Machine learning applied to analyses of FTIR spectrum to identification of antibiotic resistance in different species of microorganisms

Here we develop an innovative protocol for the rapid and safe identification of antimicrobial resistance. This advance is crucial for optimizing treatment strategies and avoiding the spread of resistance. Which emphasizing the relevance of specialized machine learning bases in effectively differentiating between resistance profiles in Gram-negative and Gram-positive bacteria. We established a methodology capable of analyzing the Fourier Transform Infrared Spectroscopy (FTIR) structural profile of samples of Streptococcus pyogenes, Streptococcus mutans, Escherichia coli and Klebsiella pneumoniae, tested in a data bank of Staphylococcus aureus. It demonstrates cross-sectional applicability of antibiotic identification on different microorganisms, and providing a multidimensional database that transcends microbial variability [1–5]. The results reinforce the premise that the structural characteristics identified are universal among the microorganisms tested. The results bring a safe and quick alternative in the identification of antibiotic resistance in microorganisms. The obtained result has high potential to be applied to clinical procedures needs.