Tuberculosis and Machine learning

Antimicrobial resistance (AMR) represents a health threat that demands joint action globally. At TTA4, we will address bacterial physiology, metabolism, virulence and host adaptation, exemplified by Mycobacterium tuberculosis (Mtb), and how genome dynamics impact on Mtb fitness adaptation in changing environments and on antimicrobial resistance (AMR). The topics addressed will be relevant for mycobacterial pathogenesis and evolution, genome dynamics and AMR in general. Biochemical, genetic, live imaging and ultrastructural approaches are used to probe the interactions between proteins of these pathways. The objective of the meeting is to highlight recent progress, to reveal a more integrated understanding of the architecture of mycobacterial physiology, fitness for survival and AMR. A main part of the meeting is dedicated to machine learning relevant for these topics. Infection biology and biomedicine are prime examples of research fields in swift development, not the least because of integrated approaches and multidisciplinary interactions between different segments of the life sciences. The increasing complexity of microbiological data and emergence of Big Data invigorates a need for deep learning, machine learning (ML) and artificial intelligence (AI). All the new –omics data pave the way for ML and AI. Big Data has become too complex for humans to even try to understand their impact. That's what big data is: It's the realization that there exist piles of data beyond the capacity of the traditional human methods of analysis. ML is a field that combines systematic information, computer programming, and AI, all in one synergistic manner. Big data and ML will have a tremendous influence on our society ahead. This presents a serious challenge and is a tremendous opportunity to apply automated techniques to help solve problems in infection biology in the 21st century.