In-person Tutorials (All times CDT)
- Tutorial IP1: Nextflow Run: A hands-on introduction to running reproducible and scalable bioinformatics workflows
- Tutorial IP2: Introduction to Machine Learning using Genomics and Imaging Data
Tutorial IP1: Nextflow Run: A hands-on introduction to running reproducible and scalable bioinformatics
workflows
Room: TBD
Date: September 28 at 09:00
Organizer:
Amnah Siddiqa, PhD
Max Participants: 40
Description
Nextflow Run is a hands-on introduction to running reproducible and scalable data analysis workflows. Working through practical examples and guided exercises, participants will learn the fundamentals of using Nextflow — including how to execute pipelines, manage files and software dependencies, parallelize execution effortlessly, and run workflows across different computing environments (including HPC and cloud). The entire session is hands-on: the instructor demonstrates on-screen while participants follow along on their own laptops in a standardized, freely-accessible GitHub Codespaces environment with a VSCode interface. By the end, participants will have the skills and confidence to start running reproducible workflows with Nextflow in their own research. The training materials are open-source and freely available on the Nextflow training portal (https://training.nextflow.io/latest/nextflow_run).
Prerequisites
This is a beginner-level tutorial — no prior Nextflow experience is required. Participants should have basic familiarity with the command line. All exercises are domain-agnostic, so no specific scientific background is needed.
Materials
- A laptop with a modern web browser (no local software installation required — the training runs in a standardized GitHub Codespaces environment).
- A GitHub account — this is the one essential thing participants must set up in advance. Anyone who doesn’t already have one should create a free account at https://github.com before the workshop.
Room: TBD
Date: September 28 at 09:00
Organizer(s):
Dario Ghersi
Babu Guda
Sushil K Shakyawar
Max Participants: 40
Description
Fundamental concepts in machine learning will be discussed followed by hands-on practicing using genomics and imaging data. Attendees will be provided with example files of genomics and imaging data to gain hands-on experience. In the first part of the tutorial, we will discuss basic concepts in machine learning and their applications in genomics research. We will highlight how advances in data-driven modeling are reshaping basic, translational and clinical research. Building on these concepts, we will focus on using patient-level multi-omics data, including gene expression, mutation, methylation, and other molecular data. Further, we will discuss how machine learning can be used to identify meaningful and otherwise hidden patterns in these complex datasets, with applications in patient subtyping, disease diagnosis, and biomarker discovery. Attendees will work on data preprocessing, feature selection, and goal-oriented machine learning modeling with validation approaches.
In the second part of the tutorial, we introduce participants to machine learning applications in medical imaging, with a focus on pathology and radiology. We begin by surveying how ML is transforming these fields—from automated tissue classification in whole-slide images to lesion detection in radiological scans—and then turn to a practical, hands-on component: setting up a segmentation pipeline. Attendees will learn how to frame a segmentation problem, prepare and annotate their data, and configure a workflow that can be adapted to their specific imaging modality and research goals.
Prerequisites
Basic UNIX command-line knowledge.
Materials
A Gmail account is needed to work on the Google Colab environment.