Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/135208
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Journal article |
Title: | Multi-Cohort Transcriptomic Subtyping of B-Cell Acute Lymphoblastic Leukemia |
Author: | Mäkinen, V.-P. Rehn, J. Breen, J. Yeung, D. White, D.L. |
Citation: | International Journal of Molecular Sciences, 2022; 23(9):1-17 |
Publisher: | MDPI AG |
Issue Date: | 2022 |
ISSN: | 1661-6596 1422-0067 |
Statement of Responsibility: | Ville-Petteri Mäkinen, Jacqueline Rehn, James Breen, David Yeung, and Deborah L. White |
Abstract: | RNA sequencing provides a snapshot of the functional consequences of genomic lesions that drive acute lymphoblastic leukemia (ALL). The aims of this study were to elucidate diagnostic associations (via machine learning) between mRNA-seq profiles, independently verify ALL lesions and develop easy-to-interpret transcriptome-wide biomarkers for ALL subtyping in the clinical setting. A training dataset of 1279 ALL patients from six North American cohorts was used for developing machine learning models. Results were validated in 767 patients from Australia with a quality control dataset across 31 tissues from 1160 non-ALL donors. A novel batch correction method was introduced and applied to adjust for cohort differences. Out of 18,503 genes with usable expression, 11,830 (64%) were confounded by cohort effects and excluded. Six ALL subtypes (ETV6::RUNX1, KMT2A, DUX4, PAX5 P80R, TCF3::PBX1, ZNF384) that covered 32% of patients were robustly detected by mRNA-seq (positive predictive value ≥ 87%). Five other frequent subtypes (CRLF2, hypodiploid, hyperdiploid, PAX5 alterations and Ph-positive) were distinguishable in 40% of patients at lower accuracy (52% ≤ positive predictive value ≤ 73%). Based on these findings, we introduce the Allspice R package to predict ALL subtypes and driver genes from unadjusted mRNA-seq read counts as encountered in real-world settings. Two examples of Allspice applied to previously unseen ALL patient samples with atypical lesions are included. |
Keywords: | acute lymphoblastic leukemia RNA-seq confounder adjustment machine learning |
Rights: | © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). |
DOI: | 10.3390/ijms23094574 |
Grant ID: | http://purl.org/au-research/grants/nhmrc/1160833 |
Published version: | http://dx.doi.org/10.3390/ijms23094574 |
Appears in Collections: | Medical Sciences publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
hdl_135208.pdf | Published version | 988.4 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.