Predicting Distant Metastatic Sites in Cancer Using miRNA and mRNA Expression Data

Dostonjon Mamatkarimov; Jiahui Kang; Kyungsook Han

doi:10.2174/0115748936338628241104110200

ISSN: 1574-8936
E-ISSN: 2212-392X

Predicting Distant Metastatic Sites in Cancer Using miRNA and mRNA Expression Data
Authors: Dostonjon Mamatkarimov¹, Jiahui Kang¹ and Kyungsook Han¹
View Affiliations Hide Affiliations

¹ Department of Electrical and Computer Engineering, Inha University, Incheon, South Korea
Source: Current Bioinformatics, Volume 20, Issue 5, Jun 2025, p. 473 - 485
DOI: https://doi.org/10.2174/0115748936338628241104110200
- Received: 20 Jun 2024
- Accepted: 08 Oct 2024
- Available online: 04 Dec 2024

Abstract

Background

Cancer patients with metastasis face a much lower survival rate and a higher risk of recurrence than those without metastasis. So far, several learning methods have been proposed to predict cancer metastasis, but most of these methods are intended to predict lymph node metastasis rather than distant metastasis. Distant metastasis is more difficult to predict than lymph node metastasis because distant metastasis is detected after a comprehensive examination of the entire body, and there are not enough publicly available tumor samples with distant metastasis that can be used for training learning methods. Predicting distant metastatic sites is even more challenging than predicting whether distant metastasis will occur or not.

Methods

The problem of predicting distant metastatic sites is a multi‐class and multi‐label classification problem; there are more than two classes for distant metastatic sites (bone, brain, liver, lung, and other organs), and a single sample can have multiple labels for multiple metastatic sites. We transformed the multi‐label and multi‐class problem into multiple single‐label binary problems. For each metastatic site, we built a random forest model that deals with binary classification and linked the models along a chain.

Results

Testing the model on miRNA and mRNA expression datasets of several cancer types showed a high performance in all performance measures. In the comparison of our model with other methods, our method outperformed the others.

Conclusion

We developed a new method for predicting multiple metastatic sites using miRNA and mRNA expression data. The technique will be useful in predicting distant metastatic sites before distant metastasis occurs, which in turn will help clinicians determine treatment options for cancer patients.

Article metrics loading...

/content/journals/cbio/10.2174/0115748936338628241104110200

2024-12-04

2025-07-04

From This Site

/content/journals/cbio/10.2174/0115748936338628241104110200

dcterms_title,dcterms_subject,pub_keyword

-contentType:Contributor -contentType:Concept -contentType:Institution

10

5

Full text loading...

