INTEGRATIVE PREDICTIVE MODELING OF METASTASIS IN MELANOMA CANCER

Download

Thesis_PhD_Aysegul_Kutlay.pdf

Date

2022-2-08

Author

KUTLAY, AYŞEGÜL

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

283
views

200
downloads

This study focused on identifying the regulatory impact of genetic biomarkers for monitoring metastatic molecular signatures of melanoma by investigating the consolidated effect of miRNA, mRNA, and DNA methylation. We developed multiple machine learning models to distinguish the metastasis by integrating miRNA, mRNA, and DNA methylation markers. We used the TCGA melanoma dataset to differentiate metastatic melanoma samples by assessing a set of predictive models. An iterative combination of differentially expressed miRNA, mRNA, and methylation signatures is used as candidate markers to reveal each new biomarker category's impact. In each iteration, the performances of the combined models are calculated. The choice of feature selection method and under and oversampling approaches are analyzed during all comparisons. Selected biomarkers of the highest performing models are further analyzed for the biological interpretation of functional enrichment. MiRNA biomarkers can identify metastatic melanoma with an 81% F-score in the initial model. The addition of mRNA markers upon miRNA increased F-score to 92 %. In the final integrated model, the inclusion of the methylation data resulted in a similar F-score of 92% but produced a stable model with low variance across multiple trials. Our results support the role of miRNA regulation in metastatic melanoma as miRNA markers models metastasis outcomes with high accuracy. Moreover, the integrated evaluation of miRNA with mRNA and Methylation biomarkers increases the model's accuracy. It populates selected biomarkers on the metastasis-associated pathways of melanoma, such as "Osteoclast," "Rap1 Signaling" "and "Chemokine Signaling" Pathways.

Subject Keywords

Machine Learning, Metastatic Molecular Signatures, miRNA, mRNA, DNA Methylation

URI

https://hdl.handle.net/11511/96330

Collections

Graduate School of Informatics, Thesis

Suggestions

OpenMETU
Core

A multi-layered graphical model of the relation among SNPS, GENES, and pathways based on subgraph search Ersoy, Gökhan; Aydın Son, Yeşim; Can, Tolga; Department of Bioinformatics (2015) The analysis of Single Nucleotide Polymorphisms (SNPs) through Genome Wide Association Studies (GWAS) presents great potential for describing disease loci and gaining insight into the underlying etiology of diseases. Recently described combined p-value approach allows identification of associations at gene and pathway level. The integrated programs like METU-SNP produce simple lists of either SNP id/gene id/pathway title and their p-values and significance status or SNP id/disease id/pathway information. In...
IDENTIFYING ISOFORM SWITCHES IN BREAST CANCER HENDEN, Şevki Onur; Can, Tolga; Department of Computer Engineering (2021-9-9) Characterizing the human genome's molecular functions and their variations across people is vital for understanding the cellular processes behind human genetic characteristics and diseases. With the advent of single-cell RNA sequencing (scRNA-seq), it is now possible to investigate gene expression in individual cells. Although a number of scRNA-seq bioinformatics tools are now available, many of them focus on overall gene expression levels and, as a result, often ignore heterogeneity caused by individual tr...
FEN BİLİMLERİ ENSTİTÜSÜ/LİSANSÜSTÜ TEZ PROJESİ Akkaya, Mahinur; Mustafa, Zemran(2014-12-31) SITE DIRECTED MUTATIONS OF AN PLANT PATHOGEN EFFECTOR GENE FOR FUNCTIONAL ANALYSIS
Targeting human telomeric DNA with azacyanines Küçükakdağ Doğu, Ayça; Persil Çetinkol, Özgül; Department of Chemistry (2019) Small molecules targeting telomeric DNA or its interactions with telomerase have been an active area of cancer research. Within this thesis, a series of five new benzimidazole compounds differing from each other in alkyl chain length and branching in the benzimidazole ring (ethyl, propyl, isopropyl, butyl, and isobutyl) were synthesized and characterized using Nuclear Magnetic Resonance (NMR) spectroscopy, High Resolution Mass spectroscopy and C/H/N elemental analysis. Their interactions with human telomeri...
Predicting the effect of hydrophobicity surface on binding affinity of PCP-like compounds using machine learning methods Yoldaş, Mine; Alpaslan, Ferda Nur; Büyükbingöl, Erdem; Department of Computer Engineering (2011) This study aims to predict the binding affinity of the PCP-like compounds by means of molecular hydrophobicity. Molecular hydrophobicity is an important property which aff ects the binding affinity of molecules. The values of molecular hydrophobicity of molecules are obtained on three-dimensional coordinate system. Our aim is to reduce the number of points on the hydrophobicity surface of the molecules. This is modeled by using self organizing maps (SOM) and k-means clustering. The feature sets obtained fro...

Citation Formats

A. KUTLAY, “INTEGRATIVE PREDICTIVE MODELING OF METASTASIS IN MELANOMA CANCER,” Ph.D. - Doctoral Program, Middle East Technical University, 2022.