AI Seminar - Crowdsourcing to structure biological knowledge
- When:
- Thursday, August 16, 2012, 11:00 am - 12:00 pm
- Where:
- 11th floor large conference room
- Speaker:
- Andrew Su, Scripps Research Institute
- Description:
Note: Refreshments will be served at 10:30am. We will begin the seminar at 11:00 sharp and would appreciate all attendees to arrive before then.Title: Crowdsourcing to structure biological knowledge
Abstract:
Comprehensively annotating the function of human genes is a
significant challenge in biomedical research. This challenge can be
separated into two discrete parts -- organizing biological knowledge
across many databases, individuals, and resources, and then
structuring that knowledge to make it computable. This talk will
describe our efforts to use crowdsourcing to address both of these
important issues.Bio:
Andrew Su is associate professor in the Department of Molecular and
Experimental Medicine at the Scripps Research Institute. Prior to
joining Scripps in July 2011, he was the associate director of
Bioinformatics at the Genomics Institute of the Novartis Research
Foundation (GNF) in San Diego, CA. He also serves as an Executive
Editor of the journal Gene and a Section Editor for BMC Genomics. He
earned his PhD degree (Chemistry) from The Scripps Research Institute,
and BA degrees (Chemistry, Computing and Information Systems,
Integrated Science) at the Northwestern University.The activities in the Su laboratory can be broadly separated into two
categories. First, his lab creates tools to accelerate biomedical
research, specifically focusing on harnessing the collective efforts
of the biology community. These “community intelligence” initiatives
have the potential to scale with the explosive growth of data
generation in sciencie. The two flagship projects in this area are the
Gene Wiki, to create a gene-specific review article for every human
gene, and BioGPS, to create an extensible and customizable gene
annotation portal.Second, the lab also focuses on directly participating in biomedical
discovery using the tools of statistics, machine learning and computer
science. The group embraces the data mining challenges that have
resulted from high-throughput biology. Many past and ongoing research
projects have spanned multiple disease areas, from immunology to
metabolism to neurobiology. These projects are based on data from
high-throughput transcriptomics, sequencing, genotyping, and
phenotyping.
