Fall 2024

Data Science using R

September 5 & 6, 2024
9 AM to 5 PM both days
G9.250A

This course would benefit students who pursue advanced R programing techniques for data science. We will provide information about key elements for data science and machine learning, including how to properly preprocess data, how to select meaningful features from the data, how to identify data clusters, and how to build a predictive model. We will then cover statistical test basics and provides semi-hands-on sessions on how to utilize the statistics for biomarker discoveries.

Please note that this IS NOT a course to learn R; rather it is aimed at teaching R users best practices to analyze data.

Day 1: Data preprocessing, Feature selection/dimensionality reduction, Data clustering, Predictive models
Day 2: Statistical test basics, Biomarker discovery I: metabolomics/proteomics data, Biomarker discovery II: RNA-seq data

Registration closed.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5095 - 01 SPECIAL TOPICS IN BIOINFORMATICS - Data Science using R.
UTSW Grad Students: BME 5096 - 03 SPECIAL TOPICS: Data Science using R.

Lead Instructor: Jeon Lee, PhD
Other instructors: Austin Marckx, Jui Wan Loh

Deep Learning for Beginners

September 11 & 12, 2024
9 AM to 5 PM both days
G9.250A

NOTE for BME graduate students: this is the first of four courses in the AI series.

This course is intended to provide a theoretical as well as practical introduction to Deep Learning. This is not a boiler plate presentation of Deep Learning as widely accessible through online courses. Instead, we hope attendees will take away a deeper understanding of the motivation of implementing neural networks for data modeling and the consequential complexities in formulating the underlying optimization problem. We will then make the critical step towards convolutional neural networks (CNNs), which permit a multiscale analysis of data. We will also offer a balanced discussion of the strengths and weaknesses of Deep Learning vis-à-vis conventional Machine Learning approaches. We will first introduce the intuition and computational underpinnings of Deep Learning, followed by hands on sessions, training attendees on practical approaches to implementing Deep Learning in Pytorch. The entire course revolves around the conceptually simple problem of two-class data classification. See syllabus for a preview of the course content. The course is targeted at biomedical researchers with no prior machine learning experience, yet a keen curiosity in the mathematical and computational of Deep Learning.

Competence in (python) programming is required.

Course outcomes & objectives:
1. Understand the core elements of data modeling with neural networks.
2. Understand the power of learning convolution kernels for data modeling.
3. Learn how to implement a deep learning pipeline in python.
4. Understand why deep learning methods are able to perform so well and identify situations where they are likely to outperform (or underperform!) classical machine learning approaches.
5. Gain a practical understanding of various choices in designing and validating a deep learning model.

Registration closed.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5095 - 02 SPECIAL TOPICS IN BIOINFORMATICS - Deep Learning for Beginners.
UTSW Grad Students: BME 5096 - 04 SPECIAL TOPICS: Deep Learning for Beginners.

Course Director: Satwik Rajaram, PhD
Instructors: Gaudenz Danuser, PhD, Hongqing Han, PhD, Aleksandra Nielsen

Time Series Analysis

September 19 & 20, 2024
9 AM to 5 PM both days
G9.250A

This course aims to promote understanding of time-series data and their processing/analysis methods. Starting with an introduction to techniques for time-series data processing, we will cover analysis, modeling, and various time-series data analysis techniques being used for neural spiking data.

Day 1: Time-series signal processing (filtering, imputation, etc.), Feature extraction from time-series signals, Autocorrelation Function (ACF), AR modeling
Day 2: Neural spiking data analysis (Spike train statistics, Reverse-correlation to estimate receptive fields, Poisson neuron model, Generalized linear model)

Familiarity with R and python is required.

Registration closed.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5095 - 03 SPECIAL TOPICS IN BIOINFORMATICS - Time Series Analysis.
UTSW Grad Students: BME 5096 - 05 SPECIAL TOPICS: Time Series Analysis

Lead Instructor: Jungsik Noh, PhD
Other instructors: Jeon Lee, PhD, Wenhao Zhang, PhD, and Srinivas Kota, PhD

Advanced Concepts of Deep Learning

September 19, 24, 26, & October 1, 2024
10:30 AM to 12 PM all four days
D1.200 on 9/19
D1.102 on 9/24, 9/26, & 10/1

NOTE for BME graduate students: this is the second of four courses in the AI series.

This course will provide an introduction to key and emerging concepts and ideas in deep learning. We will introduce the design and principle behind recent advances in model architecture: transformers (including several efficient transformer designs), graph neural networks, and several other new architectures that utilize attention-like multiplicative updates. Then, we will cover mathematics and algorithms of generative probabilistic modeling with deep learning, including energy-based models, variational autoencoder, generative adversarial network, normalizing flow, neural ODE, and diffusion probabilistic models. Conceptual advances will be the focus of this nanocourse.

This course is advanced and requires basic knowledge of programming, machine learning, and deep learning.

Registration closed.

There is NO academic credit for this nanocourse. You will be sitting in 4 lectures with regular students taking BME 5317.

Lead Instructor: Jian Zhou, PhD

Architectures and Applications of Deep Learning

October 29 & 30, 2024
9 AM to 5 PM both days
G9.102

NOTE for BME graduate students: this is the third of four courses in the AI series.

