This course provides a practical experience in integration of bioinformatics data of diverse types in collaboration with a pharmaceutical or biotechnology company. At the beginning of the course, students will be presented with a description of the problem and sample data sets. Students will work as part of independent teams to design, implement and evaluate an appropriate data integration or analysis system (with the opportunity for interaction with company developers for advice and feedback). The course grade will be based on an oral presentation of the developed software system and a written report describing its development and evaluation. Selected students will have the opportunity to present their work to the company. Prerequisites: 03-310 or 03-311 or 03-510 and 15-211 (15-415 or 15-451 recommended), or permission of instructor.
This course was piloted in Spring 2003 as a special section of the Biological Sciences Independent Study course (03-410B) and of the Masters Research course (03-700B) in collaboration with GlaxoSmithKline. Six students participated in teams of two and five of those students traveled to Philadelphia to present their project results.
In Spring 2005, six students participated in a project in collaboration with Cellomics, Inc. The students worked in teams of three and presented their results at Cellomics headquarters in Pittsburgh.
In Spring 2006, three students participated in a project in collaboration with the Immune Tolerance Network (coordinator: Dave Parrish). The project involved using machine learning methods on large sets of flow cytometry data.
In Spring 2008, eight students participated in a project in collaboration with ChemImage Corporation (coordinator: John Maier). The project involved developing a prognistic index for subjects using machine vision methods on images from Raman molecular imaging.
In Spring 2009, six students participated in a project in collaboration with Cognition Therapeutics, Inc (coordinator: Susan Catalano). The project involved building an image processing algorithm to distinguish subtle phenotypes in a high content screening assay.