Machine Learning Assisted Experimental Design Approach to Optimize Parameters for Photodynamic Antimicrobial Chemotherapy


Kırımlı E. E., Dumoulin F., Lhez S., İşci Ü., Kirimli C.

Diğer, ss.23, 2024

  • Yayın Türü: Diğer Yayınlar / Diğer
  • Basım Tarihi: 2024
  • Sayfa Sayıları: ss.23
  • Acıbadem Mehmet Ali Aydınlar Üniversitesi Adresli: Evet

Özet

Antimicrobial resistance (AMR) is a major threat for mankind, and 10 million deaths are feared per year by 2050 if no solution is found. Because of the unlikely development of resistance thanks to its general oxidative mode of action, photodynamic antimicrobial chemotherapy (PACT) is a promising alternative to antibiotics. If many researches are performed, they are hardly comparable due to the very different types of photosensitisers and delivery systems, and experimental conditions. Machine learning (ML) is an important component of the growing field of data science. Through the use of statistical methods, various types of algorithms are trained to reveal key insights in data analysis projects. In this study, to provide a comprehensive explanation of the optimized structural and experimental parameters to prepare phthalocyanine-containing lignin nanoparticles for PACT. Multiple inputs will be tested, such as phthalocyanines’ metalation and substitution, acetylation vs methylation of lignin, PS/lignin ratio, bacteria strain, illumination conditions to determine their effects on intermediate outputs such as nanoparticles features and properties, the ultimate output being the photodynamic killing efficiency on bacteria.