Dates, Price and Registration

Machine Learning for Single Cell Analysis is a three-day workshop hosted by the Yale Center for Biomedical Data Science and designed by the Krishnaswamy Laboratory.

Students, Postdocs, and Faculty are encourage to apply. Experience with Python is strongly recommended. We encourage people to take the following free courses from IBM’s CognitiveClass:

  1. The Introducing Jupyter Notebooks module of the “Data Science Tools” course. The rest of the Cognitive Class courses use Jupyter notebooks, and we will use Jupyter Notebooks in our workshop. (Est. 20 minutes)

  2. Python for Data Science, which teaches the fundamentals of working with Python and some basics of working with data. (Est. 5 hours)

  3. Data Analysis with Python, which teaches the basics of Numpy and Pandas for handling data in Python. (Est. 5 hours)

The workshop will be held from October 16-18, 2019.

For pricing and registration, please visit:

About the Course

Single cell methods, such as single cell RNA-sequencing, are becoming an increasingly popular way for scientists to probe the heterogeneity and dynamics of biological systems. However, analysis of single cell datasets is a challenging task. The data itself is large and noisy, and choosing the correct tools for analysis requires sifting through literally hundreds of published methods. Getting started with a new single cell project can be a daunting task.

We want to help.

The purpose of this three day workshop is to tear back some of the complexity behind single cell analysis. Students will learn practical skills for analyzing single cell datasets and develop a conceptual understanding of the machine learning foundations behind each method. Students will also receive an introduction to emerging trends in single cell analysis such as deep learning.

Each day, students will hear lectures from instructors with experience developing and applying single cell methods followed by intensive hands-on lab sessions with a 5:1 student:instructor ratio. In these lab sessions, students will work in teams to analyze real-world single cell datasets. The workshop will conclude with a hands-on bring-your-own-data workshop where students will have the opportunity to bring in their own experimental datasets (or use one we provide) and collaborate with students and instructors on their projects.

By the end of the course, students will:

1.     Understand the common workflow of a single cell experiment

2.     Be able to apply common machine learning methods for analysis of single cell data

3.     Grasp the impact of method choice and parameter selection on analysis

4.     Build a foundation for exploring the single cell literature

Online Materials

Our goal of this workshop is to compile a set of online Python notebooks, course materials, and recorded lectures that are freely available online. To get a sense of the direction we are headed checking out the following:

The first pilot of this workshop was organized as a half-day course through the Yale GENE 760 Methods for Genomic Analysis class in Spring 2019. The Google CoLab notebook for this pilot can be found at

We are also producing a set of online content organized around the workshop that can be used for self-directed learning before, during, or after the course. These materials are still a work-in-progress, and a rough draft can be found at

Finally, tutorials for our methods can be found on their respective GitHub pages at

Course Schedule

Day 1 - Wednesday, October 16th

9:00-10:15am         Lecture - Introduction to single cell experiments and design

10:15-10:30am    Coffee Break

10:30-12:00pm     Tutorial - Loading and preprocessing single cell data

12:00-1:00pm        Lunch (provided)

1:00-2:30pm        Lecture - Review of Linear algebra and Graph theory

2:30-2:45pm        Coffee break

2:45-5:00pm        Tutorial - Visualizing single cell datasets

Day 2 - Thursday, October 17th

9:00-10:15am       Tutorial - Imputing missing gene expression

10:15-10:30am   Coffee Break

10:30-12:00pm     Tutorial - Clustering and Differential Expression

12:00-1:00pm       Lunch (provided)

1:00-2:30pm        Tutorial - Trajectory inference

2:30-2:45pm        Coffee break

2:45-5:00pm        Tutorial - Gene interaction

Day 3 - Friday, October 18th

9:00-10:15am         Lecture -  Introduction to Deep Learning

10:15-10:30am    Coffee Break

10:30-12:00pm     Tutorial - Deep Learning for Large Single Cell Data

12:00-1:00pm        Lunch (provided)

1:00-5:00pm        Bring-Your-Own-Data Workshop