Explore the driving principles behind state of the art deep neural network architectures for generative modeling with GANS (CGAN, WGAN, InfoGAN, CycleGAN), unsupervised learning with autoencoders (CVAE), image analysis (Vision Transformers and CNNs), learning from limited data (Siamese nets), and sequence learning (LSTMs). Learning objectives for this practical course are: (1) Learn to implement these architectures using leading python frameworks: TensorFlow/Keras and PyTorch, (2) Learn design patterns that increase accuracy and network understanding, (3) Learn best practices to achieve winning performance. Throughout you will learn practical applications of deep learning for prediction from a wide array of domains including tabular data and high dimensional signal, image, and video data.

Day 1: Data preprocessing, Feature selection/dimensionality reduction, Data clustering, Predictive models
Day 2: Statistical test basics, Biomarker discovery I: metabolomics/proteomics data, Biomarker discovery II: RNA-seq data

This course is advanced and requires knowledge of programming, machine learning, and deep learning.

Please register using this form. Registration closes on 9/30/2024, 5 PM.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5095 - 04 SPECIAL TOPICS IN BIOINFORMATICS - Architectures & Applications of Deep Learning.
UTSW Grad Students: BME 5096 - 06 SPECIAL TOPICS: Architectures & Applications of Deep Learning.

Lead Instructor: Albert Montillo, PhD
Other instructors: Aixa Andrade Hernandez and Ameer Hamza Shakur

Introduction to Python

October 30 & 31, 2024
9 AM to 5 PM both days
G9.250A

This two-day intensive course is designed to introduce Python programming to graduate students and postdocs in biomedical fields. The course aims to provide a solid foundation in Python, emphasizing practical applications relevant to research. Participants will learn about Python's structures, flow control, data handling, basic analysis techniques, and how to write clean, reusable code.

Course Objectives: by the end of this course, participants will be able to

  • Understand and implement basic Python syntax and programming concepts.

  • Manage project dependencies and create reproducible Python environments.

  • Apply Python data structures effectively in solving real-world problems.

  • Utilize Python for data manipulation, basic statistical analysis, and visualization.

  • Write reusable and efficient code using object-oriented programming principles.

  • Explore parallel processing techniques to optimize performance for larger datasets.

Please register using this form. Registration closes on 10/1/2024, 5 PM.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5143 - 01 BIOINFORMATICS - PYTHON LEVEL 1.
UTSW Grad Students: BME 5096 - 07 SPECIAL TOPICS: Introduction to Python.

Lead Instructor: Kevin Dean, PhD
Other instructors: Felix Zhou, PhD

Leveraging AI in Computational Imaging for Improved Image Analysis

PLEASE NOTE THAT THIS NANOCOURSE HAS BEEN PULLED FROM THE FALL LIST AND WILL BE RE-OFFERED IN JANUARY 2025 POTENTIALLY.

November 5 & 6, 2024
9 AM to 5 PM both days
G9.102

This two-day course is designed for users already familiar with computational image analysis tools, but interested in enhancing their analyses with artificial intelligence. The first half of the course will provide an overview of image analysis tools on BioHPC such as ImageJ, webGUI, webGPU, etc. and cover concepts of using Python, MATLAB, and Jupyter Notebook. The focus will be integration of artificial intelligence alongside and within these tools. The second half of the course will be hands-on exercises to explore AI capabilities and learn about employing AI features with current workflows of image analysis.

Diffusion Models: From Image to Biological Sequence Generation

November 11, 12, 13, & 14, 2024
9 AM to 1 PM all four days
G9.250A

NOTE for BME graduate students: this is the last of four courses in the AI series.

Diffusion generative models such as Stable Diffusion have achieved remarkable results in generating images, videos, and so on. This two-day course explores the key principles behind diffusion models. During the first part of course, participants will gain a theoretical understanding behind the original diffusion models and become familiar with score-based generative stochastic differential equation models. Participants will be having an opportunity to implement the first diffusion model and generate images. During the second part, we will depart from image generation and will venture to biological sequence generation by studying several state-of-art diffusion models. As a result of the course, participants will learn how to implement diffusion models and how to generate various data modalities including images and DNA sequences.

Day 1: diffusion model - DDPM, score-based stochastic differential equation model, image generation, diffusion model - EDM
Day 2: bit diffusion, dirichlet diffusion score model, DNA sequence generation, last developments of diffusion generative models

Course outcomes & objectives:

  1. Learn main ideas behind diffusion models

  2. Learn best practices to achieve state-of-art performance in image and DNA sequence generation

  3. Gain a practical understanding of various choices in designing diffusion models.

This nanocourse requires basic knowledge of deep learning and the ability to develop and train own models using PyTorch on GPU.

Please register using this form. Form closes on 10/7/2024, 5 PM.

Academic credit (1 credit hour) is available.
UTSW PostDocs use PDRT 5095 - 06 SPECIAL TOPICS IN BIOINFORMATICS - Diffusion Models: From Image to Biological Sequence Generation.
UTSW Grad Students: BME 5096 - 08 SPECIAL TOPICS: Diffusion Models: From Image to Biological Sequence Generation.

Course Director: Jian Zhou
Instructor: Pavel Avdeev