Differentiation of Pectobacterium and Dickeya spp. phytopathogens using infrared spectroscopy and machine learning analysis

Abstract

Pectobacterium and Dickeya spp. are soft rot Pectobacteriaceae that cause aggressive diseases on agricultural crops leading to substantial economic losses. The accurate, rapid and low-cost detection of these pathogenic bacteria are very important for controlling their spread, reducing the consequent financial loss and for producing uninfected potato seed tubers for future generations. Currently used methods for the identification of these bacterial pathogens at the strain level are based mainly on molecular techniques, which are expensive. We used an alternative method, infrared spectroscopy, to measure 24 strains of five species of Pectobacterium and Dickeya. Measurements were then analyzed using machine learning methods to differentiate among them at the genus, species and strain levels. Our results show that it is possible to differentiate among different bacterial pathogens with a success rate of~99% at the genus and species levels and with a success rate of over 94% at the strain level.linear support vector machine (lSVM), quadratic support vector machine (qSVM), soft rot Pectobacteriaceae (SRP), vibrational spectroscopy

Discrimination of bacteria using whole organism fingerprinting: the utility of modern physicochemical techniques for bacterial typing

“…Other authors have also illustrated the ability of FT-IR coupled with robust chemometrics to discriminate between different infectious Listeria spp. 66 , lactic acid bacteria 67 , Salmonella 68 and Pectobacterium and Dickeya spp.. 69 These studies clearly demonstrate that FT-IR spectroscopy is capable of classifying and differentiating between medically and industrially important bacteria and other microorganisms at various taxonomic levels, which are important prerequisites for appropriate patient management and protection of public health.…”

Advances in Spectral Techniques for Detection of Pathogenic Microorganisms

“…FTIR can be combined with multivariate analysis to identify organisms at the species and strain levels, thus helping to prevent food poisoning and zoonoses [41,42]. Through a combination of FTIR with machine learning methods such as PCA, 24 strains in five species of Pectobacterium and Dickeya have been identified with 99% accuracy at the genus and species levels, and above 94% accuracy at the strain level [43]. A total of 174 food-related bacteria (of 93 species) from an in-house collection and 40 fresh isolates from routine foods have been analyzed by FTIR and matrix assisted laser desorption/ionization-time of flight mass spectrometry, with identification accuracy at the species level of 88% and 75%, respectively [44].…”

Raman Spectroscopy and Machine Learning for Agricultural Applications: Chemometric Assessment of Spectroscopic Signatures of Plants as the Essential Step Toward Digital Farming

“…The greatest advantage of IR is its ability to associate chemical changes with differences between stresses or varieties of plants or pathogens. Abu-Aqil and colleagues illustrated this in their differentiation of phytopathogenic bacteria from two different genera and several strains ( Abu-Aqil et al, 2020 ). Bacterial samples were isolated from infected plant material, cultured, then sampled using FT-IR following a brief drying period.…”