Home Page Image
  John T. Halloran


I am a postdoc at UC Davis working with David Rocke on solving problems in computational biology using machine learning. Previously, I was a PhD student in the University of Washington Department of Electrical Engineering (I was also affiliated with the Department of Genome Sciences), where I worked with professors Jeff Bilmes and Bill Noble on peptide sequencing of tandem mass spectra using dynamic graphical models and other machine learning/optimization techniques.
My research interests are:

  1. Machine Learning Applications
  2. Proteomics, particularly Analysis of Shotgun Proteomics Data
  3. Time-series Analysis using Dynamic Graphical Models
  4. Approximate Inference in Graphical Models
  5. Online learning
  6. Information Theory

One may find old graduate/undergrad projects I've worked on in the past here.

  1. Ph.D. in Electrical Engineering, University of Washington, March 2016.
  2. M.S. in Electrical Engineering, University of Hawaii at Manoa, August 2010.
  3. B.S. in Electrical Engineering and B.S. in Mathematics, Seattle University, June 2008.

  • John T. Halloran, Jeff A. Bilmes, and William, S. Noble. A dynamic Bayesian network for accurate detection of peptides from tandem mass spectra. In Journal of Proteome Research, July 2016.
    [PDF], [Software]
  • Shengjie Wang, John T. Halloran, Jeff A. Bilmes and William S. Noble. Faster and more accurate graphical model identification of tandem mass spectra using trellises. In Bioinformatics (Proceedings of the ISMB), 2016.
  • John T. Halloran, Graphical Models for Peptide Identification of Tandem Mass Spectra, Ph.D. Thesis, University of Washington, Department of Electrical Engineering, 2016.
  • John T. Halloran, Jeff A. Bilmes, and William S. Noble. Learning Peptide-Spectrum Alignment Models for Tandem Mass Spectrometry, In Uncertainty in Artificial Intelligence (UAI), AUAI, Quebic City, Quebec Canada, July 2014.
    [PDF], [Supplementary Data]
  • John Halloran, Ajit P. Singh, Jeff A. Bilmes, William S. Noble, Peptide Identification of Tandem Mass Spectra via Spectrum Alignment using a Dynamic Bayesian Network, Neural Information Processing Systems (NIPS) Workshop on Machine Learning in Computational Biology (MLCB), December 2012. Extended Abstract and Oral Presentation.
  • Ajit P. Singh, John Halloran, Jeff A. Bilmes, Katrin Kirchoff, William S. Noble, Spectrum Identification using a Dynamic Bayesian Network Model of Tandem Mass Spectra, Proc. of the Conference on Uncertainty in Artificial Intelligence (UAI), 2012.
  • Ajit P. Singh, John Halloran, Jeff A. Bilmes, Katrin Kirchoff, William S. Noble, Spectrum Identification with a Dynamic Bayesian Network model of Tandem Mass Spectra, RECOMB Workshops, Satellite Conference on Computational Proteomics, April 2012. Abstract.
  • Yingbin Liang, Lifeng Lai, John Halloran, Distributed cognitive radio network management via algorithms in probabilistic graphical methods, IEEE JSAC, Special Issue on Advances in Cognitive Radio Networking and Communications, Feb. 2011.
  • John Halloran, Probabilistic Graphical Models and Random Graphs with Applications to Wireless Communications and Data Compression, Master's Thesis, UH Manoa, Department of Electrical Engineering, 2010.
  • Yingbin Liang, Lifeng Lai, John Halloran, Distributed algorithm for collaborative detection in cognitive radio networks, Proc. Allerton Conf. on Communication, Control, and Computing, Monticello, IL, Sept. 2009.
The DRIP Toolkit

    The DRIP Toolkit (DTK), for searching a tandem mass spectra using a dynamic Bayesian network (DBN) for Rapid Identification of Peptides (DRIP), is now available! DTK utilizes the Graphical Models Toolkit for efficient DBN inference and supports parameter estimation for low-resolution MS2 searches, multithreading on a single machine, utilities easing cluster use, instantiating/decoding/plotting DRIP PSMs in the python shell, and in-browser analysis of identified spectra via the Lorikeet plugin. Further information and documentation regarding the toolkit's use is available in the DRIP Toolkit documentation. Details of the DRIP model may be found in here.

GMTK tutorial

    I've written a short tutorial for the Graphical Models Toolkit (GMTK), with all pertinent files available in this tarball. The following is a copy of the tutorial's documentation. This tutorial covers training an HMM in GMTK via generative training (expectation maximization), discriminative training (maximum mutual information), and training an HMM/DNN hybrid.

Contact Info
  1. Email: the first five letters of my last name concatenated with j3 at u dot washington dot edu


Last updated on June 14, 2017