Identification of molecular signatures and pathways of obese breast cancer gene expression data by a machine learning algorithm

Abstract

Aim: Currently, the obesity epidemic is one of the biggest problems for human health. Obesity is impacted on survival in patients with breast cancer. However, key biomarkers of obesity-related breast cancer risk are still not well known. Thus, using machine learning to identify the most appropriate features in obesity-associated breast cancer patients may improve the predictive accuracy and interpretability of regression models.

Methods: In the present study, we identified 23 differentially expressed genes (DEGs) from the GSE24185 transcriptome dataset. Seed genes were identified from DEGs, the co-expression network genes and hub genes of the protein-protein interaction network. Pathway enrichment analysis was performed for DEGs. The Ridge penalty regression model was executed by using P-values of enriched pathways and seed gene pathway association score to obtain the most relevant molecular signatures. The model was performed using 10-fold cross-validation to fit the penalized models.

Results: Angiotensin II receptor type 1 (AGTR1), cyclin D1 (CCND1), glutamate ionotropic receptor AMPA type subunit 2 (GRIA2), interleukin-6 cytokine family signal transducer (IL6ST), matrix metallopeptidase 9 (MMP9), and protein kinase CAMP-dependent type II regulatory subunit beta (PRKAR2B) were considered as candidate molecular signatures of obese patients with breast cancer. In addition, RAF-independent MAPK1/3 activation, collagen degradation, bladder cancer, drug metabolism-cytochrome P450, and signaling by Hedgehog pathways in cancer were primarily associated with obesity-associated breast cancer.

Conclusion: These genes may be used for risk analysis of the disease progression of obese patients with breast cancer. Corresponding genes and pathways should be validated via experimental studies.

Keywords

Obesity / breast cancer / machine learning / penalty regression models

References

[1] MckinneySM,GodboleV.International evaluation of an AI system for breast cancer screening.Nature2020;577:89-94

[2] World Cancer Report: Cancer Research for Cancer Prevention (PDF). Available from: https://shop.iarc.fr/products/world-cancer-report-cancer-research-for-cancer-prevention-pdf [Last accessed on 7 Jan 2022]

[3] McPhersonK,DixonJM.ABC of breast diseases. Breast cancer-epidemiology, risk factors, and genetics.BMJ2000;321:624-8 PMCID:PMC1118507

[4] AndòS,PanzaS.Obesity, leptin and breast cancer: epidemiological evidence and proposed mechanisms.Cancers (Basel)2019;11:62 PMCID:PMC6356310

[5] AfshinA,ReitsmaMB.GBD 2015 Obesity CollaboratorsHealth effects of overweight and obesity in 195 countries over 25 years.N Engl J Med2017;377:13-27 PMCID:PMC5477817

[6] JamesFR,JacksonA,CopsonER.Obesity in breast cancer--what is the risk factor?.Eur J Cancer2015;51:705-20

[7] ArgoloDF,IyengarNM.The impact of obesity on breast cancer.Curr Oncol Rep2018;20:47

[8] GuiY,ChenX,LuoX.The association between obesity related adipokines and risk of breast cancer: a meta-analysis.Oncotarget2017;8:75389-99 PMCID:PMC5650429

[9] WuX,HaoY.Obesity-related protein biomarkers for predicting breast cancer risk: an overview of systematic reviews.Breast Cancer2021;28:25-39

[10] DiaoS,ZhangX.Obesity-related proteins score as a potential marker of breast cancer risk.Sci Rep2021;11:8230 PMCID:PMC8050206

[11] ModiND,RowlandA.The obesity paradox in early and advanced HER2 positive breast cancer: pooled analysis of clinical trial data.NPJ Breast Cancer2021;7:30 PMCID:PMC7985140

[12] ChangMC,EnnisM.Crown-like structures in breast adipose tissue of breast cancer patients: associations with CD68 expression, obesity, metabolic factors and prognosis.NPJ Breast Cancer2021;7:97 PMCID:PMC8298396

[13] MasonC,DugganC.Gene expression in breast and adipose tissue after 12 months of weight loss and vitamin D supplementation in postmenopausal women.NPJ Breast Cancer2017;3:15 PMCID:PMC5460115

[14] LeeK,Dieli-ConwrightCM.The impact of obesity on breast cancer diagnosis and treatment.Curr Oncol Rep2019;21:41 PMCID:PMC6437123

[15] CreightonCJ,ZhangY.A gene transcription signature of obesity in breast cancer.Breast Cancer Res Treat2012;132:993-1000

[16] BarrettT,LedouxP.NCBI GEO: archive for functional genomics data sets--update.Nucleic Acids Res2013;41:D991-5 PMCID:PMC3531084

[17] IrizarryRA,CollinF.Exploration, normalization, and summaries of high density oligonucleotide array probe level data.Biostatistics2003;4:249-64

[18] SmythGK.Limma: linear models for microarray data. In: Gentleman R, Carey VJ, Huber W, Irizarry RA, Dudoit S, editors. Bioinformatics and computational biology solutions using R and bioconductor. New York: Springer-Verlag; 2005. p. 397-420.

