Doctoral Seminar: Stephanie Kamgnia Wonkap

Speaker: Stephanie Kamgnia Wonkap

Supervisor: Dr. G. Butler

Supervisory Committee: Drs. V. Haarslev, L. Kosseim, M. Whiteway

Title: Integrative Gene Regulatory Network Inference with Machine Learning Techniques

Date: Thursday, March 21, 2019

Time: 11:40 a.m.

Place: EV 3.309

ABSTRACT

Gene regulatory network inference is one of the central problems in computational biology. The limited availability of biological data as well as the intrinsic noise they contain has triggered the need of models that integrate the vast variety of data available to take advantage of the complementarity of the information they provide about regulation, to the extent of inferencing more accurate networks. With this idea in mind, we propose BENIN: Biologically Enhanced Network Inference. BENIN is a general framework that permits to jointly considerate different types of prior to boosting the network inference. BENIN principally rely on linear model Elastic Net to solve the problem, but we compared to other possible nonlinear models such as gradient boosting machine. BENIN is capable of weighing the prior knowledge integration as a solution to cope with the noise inherent in the biological prior knowledge data. We tested BENIN on simulated and real biological data: the Yeast cell-cycle expression data. Our results demonstrate that, with careful integration of prior evidence about regulatory links, BENIN can significantly outperform the state of art.