SUPPLEMENTARY MATERIAL: Machine learning-based analysis of glioma grades reveals co-enrichment

SND-ID: 2024-339. Version: 1. DOI: https://doi.org/10.57804/6fa3-6v37

Citation

Creator/Principal investigator(s)

Mateusz Garbulowski - Uppsala University orcid

Research principal

Uppsala University rorId

Description

Examining glioma grading processes is valuable for improving therapeutic challenges. One of the most extensive repositories storing transcriptomics data for gliomas is The Cancer Genome Atlas (TCGA). However, such big cohorts should be processed with caution and evaluated thoroughly as they can contain batch and other effects. Furthermore, biological mechanisms of cancer contain interactions among biomarkers. Thus, we applied an interpretable machine learning approach to discover such relationships. This type of transparent learning provides not only good predictability, but also reveals co-predictive mechanisms among features. In this study, we corrected the strong and confounded batch effect in the TCGA glioma data. We further used the corrected datasets to perform comprehensive machine learning analysis applied on single-sample gene set enrichment scores using collections from the Molecular Signature Database. Furthermore, using rule-based classifiers, we displayed networks of co-enrichment related to glioma grades. Moreover, we validated our results using the external glioma cohorts.

The

... Show more..
Examining glioma grading processes is valuable for improving therapeutic challenges. One of the most extensive repositories storing transcriptomics data for gliomas is The Cancer Genome Atlas (TCGA). However, such big cohorts should be processed with caution and evaluated thoroughly as they can contain batch and other effects. Furthermore, biological mechanisms of cancer contain interactions among biomarkers. Thus, we applied an interpretable machine learning approach to discover such relationships. This type of transparent learning provides not only good predictability, but also reveals co-predictive mechanisms among features. In this study, we corrected the strong and confounded batch effect in the TCGA glioma data. We further used the corrected datasets to perform comprehensive machine learning analysis applied on single-sample gene set enrichment scores using collections from the Molecular Signature Database. Furthermore, using rule-based classifiers, we displayed networks of co-enrichment related to glioma grades. Moreover, we validated our results using the external glioma cohorts.

The dataset was originally published in DiVA and moved to SND in 2024. Show less..

Data contains personal data

No

Language

Method and outcome

Data format / data structure

Data collection
Geographic coverage
Administrative information

Contributor(s)

Karolina Smolinska Garbulowska - Uppsala University, Beräkningsbiologi och bioinformatik orcid

Uğur Çabuk - Uppsala University, Institutionen för cell- och molekylärbiologi

Sara A. Yones - Uppsala University, Institutionen för cell- och molekylärbiologi

Ludovica Celli - Uppsala University, Institutionen för cell- och molekylärbiologi

Esmanur Yaz - Uppsala University, Institutionen för cell- och molekylärbiologi

... Show more..

Karolina Smolinska Garbulowska - Uppsala University, Beräkningsbiologi och bioinformatik orcid

Uğur Çabuk - Uppsala University, Institutionen för cell- och molekylärbiologi

Sara A. Yones - Uppsala University, Institutionen för cell- och molekylärbiologi

Ludovica Celli - Uppsala University, Institutionen för cell- och molekylärbiologi

Esmanur Yaz - Uppsala University, Institutionen för cell- och molekylärbiologi

Fredrik Barrenäs - Uppsala University, Beräkningsbiologi och bioinformatik

Klev Diamanti - Uppsala University, Beräkningsbiologi och bioinformatik orcid

Claes Wadelius - Uppsala University, Medicinsk genetik och genomik orcid

Jan Komorowski - Uppsala University, Beräkningsbiologi och bioinformatik orcid

Show less..

Identifiers

Topic and keywords

Research area

Bioinformatics (computational biology) (Standard för svensk indelning av forskningsämnen 2011)

Publications

Garbulowski M, Smolinska K, Çabuk U, Yones SA, Celli L, Yaz EN, Barrenäs F, Diamanti K, Wadelius C, Komorowski J. Machine Learning-Based Analysis of Glioma Grades Reveals Co-Enrichment. Cancers (Basel). 2022 Feb 17;14(4):1014. doi: 10.3390/cancers14041014. PMID: 35205761; PMCID: PMC8870250.
URN: urn:nbn:se:uu:diva-455177

If you have published anything based on these data, please notify us with a reference to your publication(s). If you are responsible for the catalogue entry, you can update the metadata/data description in DORIS.

Published: 2021-10-05
Last updated: 2024-08-21