scikit-bio-tutorials

Interactive tutorials for using scikit-bio in biological research.

This repository hosts tutorial materials that were initially taught during the ISMB 2024 conference. They were latter updated and expanded to reflect the new features of scikit-bio. The current tutorials are up-to-date with scikit-bio 0.7.0.

Walk-through tutorials

The tutorials are broken down into eight sections. They can be directly launched in Google Colab via the following links.

Basic bioinformatics

1. Basic bioinformatics using scikit-bio

Microbiome data analysis

2. Working with various omic data types
3. Analyzing microbial communities
4. Comparing microbial community structure
5. Inferring and associating critical features
6. Predicting host and environmental traits

These sections use the EMP500 dataset, available for download at this Dropbox link.

Advanced topics

7. Single-cell data analysis
8. Protein language modeling

References

1. Protein remote homology detection and structural alignment using deep learning
2. ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Learning
3. UniFrac: a New Phylogenetic Method for Comparing Microbial Communities
4. Establishing microbial composition measurement standards with reference frames
5. Unifying the analysis of high-throughput sequencing datasets: characterizing RNA-seq, 16S rRNA gene sequencing and selective growth experiments by compositional data analysis
6. Balances: a New Perspective for Microbiome Analysis
7. Compositionally Aware Phylogenetic Beta-Diversity Measures Better Resolve Microbiomes Associated with Phenotype