• GAIN-BRCA: a graph-based AI-ne...

Treffer: GAIN-BRCA: a graph-based AI-net framework for breast cancer subtype classification using multiomics data.

Title:
GAIN-BRCA: a graph-based AI-net framework for breast cancer subtype classification using multiomics data.
Authors:
Patel JC; Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198, United States., Shakyawar SK; Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198, United States., Sethi S; Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198, United States., Guda C; Department of Genetics, Cell Biology and Anatomy, University of Nebraska Medical Center, Omaha, NE 68198, United States.; Center for Biomedical Informatics, Research and Innovation, University of Nebraska Medical Center, Omaha, NE 68198, United States.
Source:
Bioinformatics advances [Bioinform Adv] 2025 May 14; Vol. 5 (1), pp. vbaf116. Date of Electronic Publication: 2025 May 14 (Print Publication: 2025).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Oxford University Press Country of Publication: England NLM ID: 9918282081306676 Publication Model: eCollection Cited Medium: Internet ISSN: 2635-0041 (Electronic) Linking ISSN: 26350041 NLM ISO Abbreviation: Bioinform Adv Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: [Oxford] : Oxford University Press : International Society for Computational Biology, [2021]-
References:
Nat Commun. 2021 Jun 8;12(1):3445. (PMID: 34103512)
Cancer Res. 2021 Nov 1;81(21):5491-5505. (PMID: 34408002)
Front Genet. 2022 Feb 02;13:806842. (PMID: 35186034)
Bioinformatics. 2020 Mar 1;36(5):1476-1483. (PMID: 31603461)
Genet Test Mol Biomarkers. 2010 Aug;14(4):533-7. (PMID: 20642364)
Front Genet. 2023 Jul 20;14:1199087. (PMID: 37547471)
Gene. 2018 Jun 15;659:44-51. (PMID: 29555201)
Nucleic Acids Res. 2022 May 20;50(9):e51. (PMID: 35100398)
Proc Natl Acad Sci U S A. 2001 Sep 11;98(19):10869-74. (PMID: 11553815)
Nucleic Acids Res. 2016 May 5;44(8):e71. (PMID: 26704973)
Elife. 2015 Aug 12;4:. (PMID: 26267216)
Nucleic Acids Res. 2003 Jul 1;31(13):3812-4. (PMID: 12824425)
BMC Bioinformatics. 2019 Oct 28;20(1):527. (PMID: 31660856)
Breast Cancer Res Treat. 2011 Dec;130(3):735-45. (PMID: 21409395)
Proc Natl Acad Sci U S A. 2003 Jul 8;100(14):8418-23. (PMID: 12829800)
IJCAI (U S). 2021 Aug;2021:1505-1511. (PMID: 35480631)
Sci Rep. 2016 Feb 08;6:20616. (PMID: 26852921)
Cancer Res. 2009 Jun 15;69(12):5049-56. (PMID: 19491269)
Genes (Basel). 2020 Aug 04;11(8):. (PMID: 32759821)
Wiley Interdiscip Rev Comput Stat. 2022 May-Jun;14(3):. (PMID: 35573155)
Cancer Sci. 2021 Mar;112(3):1209-1224. (PMID: 33340428)
Mol Cancer. 2020 Dec 5;19(1):170. (PMID: 33276788)
Nature. 2000 Aug 17;406(6797):747-52. (PMID: 10963602)
NPJ Breast Cancer. 2018 Aug 2;4:22. (PMID: 30083595)
Cell Cycle. 2011 Feb 1;10(3):507-17. (PMID: 21270527)
Nat Commun. 2018 Oct 26;9(1):4453. (PMID: 30367051)
BioData Min. 2024 Nov 23;17(1):53. (PMID: 39580456)
Nucleic Acids Res. 2014 Jan;42(Database issue):D993-D1000. (PMID: 24150940)
Am J Pathol. 2010 Oct;177(4):2034-45. (PMID: 20724597)
Oncotarget. 2017 Dec 12;9(1):842-852. (PMID: 29416660)
Bioinform Adv. 2024 Jan 30;4(1):vbae015. (PMID: 38698887)
J Clin Oncol. 2009 Mar 10;27(8):1160-7. (PMID: 19204204)
BMC Cancer. 2015 Jan 30;15:22. (PMID: 25632947)
Bioinformatics. 2014 Feb 01;30(3):428-30. (PMID: 24336642)
Genome Biol. 2004;5(10):R80. (PMID: 15461798)
CA Cancer J Clin. 2023 Jan;73(1):17-48. (PMID: 36633525)
Mol Med Rep. 2018 Jun;17(6):8069-8078. (PMID: 29658578)
Front Genet. 2021 Apr 15;12:618803. (PMID: 33936160)
AMIA Jt Summits Transl Sci Proc. 2016 Jul 20;2016:52-9. (PMID: 27570650)
Genome Biol. 2018 Jun 26;19(1):81. (PMID: 29945659)
Breast Cancer Res. 2024 Aug 28;26(1):126. (PMID: 39198859)
Environ Microbiol. 2020 Aug;22(8):3020-3038. (PMID: 32436334)
Oncotarget. 2017 Apr 25;8(17):28990-29012. (PMID: 28423671)
Breast Cancer Res. 2009;11(3):R27. (PMID: 19432961)
J Breast Cancer. 2019 Dec 02;22(4):548-561. (PMID: 31897329)
Am J Physiol Cell Physiol. 2023 Oct 1;325(4):C833-C848. (PMID: 37642235)
Front Genet. 2020 Oct 20;11:522125. (PMID: 33193605)
BMC Genomics. 2019 Dec 20;20(Suppl 11):944. (PMID: 31856727)
Genes (Basel). 2022 Aug 25;13(9):. (PMID: 36140696)
Front Genet. 2020 Mar 31;11:278. (PMID: 32296462)
BMC Bioinformatics. 2023 Apr 26;24(1):169. (PMID: 37101124)
Grant Information:
P01 AG029531 United States AG NIA NIH HHS; P20 GM103427 United States GM NIGMS NIH HHS; P30 CA036727 United States CA NCI NIH HHS
Entry Date(s):
Date Created: 20250611 Latest Revision: 20250621
Update Code:
20250621
PubMed Central ID:
PMC12151285
DOI:
10.1093/bioadv/vbaf116
PMID:
40496492
Database:
MEDLINE

