Pathway and Network Based Discovery of Gene Signatures

This webinar featured Dr. Lee Lancashire, a bioinformatics scientist within the computational biology group at Thomson Reuters, who presented “Pathway and Network Based Discovery of Gene Signatures.”

In the webinar, Dr. Lancashire will discuss the use of prior knowledge about pathway and network information to drive biomarker discovery, presenting recent results generated through the Orion Bionetworks Multiple Sclerosis Computational program (MS 1.0).

Learn More

Webinar originally hosted June 17, 2014
Watch Webinar

Dr. Lancashire has over ten years of experience in the application of statistical and machine learning approaches for the analysis of complex biological datasets. He is a bioinformatician within the computational biology group at Thomson Reuters (IP & Science). His responsibilities are in the identification and development of strategies for the delivery of informative biomarker signatures from big ‘omics’ data through the use of sophisticated statistical algorithms in combination with Thomson Reuters’ knowledgebase of pathways and interaction networks. His work focuses on the discovery of discriminatory biomarker signatures that will facilitate the design of molecularly targeted clinical trials, and ultimately assist in the molecular profiling of disease for improved patient stratification.

Lee has over ten years of experience in the application of statistical and machine learning approaches for analysis of complex biological datasets. Lee completed his post-doctoral research in biostatistics and bioinformatics at the Paterson Institute for Cancer Research. He has also worked as a bioinformatics team leader in personalized medicine and diagnostics companies CompanDX and Almac Diagnostics. Lee holds a PhD in bioinformatics & machine learning and has published in over 25 key industry journals.

More Webinars

ALS Patients Being PRO-ACTive: Can ALS Big Data Bring the Next ALS Breakthrough
Collaborative bottom-up modeling in computational biomedicine
Seeking best practices in classifier construction and testing