OpenLB
Open Library of Bioscience
Advanced Search
Genes
12 07, 2022;13 (12):

Biomarker Discovery for Meta-Classification of Melanoma Metastatic Progression Using Transfer Learning.

Jose Marie Antonio Mi��oza, Jonathan Adam Rico, Pia Regina Fatima Zamora, Manny Bacolod, Reinhard Laubenbacher, Gerard G Dumancas, Romulo de Castro
Author Information
  1. Jose Marie Antonio Mi��oza: System Modeling and Simulation Laboratory, Department of Computer Science, University of the Philippines Diliman, Quezon City 1101, Philippines. ORCID
  2. Jonathan Adam Rico: Center for Informatics, University of San Agustin, Iloilo City 5000, Philippines. ORCID
  3. Pia Regina Fatima Zamora: Center for Informatics, University of San Agustin, Iloilo City 5000, Philippines.
  4. Manny Bacolod: Department of Microbiology and Immunology, Weill Cornell Medicine, New York, NY 10065, USA. ORCID
  5. Reinhard Laubenbacher: Department of Medicine, University of Florida, Gainesville, FL 32610, USA.
  6. Gerard G Dumancas: Center for Informatics, University of San Agustin, Iloilo City 5000, Philippines. ORCID
  7. Romulo de Castro: Center for Informatics, University of San Agustin, Iloilo City 5000, Philippines.
PMID: 36553569 DOI: 10.3390/genes13122303

Abstract

Melanoma is considered to be the most serious and aggressive type of skin cancer, and metastasis appears to be the most important factor in its prognosis. Herein, we developed a transfer learning-based biomarker discovery model that could aid in the diagnosis and prognosis of this disease. After applying it to the ensemble machine learning model, results revealed that the genes found were consistent with those found using other methodologies previously applied to the same TCGA (The Cancer Genome Atlas) data set. Further novel biomarkers were also found. Our ensemble model achieved an AUC of 0.9861, an accuracy of 91.05, and an F1 score of 90.60 using an independent validation data set. This study was able to identify potential genes for diagnostic classification (C7 and GRIK5) and diagnostic and prognostic biomarkers (S100A7, S100A7, KRT14, KRT17, KRT6B, KRTDAP, SERPINB4, TSHR, PVRL4, WFDC5, IL20RB) in melanoma. The results show the utility of a transfer learning approach for biomarker discovery in melanoma.

