AI and Machine Learning in Bioinformatics

Catalog description

The digital revolution has seen a dramatic increase in data collection in various disciplines of health sciences. The challenge of big and wide data is especially pronounced in the biomedical space where, for example, whole genome sequencing technology enables researchers to interrogate all 3 billion base pairs of the human genome. With an expected 50% of the world¿s population likely to have been sequenced by 2025, the resulting datasets may surpass those generated in Astronomy, Twitter and YouTube combined. Machine Learning approaches are hence necessary to gain insights from these enormous and highly complex modern datasets enabling the training of very sophisticated Machine Learning models under the context of Artificial intelligence. The course addresses various topics of Machine Learning approaches that have been applied under the genomic revolution. Emphasis are placed on Machine Learning algorithms to recognize patterns in DNA sequences such as pinpointing the locations of transcription start sites (TSSs), identifying the importance of junk DNA in the genome and identifying untranslated regions (UTRs), introns and exons in eukaryotic chromosomes. The input data can include the genomic sequence, gene expression pro¿les across various experimental conditions or phenotypes, protein-protein interaction data, synthetic lethality data, open chromatin data, and ChIP-seq data. Three credits; one-hour laboratory. Prerequisites: AI 681 A pre requisite of AI 681 is required.