14 Artificial intelligence and MALDI-TOF MS
-
Vaidya Mayuri
Abstract
Matrix-assisted laser desorption ionization – time of flight (MALDI-TOF) mass spectrometry (MS) is a technology for the identification of microorganisms since 2009. Although MALDI-TOF MS is highly accurate for microbial fingerprinting and the discovery of new organisms, its resolution power falls to the genus level with phylogenetically closely related species. In this era of advancement in artificial intelligence (AI), various frontiers are being explored to develop machine learning (ML)-based solutions. The analysis of the huge amount of information in the MS, derived from MALDI-TOF, using AI has the potential to be a breakthrough in biomolecular identification. Unidentified proteins can be characterized by AI algorithms comparing MS spectra with well-populated protein databases. These identifications can be made more accurate with ML models, which are able to learn from large datasets of known spectra. Using their mass spectra, proteins or peptides could be grouped into different categories by ML models support vector machine, genetic algorithm, artificial/supervised neural networkartificial/supervised neural network, and quick classifier. AI-assisted MALDI-TOF MS could be the next-gen solution to interpret data faster and more accurately.
Abstract
Matrix-assisted laser desorption ionization – time of flight (MALDI-TOF) mass spectrometry (MS) is a technology for the identification of microorganisms since 2009. Although MALDI-TOF MS is highly accurate for microbial fingerprinting and the discovery of new organisms, its resolution power falls to the genus level with phylogenetically closely related species. In this era of advancement in artificial intelligence (AI), various frontiers are being explored to develop machine learning (ML)-based solutions. The analysis of the huge amount of information in the MS, derived from MALDI-TOF, using AI has the potential to be a breakthrough in biomolecular identification. Unidentified proteins can be characterized by AI algorithms comparing MS spectra with well-populated protein databases. These identifications can be made more accurate with ML models, which are able to learn from large datasets of known spectra. Using their mass spectra, proteins or peptides could be grouped into different categories by ML models support vector machine, genetic algorithm, artificial/supervised neural networkartificial/supervised neural network, and quick classifier. AI-assisted MALDI-TOF MS could be the next-gen solution to interpret data faster and more accurately.
Kapitel in diesem Buch
- Frontmatter I
- Dedication V
- Preface VII
- Contents IX
- 1 Understanding artificial intelligence: an introduction, history, and foundations 1
- 2 Basics of machine learning (ML) and deep learning (DL), secondary data source and training, application and AI tools, challenges, and future perspectives of AI 25
- 3 Cellular image classification and identification of genetic variations using artificial intelligence 47
- 4 Artificial intelligence in bacterial staining and cell counting 65
- 5 Use of artificial intelligence in the prediction of microbial species 79
- 6 Transformative AI applications in environmental microbiology: pioneering research and sustainable solutions 97
- 7 AI in food production and processing: applications and challenges 125
- 8 Artificial intelligence in microbial food safety 153
- 9 AI in plant growth promotion and plant disease management 183
- 10 Role of artificial intelligence (AI) and machine learning (ML) in disease forecasting and disease epidemiology 207
- 11 Artificial intelligence in diagnostics 229
- 12 Artificial intelligence in bacterial culture plate images 263
- 13 Prediction of antimicrobial activity using artificial intelligence 281
- 14 Artificial intelligence and MALDI-TOF MS 313
- 15 Artificial intelligence in clinical microbiology: regeneration of diagnostics techniques using GANs and reinforcement learning for drug discovery and development in human welfare 337
- 16 Reimagining perfusion bioreactors with artificial intelligence 357
- Index 381
Kapitel in diesem Buch
- Frontmatter I
- Dedication V
- Preface VII
- Contents IX
- 1 Understanding artificial intelligence: an introduction, history, and foundations 1
- 2 Basics of machine learning (ML) and deep learning (DL), secondary data source and training, application and AI tools, challenges, and future perspectives of AI 25
- 3 Cellular image classification and identification of genetic variations using artificial intelligence 47
- 4 Artificial intelligence in bacterial staining and cell counting 65
- 5 Use of artificial intelligence in the prediction of microbial species 79
- 6 Transformative AI applications in environmental microbiology: pioneering research and sustainable solutions 97
- 7 AI in food production and processing: applications and challenges 125
- 8 Artificial intelligence in microbial food safety 153
- 9 AI in plant growth promotion and plant disease management 183
- 10 Role of artificial intelligence (AI) and machine learning (ML) in disease forecasting and disease epidemiology 207
- 11 Artificial intelligence in diagnostics 229
- 12 Artificial intelligence in bacterial culture plate images 263
- 13 Prediction of antimicrobial activity using artificial intelligence 281
- 14 Artificial intelligence and MALDI-TOF MS 313
- 15 Artificial intelligence in clinical microbiology: regeneration of diagnostics techniques using GANs and reinforcement learning for drug discovery and development in human welfare 337
- 16 Reimagining perfusion bioreactors with artificial intelligence 357
- Index 381
