Hands-on with WEKA

In this section, we will present two hands-on examples for using WEKA. The first example uses clustering to explore a CRISPR dataset, and the second example uses classification to identify cancer-causing genes. 

Exploring targets using CRISPR-Cas9 screens

CRISPR are arrays of regularly spaced repeats first detected in prokaryotes [13, 14], where they play an important role in the bacterial immune response to virus [15]. Since its discovery in 1993, the CRISPR system has been thoroughly characterised at the biochemical, genetic and molecular level, culminating with its versatile capability for enabling genome editing in mammals and altering expressing of gene products (patent US08697359B1). For more details on the 20 year journey of CRISPR, read Lander, 2016 [16].

CRISPR holds the promise to revolutionise drug discovery [17] for its ease and precision to introduce changes to the DNA sequence in a high-throughput fashion. This system has been applied to a variety of disease models e.g. cancer cell lines, iPS neuronal cells, T cells, organoids and much more. In this section of the course, we will be using drug targets prioritised from the study on the systematic CRISPR-Cas9 screening in a 1,000 cancer cell line panel [18].