Optimization of Optical Nanosensor Response for the Detection of Anthracyclines Using a Binary Machine Learning Classifier

<p>Pharmacokinetic variables such as interindividual variation in metabolizing and eliminating drugs makes dose selection of chemotherapeutic anthracyclines difficult. One potential solution to determining dosing levels of an anthracycline is the development of non-invasive sensors to monitor their pharmacology in vivo. Single-walled carbon nanotubes (SWCNT) have substantial potential for in vivo sensor development, as they exhibit near-infrared fluorescence in the tissue-transparent window and a robust response to their local environment. An emerging method for evaluating and optimizing SWCNT sensor response is through machine learning. In this study, anthracyclines Daunorubicin, Doxorubicin, Epirubicin, Mitoxantrone and Idarubicin, were used to interrogate 12 SWCNT preparations wrapped with separate oligonucleotide sequences. In triplicate, the near-infrared fluorescence responses of each combination of oligonucleotide and anthracycline were evaluated when challenged with concentrations ranging from 0.01 µM – 1000 µM using a custom-built high-throughput platereader. A machine learning algorithm using MATLAB’s machine learning toolbox was implemented which utilized cross validation and validated distinct machine learning models to test the dataset for various anthracycline predictor variables. It was used to detect several anthracyclines at varying concentrations for each oligonucleotide sequence for chemometric screening. Analysis of each anthracycline-SWCNT combination revealed specific patterns of fluorescence modulation. The machine learning algorithm allowed for optimized prediction of responses in fluorescence signals, including changes in wavelength and intensity, for a specific combination following laser excitation and high-throughput spectroscopy. We found that such an algorithm can be utilized not only for precision medicine but also for analyzing patterns in responses of fluorescent nanosensors to a class of chemotherapeutics and therefore detecting the specific anthracycline. We anticipate future work in developing multi-purpose nanosensors that monitor the pharmacokinetics of active pharmaceutics to decrease toxicity while improving on-target efficacy. </p>

Name thesis:degree_name

Master of Science (M.S.)

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Biomedical Engineering

Year dc:date.available

2023

Author dc:creator

• Thahsin, Myesha

Contributors dc:contributor

• Ryan M. Williams
• Steven B. Nicoll
• Bingmei Fu

• Nanosensors
• Machine Learning
• Anthracycline
• Pharmacokinetics
• Chemotherapy
• Biomedical Engineering and Bioengineering
• Computer Sciences

Repository record dc:identifier

https://academicworks.cuny.edu/cc_etds_theses/1154

OAI identifier oai:identifier

oai:academicworks.cuny.edu:cc_etds_theses-2194