Managing machine learning experiments and models for life science with MLflow

Join us for the next webinar in the Tools for AI/ML research in life sciences event series. This webinar will introduce MLflow, an open-source tool for managing machine learning experiments and models, with a practical research use case and a demonstration of how to access MLflow through SciLifeLab Serve.

Date and time: Tuesday 19 January 2027, 10:00–11:00 CET (Stockholm time)
Speakers: Nikita Churikov (SciLifeLab Data Centre) and Mariya Lysenkova Wiklander (Uppsala University)

Registration: Please register by 18th January (18:00 CET). Registered participants will receive the Zoom link shortly before the webinar.

Abstract:

In research involving machine learning, we often train many different models or evaluate multiple sets of parameters. It can quickly become challenging to keep track of the metadata and model artefacts for each model and compare results between different runs. Additionally, sharing a model with others for inference (predictions) is not always straightforward.

MLflow is an open-source tool designed to address these challenges. It offers experiment tracking (parameters, metrics and artefacts), a model registry (versioning and stages), and model packaging and serving. MLflow is widely used to manage the full lifecycle of models in industry but is less familiar in academia.

In this webinar, we will introduce the basics of MLflow and present a research use case by Mariya Lysenkova Wiklander (Uppsala University). MLflow can be run locally on your own computer or accessed online (for example, when working in a team). We will also demonstrate how MLflow can be accessed through SciLifeLab Serve, which is free and openly available to all life science researchers in Sweden.

The Tools for AI/ML research in life sciences is an event series by the SciLifeLab Data Centre aimed at life science researchers who use data science and machine learning methods in their work. The goal of the events in this seminar series is to provide introductions to different tools for ML research, but also to foster discussions around our practices and how they can be improved. We organise in-person workshops and webinars as part of the event series. The events are open to all researchers in Sweden and beyond, regardless of SciLifeLab affiliation.

Contact: SciLifeLab Data Centre | serve@scilifelab.se