“Machine Learning for Biomedical Data - Workflows in Next Generation Sequencing Transcriptomics”
Part 1: Conventional Machine Learning Approaches for Next Generation Sequencing
Using a public-domain dataset that models multi-omics integration in Precision Medicine ( https://genomebiology.biomedcentral.com/articles/10.1186/gb-2013-14-10-r110 ), we will review rapid RNA-seq processing for expression quantification applying logical pipeline construction and pre-processing considerations. In hands-on exercises, participants will explore the expression table using conventional unsupervised machine learning methods and build supervised classifiers with and without feature extraction. The session will be conducted in a non-coding environment to accommodate all levels of users. Using the T-BioInfo platform, participants will learn about the logic and considerations of applying such methods and be prepared for independent downstream analysis and visualization of data using the downloaded R scripts produced by the system. The produced/downloaded code will be reviewed, customized and used in subsequent sessions.
Part 2: Combining custom software with R to streamline analysis workflows and visualize 'Omics data insights.
The second session will build on the same topics and utilize the same dataset to focus on basic data exploration and visualization in R. Once processed, expression values from huge Next Generation Sequencing datasets are hard to work with and need to be reduced to provide meaningful insights. Once key genes or isoforms are selected, the produced tables can be used This session will strengthen the participants ability to transition to script-based workflows in RNA-seq downstream analysis and visualization. Participants will learn the basics of loading, transforming and manipulation of tables and subsequent visualization of produced tables to represent meaningful findings.
Sessions led by Stepan Nersisyan (Tauber Bioinformatics Research Center)