When: February 15, 2017, 2:00 PM
Location: 3rd Floor Orchard View Room , Discovery Building
Contact: 608-316-4401, email@example.com
Machine learning for predicting developmental neurotoxicity in brain organoids
Animal models are the gold standard for assessing drug toxicity, but animal testing is slow, expensive, and can be misleading due to differences from human physiology. In vitro cellular models on the other hand are cost-effective and much of the work can potentially be automated with robotics. While many in vitro human cellular models of toxicity have historically been infeasible due to a lack of access to necessary cell types, induced pluripotent stem (iPS) cells offer a scalable source of cells to build models of toxicity in many different tissue types. These models, along with modern sequencing technologies and machine learning, may provide a solution to the need for fast, accurate, and cost-effective assessment of toxicity. To this end, our lab has developed a fast and accurate method of assessing developmental neurotoxicity by growing neural tissue organoids in 3D hydrogel matrices, exposing the organoids to compounds that are known to be toxic or non-toxic, gathering expression data from the samples using RNA-Seq, and building predictive models of toxicity from the expression data.
All qBio sponsored talks take place on Wednesdays at 2:00 p.m. in the 3rd floor Orchard View room of the Discovery Building unless otherwise noted. Talks are open to the public. Access to the room is via the elevator behind Aldo’s Cafe in the Northeast corner of the building.