Machine Learning for Biologists (ML4Bio) workshop

Recent advances in high-throughput technologies have led to rapid growth in the amount of omics data. These massive datasets, accompanied by numerous data points enriched over the past decades, are extremely valuable in the discovery of complex biological structures, but also present challenges in various aspects of data analysis. This workshop introduces biologists to concepts in machine learning, a powerful set of models for drawing inference from data. Upon completion of the workshop, attendees will be able to identify machine learning applications, examine factors that influence model selection, recognize major methodological flaws in a machine learning experiment, and gain a greater appreciations for machine learning.

This repository contains materials for the ML4Bio workshop. It generates the corresponding lesson website from The Carpentries lesson template.

Getting started

Visit the software setup page for instructions on installing the ml4bio software and downloading the example datasets, guides, and slides contained in this repository.

Overview

In addition to the materials needed to build the lesson website, this repository contains the following files and subdirectories:

• binder: a configuration file to enable running the illustration.ipynb notebook interactively using Binder
• data: example datasets to use with the ml4bio classification software, including both real and toy (illustrative simulated) datasets
• fig: figures for the lessons and guides
• guide: tutorials about the ml4bio software, machine learning concepts, and various classifiers
• planning: materials for instructors to plan the workshop
• scripts: ml4bio installation scripts
• illustration.ipynb: a Jupyter notebook the demonstrates the machine learned workshop in Python code

The ml4bio repository contains the Python software.

Contributing

We welcome contributions to improve the workshop! The best way to provide suggestions or propose contributions is in the GitHub issues.

Maintainers

Current maintainers of this lesson are

• @cmilica
• @csmagnano
• @agitter

Authors

A list of contributors to the lesson can be found in AUTHORS and the GitHub contributors.

Citation

To cite this lesson, please consult with CITATION

Licenses

The original workshop materials and guides created in this repository are licensed under the Creative Commons Attribution 4.0 International Public License. However, the guides also contain images from third-party sources, as noted in the image links and guide references. See the linked original image sources for their licenses and terms of reuse.

The workshop template is derived from The Carpentries lesson template. The template is Copyright © 2018–2020 The Carpentries and licensed CC BY 4.0. See the license for additional information.