Courses

Faculty members Michael Buck and Yijun Sun stand in a learning setting.

Faculty members like Yijun Sun, PhD (left), and Michael Buck, PhD, have indispensable bioinformatics experience and are eager to share their knowledge with you.

As a trainee in our program, you can expect to undertake courses that help you build critical skills and absorb information that’s invaluable to developing your expertise in biomedical informatics and data science.

Starting on the second week of the 12-week experience, we’ll provide you with the following courses:

Introduction to Python Programming

A foundational understanding of one of the most popular programming languages is crucial for future biomedical informaticians to excel in research. This module will provide a crash course in Python with a focus on simple functions, data manipulation (Pandas and NumPy) and basics of interfacing with a SQL database (SQLAlchemy).

You will learn about:

  • creating a python script with an integrated development environment (IDE) and text editor
  • executing a python script with a python interpreter (using an IDE and command line)
  • using basic functions and installing and loading packages
  • using functions from packages toward solving biomedical informatics problems

Structural Bioinformatics

A major component of understanding biological function involves resolving biological structures, especially tertiary and quaternary protein structures. This module focuses on teaching you about the difficulties in structural bioinformatics, the complexities of protein folding and the theories and algorithms that exist to predict protein structure conformations.

 You can expect to learn about:

  • finding similar sequences using Hidden Markov Models (HMMs)
  • differences between de novo and template based structure prediction
  • methods to predict binding sites and binding ligands for proteins

Sequential Data Learning

Sequential data is ubiquitous in biomedical informatics (textual data from biomedical publications, DNA sequences, biomedical sensor data, longitudinal clinical data).

In this module you will explore similarities among data types and investigate common analytical strategies. You can expect to learn time of flight analysis, understand how to bridge health data types and learn the basis of health data repositories.

Natural Language Processing and Data Reliability

You will learn about natural language processing in the context of indexing clinical and image data. We will discuss data reliability including data cleaning, missing data, duplicate data, conflicting data and unreliable data.

Biomedical Ontology

We’ll make sure you’re familiar with the principles of realism-based ontology. You will learn elements of metaphysics and philosophy of science necessary and sufficient to build biomedical ontologies.

This module will help you:

  • understand strengths and weaknesses of prevailing biomedical data-, information- and knowledge-management paradigms
  • identify opportunities, risks and challenges to current biomedical data-, information- and knowledge-management paradigms
  • assess the quality of existing clinical research data repositories using ontological principles

Data Mining and Machine Learning

Based on a standard and widely accepted set of algorithms and platforms and multi-format reference data sets, this module will teach you supervised, unsupervised, mixed learning and deep learning approaches for addressing practical health care questions.

This course will help you gain knowledge about:

  • the differences of machine and deep learning types
  • creating linear regression, logistic regression and random forest models using pre-cleaned data
  • evaluating a machine learning model using various metrics and understand when certain metrics are appropriate

Image Data Analytics

Interested in learning about standard modalities of health image generation, as well as image storage, curation and manipulation using standard analytics tools? This course will strengthen your knowledge in all of these areas.

You will gain an understanding of:

  • how image data analysis software works
  • when to utilize Image data analytics
  • how to use clinical data as the prior probability of disease and how to integrate that data with the results of image data analysis

Population Health Analytics

We’re here to help you understand the rationale for population health, learn about quality and patient safety, see what constitutes a learning health system and expand your knowledge of implementation science.

This is the course in which you’ll learn about aggregation, annotation, storage and data warehousing of large population-centric data sets and their practical applications.

Research Ethics, Privacy and Security in Big Data Science

If you’re eager to learn about privacy and security policies associated with health data — that are rooted in national and local regulations and laws in the U.S. — you’ll find this module especially valuable.

We will familiarize you with the ethics associated with data collection; you will gain an important understanding of the consequences of poor or unethical data management.

You’ll also see what constitutes best practice in research data management and learn HIPAA regulations.

Clinical Decision Support in the Era of Big Data

Access to comprehensive and longitudinal data on patients has created the potential to develop highly accurate and robust decision support aids.

Our faculty members are enthusiastic to help you understand topics including the design, work-flow analysis, architecture, deployment, change management, usability and knowledge-base maintenance that go with modern CDS systems.