Based on the genome sequence and patient clinical data, we experiment and practice various bioinformatics methodologies related to interpretable artificial intelligence technologies such as disease prediction, diagnosis, and selection of treatment biomarker targets. We learn methods for analyzing large-scale biomedical data, such as genome (WES) mutation analysis and transcriptomics expression levels. We study genetic sequence analysis methodologies, essential technologies for clinical and life big data analysis, and statistical methodologies. We learn Python coding and bio data formats required for bio big data analysis.

With the development of large-scale personalized genetic analysis technology, patients' bio big data is accumulating. We study artificial intelligence methodologies required for the development of digital healthcare technology, disease gene exploration through analysis of clinical big data obtained from patients and hospitals, bioinformatics methodologies related to disease prognosis and survival rate prediction, and data analysis techniques using artificial intelligence. In addition, we practice methods that can quantitatively explore the correlation between disease onset and genetic abnormalities based on this.

You can learn basic Python coding with an instructor during class time. You can take the course if you only have basic life science knowledge. You can learn bio and medical data analysis methods through lectures on concepts and practical training.

General Life Science (1st year) and Programming and Problem Solving (1st year). It is an experimental and practical course for undergraduate students. You must study the basics of Python coding before taking the course.

Evaluation method: Evaluation based on attendance, midterm presentation, and final assignment submission (no written exam)
Grading: Attendance 50%, presentation and assignment 50%

No need to purchase textbooks. Materials related to bioinformatics and healthcare informatics are distributed as handouts during class.

For 3-4 weeks, you will learn basic data structures and analysis methods and practice analyzing various bio or medical data.

Then, you will prepare a project presentation on cancer patient data analysis, disease genes, biomarkers, drug genomics analysis, etc., and conduct the practice with the help of a teaching assistant.

1st week: Structure of bio-big data
2nd week: Structure of bio-big data
3rd week: Domain knowledge of biology and healthcare informatics
4th week: Domain knowledge of biology and healthcare informatics
5th week: Biological network and module structure
6th week: Biological network and module structure
7th week: Midterm review and project topic selection
8th week: Analysis of genome and protein functions
9th week: Disease module analysis and phenotypic ontology
10th week: Methodology for analyzing gene mutation and expression level variation
11th week: Method for integrating omics data
12th week: Method for integrating omics data
13th week: Construction of gene-disease phenotype map
14th week: Construction of gene-disease phenotype map
15th week: Project research presentation
16th week: Writing and evaluating project report

Consists of project classes, practical training, and assignment presentations.
Basic Python coding can be learned with a teaching assistant during class time.
You can take the course if you have basic knowledge of life science.
Practical training is conducted considering the students' level.
This subject is a laboratory training subject.

Learning data science and artificial intelligence techniques in bio and medical fields
Basically, one teaching assistant per three students