Statistics and machine learning
Statistical Analyses for omics data and machine learning using Galaxy tools
Before diving into this topic, we recommend you to have a look at:
|Lesson||Slides||Hands-on||Input dataset||Workflows||Galaxy tour||Galaxy instances|
|Age prediction using machine learning||tutorial Toggle Dropdown||zenodo_link||workflow|
|Basics of machine learning||tutorial Toggle Dropdown||zenodo_link|
|Interval-Wise Testing for omics data||tutorial Toggle Dropdown||zenodo_link||workflow||interactive_tour||instances|
|Machine learning: classification and regression||tutorial Toggle Dropdown||zenodo_link||workflow|
You can use a public Galaxy instance which has been tested for the availability of the used tools. They are listed along with the tutorials above.
You can also use the following Docker image for these tutorials:
docker run -d -p 8080:80 quay.io/galaxy/statistics-training
It will launch a flavored Galaxy instance available on http://localhost:8080.
This material is maintained by:
For any question related to this topic and the content, you can contact them or visit our Gitter channel.
This material was contributed to by:
Marzia A. Cremona, Alessia Pini, Fabio Cumbo, Kateryna D. Makova, Francesca Chiaromonte, and Simone Vantini: IWTomics: testing high-resolution sequence-based "Omics" data at multiple locations and scales
IWTomics is an R/Bioconductor package (integrated in Galaxy) that, exploiting sophisticated Functional Data Analysis techniques (i.e. statistical techniques that deal with the analysis of curves), allows users to pre-process, visualize and test these data at multiple locations and scales.
Alessia Pini and Simone Vantini: Interval-wise testing for functional data
In the framework of null hypothesis significance testing for functional data, it proposes a procedure able to select intervals of the domain imputable for the rejection of a null hypothesis.