References

BrayF. LaversanneM. WeiderpassE. SoerjomataramI. The ever-increasing importance of cancer as a leading cause of premature death worldwide.Cancer2021127163029303010.1002/cncr.3358734086348
[Google Scholar]
Cancer.Available from: https://www.who.int/health-topics/cancer#tab=tab_1
GuanX. Cancer metastases: Challenges and opportunities.Acta Pharm. Sin. B20155540241810.1016/j.apsb.2015.07.00526579471
[Google Scholar]
GaneshK. MassaguacJ. Targeting metastatic cancer.Nat. Med.2021271344410.1038/s41591‑020‑01195‑433442008
[Google Scholar]
EdgeS.B. ComptonC.C. The American Joint Committee on Cancer: The 7th edition of the AJCC cancer staging manual and the future of TNM.In: Ann. Surg. Oncol.1714711474201010.1245/s10434‑010‑0985‑420180029
[Google Scholar]
HamaokaT. MadewellJ.E. PodoloffD.A. HortobagyiG.N. UenoN.T. Bone imaging in metastatic breast cancer.J. Clin. Oncol.200422142942295310.1200/JCO.2004.08.18115254062
[Google Scholar]
RiggioA.I. VarleyK.E. WelmA.L. The lingering mysteries of metastatic recurrence in breast cancer.Br. J. Cancer20211241132610.1038/s41416‑020‑01161‑433239679
[Google Scholar]
LambertA.W. PattabiramanD.R. WeinbergR.A. Emerging biological principles of metastasis.Cell2017168467069110.1016/j.cell.2016.11.03728187288
[Google Scholar]
RobinsonD.R. WuY.M. LonigroR.J. VatsP. CobainE. EverettJ. CaoX. RabbanE. Kumar SinhaC. RaymondV. SchuetzeS. AlvaA. SiddiquiJ. ChughR. WordenF. ZalupskiM.M. InnisJ. ModyR.J. TomlinsS.A. LucasD. BakerL.H. RamnathN. SchottA.F. HayesD.F. VijaiJ. OffitK. StoffelE.M. RobertsJ.S. SmithD.C. KunjuL.P. TalpazM. CieslikM. ChinnaiyanA.M. Integrative clinical genomics of metastatic cancer.Nature2017548766729730310.1038/nature2330628783718
[Google Scholar]
MetriR. MohanA. NsengimanaJ. PozniakJ. Molina ParisC. Newton-BishopJ. BishopD. ChandraN. Identification of a gene signature for discriminating metastatic from primary melanoma using a molecular interaction network approach.Sci. Rep.2017711731410.1038/s41598‑017‑17330‑029229936
[Google Scholar]
ZhaoS. YuJ. WangL. Machine learning based prediction of brain metastasis of patients with IIIA-N2 lung adenocarcinoma by a three-miRNA signature.Transl. Oncol.201811115716710.1016/j.tranon.2017.12.00229288987
[Google Scholar]
ZhangS. ZhangC. DuJ. ZhangR. YangS. LiB. WangP. DengW. Prediction of lymph node metastasis in cancers using differentially expressed mRNA and non coding RNA signatures.Front. Cell Dev. Biol.2021960597710.3389/fcell.2021.60597733644044
[Google Scholar]
AlbaradeiS. AlbaradeiA. AlsaediA. UludagM. ThafarM.A. GojoboriT. EssackM. GaoX. MetastaSite: Predicting metastasis to different sites using deep learning with gene expression data.Front. Mol. Biosci.2022991360210.3389/fmolb.2022.91360235936793
[Google Scholar]
JhaA. KhanY. SahayR. d AquinM. Metastatic site prediction in breast cancer using omics knowledge graph and pattern mining with kirchhoff's law traversal.bioRxiv10.1101/2020.07.14.203208
[Google Scholar]
WeinsteinJ.N. CollissonE.A. MillsG.B. ShawK.R.M. OzenbergerB.A. EllrottK. ShmulevichI. SanderC. StuartJ.M. The cancer genome atlas pan cancer analysis project.Nat. Genet.201345101113112010.1038/ng.276424071849
[Google Scholar]
ColapricoA. SilvaT.C. OlsenC. GarofanoL. CavaC. GaroliniD. SabedotT.S. MaltaT.M. PagnottaS.M. CastiglioniI. CeccarelliM. BontempiG. NoushmehrH. TCGAbiolinks: An R/Bioconductor package for integrative analysis of TCGA data.Nucleic Acids Res.2016448e7110.1093/nar/gkv150726704973
[Google Scholar]
MounirM. LucchettaM. SilvaT.C. OlsenC. BontempiG. ChenX. NoushmehrH. ColapricoA. PapaleoE. New functionalities in the TCGAbiolinks package for the study and integration of cancer data from GDC and GTEx.PLOS Comput. Biol.2019153e100670110.1371/journal.pcbi.100670130835723
[Google Scholar]
RobinsonM.D. OshlackA. A scaling normalization method for differential expression analysis of RNA seq data.Genome Biol.2010113R2510.1186/gb‑2010‑11‑3‑r2520196867
[Google Scholar]
ChawlaN.V. BowyerK.W. HallL.O. KegelmeyerW.P. SMOTE: synthetic minority over sampling technique.J. Artif. Intell. Res.20021632135710.1613/jair.953
[Google Scholar]
WilsonD.L. 1972Asymptotic properties of nearest neighbor rules using edited data.IEEE Trans. Syst. Man. Cybern.SMC-2340842110.1109/TSMC.1972.4309137
[Google Scholar]
YilmazM. ChristoforiG. LehembreF. Distinct mechanisms of tumor invasion and metastasis.Trends Mol. Med.2007131253554110.1016/j.molmed.2007.10.00417981506
