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

Overview

Journal Genes (Basel)

Publisher MDPI

Date 2022 Dec 23

PMID 36553569

Authors

Jose Marie Antonio Minoza

Jonathan Adam Rico

Pia Regina Fatima Zamora

Manny Bacolod

Reinhard Laubenbacher

Gerard G Dumancas

Romulo de Castro

Affiliations

Soon will be listed here.

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.

Citing Articles

Assessment of Concentration KRT6 Proteins in Tumor and Matching Surgical Margin from Patients with Head and Neck Squamous Cell Carcinoma.

Nalecz D, Swietek A, Hudy D, Wiczkowski K, Zlotopolska Z, Strzelczyk J Int J Mol Sci. 2024; 25(13).

PMID: 39000463 PMC: 11242288. DOI: 10.3390/ijms25137356.

Current knowledge about immunotherapy resistance for melanoma and potential predictive and prognostic biomarkers.

Song L, Yang Y, Tian X Cancer Drug Resist. 2024; 7:17.

PMID: 38835341 PMC: 11149101. DOI: 10.20517/cdr.2023.150.

Complete chloroplast genomes of three copal trees (Bursera: Bullockia): comparative analysis and phylogenetic relationships.

Lorenzana G, Rico Y Mol Biol Rep. 2024; 51(1):406.

PMID: 38459415 DOI: 10.1007/s11033-024-09304-z.

Emerging Prognostic and Predictive Significance of Stress Keratin 17 in HPV-Associated and Non HPV-Associated Human Cancers: A Scoping Review.

Lozar T, Wang W, Gavrielatou N, Christensen L, Lambert P, Harari P Viruses. 2023; 15(12).

PMID: 38140561 PMC: 10748233. DOI: 10.3390/v15122320.

Neurotransmitter receptor-related gene signature as potential prognostic and therapeutic biomarkers in colorectal cancer.

Zhang L, Deng Y, Yang J, Deng W, Li L Front Cell Dev Biol. 2023; 11:1202193.

PMID: 38099288 PMC: 10720326. DOI: 10.3389/fcell.2023.1202193.

References

Yosifova A, Mushiroda T, Kubo M, Takahashi A, Kamatani Y, Kamatani N . Genome-wide association study on bipolar disorder in the Bulgarian population. Genes Brain Behav. 2011; 10(7):789-97. DOI: 10.1111/j.1601-183X.2011.00721.x. View

Mason R, Au L, Ingles Garces A, Larkin J . Current and emerging systemic therapies for cutaneous metastatic melanoma. Expert Opin Pharmacother. 2019; 20(9):1135-1152. DOI: 10.1080/14656566.2019.1601700. View

De Las Rivas J, Fontanillo C . Protein-protein interactions essentials: key concepts to building and analyzing interactome networks. PLoS Comput Biol. 2010; 6(6):e1000807. PMC: 2891586. DOI: 10.1371/journal.pcbi.1000807. View

Sheshadri N, Catanzaro J, Bott A, Sun Y, Ullman E, Chen E . SCCA1/SERPINB3 promotes oncogenesis and epithelial-mesenchymal transition via the unfolded protein response and IL6 signaling. Cancer Res. 2014; 74(21):6318-29. PMC: 4216755. DOI: 10.1158/0008-5472.CAN-14-0798. View

Liu T, Men Q, Su X, Chen W, Zou L, Li Q . Downregulated expression of TSHR is associated with distant metastasis in thyroid cancer. Oncol Lett. 2018; 14(6):7506-7512. PMC: 5755142. DOI: 10.3892/ol.2017.7122. View

Ellerhorst J, Cooksley C, Broemeling L, Johnson M, Grimm E . High prevalence of hypothyroidism among patients with cutaneous melanoma. Oncol Rep. 2003; 10(5):1317-20. View

Manzo M, Pellino S . Bucket of Deep Transfer Learning Features and Classification Models for Melanoma Detection. J Imaging. 2021; 6(12). PMC: 8321205. DOI: 10.3390/jimaging6120129. View

Miller A, Mihm Jr M . Melanoma. N Engl J Med. 2006; 355(1):51-65. DOI: 10.1056/NEJMra052166. View

Szklarczyk D, Gable A, Lyon D, Junge A, Wyder S, Huerta-Cepas J . STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets. Nucleic Acids Res. 2018; 47(D1):D607-D613. PMC: 6323986. DOI: 10.1093/nar/gky1131. View

10.

