This mini-course offers an overview of recent machine learning methods for protein design and modeling. Lectures will cover a range of different approaches including but not limited to protein structure prediction, modeling mutational effects, designing protein-protein interactions, and protein sequence design. This course is designed to teach students how to assess their protein modeling problem, choose which tool(s) would best suit their problem, and determine the 'success' of these methods in silico. This course will include demo Colab notebooks that students can use to try these methods and apply to their own research. The course will be lecture-based, with frequent opportunities for discussion and questions. Introductory biochemistry and introductory programming knowledge is expected.
1 units · Medical Satisfactory/No Credit
This mini-course offers an overview of recent machine learning methods for protein design and modeling. Lectures will cover a range of different approaches including but not limited to protein structure prediction, modeling mutational effects, designing protein-protein interactions, and protein sequence design. This course is designed to teach students how to assess their protein modeling problem, choose which tool(s) would best suit their problem, and determine the 'success' of these methods in silico. This course will include demo Colab notebooks that students can use to try these methods and apply to their own research. The course will be lecture-based, with frequent opportunities for discussion and questions. Introductory biochemistry and introductory programming knowledge is expected.
Offered in Spring 2027 at Stanford University.