[Google Scholar]
TibshiraniR Regression shrinkage and selection via the lasso.J. R. Stat. Soc., B.199658126728810.1111/j.2517‑6161.1996.tb02080.x
[Google Scholar]
MackiewiczA. RatajczakW. Principal components analysis (PCA).Comput. Geosci.199319330334210.1016/0098‑3004(93)90090‑R
[Google Scholar]
ChiccoD. JurmanG. The Matthews correlation coefficient (MCC) should replace the ROC AUC as the standard metric for assessing binary classification.BioData Min.2023161410.1186/s13040‑023‑00322‑436800973
[Google Scholar]
ChiccoD. JurmanG. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation.BMC Genomics2020211610.1186/s12864‑019‑6413‑731898477
[Google Scholar]
ChuahJ. KrugerU. WangG. YanP. HahnJ. Framework for testing robustness of machine learning based classifiers.J. Pers. Med.2022128131410.3390/jpm1208131436013263
[Google Scholar]
FawziA. Moosavi DezfooliS.M. FrossardP. The robustness of deep networks: A geometrical perspective.IEEE Signal Process. Mag.2017346506210.1109/MSP.2017.2740965
[Google Scholar]
BrownO. CurtisA. GoodwinJ. Principles for evaluation of AI/ML model performance and robustness.ArXiv10.48550/arXiv.2107.02868
[Google Scholar]
GamaJ. ZliobaiteI. BifetA. PechenizkiyM. BouchachiaA. A survey on concept drift adaptation.ACM Comput. Surv.201446413710.1145/2523813
[Google Scholar]
PachmayrE. TreeseC. SteinU. Underlying mechanisms for distant metastasis molecular biology.Visc. Med.2017331112010.1159/00045469628785563
[Google Scholar]
JaninM. DavalosV. EstellerM. Cancer metastasis under the magnifying glass of epigenetics and epitranscriptomics.Cancer Metastasis Rev.20234241071111210.1007/s10555‑023‑10120‑337369946
[Google Scholar]
SellM.C. Ramlogan SteelC.A. SteelJ.C. DhungelB.P. MicroRNAs in cancer metastasis: Biological and therapeutic implications.Expert Rev. Mol. Med.25e14202310.1017/erm.2023.7
[Google Scholar]
PengY. CroceC.M. The role of MicroRNAs in human cancer.Signal Transduct. Target. Ther.2016111500410.1038/sigtrans.2015.429263891
[Google Scholar]
Malka TunitskyN. Sas ChenA. Role of RNA modifications in cancer metastasis.Curr. Opin. Genet. Dev.20248710223210.1016/j.gde.2024.10223239047587
[Google Scholar]
PopnikolovN.K. DalwadiB.H. ThomasJ.D. JohannesG.J. ImagawaW.T. Association of autotaxin and lysophosphatidic acid receptor 3 with aggressiveness of human breast carcinoma.Tumour Biol.20123362237224310.1007/s13277‑012‑0485‑122922883
[Google Scholar]
LiG.C. QinX.L. SongH.H. LiY.N. QiuY.Y. CuiS.C. WangY.S. WangH. GongJ.L. Retraction: Upregulated microRNA-15b alleviates ovarian cancer through inhitbition of the PI3K/Akt pathway by targeting LPAR3J. Cell. Physiol.201923412223312234210.1002/jcp.2879931140597
[Google Scholar]
KanB. YanG. ShaoY. ZhangZ. XueH. CircRNA RNF10 inhibits tumorigenicity by targeting miR 942 5p/GOLIM4 axis in breast cancer.Environ. Mol. Mutagen.202263736237210.1002/em.2250636054164
[Google Scholar]
ZhengW. WangX. YuY. JiC. FangL. CircRNF10-DHX15 interaction suppressed breast cancer progression by antagonizing DHX15 NF KB p65 positive feedback loop.Cell. Mol. Biol. Lett.20232813410.1186/s11658‑023‑00448‑737101128
[Google Scholar]
HormT.M. SchroederJ.A. MUC1 and metastatic cancer.Cell Adhes. Migr.20137218719810.4161/cam.2313123303343
[Google Scholar]
ApostolopoulosV. PieterszG.A. TsibanisA. TsikkinisA. DrakakiH. LovelandB.E. PiddlesdenS.J. PlebanskiM. PouniotisD.S. AlexisM.N. McKenzieI.F. VassilarosS. Pilot phase III immunotherapy study in early-stage breast cancer patients using oxidized mannan-MUC1 [ISRCTN71711835].Breast Cancer Res.200683R2710.1186/bcr150516776849
[Google Scholar]
LongJ.S. KaniaE. McEwanD.G. BarthetV.J.A. BrucoliM. LaddsM.J.G.W. NassingC. RyanK.M. ATG7 is a haploinsufficient repressor of tumor progression and promoter of metastasis.Proc. Natl. Acad. Sci. USA202211928e211346511910.1073/pnas.211346511935867735
[Google Scholar]
NagaokaK. FujiiK. ZhangH. UsudaK. WatanabeG. IvshinaM. RichterJ.D. CPEB1 mediates epithelial to Mesenchyme transition and breast cancer metastasis.Oncogene201635222893290110.1038/onc.2015.35026411364
[Google Scholar]
RibeiroM.T. SinghS. GuestrinC. "Why should i trust you?" Explaining the predictions of any classifierProceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningCalifornia, San Francisco, USA, Aug. 13-17, 2016, pp. 1135-1144.10.1145/2939672.2939778
[Google Scholar]

