Rapid identification of pathogenic bacteria using Raman spectroscopy and deep learning

arXiv.org Machine Learning

Rapid identification of bacteria is essential to prevent the spread of infectious disease, help combat antimicrobial resistance, and improve patient outcomes. Raman optical spectroscopy promises to combine bacterial detection, identification, and antibiotic susceptibility testing in a single step. However, achieving clinically relevant speeds and accuracies remains challenging due to the weak Raman signal from bacterial cells and the large number of bacterial species and phenotypes. By amassing the largest known dataset of bacterial Raman spectra, we are able to apply state-of-the-art deep learning approaches to identify 30 of the most common bacterial pathogens from noisy Raman spectra, achieving antibiotic treatment identification accuracies of 99.0$\pm$0.1%. This novel approach distinguishes between methicillin-resistant and -susceptible isolates of Staphylococcus aureus (MRSA and MSSA) as well as a pair of isogenic MRSA and MSSA that are genetically identical apart from deletion of the mecA resistance gene, indicating the potential for culture-free detection of antibiotic resistance. Results from initial clinical validation are promising: using just 10 bacterial spectra from each of 25 isolates, we achieve 99.0$\pm$1.9% species identification accuracy. Our combined Raman-deep learning system represents an important proof-of-concept for rapid, culture-free identification of bacterial isolates and antibiotic resistance and could be readily extended for diagnostics on blood, urine, and sputum.

New material kills E. coli bacteria in 30 seconds


Infectious diseases and the increasing threat of worldwide pandemics have underscored the importance of antibiotics and hygiene. Intensive efforts have been devoted to developing new antibiotics to meet the rapidly growing demand. In particular, advancing the knowledge of the structure–property–activity relationship is critical to expedite the design and development of novel antimicrobial with the needed potential and efficacy. Herein, a series of new antimicrobial imidazolium oligomers are developed with the rational manipulation of terminal group's hydrophobicity.

Komodo DRAGONS could hold the key to beating superbugs

Daily Mail - Science & tech

They're the largest lizards in the world, with deadly saliva that's loaded with at least 57 species of bacteria to bring down their prey. And, according to new research, the blood of Komodo dragons could be the key to developing new drugs in the fight against antibiotic-resistant superbugs. The team used a method known as'bioprospecting,' revealing antimicrobial protein fragments in their blood that protects them against infections. They're the largest lizards in the world, with deadly saliva that's loaded with at least 57 species of bacteria to bring down their prey. Antibiotic resistance occurs when bacteria change to'outsmart' or resist antibiotic medicine, making it close to impossible to treat the infection.

3D-printed anti-bacterial smartphone cases could help to stop the spread of superbugs like MRSA

Daily Mail - Science & tech

A new anti-bacterial material that can be used to make smartphone cases could hep to stop the spread of deadly superbugs. British scientists have created 3D-printed parts that kill bacteria which have become resistant to antibiotics, such as the dreaded MRSA. The material could be used in general parts for hospitals, door handles, children's toys, dentures and everyday consumer products. It promises to halt outbreaks of serious illnesses in wards and care homes – potentially saving the lives of vulnerable patients. 'Managing the spread of harmful bacteria, infection and the increasing resistance to antibiotics is a global concern,' said Dr Candice Majewski, a mechanical engineering at the University of Sheffield.

Quick 2 test reveals if you caught a superbug in hospital

New Scientist

At last we have a way to rapidly detect if a patient has picked up a bacterial infection while in hospital. The device could help doctors catch and treat infections more quickly, and slow the rise of deadly superbugs like MRSA (methicillin-resistant Staphylococcus aureus). Hospitals are meant to be places of healing, but 1 in 15 patients in developed countries will catch an infection during their stay. Such bacteria can be resistant to antibiotics, and can spread between patients with fatal consequences. Doctors therefore need ways to identify infected patients early, so they can be isolated and treated before the infection passes to others, says Hakho Lee of Harvard Medical School in Boston.