TY - JOUR
T1 - Biomarker Discovery for Meta-Classification of Melanoma Metastatic Progression Using Transfer Learning
AU - Miñoza, Jose Marie Antonio
AU - Rico, Jonathan Adam
AU - Zamora, Pia Regina Fatima
AU - Bacolod, Manny
AU - Laubenbacher, Reinhard
AU - Dumancas, Gerard G
AU - de Castro, Romulo
PY - 2022/12/1
Y1 - 2022/12/1
N2 - 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.
AB - 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.
KW - bias
KW - biomarker
KW - ensemble model
KW - machine learning
KW - melanoma
KW - transfer learning
UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85144503236&origin=inward
UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85144503236&origin=inward
U2 - 10.3390/genes13122303
DO - 10.3390/genes13122303
M3 - Article
C2 - 36553569
SN - 2073-4425
VL - 13
JO - Genes
JF - Genes
IS - 12
M1 - 2303
ER -
