Analysis of Microarray Data using Machine Learning/AI in R

Microarrays are one of the most common tools to understand biological spectacle by large-scale dimensions of biological samples, typically DNA, RNA, or proteins. The technique has been used for a variety of purposes in life science research, ranging from gene expression profiling to SNP or other biomarker identification, and further, to understand relations between genes and their activities on a large scale. Artificial intelligence (AI) and machine learning (ML) techniques can be used to analyse microarray data to gain insights into biological processes. Machine learning tools can automate the analysis of microarray data to identify patterns of gene expression. These patterns can be used to compare gene expression between different conditions, such as healthy and diseased cells. There are no curated machine learning/AI-ready datasets that meet the requirements for machine learning analyses within public functional genomics repositories at the moment. The R language supports identifying gene expression through Bioconductor packages to show all differential gene expressions by generating the volcano map, Euclidean distances to perform clustering, Venn diagram, and heatmap.

The aim of microarray data analyses is the identification of genes showing significant differences in expression levels between two or more groups.

DAY 1: Functional genomics repositories

• General Overview of public genomics repositories
• Overview of GEO2R, procedure to use, Edit options and features, Limitations and caveats, Summary Statistics.

DAY 2: R studio and Bioconductor packages

• R and Bioconductor packages installation
• GEOquery and limma Bioconductor package

DAY 3: Microarray Data Analysis

• Gene expression analysis with GEOquery and limma for Microarray data analysis