Science AMA Series: Dr. Anne Carpenter, Institute Scientist at the Broad
Institute of MIT and Harvard providing background on the 2018 Data
Science Bowl and questions on cell biology, microscopy, and
computational biology. Ask Me Anything.
Abstract
Hi, I’m Dr. Anne Carpenter, I lead a computational research group at the
Broad Institute of MIT and Harvard. My Ph.D. is in cell biology and my
lab’s expertise is in developing and applying algorithms and software
for extracting information from biological images. My team’s open-source
CellProfiler software is used by thousands of biologists worldwide, and
is accelerating the discovery of new medicines. We’re passionate about
developing tools to speed up research and discover cures to diseases.
Nucleus detection is a very important part of this process because most
of the human body’s 30 trillion cells contain a nucleus full of DNA, the
genetic code that programs each cell. Identifying nuclei allows
researchers to identify each individual cell in a sample, and by
measuring how cells react to various treatments, the researcher can
understand the underlying biological processes at work. This year’s Data
Science Bowl is challenging teams to automate the process of identifying
nuclei in images, to allow for more efficient drug testing (right now it
takes ~10 years for a new drug to come to market!) Check
out my 5 minute video introduction to the challenge. My team (including
yours truly!) hand-annotated more than 20,000 nuclei for the data
challenge - we think it was worth it to solve this challenge. My lab’s
focus has been on deep learning algorithms and we’d love someone to beat
our best efforts! Thanks for caring about the intersection of computer
science and biology! You can catch me anytime on Twitter, and I’m here
from 12-1PM to answer your questions about the challenge, my lab’s work,
and being a scientist. Ask me anything! Thank you all for joining me
today! I’m done! There’s still plenty of time to register and compete in
the 2018 Data Science Bowl focused on algorithms to spot nuclei. The
winning algorithms will be released to the community. Stay connected or
join the competition by visiting DataScienceBowl.com. You can also learn
more at NVIDIA’s GPU Technology Conference: March 26 to 29th in San
Jose, CA Booz Allen Hamilton will be hosting a Business Track focused on
AI for Social Good as an Innovation Driver, Tuesday, March 27th. Thanks
again for joining!