Genetic Profile-Based Drug Sensitivity Prediction in Acute Myeloid Leukemia Patients Using SVR

TL;DR

This study demonstrates that Support Vector Regression can accurately predict drug sensitivity in AML patients using genetic profiles, potentially enabling personalized treatment strategies.

Contribution

The paper introduces a novel application of SVR for predicting drug response in AML based solely on genetic features, achieving high accuracy.

Findings

SVR model achieved R-squared of 0.9523 on validation set

Identified key genetic features influencing drug response

Demonstrated potential for personalized AML treatment

Abstract

Acute Myeloid Leukemia (AML) is a highly aggressive blood cancer with low survival rates. Hence, emphasizing the importance of the urgent need for effective treatment modalities. In recent times, the advances in cancer genomics have increased our understanding of AML, as a result, enabling precision oncologists to develop personalized treatment based on individual genetic features and increase the survival rate. However, there is a lack of understanding of how effectively genetic features can be used to predict which drugs are the most suitable for individual-tailored treatment. Therefore, this study explores the potential of Support Vector Regression (SVR) in predicting drug sensitivity of AML patients solely based on their genetic profile. The paper utilized a dataset from Genomics of Drug Sensitivity (GDSC) and developed a precise model that identified the most significant genetic features affecting drug response and achieved promising results with an R-squared score of 0.9523 on the validation set and 0.8928 on the test set.