies
Excellent problem-solving skills
On this page