*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
In partial fulfillment of the requirements for the degree of
Doctor of Philosophy in Quantitative Biosciences
in the School of Biological Sciences
Nolan English
Defends his thesis:
Using heuristic derived features in machine learning to recommend post translational modifications for experimental study
Wednesday, April 13, 2022
2:30pm Eastern Time
Via BlueJeans: https://bluejeans.com/4537128340
Open to the Community
Dr. Matthew Torres
School of Biological Sciences
Georgia Institute of Technology
Committee Members:
Dr. Christopher Rozell; School of Electrical and Computer Engineering, Georgia Tech
Dr. Peng Qiu; Department of Biomedical Engineering, Georgia Tech & Emory
Dr. Raquel Lieberman; School of Chemistry and Biochemistry, Georgia Tech
Dr. Melissa Kemp; Department of Biomedical Engineering, Georgia Tech & Emory
Abstract:
Post-translational modifications (PTMs) alter the chemistry of amino acid residues within translated proteins and thereby have the potential to expand the function and complexity of the proteome beyond the limits of the genome. Since the advent of high-throughput protein sequencing by mass spectrometry, hundreds of different types of PTMs have been discovered enabling cell signaling, protein degradation, DNA regulation, and nearly every other cellular function. However, the rate at which PTM data are generated far surpasses the rate at which it is being curated and/or processed for interpretation. Today, more than 2 million PTMs contributing to over 400 types of modifications exist within the public domain, however far fewer PTMs are thought to have a function. Even less have their functional context understood due to the high burden of experimental evidence needed to uncover functionality. In this seminar I will describe the development of SAPH-ire, a machine learning model meant to recommend potentially functional PTMs for experimental investigation. I will present this model as part of a general data, analytics, and visualization approach meant to close the gap between PTM detection and study.
