NERDG 2026
Poster 33 Abstract
Detection of Anthracycline Accumulation Using Optical Spectral Fingerprinting
Atara R. Israel (1), Yunjung Kim (2,3), Adnan Arnaout (1), Myesha Thahsin (1), Yumna Ahmed (1), Zachary Cohen (1), Amelia Ryan (1), Syeda Rahman (1), Mijin Kim (2), Ryan Williams (1,4)
(1) Department of Biomedical Engineering, The City College of New York, New York, NY, USA, (2) School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, GA, USA (3) Department of Chemistry, Hanyang University, Seoul, Republic of Korea, (4) Department of Medicine, Stony Brook University, Stony Brook, NY, USA
Presenting and Corresponding Author: Atara R. Israel, [email protected]
Abstract
A major side effect of anthracycline administration presents is cardiotoxicity, as anthracyclines accumulate in cardiac tissue. The inability to monitor their accumulation in vivo in a noninvasive, rapid, and continuous manner presents a challenge in early diagnosis of cardiotoxicity and therapeutic drug monitoring of anthracyclines. While there are established guidelines for dosing these drugs, high interpatient variability coupled with variable drug pharmacology make it difficult to gauge the onset of cardiotoxicity. To reduce this risk and more effectively understand these drugs’ pharmacology, we developed fluorescent nanosensors using single walled carbon nanotubes (SWCNT) that can rapidly and continuously monitor anthracycline accumulation in a concentration-dependent manner. SWCNT fluoresce stably in the near infrared region, which is tissue-transparent. Several species of fluorescent SWCNT exist due to structural chirality which have independent excitation/emission wavelengths. SWCNT are dispersed with ssDNA for individual dispersion, which imparts hydrophilicity and fluorescence, and promotes interaction with anthracyclines.
To create chemical library diversity, multi-species SWCNT were dispersed with 12 unique ssDNAs and challenged with four anthracyclines: daunorubicin, doxorubicin, epirubicin, and idarubicin, at concentrations ranging from 0.1–100 μM. We evaluated spectral fingerprints for each drug by analyzing spectral changes and ssDNA-chirality pairings using principal component analysis (PCA) to determine which factors most contributed to anthracycline detection. PCA successfully differentiated sensor responses based on anthracycline concentration. Further binary classification used supervised machine learning models k-nearest neighbor (k-NN) and support vector machine (SVM) to determine the accuracy of classifying each anthracycline’s concentration-based spectral changes in buffer and synthetic biofluids. We found that the models were strongly predictive for classifying responses from daunorubicin and idarubicin, exhibiting 100% cross validation, test accuracy, and validation in synthetic biofluids. Multi-class classification distinguished anthracycline type by spectral fingerprint, with 100% accuracy using Decision Tree and eXtreme Gradient Boosting models. Future work will use the top performing sensor platforms determined by PCA to develop a noninvasive therapeutic drug monitoring tool to monitor accumulation at the tumor and in the heart during chemotherapy. We anticipate this work will improve tolerance for anthracycline chemotherapy by establishing personalized pharmacological treatment windows and improving current computational pharmacologic models.
Keywords
doxorubicin, single-walled carbon nanotubes, machine learning, near-infrared, cardiotoxicity
Poster 33 Abstract
Detection of Anthracycline Accumulation Using Optical Spectral Fingerprinting
Atara R. Israel (1), Yunjung Kim (2,3), Adnan Arnaout (1), Myesha Thahsin (1), Yumna Ahmed (1), Zachary Cohen (1), Amelia Ryan (1), Syeda Rahman (1), Mijin Kim (2), Ryan Williams (1,4)
(1) Department of Biomedical Engineering, The City College of New York, New York, NY, USA, (2) School of Chemistry and Biochemistry, Georgia Institute of Technology, Atlanta, GA, USA (3) Department of Chemistry, Hanyang University, Seoul, Republic of Korea, (4) Department of Medicine, Stony Brook University, Stony Brook, NY, USA
Presenting and Corresponding Author: Atara R. Israel, [email protected]
Abstract
A major side effect of anthracycline administration presents is cardiotoxicity, as anthracyclines accumulate in cardiac tissue. The inability to monitor their accumulation in vivo in a noninvasive, rapid, and continuous manner presents a challenge in early diagnosis of cardiotoxicity and therapeutic drug monitoring of anthracyclines. While there are established guidelines for dosing these drugs, high interpatient variability coupled with variable drug pharmacology make it difficult to gauge the onset of cardiotoxicity. To reduce this risk and more effectively understand these drugs’ pharmacology, we developed fluorescent nanosensors using single walled carbon nanotubes (SWCNT) that can rapidly and continuously monitor anthracycline accumulation in a concentration-dependent manner. SWCNT fluoresce stably in the near infrared region, which is tissue-transparent. Several species of fluorescent SWCNT exist due to structural chirality which have independent excitation/emission wavelengths. SWCNT are dispersed with ssDNA for individual dispersion, which imparts hydrophilicity and fluorescence, and promotes interaction with anthracyclines.
To create chemical library diversity, multi-species SWCNT were dispersed with 12 unique ssDNAs and challenged with four anthracyclines: daunorubicin, doxorubicin, epirubicin, and idarubicin, at concentrations ranging from 0.1–100 μM. We evaluated spectral fingerprints for each drug by analyzing spectral changes and ssDNA-chirality pairings using principal component analysis (PCA) to determine which factors most contributed to anthracycline detection. PCA successfully differentiated sensor responses based on anthracycline concentration. Further binary classification used supervised machine learning models k-nearest neighbor (k-NN) and support vector machine (SVM) to determine the accuracy of classifying each anthracycline’s concentration-based spectral changes in buffer and synthetic biofluids. We found that the models were strongly predictive for classifying responses from daunorubicin and idarubicin, exhibiting 100% cross validation, test accuracy, and validation in synthetic biofluids. Multi-class classification distinguished anthracycline type by spectral fingerprint, with 100% accuracy using Decision Tree and eXtreme Gradient Boosting models. Future work will use the top performing sensor platforms determined by PCA to develop a noninvasive therapeutic drug monitoring tool to monitor accumulation at the tumor and in the heart during chemotherapy. We anticipate this work will improve tolerance for anthracycline chemotherapy by establishing personalized pharmacological treatment windows and improving current computational pharmacologic models.
Keywords
doxorubicin, single-walled carbon nanotubes, machine learning, near-infrared, cardiotoxicity