Kalinina P, Vorstandlechner V, Buchberger M, Eckhart L, Lengauer B, Golabi B . The Whey Acidic Protein WFDC12 Is Specifically Expressed in Terminally Differentiated Keratinocytes and Regulates Epidermal Serine Protease Activity. J Invest Dermatol. 2020; 141(5):1198-1206.e13. DOI: 10.1016/j.jid.2020.09.025. View

11.

Haenssle H, Fink C, Schneiderbauer R, Toberer F, Buhl T, Blum A . Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists. Ann Oncol. 2018; 29(8):1836-1842. DOI: 10.1093/annonc/mdy166. View

12.

Gratacos M, Costas J, de Cid R, Bayes M, Gonzalez J, Baca-Garcia E . Identification of new putative susceptibility genes for several psychiatric disorders by association analysis of regulatory and non-synonymous SNPs of 306 genes involved in neurotransmission and neurodevelopment. Am J Med Genet B Neuropsychiatr Genet. 2008; 150B(6):808-16. DOI: 10.1002/ajmg.b.30902. View

13.

Han W, Hu C, Fan Z, Shen G . Transcript levels of keratin 1/5/6/14/15/16/17 as potential prognostic indicators in melanoma patients. Sci Rep. 2021; 11(1):1023. PMC: 7806772. DOI: 10.1038/s41598-020-80336-8. View

14.

Barnum S, Bubeck D, Schein T . Soluble Membrane Attack Complex: Biochemistry and Immunobiology. Front Immunol. 2020; 11:585108. PMC: 7683570. DOI: 10.3389/fimmu.2020.585108. View

15.

Mounir M, Lucchetta M, C Silva T, Olsen C, Bontempi G, Chen X . New functionalities in the TCGAbiolinks package for the study and integration of cancer data from GDC and GTEx. PLoS Comput Biol. 2019; 15(3):e1006701. PMC: 6420023. DOI: 10.1371/journal.pcbi.1006701. View

16.

Noorbakhsh J, Farahmand S, Foroughi Pour A, Namburi S, Caruana D, Rimm D . Deep learning-based cross-classifications reveal conserved spatial behaviors within tumor histological images. Nat Commun. 2020; 11(1):6367. PMC: 7733499. DOI: 10.1038/s41467-020-20030-5. View

17.

Lee S, Lee E, Kim S, Jeong P, Cho Y, Yun S . Identification of pro-inflammatory cytokines associated with muscle invasive bladder cancer; the roles of IL-5, IL-20, and IL-28A. PLoS One. 2012; 7(9):e40267. PMC: 3433484. DOI: 10.1371/journal.pone.0040267. View

18.

Kabbarah O, Nogueira C, Feng B, Nazarian R, Bosenberg M, Wu M . Integrative genome comparison of primary and metastatic melanomas. PLoS One. 2010; 5(5):e10770. PMC: 2875381. DOI: 10.1371/journal.pone.0010770. View

19.

Shibata H, Aramaki T, Sakai M, Ninomiya H, Tashiro N, Iwata N . Association study of polymorphisms in the GluR7, KA1 and KA2 kainate receptor genes (GRIK3, GRIK4, GRIK5) with schizophrenia. Psychiatry Res. 2005; 141(1):39-51. DOI: 10.1016/j.psychres.2005.07.015. View

20.

Smith M, Wilkinson S . CCPG1, a cargo receptor required for reticulophagy and endoplasmic reticulum proteostasis. Autophagy. 2018; 14(6):1090-1091. PMC: 6103402. DOI: 10.1080/15548627.2018.1441473. View