About this Course

This data science course is perfect for those interested in data analysis and interpretation. Initially, the course introduces the mathematical definition of distance, motivating the use of singular value decomposition (SVD) for dimension reduction in handling high-dimensional datasets. Additionally, the relationship between multi-dimensional scaling and principal component analysis is explored. The course further details the batch effect problem in genomics and provides methods to detect and adjust for these effects.

As the course progresses, learners engage with machine learning applications to large-scale data, focusing on clustering analysis, including K-means and hierarchical clustering. Essentials of creating prediction algorithms are covered, demonstrating real-world applications in genomics.

Designed for a diverse audience, this course offers a flexible learning pathway, part of two professional certificates. It gradually increases in difficulty, advancing into complex statistical models and sophisticated software engineering techniques.

What Students Will Learn

• Understanding of mathematical distances and their applications.
• Techniques for reducing data dimensionality including SVD and principal component analysis.
• Skills in multi-dimensional scaling plots and factor analysis.
• Strategies to handle batch effects in data analysis.
• Fundamentals of clustering and the generation of heatmaps.
• Introduction to basic concepts in machine learning targeted to large datasets.

Pre-requisites or Skills Necessary

Students should have a basic understanding of programming, introduction to statistics, and introduction to linear algebra or they should have completed courses PH525.1x and PH525.2x. Alternatively, advanced students in statistics may skip the initial courses.

Course Content

• Overview of data science and its applications in real-world scenarios.
• Detailed exploration of distance metrics and their importance in data science.
• Comprehensive study of SVD and PCA for dimensionality reduction.
• Analytical approaches to tackle batch effects in genomics data analysis.
Efficacy of clustering methods like K-means and hierarchical clustering in data segmentation.
• Foundation of machine learning and its implication in analyzing large-scale data.

Who This Course Is For

This course is designed for students from various backgrounds, including statistics and biology, who are interested in applying data science techniques to real-world problems, particularly in genomics and life sciences. The flexibility in the course structure allows both beginners and advanced learners to find valuable knowledge tailored to their level.

Real World Applications

Skills from this course can be directly applied to genomic data analysis, personalizing medical treatments, improving agricultural methods, and enhancing environmental preservation efforts. They are also invaluable in fields like marketing, finance, and public policy, where large data sets need to be analyzed and interpreted.

Syllabus

• PH525.1x: Statistics and R for the Life Sciences
• PH525.2x: Introduction to Linear Models and Matrix Algebra
• PH525.3x: Statistical Inference and Modeling for High-throughput Experiments
• PH525.4x: High-Dimensional Data Analysis
• PH525.5x: Introduction to Bioconductor
• PH525.6x: Case Studies in Functional Genomics
• PH525.7x: Advanced Bioconductor