Biomedical Informatics Bootcamp
BMI Bootcamp 2026
Each summer, the University at Buffalo hosts a free, virtual biomedical informatics bootcamp. With a wide variety of courses and experienced instructors, these lessons offer knowledge and skills for novice to experienced learners.
Available Courses
- Introduction to Python Programming
This course covers the basics of the coding language, Python. It starts with syntax for beginners and covers a variety of practical topics needed for the language. - Introduction to Cheminformatics using the Python Software RDKit
This class covers the basic usage and installation of RDKit (an open-source cheminformatics software (https://www.rdkit.org/). This tutorial includes loading molecules, drawing molecules, molecular fingerprint analysis, similarity metrics, and more. - R-Studio Basics and Regression Analysis
This course covers the basics of the coding language, R (Posit). It starts with syntax for beginners and covers a variety of practical topics needed to use the language for medical informatics purposes. This class also covers a basic understanding of Linear Regression models. - Introduction to Tidyverse, dplyr, and ggplot2 in R
This lecture will provide an overview of the “Tidyverse” approach to data analysis. We will explore basic functions from the R packages dplyr and ggplot2 and using the “tidy data” concept. - Structured Query Language (SQL)
Structured Query Language (SQL) is used to create and query relational databases. This lecture teaches you how to write and read SQL statements. Practicing clinical informaticians use this skill more often than any other. - Introduction to Unix/Linux Programming
Master the essential Unix/Linux commands and tools that drive high-performance and cloud computing. This hands-on class will equip you with the skills to efficiently navigate, organize, and process data. - Additional Commandline Unix and Regular Expressions
This class builds upon Introduction to Unix/Linux Programming, with more commands useful for navigating large Unix based servers via command line. Also includes demonstrations of regular expressions to manipulate text using https://regex101.com/.
- Consumer Health Informatics
This workshop will introduce participants to the relationship between health information technology (HIT) and health literacy (i.e. the consumers’/patients’ crucial ability to find, understand and use health information). - Public Health Informatics
This workshop will introduce participants to the concept of Big Data analytics and will teach attendees to apply critical thinking skills to make important clinical decisions that will improve quality, lower cost and improve health outcomes. - Human Factors Engineering
This course on “human factors” focuses on how people interact with products, systems and processes. In our case, we examine how we use and design EHRs, medical devices and the visualization of medical data. - Cybersecurity & Qualitative Research Methods
- Cybersecurity–how we seek to protect systems, networks and programs from digital attack with a focus on the protection of patient data.
- Qualitative Methods–review the many methods of observations, interviews, focus groups and unobtrusive measures that allow us to better understand behaviors and attitudes of patients and providers.
- Clinical Decision Support (CDS)
Clinical decision support is how we implement clinical guidelines into the practice of medicine. In this talk we explore several types of CDS implementations and their impact on clinical care. Learners will understand how to specify CDS rules and codify them consistently. - Modeling and HL7 (including FHIR)
Modeling and HL7 teaches methods for doing object oriented modeling and provides learners with tools to represent systems formally. We also discuss how to use HL7 FHIR to query, modify and delete data, which can be helpful in linking externally developed CDS to an EHR.
