A research team from the Korea Advanced Institute of Science and Technology (KAIST) has developed a ‘fingerprint’ algorithm to aid in a quicker and more accurate bacterial identification process.
Why is this bacterial identification method ‘better’?
Typically, bacterial identification can take hours and often longer, which is valuable time when it comes to diagnosing infections and selecting appropriate treatments.
Researchers at KAIST approached this issue by teaching a deep learning algorithm to identify the ‘fingerprint’ spectra of the molecular components of various bacteria. This means that researchers can classify several bacteria in different media with accuracies of up to 98%.
The scientists’ results were made available online on 18 January in Biosensors and Bioelectronics.
Bacteria-induced illnesses caused by direct bacterial infection, or by exposure to bacterial toxins, can induce painful symptoms and even lead to death, so the swift detection of bacteria is critical both in preventing the intake of contaminated foods, and diagnosing infections from clinical samples, such as urine.
How does this fingerprint algorithm work?
“By using surface-enhanced Raman spectroscopy (SERS) analysis boosted with a newly proposed deep learning model, we demonstrated a markedly simple, fast, and effective route to classify the signals of two common bacteria and their resident media without any separation procedures,” explained Professor Sungho Jo, from the School of Computing.
Raman spectroscopy sends light through a sample to see how it scatters. Scientists noted structural information about the sample — or the spectral fingerprint — allowed researchers to identify its molecules. The surface-enhanced version places sample cells on noble metal nanostructures that help amplify the sample’s signals.
However, it is challenging to obtain consistent and clear spectra of bacteria due to several overlapping peak sources, such as the proteins in cell walls. “Moreover, strong signals of surrounding media are also enhanced to overwhelm target signals, requiring time-consuming and tedious bacterial separation steps,” said Professor Yeon Sik Jung, from the Department of Materials Science and Engineering.
To analyse the noisy signals, the research team implemented an artificial intelligence method called ‘deep learning’ that can hierarchically extract certain features of the spectral information to classify data.
Scientists specifically designed their model, identified as the dual-branch wide-kernel network (DualWKNet), to efficiently learn the correlation between spectral features. Such an ability is critical for analysing one-dimensional spectral data, according to Professor Jo.
Jo added: “Despite having interfering signals or noise from the media, which make the general shapes of different bacterial spectra and their residing media signals look similar, high classification accuracies of bacterial types and their media were achieved.
“Ultimately, with the use of DualWKNet replacing the bacteria and media separation steps, our method dramatically reduces analysis time.”
The researchers intend to employ their platform to study more bacteria and media types, utilising the information to build a training data library of various bacterial types in additional media to reduce the collection and detection times for new samples.
“We developed a meaningful universal platform for rapid bacterial detection with the collaboration between SERS and deep learning,” Professor Jo concluded. “We hope to extend the use of our deep learning-based SERS analysis platform to detect numerous types of bacteria in additional media that are important for food or clinical analysis, such as blood.”
To keep up to date with our content, subscribe for updates on our digital publication and newsletter.
