Cytometry technologies are essential tools for immunology research, providing high-throughput measurements of the immune cells at the single-cell level. In this workshop, we will build and test a deep convolutional neural network to diagnose the latent cytomegalovirus (CMV) in healthy individuals using CyTOF data. In addition, we will developed a permutation-based method for interpreting the deep convolutional neural network model and identify key immune cells associated with the CMV infection.

Registration opens on Feb 24, 2020

Learning Objectives

• Understand basic concepts in neural networks
• Learn to build and train neural networks using Keras
• Design customized deep learning models for cytometry data (CyTOF and flow cytometry data)
• Apply techniques to interpret deep learning models

Prerequisites / Preparation

Must be familiar with Jupyter notebooks and basic Python 3 data structures including: dictionary, NumPy arrays, and pandas data frames.

Software

The workshop will be cloud-based. Users must have one of the mainstream browsers (IE, Firefox, Chrome, Safari).

Materials

Workshop materials will be available online by the time of the workshop here

Instructors

Zicheng Hu is a Research Scientist in the Butte Lab at the Bakar Computational Health Sciences Institute at UCSF.

Sanchita Bhattacharya is a Bioinformatics Project Leader in the Butte Lab at the Bakar Computational Health Sciences Institute at UCSF.

Registration opens on Feb 24, 2020