- Medical Terminology & Standards
Medical Terminology and standards are used to create interoperability that can help to ensure that data transferred retains its computable meaning. This talk will ensure that you know relevant terminological standards and representative tooling. - Elements of Logic for Ontology Design
This class provides a gentle introduction to different sorts of knowledge representation systems and the reasoning methods that are suitable for them (i.e. propositional logic, description logics and first order logic). Snomed CT and the Basic Formal Ontology are used as specific examples. - Realism-Based Biomedical Ontology
Students will learn the pragmatic principles used in the OBO Foundry and the BioPortal ontologies and how they differ from the realism-based principles underlying the Basic Formal Ontology and the Ontology for General Medical Science (OGMS). They will also learn that distinct concept-based ontologies rarely use the same set of principles so that they promote data-silos rather than avoiding them. - Using First-Order Logic to Develop Realism-based Ontologies
The Basic Formal Ontology (BFO) serves as upper ontology for hundreds domain and application ontologies, many of them in the healthcare domain. Although the BFO is axiomatized and distributed in first-order logic (FOL), most of the ontologies depending from it limit their axiomatization, if any present at all, to what can be expressed with binary predicates in OWL. Students frequently make poor ontological choices when restricted to OWL, mistakes we assess would not occur were they to base their work on BFO FOL. However, use of BFO FOL has previously been limited due to the lack of good tool support. Here, we demonstrate a toolset that makes ontology development in FOL more accessible allowing to produce ontologies that can be used with more advanced forms of reasoning that go beyond mere classification or terminology development typical of OWL use. - Biomedical Ontology – SPARQL Queries
This course covers some of the basics of the SPARQL triple-store query language. It starts with background about ontologies and triple stores and demonstrates a range of SPARQL queries of increasing complexity. - Natural Language Processing (NLP)
This course will be a brief introduction to using natural language processing for doing information extraction for biomedical science. Topics covered will include a brief overview of NLP techniques such as parts-of-speech and named entity identification and how such techniques can be used to perform biomedical informatics tasks.
- Machine Learning with Python – Part 1
The first of two introductory sessions on machine and deep learning topics. In this class we will cover general background on ML/DL and walk through a few machine learning examples using decision trees and leverage a publicly available dataset. This class will involve hands-on programming with Python using Jupyter notebooks. - Machine Learning with Python – Part 2
In part two of this introduction to machine learning, we will explore and implement other types of models including random forest and logistic regression. We will also introduce neural networks and further explore topics in machine and deep learning such as hyperparameters, under/overfitting, and performance metrics. - Structural Bioinformatics and Drug Discovery – CANDO Part 1 &
Translational Bioinformatics – CANDO Part 2
The CANDO platform uses advanced computational methods to look at how thousands of potential drugs interact with a wide range of biological targets at multiple scales, all at once. Researchers are able to quickly identify, repurpose, and design promising compounds for further study and development by analyzing this data using advanced AI methods. - Explainable AI (XAI) in Biomedical Informatics
This lecture will introduce the fundamentals of Explainable AI (XAI) and its importance in biomedical informatics. Through real data analysis examples, we will explore how XAI methods can be applied to biomedical research.
- Introduction to Precision Genome Informatics
Learn how clinical genomic data is analyzed, interpreted, and integrated with electronic health records (EHR) using advanced bioinformatics tools. This course covers key concepts in genomic data processing, variant analysis, EHR integration, and their applications in precision medicine, with a focus on clinical genomic diagnosis. - Integrating Biomedical Informatics with Other Data Science Disciplines
Solving complex health challenges requires team science approaches involving multiple scientific disciplines. Biomedical informaticians frequently collaborate with not only health science domain experts, but with a breadth of discipline experts in epidemiology, population health, biostatistics, health economics, health services research and other data science disciplines. This class will describe transdisciplinary team science approaches designed to address complex health science challenges. - Image Analytics
This talk will define digitized biomedical image data, image processing, feature extraction, image classification, object detection, image segmentation, and image generation. Attendees will get a brief overview of both traditional and AI-centric approaches to these applications, with demonstrations in digital and computational pathology. - The Exposome: Biomedical Informatics in Exposomics
Exposomics is the scientific study of the exposome, from a life course perspective, beginning at conception. This includes everything a person is exposed to that is not in their genome. We look at how these exposures affect health and health outcomes. Biomedical Informatics tools are pivotal in supporting exposomics research by providing methods to manage, analyze, and interpret large and complex datasets. - Intro to Pathology Informatics
Explore key pathology systems, data sources and the integration of LIS, Middleware and EHR in laboratory workflows. Learn how informatics and digital pathology enhance disease diagnosis and research by analyzing laboratory data and anatomic pathology images, empowering biomedical practitioners and researchers to better understand illnesses.