Tracing the transition of methicillin resistance in sub-populations of Staphylococcus aureus, using SELDI-TOF Mass Spectrometry and Artificial Neural Network Analysis

Haroun N. Shah, Lakshani Rajakaruna, Graham Ball, Raju Misra, Ali Al-Shahib, Min Fang, Saheer Gharbia

Research output: Contribution to journalArticlepeer-review

28 Citations (Scopus)

Abstract

Strains (n= 99) of Staphylococcus aureus isolated from a large number of clinical sources and tested for methicillin sensitivity were analysed by MALDI-TOF-MS using the Weak Cation Exchange (CM10) ProteinChip Array (designated SELDI-TOF-MS). The profile data generated was analysed using Artificial Neural Network (ANN) Analysis modelling techniques. Seven key ions identified by the ANNs that were predictive of MRSA and MSSA were validated by incorporation into a model. This model exhibited an area under the ROC curve value of 0.9147 indicating the potential application of this approach for rapidly characterising MRSA and MSSA isolates. Nearly all strains (n= 97) were correctly assigned to the correct group, with only two aberrant MSSA strains being misclassified. However, approximately 21% of the strains appeared to be in a process of transition as resistance to methicillin was being acquired.

Original languageEnglish
Pages (from-to)81-86
Number of pages6
JournalSystematic and Applied Microbiology
Volume34
Issue number1
DOIs
Publication statusPublished - Feb 2011

Keywords

  • ANN
  • CM10
  • MRSA
  • MSSA
  • SELDI-TOF-MS
  • Staphylococcus aureus

Fingerprint

Dive into the research topics of 'Tracing the transition of methicillin resistance in sub-populations of Staphylococcus aureus, using SELDI-TOF Mass Spectrometry and Artificial Neural Network Analysis'. Together they form a unique fingerprint.

Cite this