We are excited to share updates about the upcoming OmicsLogic Data Science program that will focus on the application of data science principles to biological data. Primarily, we will focus on the use of high-throughput datasets like genomics, metagenomics, and transcriptomics to train machine learning models for predictive analysis. OmicsLogic Data Science is a program focused on data-science in application to projects sourced from current topics in biomedical research. In this program, we will focus on methods for the analysis of big data and data wrangling – essential skills for bioinformaticians as well as those interested in other types of non-biology related research.

We will work with the program participants providing support and guidance into these topics. Our expert team has been working for the past several weeks to make sure we have interesting examples, up-to-date methods, and a lot of resources that you will be able to access for the duration of this program. These include project examples, detailed coursework on each one of the methods we will use, practical exercises in coding and the logic of analysis, as well as the sessions where all of your questions will be answered.

Let’s start from the basics: What is Data Science and how is it related to Bioinformatics?

The truth is, both domains are very similar, but while data science assumes no particular specialization and is open to any type of domain knowledge, bioinformatics is specific to biological domain knowledge with applications in basic biological research, as well as clinical, biotech, pharmaceutical and even agricultural projects.

Thus the program is structured to provide you with insights into various data types, formats, and challenges and then introduce you to the typical processing, analysis, and interpretation methods for these data.

In Week 1, we will focus on omics data types, challenges associated with big data, and an overview of methods to handle and prepare data for in-depth analysis

In Week 2 of the program, we will focus on multivariate analysis methods and examples using Machine Learning and Artificial Intelligence.

Many of the exercises we prepared will include source code and practical assignments that you can complete in R and Python – two languages that are used in both bioinformatics domains and many others. Many statistical tools, visualization packages, and workflow in these languages make them a good choice if you plan to dabble in data processing and analysis. We will also provide you with cloud access to the T-BioInfo computational platform for processing of large scale NGS data:

After you have prepared the data, we will also explore the code behind each step so that you can understand how it works and modify it to fit your project needs. To learn these pieces of code, you will get practical examples and assignments every session. The practical coding assignments will also help you understand the R and Python code elements that will be a part of any data science project you end up working on in your future.