/content/journals/cbio/10.2174/0115748936338628241104110200

Predicting Distant Metastatic Sites in Cancer Using miRNA and mRNA Expression Data

Curr Bioinform 20, 473 (2025); https://doi.org/10.2174/0115748936338628241104110200

/content/journals/cbio/10.2174/0115748936338628241104110200

Data & Media loading...

Supplements

Supplementary material is available on the publisher’s website along with the published article.

Article Type: Research Article

Keyword(s): cancer; Distant metastasis; machine learning; metastatic site; miRNA expression; mRNA expression; multi‐class classification

Most Cited Most Cited RSS feed

- A Review of Ensemble Methods in Bioinformatics
  
  Authors: Pengyi Yang, Yee Hwa Yang, Bing B. Zhou and Albert Y. Zomaya
- Bioinformatics Tools for Mass Spectroscopy-Based Metabolomic Data Processing and Analysis
  
  Authors: Masahiro Sugimoto, Masato Kawakami, Martin Robert, Tomoyoshi Soga and Masaru Tomita
- Distance-based Support Vector Machine to Predict DNA N6- methyladenine Modification
  
  Authors: Haoyu Zhang, Quan Zou, Ying Ju, Chenggang Song and Dong Chen
- A Review on the Recent Developments of Sequence-based Protein Feature Extraction Methods
  
  Authors: Jun Zhang and Bin Liu
- Molecular Genetic Markers: Discovery, Applications, Data Storage and Visualisation
  
  Authors: Chris Duran, Nikki Appleby, David Edwards and Jacqueline Batley
- A Brief Survey of Machine Learning Methods in Protein Sub-Golgi Localization
  
  Authors: Wuritu Yang, Xiao-Juan Zhu, Jian Huang, Hui Ding and Hao Lin
- Cancer Diagnosis Through IsomiR Expression with Machine Learning Method
  
  Authors: Zhijun Liao, Dapeng Li, Xinrui Wang, Lisheng Li and Quan Zou
- The Advances and Challenges of Deep Learning Application in Biological Big Data Processing
  
  Authors: Li Peng, Manman Peng, Bo Liao, Guohua Huang, Weibiao Li and Dingfeng Xie
- Gene Expression Profile Classification: A Review
  
  Authors: Musa H. Asyali, Dilek Colak, Omer Demirkaya and Mehmet S. Inan
- Relevance of Molecular Docking Studies in Drug Designing
  
  Authors: Ritu Jakhar, Mehak Dangi, Alka Khichi and Anil K. Chhillar
More Less

Predicting Distant Metastatic Sites in Cancer Using miRNA and mRNA Expression Data

Abstract

Supplementary material is available on the publisher’s website along with the published article.

Most Read This Month

Most Cited Most Cited RSS feed