GSgalgoR-package: GSgalgoR: A bi-objective evolutionary meta-heuristic to...

In GSgalgoR: An Evolutionary Framework for the Identification and Study of Prognostic Gene Expression Signatures in Cancer

Description

This package was developed to provide a simple to use set of functions to use the galgo algorithm. A multi-objective optimization algorithm for disease subtype discovery based on a non-dominated sorting genetic algorithm.

Different statistical and machine learning approaches have long been used to identify gene expression/molecular signatures with prognostic potential in different cancer types. Nonetheless, the molecular classification of tumors is a difficult task and the results obtained via the current statistical methods are highly dependent on the features analyzed, the number of possible tumor subtypes under consideration, and the underlying assumptions made about the data. In addition, some cancer types are still lacking prognostic signatures and/or of subtype-specific predictors which are continually needed to further dissect tumor biology. In order to identify specific molecular phenotypes to develop precision medicine strategies we present Galgo: A multi-objective optimization process based on a non-dominated sorting genetic algorithm that combines the advantages of clustering methods for grouping heterogeneous omics data and the exploratory properties of genetic algorithms (GA) in order to find features that maximize the survival difference between subtypes while keeping high cluster consistency.

Package:	GSgalgoR
Type:	Package
Version:	1.0.0
Date:	2020-05-06
License:	GPL-3
Copyright:	(c) 2020 Martin E. Guerrero-Gimenez.
URL:	https://www.github.com/harpomaxx/galgo
LazyLoad:	yes

Author(s)

Martin E. Guerrero-Gimenez [e-mail]

Maintainer: Carlos A. Catania [e-mail]

GSgalgoR documentation built on Nov. 8, 2020, 6:57 p.m.