Drug and genetic perturbations characterisations using network-based similarity method on the LINCS L1000 data

Date of Presentation: 
Wednesday, October 7, 2015
2015 Fall
Research Focus: 

Abstract - The LINCS L1000 data comprises of a large number of gene expression profiles of many cancer cell lines treated under drugs and genetic perturbation. In this works, we intend to derive a biologically valid characterisations of the drugs and the perturbation through the use of a graph kernel similarity method and the integration of prior knowledge in the form of gene interaction networks. Graph kernel algorithms are performed on top of the network representation of the data and prior knowledge to obtain similarity scores. Some characterisations aimed in this work is the drug target prioritisation and drug pathway identification.

We will report the methods and current results of the project.

Bio - Mushthofa was born and raised Indonesia. He finished his Bachelor of Computer Science at Bogor Agricultural University in Bogor, Indonesia on 2005, and promptly continued with a Master's degree in Computational Logic, which he completed at the New University of Lisbon, Portugal and Technical University of Vienna, Austria, with the support of the European Erasmus Mundus scholarship funding. After briefly working as an assistant instructor at his former university in Bogor, starting from January 2014, he has been a PhD student at Ghent University, Ghent, Belgium, under the supervision of Prof. Martine De Cock, Prof. Kathleen Marchal and Prof. Yves Van de Peer, taking the topic of Bioinformatics for his research.


Speaker affiliation: 
Ghent University