Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia

Olga Krali; Yanara Marincevic-Zuniga; Gustav Arvidsson; Anna Pia Enblad; Anders Lundmark; Shumaila Sayyab; Vasilios Zachariadis; Merja Heinäniemi; Janne Suhonen; Laura Oksa; Kaisa Vepsäläinen; Ingegerd Öfverholm; Gisela Barbany; Ann Nordgren; Henrik Lilljebjörn; Thoas Fioretos; Hans O. Madsen; Hanne Vibeke Marquart; Trond Flaegstad; Erik Forestier; Ólafur G. Jónsson; Jukka Kanerva; Olli Lohi; Ulrika Norén-Nyström; Kjeld Schmiegelow; Arja Harila; Mats Heyman; Gudmar Lönnerholm; Ann Christine Syvänen; Jessica Nordlund

doi:10.1038/s41698-023-00479-5

Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia

Olga Krali, Yanara Marincevic-Zuniga, Gustav Arvidsson, Anna Pia Enblad, Anders Lundmark, Shumaila Sayyab, Vasilios Zachariadis, Merja Heinäniemi, Janne Suhonen, Laura Oksa, Kaisa Vepsäläinen, Ingegerd Öfverholm, Gisela Barbany, Ann Nordgren, Henrik Lilljebjörn, Thoas Fioretos, Hans O. Madsen, Hanne Vibeke Marquart, Trond Flaegstad, Erik ForestierÓlafur G. Jónsson, Jukka Kanerva, Olli Lohi, Ulrika Norén-Nyström, Kjeld Schmiegelow, Arja Harila, Mats Heyman, Gudmar Lönnerholm, Ann Christine Syvänen, Jessica Nordlund

Research output: Contribution to journal › Article › Scientific › peer-review

5 Citations (Scopus)

6 Downloads (Pure)

Abstract

Genomic analyses have redefined the molecular subgrouping of pediatric acute lymphoblastic leukemia (ALL). Molecular subgroups guide risk-stratification and targeted therapies, but outcomes of recently identified subtypes are often unclear, owing to limited cases with comprehensive profiling and cross-protocol studies. We developed a machine learning tool (ALLIUM) for the molecular subclassification of ALL in retrospective cohorts as well as for up-front diagnostics. ALLIUM uses DNA methylation and gene expression data from 1131 Nordic ALL patients to predict 17 ALL subtypes with high accuracy. ALLIUM was used to revise and verify the molecular subtype of 281 B-cell precursor ALL (BCP-ALL) cases with previously undefined molecular phenotype, resulting in a single revised subtype for 81.5% of these cases. Our study shows the power of combining DNA methylation and gene expression data for resolving ALL subtypes and provides a comprehensive population-based retrospective cohort study of molecular subtype frequencies in the Nordic countries.

Original language	English
Article number	131
Journal	NPJ precision oncology
Volume	7
Issue number	1
DOIs	https://doi.org/10.1038/s41698-023-00479-5
Publication status	Published - Dec 2023
Publication type	A1 Journal article-refereed

Funding

This work was supported by grants from the Swedish Research Council (2019-01976 to JN), the Swedish Cancer Society (CAN2018-623 to ACS and CAN2022-2395 to JN), the Swedish Childhood Cancer Foundation (PR2017-0023 to ACS and PR2019-0046 to JN), the Göran Gustafsons Foundation (to JN), the Jane and Aatos Erkko Foundation and the Academy of Finland #321550 (to OL and MH). DNA methylation array analysis and RNA-sequencing was performed with assistance from the SciLifeLab National Genomics Infrastructure, SNP&SEQ Technology Platform, which is funded by the Swedish Research Council and the Knut and Alice Wallenberg Foundation. Computational resources were provided by the Swedish National Infrastructure for Computing (SNIC), National Academic Infrastructure for Supercomputing in Sweden (NAISS) and the Finnish IT Centre of Science (CSC) and University of Eastern Finland Bioinformatics Center. SNIC and NAISS are partially funded by the Swedish Research Council. We thank Sara Nystedt and Sara Nilsson for technical assistance, Jonas Carlsson Almlöf and Christofer Bäcklin for input on DNA methylation classification, and our colleagues from NOPHO LL Biology Group, Lucia Cavelier, Anna Bremer and Tatjana Pandzic for valuable input on the study design. We especially thank the ALL patients who contributed samples to this study. Figures 1 , 5f and Supplementary Figs. 2 –3 were made with Biorender.com. This work was supported by grants from the Swedish Research Council (2019-01976 to JN), the Swedish Cancer Society (CAN2018-623 to ACS and CAN2022-2395 to JN), the Swedish Childhood Cancer Foundation (PR2017-0023 to ACS and PR2019-0046 to JN), the Göran Gustafsons Foundation (to JN), the Jane and Aatos Erkko Foundation and the Academy of Finland #321550 (to OL and MH). DNA methylation array analysis and RNA-sequencing was performed with assistance from the SciLifeLab National Genomics Infrastructure, SNP&SEQ Technology Platform, which is funded by the Swedish Research Council and the Knut and Alice Wallenberg Foundation. Computational resources were provided by the Swedish National Infrastructure for Computing (SNIC), National Academic Infrastructure for Supercomputing in Sweden (NAISS) and the Finnish IT Centre of Science (CSC) and University of Eastern Finland Bioinformatics Center. SNIC and NAISS are partially funded by the Swedish Research Council. We thank Sara Nystedt and Sara Nilsson for technical assistance, Jonas Carlsson Almlöf and Christofer Bäcklin for input on DNA methylation classification, and our colleagues from NOPHO LL Biology Group, Lucia Cavelier, Anna Bremer and Tatjana Pandzic for valuable input on the study design. We especially thank the ALL patients who contributed samples to this study. Figures , and Supplementary Figs. – were made with Biorender.com.

