Bioinformatics for T-Cell immunology - Introduction to machine and deep learning analysis - Part 2

Overview:The session aims for training participants on using deep/machine learning models to discover a variety of biosynthetic gene clusters (BGCs) in literature and whole genome. BGCs are clusters of genes that produce secondary metabolites, such as antibiotics, antiviral, antitumor compounds, pollutant biodegrading enzymes, as well as antigens. This session will focus on BGCs involved in T-cell immunity. And, given the popularity of DNA vaccines, we will try to retrieve the DNA sequences of potential microbial antigens from their corresponding BGCs as vaccine targets.

Learning outcome
By the end of this session you will be able to:

• Understand the different types of biosynthetic gene clusters (BGCs) and their implications in environmental phenomena as well as health and disease.
• Understand the roles of saccharide BGCs in T-cell immunity and diseases.
• Get insights into different BGCs discover tools and how they were trained.
• Use python libraries as well as trained deep and machine learning models in identifying saccharide BGCs in whole genomes.
• Gitlab from emerald:https://gitlab.com/maaly7/emerald_bgcs_annotations

• Gitlab for the BCG discovery: https://gitlab.com/maaly7/bgc_discovery_for_t_cell_immunology

Maaly Nassar – SciBite

Maaly Nassar is a senior data scientist at Elsevier (SciBite team). She works on developing knowledge and drug discovery machine learning algorithms for pharmaceutical companies. Before moving to SciBite, Maaly worked as a machine learning scientist for the EMERALD project at EMBL- EBI.

She developed and integrated machine learning frameworks and pipelines that automatically enrich/annotate metagenomics and biosynthetic gene clusters sequences with data from literature.