A k-mer based transcriptomics analysis for NPM1-mutated AML

Abstract

Motivation: Acute Myeloid Leukemia is a highly heterogeneous disease. Although current classifications are well-known and widely adopted, many patients experience drug resistance and disease relapse. New biomarkers are needed to make classifications more reliable and propose personalized treatment. Results: We performed tests on a large scale in 3 AML cohorts, 1112 RNAseq samples. The accuracy to distinguish NPM1 mutant and non-mutant patients using machine learning models achieved more than 95% in three different scenarios. Using our approach, we found already described genes associated with NPM1 mutations and new genes to be investigated. Furthermore, we provide a new view to search for signatures/biomarkers and explore diagnosis/prognosis, at the k-mer level. Availability: Code available at https://github.com/railorena/npm1aml and https://osf.io/4s9tc/. The cohorts used in this article were authorized for use.

Risk stratification for younger and older patients with acute myeloid leukemia through transcriptomics, clinical data and machine learning

“…Using the matrices with selected k-mers, we have built machine learning models, and tested the models in samples from Beat-AML2.0. Based on our previous study to compare the best ML algorithm to predict mutations using k-mers [13], we used the eXtreme Gradient Boosting (XGB) algorithm because its complexity allowed the identification of non-linear links in biological data.…”