Weitere Informationen

Motivation: Contextual integration of multiomic datasets from the same patient could improve the accuracy of subtype prediction algorithms to help with better prognosis and management of breast cancer. Previous machine learning models have underexplored the graph-based integration, hence unable to leverage the biological associations among different omics modalities. Here, we developed a graph-based method, GAIN-BRCA, using the native features from mRNA, DNA methylation (CpG), and miRNA data as well as the synthesized features from their interactions. GAIN-BRCA computes weightage from miRNA-mRNA and CpG-mRNA interactions to derive a new transformed feature vector that captures the essential biological context.
Results: GAIN-BRCA demonstrates superior performance with an AUROC of 0.98. GAIN-BRCA, with an accuracy of 0.92 also outperformed the existing methods like MOGONET and moBRCA-net with accuracies of 0.72 and 0.86, respectively. Kaplan-Meier survival analysis revealed subtype-specific prognostic genes, including KRAS in Luminal A ( P value = 0.041), TOX in Luminal B ( P value = 0.008), and MITF and TOB1 in HER2+ ( P values = 0.029 and 0.025, respectively). However, no single gene demonstrated a significant survival correlation unique to the Basal subtype. GAIN-BRCA framework, in combination with SHAP, has identified several subtype-specific biomarkers to aid in the development of precision therapeutics for breast cancer subtypes.
Availability and Implementation: GAIN-BRCA code is publicly accessible on https://github.com/GudaLab/GAIN-BRCA.
(© The Author(s) 2025. Published by Oxford University Press.)

None declared.