<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div>Please note that Rida Assaf’s MS Presentation, which was scheduled to be held tomorrow, has been postponed.</div><div><br class=""></div><div>It will be rescheduled for a later date.</div><div><br class=""></div><div><br class="">------------------------------------------------------------------------------<br class="">Date: <strike class="">Friday, January 17, 2020</strike> <— will be rescheduled for a later date<br class=""><br class="">Time: <strike class="">9:00 AM</strike><br class=""><br class="">Place: John Crerar Library 298<br class=""><br class="">M.S. Candidate: Rida Assaf<br class=""><br class="">M.S. Paper Title: Identifying Genomic Islands with Deep Neural<br class="">Networks<br class=""><br class="">Abstract:<br class="">Horizontal gene transfer is the main source of adaptability for<br class="">bacteria, through which genes are obtained from different sources<br class="">including bacteria, archaea, viruses, and eukaryotes. This process<br class="">promotes the rapid spread of genetic information across lineages,<br class="">typically in the form of clusters of genes referred to as genomic<br class="">islands (GIs). Different types of GIs exist, often classified by the<br class="">content of their cargo genes or their means of integration and<br class="">mobility. Various computational methods have been devised to detect<br class="">different types of GIs, but no single method currently is capable of<br class="">detecting all GIs. We propose a method, which we call Shutter Island,<br class="">that uses a deep learning model (Inception V3, widely used in computer<br class="">vision) to detect genomic islands. The intrinsic value of deep<br class="">learning methods lies in their ability to generalize. Via a technique<br class="">called transfer learning, the model is pre-trained on a large generic<br class="">dataset and then re-trained on images that we generate to represent<br class="">genomic fragments. We demonstrate that this image-based approach<br class="">generalizes better than the existing tools.<br class=""><br class="">Rida's advisor is Prof. Rick Stevens<br class=""><br class="">Login to the Computer Science Department website for details:<br class=""><a href="https://newtraell.cs.uchicago.edu/phd/ms_announcements#rida" class="">https://newtraell.cs.uchicago.edu/phd/ms_announcements#rida</a><br class=""><br class="">=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<br class="">Margaret P. Jaffey margaret at cs.uchicago.edu<br class="">Department of Computer Science<br class="">Student Support Rep (JCL 350) (773) 702-6011<br class="">The University of Chicago http://www.cs.uchicago.edu<br class="">=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=<br class="">_______________________________________________<br class="">One-Click Unsubscribe: https://mailman.cs.uchicago.edu/mailman/options/cs/margaret%40cs.uchicago.edu?password=UIR/rtUW&unsub=1&unsubconfirm=1<br class=""><br class=""><br class="">When unsubscribing manually please use your cnetid@cs.uchicago.edu address to unsubscribe if your cnetid@uchicago.edu does not work.<br class=""><br class="">cs mailing list - cs@mailman.cs.uchicago.edu<br class="">Edit Options and/or Unsubscribe: https://mailman.cs.uchicago.edu/mailman/listinfo/cs<br class="">More information here: https://howto.cs.uchicago.edu/techstaff:mailinglist<br class="">_______________________________________________<br class="">One-Click Unsubscribe: https://mailman.cs.uchicago.edu/mailman/options/cs/margaret%40cs.uchicago.edu?password=UIR/rtUW&unsub=1&unsubconfirm=1<br class=""><br class=""><br class="">When unsubscribing manually please use your cnetid@cs.uchicago.edu address to unsubscribe if your cnetid@uchicago.edu does not work.<br class=""><br class="">cs mailing list - cs@mailman.cs.uchicago.edu<br class="">Edit Options and/or Unsubscribe: https://mailman.cs.uchicago.edu/mailman/listinfo/cs<br class="">More information here: https://howto.cs.uchicago.edu/techstaff:mailinglist</div></body></html>