Deep Learning for Healthcare Genomics
Presented by SGInnovate, NVIDIA & NSCC
SGInnovate, together with the NVIDIA Deep Learning Institute (DLI) and National Supercomputing Centre (NSCC) is proud to bring to you Deep Learning for Healthcare Genomics.
Led by seasoned instructors, you can expect to learn the latest deep learning techniques for designing and deploying neural network-powered machine learning across a variety of application domains.
This workshop teaches you to apply deep learning to detect chromosome co-deletion and search for motifs in genomic sequences. The workshop starts with image segmentation which is a technique to classify each pixel into a specific class, followed by image classification techniques as leveraged by Mayo Clinic to get unique results of using deep learning to predict radiomics and concludes by teaching techniques to interpret deep learning models to discover predictive genome sequence patterns. Ideally, a student who enrols in this course will have a basic familiarity with deep neural networks, such as through the DLI Fundamentals of Computer Vision course or another online training program. Basic coding experience in Python or a similar language is also useful.
In the course, participants will learn:
- How CNNs work
- To evaluate MRI images using CNNs
- To use real regulatory genomic data to research new motifs
- Understand the basics of convolutional neural networks (CNNs) and how they work
- Apply CNNs to MRI scans of low-grade gliomas (LGGs) to determine 1p/19q chromosome co-deletion status
- Use the DragoNN toolkit to simulate genomic data and to search for motifs
Click here for more SGInnovate – NVIDIA Training Programmes.
08:45am – 09:00am: Registration and Introduction
09:00am – 11:00am: Image Classification with Digits
Explore how to segment MRI images to measure parts of the heart using deep learning techniques.
- Extending Caffe with custom Python layers
- Implementing the process of transfer learning
- Creating fully Convolutional Neural Networks (CNNs) from popular image classification networks
11:00am – 11:15am: Tea Break
11:15am – 01:15pm: Deep Learning for Genomics using DragoNN with Keras and Theano
Learn to interpret deep learning models to discover predictive genome sequence patterns using the DragoNN toolkit on simulated and real regulatory genomic data.
- Demystify popular DragoNN Deep Regulatory Genomics
- Neural Network architectures
- Explore guidelines for modelling and interpreting regulatory sequence using DragoNN models
- Identify when DragoNN is a good choice for a learning problem in genomics and high-performance models
01:15pm – 02:15pm: Lunch
02:15pm – 04:15pm: Radiomics 1p19q Chromosome Image Classification with TensorFlow
Learn how to apply deep learning techniques to detect the 1p19q co-deletion biomarker from MRI imaging.
- Designing and training CNNs
- Using imaging genomics (radiomics) to create biomarkers that identify the genomics of a disease without the use of an invasive biopsy
- Exploring the radiogenomics work being done at the Mayo Clinic
04:15pm – 04:30pm: Closing Comments and Questions
A quick overview of the next steps you could leverage to build and deploy your own applications and any Q&A
- Wrap-up with the potential next steps and Q&A
- Workshop survey
This workshop is organised in conjunction with SCAsia 2019.
Kindly register under “Tutorials” in the Registration Type.
After you click “Attending” under “Tutorial Pass at SGD$250/pass (11 Mar)”, please select “Deep Learning for Healthcare Genomics”.