Course: Statistics for Omics

Overview

This introductory course gives an overview of many statistical tools to analyse omics data. The course can be followed by researchers with a minimum or elementary background in quantitative data analysis (see ‘Pre-requisites’ below).

Participants will learn and practice commonly used tools including:

• Tools to explore datasets including clustering, principal components and network analysis
• Models to answer basic statistical questions: differential behaviour (e.g. mRNA expression) and multiple testing, also using Bayesian models
• Models for classification and prediction, including penalised regression
• Models for emerging technologies: radiomics and single-cell sequencing data

Methods will be applied on experimental data in practical hands-on sessions using the statistical software R. Insight about how methods work is given in an intuitive way wherever possible which, combined with some formalisation and the practical work, makes theory accessible and helps cement concepts. Slides and instructions for the practical sessions will be made available electronically to participants.

Pre-requisites: Participants are assumed to be familiar with the following at the start of this course:

• Basic R, including how to use functions and packages
• Basic statistics: mean, variance, standard deviation
• Probability distributions: normal.
• Statistical testing: $t$-test, Wilcoxon test, significance level, $p$-value, null & alternative hypotheses.
• Measures of association: Pearson correlation, regression.

Target audience

The course is tailored for PhD students and researchers (such as pathologists, psychological biologists, human geneticists, oncologists, neuro-geneticists) whose research involves experiments that generate omics data. It can also suit researchers with a quantitative background looking for a short introductory course.

Participants that successfully complete the course receive 3 ECTS.

Teachers

Dr. R. X. de Menezes, Prof. M. A. van de Wiel, Dr. C. F. Peeters & Dr. W. N. van Wieringen (Amsterdam UMC, location VUmc)

Dr. Ahmed Mahfouz (Leiden Computational Biology Center LUMC)

Course organizers

• BioSB: Femke Francissen

• Amsterdam UMC (location VUmc): Renee de Menezes

Location: VUmc, Amsterdam

• Location on 24th, 27th and 28th: De Waver (ZH -1 C 118.17)
• Location on 26th: De IJssel (ZH 2 E 14)

The course will be from 9:00 until 17:00 on all days. Both rooms are in the hospital building of the VUmc, Amsterdam (directions).

Bring your own laptop

Participants must to bring their own laptop with R installed from the Comprehensive R Archive Network-CRAN, for example from this mirror. We advise also to use RStudio for the R interface, which enables producing reports via the RMarkdown package. Participants will also be required to install a list of packages (to be supplied) needed for the practicals.

Registration and fees

• Amsterdam UMC participants: you can register by sending a scan of the registration form to Femke Francissen. Fee: 320 euros.

• Others: you can register via the BioSB research school. Fees: 320 euros (PhD student), 480 (academic researcher), 720 (industry).

The registration fee includes coffee/tea and lunch during the course.