Anushka Peer & Dr. Varalakshmi Murugesan – James Logan High School & VIT University
Abstract
Myeloproliferative Neoplasms (MPNs) are clonal hematopoietic stem cell disorders (namely, Polycythemia Vera, Primary and Secondary Myelofibrosis, and Essential Thrombocythemia) that develop due to an abnormal mutation in the bone marrow, causing uncontrolled proliferation of blood cells. Detection and treatment for MPNs are through bone marrow biopsies, which tests for mutations in the JAK2, MPL, or CALR genes; these are mostly invasive and painful processes, carrying a risk for infection and especially for the vulnerable older patients the disease commonly targets. This project focuses on a clinal alternative: peripheral blood (PB) samples, which are blood cells produced in the bone marrow and circulating throughout the body. Using an expression profiling NCBI dataset, over 60,000 affymetrix probe IDs were analyzed from 60 MN patients, and both peripheral and bone marrow samples were utilized to develop a novel machine learning model. This model leverages many machine learning techniques, including Multi-Layer Perceptron neural networks, one-hot encode, multi-classification, binary and categorical cross entropy, and Principal Component Analysis to detect these mutations through an input of PB samples, reducing the need for bone marrow sampling. Using confusion matrices, ROC, and precision-threshold accuracy, the model was analyzed and tweaked for maximum performance. With a final binary accuracy of ~ 100% and precision of 100% and multi classification accuracy of 92.3%, the workflow was implemented into a live user interface software, taking in genetic data to predict disease status. The research also recognizes novel biomarkers of the myeloproliferative disorders through feature engineering, like VCAN, THBS1, BLNK, to name a few, which can promote future research on the disease.
Details
Session 2
3:00pm – 4:30pm
Grand Salon
Leave a Reply