AnVIL Demo: Galaxy Learning and Modeling (GLEAM): Machine Learning accessible and best practices on September 17, 2025

AnVIL Demos
1

Join our next AnVIL Demo!

Topic: Galaxy Learning and Modeling (GLEAM): Machine Learning accessible and best practices

September 17, 2025 at 10:00 AM ET on Zoom

11:00 AM - 11:30 AM ET – Demo on AnVIL

Learn to leverage Galaxy-GLEAM, powerful and accessible machine learning tools integrated directly into Galaxy. This presentation covers tabular, image, and multimodal machine learning through a simple user interface to generate high-quality Machine Learning models. We’ll demonstrate GLEAM’s value with practical biomedical applications, showing you how to tackle common ML tasks effortlessly. Presented by Paulo Lyra from Moffitt Cancer Center.

View the slide presentation: https://drive.google.com/file/d/1YlERxRvdONMCw9F_hEducz1b_dAKl4fV/view?usp=sharing

11:30 AM - 12:00 PM ET – Q&A

We’ll open up the floor to questions about the demo presented, and will have AnVIL and Terra support on call to answer any questions about AnVIL you might have!

:pencil: Sign up: Register for AnVIL Demos

What are AnVIL Demos?

AnVIL Demos are a monthly, virtual meeting where we highlight what you can do on the NHGRI Analysis, Visualization, and Informatics Lab-space (AnVIL; https://anvilproject.org/), a cloud-based computing platform for genomic data science! AnVIL Demos will start out with a 30-minute demonstration on the platform followed by open time for Q&A and user support.

The demos will highlight a range of topics, from a capability of the platform to a scientific analysis powered by AnVIL. If you’re interested in showcasing how you use AnVIL at a future AnVIL Demos session, reach out to Natalie Kucher (nkucher3@jhu.edu). After the demo, we’ll open up the floor to answer questions about the demo and to answer any general questions you might have about AnVIL.

:play_or_pause_button: Watch past AnVIL Demos recordings from our YouTube playlist!

Resources

Upcoming Events

Sign up to hear about future AnVIL Demos and announcements at Info | anvil-mailing-list@lists.anvilproject.org - lists.anvilproject.org and learn about upcoming events at AnVIL Community Events - AnVIL Portal !

2

Q: Did you test the generalizability of image transformation of the gene expression data?

A: Not yet, but that would be very interesting to explore.

–

Q: Using Galaxy as a workflow manager - when you do this on AnVIL, you can’t share between users. You can leverage it to pull tools to make sure software and computing resources are available. Are you able to do this on local HPC?

A: Sharing results is easy in Galaxy since you can share the history. Sharing the datasets in AnVIL - you’d need to grant people access to the workspace. For Galaxy you’d download the report and send it to the person.

–

Q: How did you know you needed to convert your gene expression tabular data into an image?

A: Our primary motivation was to use generate some image data to test the image model. This is also a convenient way to visualize the gene expression data since tabular datasets are hard to view.

–

Q: In Galaxy, there were a lot of models you could choose from. Does the user have to know a priori which model is relevant?

A: It depends on the complexity of the dataset. Some models are good for various inputs.

Q: Is there a default model you would recommend?

A: Usually start with Resnet 50, it’s light and fast. Then we fine tune from there.

–

Q: Is Galaxy on AnVIL able to access GPUs?

A: I think so.