Novel application of automated machine learning with MALDI-TOF-MS for rapid high-throughput screening of COVID-19: a proof of concept

Abstract

The 2019 novel coronavirus infectious disease (COVID-19) pandemic caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has created an unsustainable need for molecular diagnostic testing. Molecular approaches such as reverse transcription (RT) polymerase chain reaction (PCR) offers highly sensitive and specific means to detect SARS-CoV-2 RNA, however, despite it being the accepted “gold standard”, molecular platforms often require a tradeoff between speed versus throughput. Matrix assisted laser desorption ionization (MALDI)—time of flight (TOF)—mass spectrometry (MS) has been proposed as a potential solution for COVID-19 testing and finding a balance between analytical performance, speed, and throughput, without relying on impacted supply chains. Combined with machine learning (ML), this MALDI-TOF-MS approach could overcome logistical barriers encountered by current testing paradigms. We evaluated the analytical performance of an ML-enhanced MALDI-TOF-MS method for screening COVID-19. Residual nasal swab samples from adult volunteers were used for testing and compared against RT-PCR. Two optimized ML models were identified, exhibiting accuracy of 98.3%, positive percent agreement (PPA) of 100%, negative percent agreement (NPA) of 96%, and accuracy of 96.6%, PPA of 98.5%, and NPA of 94% respectively. Machine learning enhanced MALDI-TOF-MS for COVID-19 testing exhibited performance comparable to existing commercial SARS-CoV-2 tests.

Application and Perspectives of MALDI–TOF Mass Spectrometry in Clinical Microbiology Laboratories

“…Another proof of concept is the combination of MS-based methods with machine learning (ML) and artificial intelligence (AI) [ 117 ], which is also demonstrating reliable detection of SARS-CoV-2 in swab samples. Tran et al [ 118 ] evaluated an automated ML platform, Machine Intelligence Learning Optimizer (MILO), combined with MALDI–TOF MS for rapid high-throughput screening of COVID-19 and showing promising accuracy (96.6–98.3%), sensitivity (positive percent agreement of 98.5–100%), and specificity (negative percent agreement of 94–96%) [ 118 ], respectively, for two different ML models. Similarly, Delofeu et al analyzed 236 nasopharyngeal swab samples, and the subsequent mass spectra data was used to build different ML models, showing a performance of >90% accuracy, sensitivity, and specificity.…”

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

“…Machine learning (ML) methods can identify statistical dependencies in data while considering the nonlinearity and interaction effects between features [68]. Following current advances, machine learning technology can unravel novel information embedded in the MALDI TOF mass spectrum [69]. This information is useful for the identification and differentiation of species, especially those that are phylogenetically closer at the subspecies level.…”

MALDI MS-Based Investigations for SARS-CoV-2 Detection

“…As exemplified in Figure 2, current MALDI-MS approaches aimed at the detection of SARS-CoV-2 are based on "biotyping" [69,70] and "genotyping" [71][72][73] strategies. One study is based on "proteotyping" with high resolution MALDI-FTICR at the peptide level [74], while several studies used the "biomolecular host profiling" strategy to uncover biomarkers of diagnostic utility generated after SARS-CoV-2 infection [75][76][77][78][79]. In particular, the investigations by Iles et al and Chivte et al used both biotyping and biomolecular host profiling strategies [69,70].…”

“…In this section, we report the MALDI-MS-based investigations which aimed to detect SARS-CoV-2 infection with the use of "proteotyping" [74], "biotyping" [69,70], "genotyping" [71][72][73], and biomolecular host profiling [75][76][77][78][79] approaches. Interestingly, two of these investigations used both biotyping and biomolecular host profiling strategies [69,70].…”