addressalign-toparrow-leftarrow-rightbackbellblockcalendarcameraccwcheckchevron-downchevron-leftchevron-rightchevron-small-downchevron-small-leftchevron-small-rightchevron-small-upchevron-upcircle-with-checkcircle-with-crosscircle-with-pluscrossdots-three-verticaleditemptyheartexporteye-with-lineeyefacebookfolderfullheartglobegmailgooglegroupsimageimagesinstagramlinklocation-pinm-swarmSearchmailmessagesminusmoremuplabelShape 3 + Rectangle 1outlookpersonJoin Group on CardStartprice-ribbonImported LayersImported LayersImported Layersshieldstartickettrashtriangle-downtriangle-uptwitteruseryahoo

Augmenting Knowledge Discovery in PubMed with R

This month we have Michael Kane from Yale discussing knowledge discovery in the biomedical sciences.

Thank you again to Misha Lisovich and the iHeartRadio Theater for hosting us.

About the talk:

Electronic access to current, scientific literature is essential to continued discovery and progress in the biomedical sciences. The online literature provides for the efficient dissemination of published knowledge and has become ever more convenient, thanks to public databases such as PubMed. However there has been little change in the basic way we electronically search for information, i.e. by keyword-based queries and manual scanning of the returned titles and abstracts. This talk outlines my current efforts for the Bill and Melinda Gates Foundation to integrate higher-level, semantic approaches to understand the relational structure of articles in scientific corpuses. I will place heavy emphasis on computational principles developed to address the challenge of creating an "augmented knowledge discover engine" that allows individual researchers to understand the landscape of relevant data in their subject area. The long-term goal of this project is to provide new perspectives on the current literature and identify new, potentially untapped areas for scientific discovery. 

About Michael:

Michael Kane is part of the Biostatistics Faculty at Yale University. His research interests are in the areas of scalable computational learning, augmented knowledge discovery, and stochastic approximation. He is the 2010 winner of the American Statistical Association's Chambers Statistical Software Award for the Bigmemory Project, a set of software libraries that allow the R programming environment to scale to terabyte-scale data. In 2011 he was awarded a grant on DARPA's XDATA project, part of the White House's Big Data Initiative for design and implementation of an elastic, distributed computing framework. 

In 2012 he was was the recipient of the Bill and Melinda Gates Foundation’s Grand Challenge Round 11 Award for the semantic clustering of medical and academic literature. He serves as an Editor for the Journal of Statistical Software and is this year's Program Chair for the Graphics Section at the Joint Statistical Meetings.

Pizza starts at 6:15, giveaways and Michael's talk begin at 7 and then after we will head to a local bar.

Join or login to comment.

  • Michael K.

    Thanks to all those who attended. The talk is available at

    3 · May 30, 2014

  • doug k.

    too bad i missed it.

    May 30, 2014

  • @aaronchall

    As per Jared's suggestion, I'm posting this here: I work at Bank of America, and I know some groups that are looking for people with experience in C++ or Java to write Python. Find me on LinkedIn at and I'll tell you where to send your resume.

    1 · May 29, 2014

  • John Peter S.

    Neat , can't wait. I am implementing David Blei's work on topic Models ... So this is fortuitous.

    1 · May 28, 2014

  • Anne M.

    Are there any academic papers/talks published yet on this topic? I looked on PubMed for YCAS and didn't see any :).

    1 · May 16, 2014

    • Michael K.

      I'm going to reference topic modelling, latent semantic indexing, and visualization. However, I'm planning on making it very self-contained. I'll introduce concepts before using them. Also, I prefer very interactive talks so you're welcome to stop me with questions at any time.

      1 · May 16, 2014

Your organizer's refund policy for Augmenting Knowledge Discovery in PubMed with R

Refunds are not offered for this Meetup.

Our Sponsors

People in this
Meetup are also in:

Sign up

Meetup members, Log in

By clicking "Sign up" or "Sign up using Facebook", you confirm that you accept our Terms of Service & Privacy Policy