Funders	Funder number
Finnish IT Centre for Science
University of Eastern Finland Bioinformatics Center
Göran Gustafssons Stiftelser
Academy of Finland	321550
Cancerfonden	CAN2018-623, CAN2022-2395
Jane ja Aatos Erkon Säätiö
Knut och Alice Wallenbergs Stiftelse
Vetenskapsrådet	2019-01976
China Scholarship Council
Barncancerfonden	PR2017-0023, PR2019-0046

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Oncology
Cancer Research

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41698-023-00479-5Licence: CC BY

s41698-023-00479-5Final published version, 2.63 MBLicence: CC BY

https://urn.fi/URN:NBN:fi:tuni-202401051107Licence: CC BY

Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia
Krali, O. (Creator), Marincevic-Zuniga, Y. (Creator), Arvidsson, G. (Creator), Enblad, A. P. (Creator), Lundmark, A. (Creator), Sayyab, S. (Creator), Zachariadis, V. (Creator), Heinäniemi, M. (Creator), Suhonen, J. (Creator), Oksa, L. (Creator), Vepsäläinen, K. (Creator), Öfverholm, I. (Creator), Barbany, G. (Creator), Nordgren, A. (Creator), Lilljebjörn, H. (Creator), Fioretos, T. (Creator), Madsen, H. O. (Contributor), Marquart, H. V. (Creator), Flaegstad, T. (Creator), Forestier, E. (Creator), Jónsson, Ó. G. (Creator), Kanerva, J. (Creator), Lohi, O. (Creator), Norén-Nyström, U. (Creator), Schmiegelow, K. (Creator), Harila, A. (Creator), Heyman, M. (Creator), Lönnerholm, G. (Creator), Syvänen, A.-C. (Creator) & Nordlund, J. (Creator), SciLifeLab, 23 Mar 2023
DOI: 10.17044/scilifelab.22303531.v3
Dataset

Cite this

Krali, O., Marincevic-Zuniga, Y., Arvidsson, G., Enblad, A. P., Lundmark, A., Sayyab, S., Zachariadis, V., Heinäniemi, M., Suhonen, J., Oksa, L., Vepsäläinen, K., Öfverholm, I., Barbany, G., Nordgren, A., Lilljebjörn, H., Fioretos, T., Madsen, H. O., Marquart, H. V., Flaegstad, T., ... Nordlund, J. (2023). Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia. NPJ precision oncology, 7(1), Article 131. https://doi.org/10.1038/s41698-023-00479-5

@article{8bc0d3c53f75488e806dde77496477f0,

title = "Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia",

abstract = "Genomic analyses have redefined the molecular subgrouping of pediatric acute lymphoblastic leukemia (ALL). Molecular subgroups guide risk-stratification and targeted therapies, but outcomes of recently identified subtypes are often unclear, owing to limited cases with comprehensive profiling and cross-protocol studies. We developed a machine learning tool (ALLIUM) for the molecular subclassification of ALL in retrospective cohorts as well as for up-front diagnostics. ALLIUM uses DNA methylation and gene expression data from 1131 Nordic ALL patients to predict 17 ALL subtypes with high accuracy. ALLIUM was used to revise and verify the molecular subtype of 281 B-cell precursor ALL (BCP-ALL) cases with previously undefined molecular phenotype, resulting in a single revised subtype for 81.5% of these cases. Our study shows the power of combining DNA methylation and gene expression data for resolving ALL subtypes and provides a comprehensive population-based retrospective cohort study of molecular subtype frequencies in the Nordic countries.",

author = "Olga Krali and Yanara Marincevic-Zuniga and Gustav Arvidsson and Enblad, {Anna Pia} and Anders Lundmark and Shumaila Sayyab and Vasilios Zachariadis and Merja Hein{\"a}niemi and Janne Suhonen and Laura Oksa and Kaisa Veps{\"a}l{\"a}inen and Ingegerd {\"O}fverholm and Gisela Barbany and Ann Nordgren and Henrik Lilljebj{\"o}rn and Thoas Fioretos and Madsen, {Hans O.} and Marquart, {Hanne Vibeke} and Trond Flaegstad and Erik Forestier and J{\'o}nsson, {{\'O}lafur G.} and Jukka Kanerva and Olli Lohi and Ulrika Nor{\'e}n-Nystr{\"o}m and Kjeld Schmiegelow and Arja Harila and Mats Heyman and Gudmar L{\"o}nnerholm and Syv{\"a}nen, {Ann Christine} and Jessica Nordlund",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41698-023-00479-5",

