Forecast: Predicting Antibiotic Resistance from Susceptibility Data

Precision Medicine Project - Forecast: Predicting Antibiotic Resistance from Susceptibility Data.

Supervisor(s): Dr Thamarai Schneiders, Dr Andrea Weisse & Dr Simon Dewar
Centre/Institute: Centre for Inflammation Research, Institute Regeneration and Repair

Background

We are engaged in a continual arms race in combatting antibiotic resistance1 . It seems inevitable that the launch of any antibiotic is met with the emergence of resistance. However, the speed at which this is likely to emerge and disseminate is unknown. As such, a key challenge is being able to predict the temporal, geographic and genetic basis for resistance development for new and old antibiotics2 . Can longitudinal health data help address this question? The Atlas dataset (https://atlas-surveillance.com/login ) has curated data for almost 1M samples over a 20 year period from diagnostic labs globally. Data mining efforts from the Atlas data with cohesive outputs (eg understanding resistance emergence, transmission, geographic hotspots) have been limited. We wish to exploit this dataset to address “How can we predict the emergence of resistance based on existing global datasets on antibiotic susceptibility and genome information?”. Our approach is based on linking the susceoptibility data to bacterial genomic data thus producing the first phenotype-genotype link. In previous work (L. Jurcaga, MSc thesis, U Edinburgh 2025), we have already demonstrated that the Atlas data can be used to link trends in tigecycline (novel glycycline) resistance emergence, geographic hotspots of high rates of resistance and co-linkages to other existing or new antibiotics. As such, we wish to extend this analyses using the expanded Atlas dataset (2025), with a specific focus on pathogens posing a severe threat to human health (eg E. coli and Klebsiella pneumoniae) against new antibiotics such as cefidericol, Ceftazidime-avibactam with the following aims

Aims

  1. We will utilize the Atlas susceptibility data to mine for susceptibility trends linked to isolates, antibiotics, geographic location for WHO priority pathogens E. coli and Klebsiella spp. We will investigate the dataset for statistically significant trends in resistance development and shifts in susceptibility overall and in individual countries.
  2. Based on the trends and geographic locations identified in Aim 1 we will then focus on Klebsiella spp.. We will acquire temporally matched genome sequences from NCBI Bioproject to analyse genetic changes linked to alterations in susceptibility. Here, we will undertake both analyses of (1) targeted (known genes) (2) de novo (unknown) genes. The alterations in the unknown genes will be undertaken by sifting the strain pools into key epidemic lineages and undertaking either a gene presence or absence or SNP-based GWAS analyses.
  3. Based on genes identified in Aim 2, we will generate a subset of these known and de novo mutations to undertake targeted antibiotic resistance evolution experiments to demonstrate alterations in susceptibility to these antibiotics.
  4. We will train predictive machine learning models based on relations identified in Aim 1 to trial against a retrospective collection of bacterial samples collected from the Royal Infirmary of Edinburgh.

Training outcomes

  • Ability to mine large global datasets to undertake (1)descriptive (2) quantitative and (3) statistical predictions.
  • Link emerging themes from the data mining to publicy available genomic data to identify relevant mutations.
  • Establish if these mutations can be biologically validated to produce relevant phenotypes in vitro.
  • Apply methodologies to “real-world” samples from the Royal Infirmary of Edinburgh. 

Overall, this work is expected to provide evidence of how longitudinal susceptibility data vitally supports surveillance of antibiotic resistance trends and the emergence of known and novel resistance mechanisms.

References 

  1. Ho et al, Antimicrobial Resistance- A concise update, Lancet Microbe (2025)
  2. Cesaro et al, Challenges and applications of artificial intelligence in Infectious Diseases and Antimicrobial Resistance, npj Antimicrobials and Resistance (2025)
  3. Valavarasu V et al, Prediction of Antibiotic Resistance from Surveillance Data using Machine Learning, Sci Reports, (2025)
  4. Catalan, P., et al, Seeking Patterns of Antimicrobial Resistance in Atlas, an open raw MIC database with patient metadata, Nature Communications (2022)

Apply Now

Click here to Apply Now

  • The deadline for 26/27 applications is Monday 12th January 2026
  • Applicants must apply to a specific project. Please ensure you include details of the project on the Recruitment Form below, which you must submit to the research proposal section of your EUCLID application.
  • Please ensure you upload as many of the requested documents as possible, including a CV, at the time of submitting your EUCLID application.  

Q&A Sessions

Supervisor(s) of each project will be holding a 30 minute Q&A session in the first two weeks of December. 

If you have any questions regarding this project, you are invited to attend the session on TBC via Microsoft Teams. Click here to join the session.

This article was published on