Machine Learning in Mass Spectrometry: A MALDI-TOF MS Approach to Phenotypic Antibacterial Screening

Abstract

Machine learning techniques can be applied to MALDI-TOF mass spectral data of drug-treated cells to obtain classification models which assign the mechanism of action of drugs. Here, we present an example application of this concept to the screening of antibacterial drugs that act at the major bacterial target sites such as the ribosome, penicillin-binding proteins, and topoisomerases in a pharmacologically relevant phenotypic setting. We show that antibacterial effects can be identified and classified in a label-free, high-throughput manner using wild-type Escherichia coli and Staphylococcus aureus cells at variable levels of target engagement. This phenotypic approach, which combines mass spectrometry and machine learning, therefore denoted as PhenoMS-ML, may prove useful for the identification and development of novel antibacterial compounds and other pharmacological agents.

Mass spectrometry and machine learning for the accurate diagnosis of benzylpenicillin and multidrug resistance of Staphylococcus aureus in bovine mastitis

“…In this work, we have opted to pre-process all the data together as previously done by several studies [42,[65][66][67][68] instead of splitting it into a training and validation sets for several reasons. First, given the low number of samples in each of the two minority classes (multidrug resistant and benzylpenicillin-only resistant) it would have been not possible to have a sufficient number of observations in each set and each partition being enough representative to yield a good peak selection.…”

“…In particular, successful separation of vancomycin-intermediate (VISA) from vancomycin-susceptible S. aureus (VSSA) on the basis of MALDI-TOF data collected from clinical samples [37,40,41]. Recently, van Oosten and Klein [42], developed classification models for S. aureus which assign the mechanisms of action of antibacterial drugs.…”

Current Scenario and Challenges in the Direct Identification of Microorganisms Using MALDI TOF MS

“…This information is useful for the identification and differentiation of species, especially those that are phylogenetically closer at the subspecies level. Van Oosten et al demonstrated an application of this proof-of-concept in the screening of antibacterial drugs acting on major target proteins such as ribosomes, penicillin-binding proteins, and topoisomerases, in a pharmacologically relevant phenotypic environment, by combining MS and ML [70]. In addition, while 27 studies employed ML for species identification, nine studies used ML for antimicrobial susceptibility testing [71].…”

COVID-19 PCR Testi Veri Analizinde CAtenA Smart PCR Bioinformatik Programının Sunduğu Ön Değerlendirme Sonuçlarının Uzman Sonuçları ile Uyumunun Araştırılması

“…Son zamanlarda yapay zeka Mikrobiyoloji laboratuvarlarında görüntü analizi dışındaki çeşitli veri kaynakları ve uygulamalarda yerini almaya başlamıştır (Smith et al, 2020;Asada et al, 2021). Matrix-assisted laser desorption-ionization/time of flight mass spectrometry (MALDI-TOF) kütle spektrometri ve tüm gen analizi verilerinin yapay zeka yardımıyla işlenmesi Mikrobiyoloji alanında yeni bir çığır açmıştır (van Oosten & Klein, 2020). CAtenA Smart PCR (Ventura, Ankara, Türkiye), PCR veri dosyalarını yapay zeka ile değerlendirerek uzman onayına sunan ve onaylanmış sonuçları Laboratuvar Bilgi Yönetim Sistemi'ne aktarabilen web tabanlı biyoinformatik bir programdır (Ventura, 2020).…”