language = "English",

volume = "7",

number = "1",

}

Krali, O, Marincevic-Zuniga, Y, Arvidsson, G, Enblad, AP, Lundmark, A, Sayyab, S, Zachariadis, V, Heinäniemi, M, Suhonen, J, Oksa, L, Vepsäläinen, K, Öfverholm, I, Barbany, G, Nordgren, A, Lilljebjörn, H, Fioretos, T, Madsen, HO, Marquart, HV, Flaegstad, T, Forestier, E, Jónsson, ÓG, Kanerva, J, Lohi, O, Norén-Nyström, U, Schmiegelow, K, Harila, A, Heyman, M, Lönnerholm, G, Syvänen, AC & Nordlund, J 2023, 'Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia', NPJ precision oncology, vol. 7, no. 1, 131. https://doi.org/10.1038/s41698-023-00479-5

TY - JOUR

T1 - Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia

AU - Krali, Olga

AU - Marincevic-Zuniga, Yanara

AU - Arvidsson, Gustav

AU - Enblad, Anna Pia

AU - Lundmark, Anders

AU - Sayyab, Shumaila

AU - Zachariadis, Vasilios

AU - Heinäniemi, Merja

AU - Suhonen, Janne

AU - Oksa, Laura

AU - Vepsäläinen, Kaisa

AU - Öfverholm, Ingegerd

AU - Barbany, Gisela

AU - Nordgren, Ann

AU - Lilljebjörn, Henrik

AU - Fioretos, Thoas

AU - Madsen, Hans O.

AU - Marquart, Hanne Vibeke

AU - Flaegstad, Trond

AU - Forestier, Erik

AU - Jónsson, Ólafur G.

AU - Kanerva, Jukka

AU - Lohi, Olli

AU - Norén-Nyström, Ulrika

AU - Schmiegelow, Kjeld

AU - Harila, Arja

AU - Heyman, Mats

AU - Lönnerholm, Gudmar

AU - Syvänen, Ann Christine

AU - Nordlund, Jessica

PY - 2023/12

Y1 - 2023/12

N2 - Genomic analyses have redefined the molecular subgrouping of pediatric acute lymphoblastic leukemia (ALL). Molecular subgroups guide risk-stratification and targeted therapies, but outcomes of recently identified subtypes are often unclear, owing to limited cases with comprehensive profiling and cross-protocol studies. We developed a machine learning tool (ALLIUM) for the molecular subclassification of ALL in retrospective cohorts as well as for up-front diagnostics. ALLIUM uses DNA methylation and gene expression data from 1131 Nordic ALL patients to predict 17 ALL subtypes with high accuracy. ALLIUM was used to revise and verify the molecular subtype of 281 B-cell precursor ALL (BCP-ALL) cases with previously undefined molecular phenotype, resulting in a single revised subtype for 81.5% of these cases. Our study shows the power of combining DNA methylation and gene expression data for resolving ALL subtypes and provides a comprehensive population-based retrospective cohort study of molecular subtype frequencies in the Nordic countries.

AB - Genomic analyses have redefined the molecular subgrouping of pediatric acute lymphoblastic leukemia (ALL). Molecular subgroups guide risk-stratification and targeted therapies, but outcomes of recently identified subtypes are often unclear, owing to limited cases with comprehensive profiling and cross-protocol studies. We developed a machine learning tool (ALLIUM) for the molecular subclassification of ALL in retrospective cohorts as well as for up-front diagnostics. ALLIUM uses DNA methylation and gene expression data from 1131 Nordic ALL patients to predict 17 ALL subtypes with high accuracy. ALLIUM was used to revise and verify the molecular subtype of 281 B-cell precursor ALL (BCP-ALL) cases with previously undefined molecular phenotype, resulting in a single revised subtype for 81.5% of these cases. Our study shows the power of combining DNA methylation and gene expression data for resolving ALL subtypes and provides a comprehensive population-based retrospective cohort study of molecular subtype frequencies in the Nordic countries.

U2 - 10.1038/s41698-023-00479-5

DO - 10.1038/s41698-023-00479-5

M3 - Article

AN - SCOPUS:85179355296

SN - 2397-768X

VL - 7

JO - NPJ precision oncology

JF - NPJ precision oncology

IS - 1

M1 - 131

ER -

Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia

Abstract

Funding

Publication forum classification

ASJC Scopus subject areas

UN SDGs

Access to Document

Fingerprint

Datasets

Multimodal classification of molecular subtypes in pediatric acute lymphoblastic leukemia

Cite this