[19] Chatr-AryamontriA,BoucherL.The BioGRID interaction database: 2017 update.Nucleic Acids Res2017;45:D369-79 PMCID:PMC5210573

[20] ShannonP,OzierO.Cytoscape: a software environment for integrated models of biomolecular interaction networks.Genome Res2003;13:2498-504 PMCID:PMC403769

[21] KamburovA,LehrachH.ConsensusPathDB--a database for integrating human functional interaction networks.Nucleic Acids Res2009;37:D623-8 PMCID:PMC2686562

[22] KanehisaM,SatoY,FurumichiM.Data, information, knowledge and principle: back to metabolism in KEGG.Nucleic Acids Res2014;42:D199-205 PMCID:PMC3965122

[23] CroftD,WuG.Reactome: a database of reactions, pathways and biological processes.Nucleic Acids Res2011;39:D691-7 PMCID:PMC3013646

[24] HarrisCR,van der WaltSJ.Array programming with NumPy.Nature2020;585:357-62 PMCID:PMC7759461

[25] BetancourtR.Pandas library. Python for SAS users. Berkeley: Apress; 2019. p. 65-109.

[26] PerezF.IPython: a system for interactive scientific computing.Comput Sci Eng2007;9:21-9

[27] FriedmanJ,TibshiraniR.Regularization paths for generalized linear models via coordinate descent.J Stat Softw2010;33:1 PMCID:PMC2929880

[28] SafranM,AlexanderJ.GeneCards version 3: the human gene integrator.Database (Oxford)2010;2010:baq020 PMCID:PMC2938269

[29] LuoC,SharabiK.Obesity/Type 2 diabetes-associated liver tumors are sensitive to cyclin D1 deficiency.Cancer Res2020;80:3215-21 PMCID:PMC7442681

[30] ThunGA,BergerW,Probst-HenschNM.The association of a variant in the cell cycle control gene CCND1 and obesity on the development of asthma in the Swiss SAPALDIA study.J Asthma2013;50:147-54

[31] Martínez-PérezC,KayC.The signal transducer IL6ST (gp130) as a predictive and prognostic biomarker in breast cancer.J Pers Med2021;11:618 PMCID:PMC8304290

[32] BobboVC,JaraCP.Interleukin-6 actions in the hypothalamus protects against obesity and is involved in the regulation of neurogenesis.J Neuroinflammation2021;18:192 PMCID:PMC8408946

[33] AllottEH,CathcartMC.MMP9 expression in oesophageal adenocarcinoma is upregulated with visceral obesity and is associated with poor tumour differentiation.Mol Carcinog2013;52:144-54

[34] KlassenLMB,ManicaGCM.MMP9 gene expression regulation by intragenic epigenetic modifications in breast cancer.Gene2018;642:461-6

[35] GaglianoSA,FreemanN.Protein kinase cAMP-dependent regulatory type II beta (PRKAR2B) gene variants in antipsychotic-induced weight gain.Hum Psychopharmacol2014;29:330-5

[36] SunX,KimWY,OlshanAF.Age at diagnosis, obesity, smoking, and molecular subtypes in muscle-invasive bladder cancer.Cancer Causes Control2017;28:539-44 PMCID:PMC5477976

[37] FujitaK,MatsushitaM,NonomuraN.Obesity, inflammation, and prostate cancer.J Clin Med2019;8:201 PMCID:PMC6406330

[38] ZarezadehM,ShekarabiM,EmamiMR.The effect of obesity, macronutrients, fasting and nutritional status on drug-metabolizing cytochrome P450s: a systematic review of current evidence on human studies.Eur J Nutr2021;60:2905-21

[39] Riobo-Del Galdo NA, Lara Montero Á, Wertheimer EV. Role of Hedgehog signaling in breast cancer: pathogenesis and therapeutics.Cells2019;8:375 PMCID:PMC6523618

[40] HannaA,BaileySK.Inhibition of Hedgehog signaling reprograms the dysfunctional immune microenvironment in breast cancer.Oncoimmunology2019;8:1548241 PMCID:PMC6350695

[41] ChongYC,FuY,TergaonkarV.Indian Hedgehog links obesity to development of hepatocellular carcinoma.Oncogene2019;38:2206-22

[42] QinS,ZhangC.Downregulation of sonic hedgehog signaling in the hippocampus leads to neuronal apoptosis in high-fat diet-fed mice.Behav Brain Res2019;367:91-100