Genomics of Human Malignant Melanoma

BioMed Research International

2014

In this work the effects of simple imputations are studied, regarding the integration of multimodal data originating from different patients. Two separate datasets of cutaneous melanoma are used, an image analysis (dermoscopy) dataset together with a transcriptomic one, specifically DNA microarrays. Each modality is related to a different set of patients, and four imputation methods are employed to the formation of a unified, integrative dataset. The application of backward selection together with ensemble classifiers (random forests), followed by principal components analysis and linear discriminant analysis, illustrates the implication of the imputations on feature selection and dimensionality reduction methods. The results suggest that the expansion of the feature space through the data integration, achieved by the exploitation of imputation schemes in general, aids the classification task, imparting stability as regards the derivation of putative classifiers. In particular, although the biased imputation methods increase significantly the predictive performance and the class discrimination of the datasets, they still contribute to the study of prominent features and their relations. The fusion of separate datasets, which provide a multimodal description of the same pathology, represents an innovative, promising avenue, enhancing robust composite biomarker derivation and promoting the interpretation of the biomedical problem studied.

Section: Background and Related Workmentioning

confidence: 99%

Integration of High-Volume Molecular and Imaging Data for Composite Biomarker Discovery in the Study of Melanoma

Μούτσελος

BioMed Research International

2014

“…CM tumorigenesis is often explained as a progressive transformation of normal melanocytes to nevi that subsequently develop into primary cutaneous melanomas. The molecular pathways involved have been although little studied [6] and despite that genomic markers or gene signatures have been defined for various cancers (such as breast cancer), there has been no similar progress for malignant melanoma. Genomic studies that have been performed on CM exploit different microarray technological platforms applied in highly heterogeneous patient sets.…”

Section: Cutaneous Melanomamentioning

confidence: 99%

Gene Prioritization for Inference of Robust Composite Diagnostic Signatures in the Case of Melanoma

Valavanis

Μούτσελος²,

IFIP Advances in Information and Communication Technology

2013

An integrated dataset originating from multi-modal datasets can be used to target underlying causal biological actions that through a systems level process trigger the development of a disease. In this study, we use an integrated dataset related to cutaneous melanoma that comes from two separate sets (microarray and imaging) and the application of data imputation methods. Our goal is to associate low-level biological information, i.e. gene expression, to imaging features, that characterize disease at a macroscopic level. Using an average Spearman correlation measurement of a gene to a total of 31 imaging features, a set of 1701 genes were sorted based on their impact to imaging features. Top correlated genes, comprising a candidate set of gene biomarkers, were used to train an artificial feed forward neural network. Classification performance metrics reported here showed the proof of concept for our gene selection methodology which is to be further validated.

“…CM tumorigenesis is often explained as a progressive transformation of normal melanocytes to nevi that subsequently develop into primary cutaneous melanomas (PCM). However, the molecular pathways involved have not been clearly elucidated, although considerable progress has been made [7]. Despite the success of genomics in defining genomic markers or gene signatures for other kinds of cancers (such as breast cancer), there has been no similar progress related to malignant melanoma.…”

Section: Cutaneous Melanomamentioning

confidence: 99%

Feature Selection Study on Separate Multi-modal Datasets: Application on Cutaneous Melanoma

Μούτσελος¹,

IFIP Advances in Information and Communication Technology

2012

Abstract. In this work, we study the behavior of a feature selection algorithm (backwards selection) using random forests, by fusing multi-modal data from different subjects. Two separate datasets related to cutaneous melanoma, obtained from image (dermoscopy) and non-image (microarray) sources are used. Imputations are applied in order to acquire a unified dataset, prior the effect of machine learning algorithms. The results suggest that application of the normal random imputation method acts as an additional variation factor, helping towards stability of potential recommended biomarkers. In addition, microarray-derived features were favorably selected as best predictors compared to image-derived features.