Keywords

bias biomarker ensemble model machine learning melanoma transfer learning

References

  1. Genes Brain Behav. 2011 Oct;10(7):789-97 [PMID: 21771265]
  2. Expert Opin Pharmacother. 2019 Jun;20(9):1135-1152 [PMID: 31025594]
  3. PLoS Comput Biol. 2010 Jun 24;6(6):e1000807 [PMID: 20589078]
  4. Cancer Res. 2014 Nov 1;74(21):6318-29 [PMID: 25213322]
  5. Oncol Lett. 2017 Dec;14(6):7506-7512 [PMID: 29344196]
  6. Oncol Rep. 2003 Sep-Oct;10(5):1317-20 [PMID: 12883700]
  7. J Imaging. 2020 Nov 26;6(12): [PMID: 34460526]
  8. N Engl J Med. 2006 Jul 6;355(1):51-65 [PMID: 16822996]
  9. Nucleic Acids Res. 2019 Jan 8;47(D1):D607-D613 [PMID: 30476243]
  10. J Invest Dermatol. 2021 May;141(5):1198-1206.e13 [PMID: 33157095]
  11. Ann Oncol. 2018 Aug 1;29(8):1836-1842 [PMID: 29846502]
  12. Am J Med Genet B Neuropsychiatr Genet. 2009 Sep 5;150B(6):808-16 [PMID: 19086053]
  13. Sci Rep. 2021 Jan 13;11(1):1023 [PMID: 33441834]
  14. Front Immunol. 2020 Nov 10;11:585108 [PMID: 33240274]
  15. PLoS Comput Biol. 2019 Mar 5;15(3):e1006701 [PMID: 30835723]
  16. Nat Commun. 2020 Dec 11;11(1):6367 [PMID: 33311458]
  17. PLoS One. 2012;7(9):e40267 [PMID: 22962576]
  18. PLoS One. 2010 May 24;5(5):e10770 [PMID: 20520718]
  19. Psychiatry Res. 2006 Jan 30;141(1):39-51 [PMID: 16325263]
  20. Autophagy. 2018;14(6):1090-1091 [PMID: 29916296]
  21. PLoS One. 2013 Jun 20;8(6):e63949 [PMID: 23840300]
  22. Comput Struct Biotechnol J. 2014 Sep 03;11(18):22-7 [PMID: 25379140]
  23. Cancers (Basel). 2021 Feb 10;13(4): [PMID: 33578891]
  24. Pigment Cell Melanoma Res. 2015 Jul;28(4):453-63 [PMID: 25847062]
  25. J Biomed Inform. 2011 Dec;44 Suppl 1:S17-S23 [PMID: 21571094]
  26. Nature. 2017 Feb 2;542(7639):115-118 [PMID: 28117445]
  27. Cell. 2001 Jan 12;104(1):9-19 [PMID: 11163236]
  28. Int J Oncol. 2018 Apr;52(4):1178-1188 [PMID: 29436619]
  29. Biochem Biophys Res Commun. 2003 Oct 10;310(1):8-13 [PMID: 14511640]
  30. Ann Dermatol. 2010 Aug;22(3):370-2 [PMID: 20711283]
  31. Am J Hum Genet. 2019 Mar 7;104(3):503-519 [PMID: 30827500]
  32. F1000Res. 2016 Jun 29;5:1542 [PMID: 28232861]
  33. Semin Cell Dev Biol. 2017 Feb;62:170-177 [PMID: 27637160]
  34. BMC Med Genomics. 2008 Apr 28;1:13 [PMID: 18442402]
  35. J Am Acad Dermatol. 2018 Mar;78(3):620-621 [PMID: 28989109]
  36. PeerJ. 2013 Mar 05;1:e49 [PMID: 23638386]
  37. Pigment Cell Melanoma Res. 2008 Feb;21(1):27-38 [PMID: 18353141]
  38. Transl Cancer Res. 2020 Oct;9(10):5882-5892 [PMID: 35117201]
  39. J Intern Med. 2020 Jul;288(1):62-81 [PMID: 32128929]
  40. J Toxicol Pathol. 2019 Oct;32(4):245-251 [PMID: 31719751]
  41. J Healthc Eng. 2022 Mar 22;2022:2196096 [PMID: 35360474]
  42. Melanoma Res. 2002 Dec;12(6):627-31 [PMID: 12459653]
  43. Hum Immunol. 2012 Apr;73(4):393-8 [PMID: 22333690]
  44. Genes Immun. 2008 Jul;9(5):445-51 [PMID: 18480827]
  45. Am J Public Health. 2020 May;110(5):731-733 [PMID: 32191523]
  46. Anticancer Res. 2018 Mar;38(3):1343-1352 [PMID: 29491058]
  47. Phys Med Biol. 2020 Jul 06;65(13):135005 [PMID: 32252036]
  48. IUBMB Life. 2012 Jun;64(6):529-37 [PMID: 22573601]
  49. Oncotarget. 2016 Dec 27;7(52):86536-86546 [PMID: 27852032]
  50. Elife. 2013 Apr 30;2:e00358 [PMID: 23682311]
  51. Mol Med Rep. 2018 Feb;17(2):2907-2914 [PMID: 29257259]
  52. Cancers (Basel). 2019 May 20;11(5): [PMID: 31137558]
  53. Melanoma Res. 2019 Feb;29(1):23-29 [PMID: 30216200]
  54. Sci Rep. 2019 Oct 31;9(1):15790 [PMID: 31673075]
  55. Nature. 2007 Feb 22;445(7130):851-7 [PMID: 17314971]
  56. Pigment Cell Melanoma Res. 2014 Jan;27(1):19-36 [PMID: 24106873]
  57. Biometrics. 1988 Sep;44(3):837-45 [PMID: 3203132]
  58. Cells. 2020 Jul 20;9(7): [PMID: 32698392]
  59. J Biol Chem. 2002 Dec 6;277(49):47517-23 [PMID: 12351624]
  60. Endocr Relat Cancer. 2006 Dec;13(4):1269-77 [PMID: 17158770]

MeSH Term

Humans
Melanoma
Skin Neoplasms
Prognosis
Biomarkers, Tumor
Gene Expression Regulation, Neoplastic

Chemicals

Biomarkers, Tumor
Journal Article Research Support, Non-U.S. Gov't
Article has an altmetric score of 2

Word Cloud

Created with Highcharts 10.0.0modellearningtransferbiomarkerensemblefoundmelanomaMelanomaprognosisdiscoverymachineresultsgenesusingdatasetbiomarkersdiagnosticS100A7consideredseriousaggressivetypeskincancermetastasisappearsimportantfactorHereindevelopedlearning-basedaiddiagnosisdiseaseapplyingrevealedconsistentmethodologiespreviouslyappliedTCGACancerGenomeAtlasnovelalsoachievedAUC09861accuracy9105F1score9060independentvalidationstudyableidentifypotentialclassificationC7GRIK5prognosticKRT14KRT17KRT6BKRTDAPSERPINB4TSHRPVRL4WFDC5IL20RBshowutilityapproachBiomarkerDiscoveryMeta-ClassificationMetastaticProgressionUsingTransferLearningbias

Similar Articles

Cited By