Automation of Scientific Research (Spring 2021)

Instructor

• Christopher James Langmead cjl@cs.cmu.edu

• Computational Biology Department, School of Computer Science, Carnegie Mellon University

• Office hours: Wednesdays, 7-8pm, Pittsburgh time via Zoom (see Canvas for link)

Teaching Assistants

• TBD

Lectures: Tu,Th 4:00-5:20 pm, via Zoom

Course resources: Canvas and Piazza and this website

Course Description

CMU 02-450 (9 units) & CMU 02-750 (12 units)

Automated science and engineering combines Robotics, Machine Learning, and Artificial Intelligence to accelerate the pace of discovery and rational design. This course introduces students to the Machine Learning and Artificial Intelligence algorithms that enable this emerging paradigm. Emphasis is placed on techniques for sequential analysis (i.e., model discovery and hypothesis generation), design of experiments, and optimization to maximize the return on research capital. Specific approaches will include Active Learning, Reinforcement Learning, and Bayesian Optimization. Examples of automated science and engineering from the literature will be studied. Grading will be based on homeworks and quizzes.

Robotic scientific instruments are already used to decrease costs and increase reproducibility. Automated science and engineering take this one step further by leveraging Artificial Intelligence and Machine Learning to interpret data and select experiments in a closed-loop fashion. This emerging paradigm is motivated by the fact that most systems are too complex for humans to truly understand. Artificial Intelligence and Machine Learning can manage this complexity and find the most efficient paths to discovery and rational design by avoiding the costs of performing experiments where the outcome can already be predicted accurately.

Pre/Co-requisites

The course has been designed for graduate students in Carnegie Mellon's MS programs in Computational Biology and Automated Science. Other students are welcome, assuming that they have familiarity with basic concepts from biology (cells, proteins, nucleic acids) and statistics, as well as experience with computer programming and applied machine learning. Remedial materials will be provided to fill in any gaps you may have. Students must also understand and agree to comply with Carnegie Mellon University's policies on academic integrity (see also here).

Syllabus

• Quizzes (60%)

  • Six quizzes will be given online via canvas. Due dates can be found in Canvas.

• Homeworks (40%)

  • Four graded assignments will be given. Due dates can be found in Canvas.

  • Each student will receive a credit of 3 grace days to be applied to assignments. You do not need to ask permission to use late days, they will be deducted automatically.

  • Lateness policy: After your grace days have been exhausted, a 25% penalty will be applied for each day beyond the official due date.

  • Cheating policy: All work must be your own. Unauthorized collaboration or plagiarism will result in a negative grade (e.g., a homework worth 100 points will be factored in as a -100 points towards your final grade) and will be reported to your academic advisor and dean.

Course Outline

1. Core algorithmic techniques

   • Online Machine Learning

   • Active Machine Learning

   • Design of Experiments

   • Bayesian Optimization

2. Applications of automated science and engineering

There is no required textbook.

Course outcomes

Students who complete the course successfully will be able to:

• Understand and explain core concepts and experimental methods in molecular and cell biology

• Understand the core concepts and algorithms used in automated science and engineering

• Modify and apply software to automate several research and engineering tasks

• Apply knowledge of automated science algorithms to select and justify techniques for addressing various discovery and design challenges

• Evaluate and interpret the results of the chosen approach

• Understand, explain and critique published papers that employ automation for scientific research and engineering

Your well-being

Be sure to take care of yourself. Do your best to maintain a healthy lifestyle this semester by eating well, exercising, avoiding drugs and alcohol, getting enough sleep and taking some time to relax. This will help you achieve your goals and cope with stress.

All of us benefit from support during times of struggle. You are not alone. There are many helpful resources available on campus and an important part of the college experience is learning how to ask for help. Asking for support sooner rather than later is often helpful.

If you or anyone you know experiences any academic stress, difficult life events, or feelings like anxiety or depression, we strongly encourage you to seek support. Counseling and Psychological Services (CaPS) is here to help: call 412-268-2922 and visit their website at http://www.cmu.edu/counseling/. Consider reaching out to a friend, faculty or family member you trust for help getting connected to the support that can help.

If you or someone you know is feeling suicidal or in danger of self-harm, call someone immediately, day or night:

CaPS: 412-268-2922

Re:solve Crisis Network: 888-796-8226

If the situation is life threatening, call the police:

On campus: CMU Police: 412-268-2323

Off campus: 911

If you have questions about this or your coursework, please let me know.