Prediction and Analysis of Skin Cancer Progression using Genomics Profiles of Patients

Sherry Bhalla,Harpreet Kaur,Anjali Dhall,Gajendra P S Raghava

doi:10.1038/s41598-019-52134-4

Abstract

The metastatic Skin Cutaneous Melanoma (SKCM) has been associated with diminished survival rates and high mortality rates worldwide. Thus, segregating metastatic melanoma from the primary tumors is crucial to employ an optimal therapeutic strategy for the prolonged survival of patients. The SKCM mRNA, miRNA and methylation data of TCGA is comprehensively analysed to recognize key genomic features that can segregate metastatic and primary tumors. Further, machine learning models have been developed using selected features to distinguish the same. The Support Vector Classification with Weight (SVC-W) model developed using the expression of 17 mRNAs achieved Area under the Receiver Operating Characteristic (AUROC) curve of 0.95 and an accuracy of 89.47% on an independent validation dataset. This study reveals the genes C7, MMP3, KRT14, LOC642587, CASP7, S100A7 and miRNAs hsa-mir-205 and hsa-mir-203b as the key genomic features that may substantially contribute to the oncogenesis of melanoma. Our study also proposes genes ESM1, NFATC3, C7orf4, CDK14, ZNF827, and ZSWIM7 as novel putative markers for cutaneous melanoma metastasis. The major prediction models and analysis modules to predict metastatic and primary tumor samples of SKCM are available from a webserver, CancerSPP (http://webs.iiitd.edu.in/raghava/cancerspp/).

Highlights

Cancer is one of the major causes of mortality worldwide since the last few decades
Li et al made an attempt to predict metastatic progression of melanoma tumor samples and predicted metastatic progression scores using mRNA and miRNA expressions individually; based on which they assigned primary and metastatic samples to primary and metastatic groups. They found a correlation between clinical characteristics of samples, i.e. Clark’s level and lymph node status with metastatic progression score
All of metastatic samples were correctly assigned to the metastatic group; but, many of primary samples were incorrectly assigned to the metastatic group based on the metastatic progression score

Summary

Introduction

Cancer is one of the major causes of mortality worldwide since the last few decades. According to GLOBOCAN, 2018, 18.1 million new cancer cases and 9.6 million deaths have been estimated worldwide. The core study on SKCM done by TCGA has revealed four subtypes of cancer, which include mutant BRAF, mutant RAS, mutant NF1, triple WT (wild-type) based on mutant genes. One study has predicted the metastatic progression score for the assignment of metastatic and primary melanoma based on key miRNA and mRNA expression based putative biomarkers[38]. The current study is designated to overcome these inadequacies In this analysis, we have made an effort to understand the cutaneous skin melanoma progression based on multi-omics layers of data in TCGA that comprises of RNAseq, miRNAseq and methylation expression. Prediction models were developed based on these key identified genomic features using several supervised machine learning techniques that can segregate primary and metastasized SKCM patients

Objectives

Methods

Results

Conclusion