Research Interests

Development and application of advanced computational techniques for biomedicine, particularly the application of statistical and knowledge-based techniques to the analysis of high-throughput data and of biomedical texts. Also, neurobiologically and evolutionarily informed computational models of cognition, and ethical issues related to computational bioscience.

My laboratory is currently focused on knowledge-driven extraction of information from the primary biomedical literature, and the semantic integration of knowledge resources in molecular biology. We also have active projects in developing tools and methods for microarray analysis, proteomics and the analysis of genomic sequences.

My CV is online. Click here to see Medline records for many of my publications
 

Recent Publications

• Proteomic Informatics with Steven A. Russell, William Old, and Katheryn A. Resing. International Review of Neurobiology v. 61 pp. 129-157, "Human Brain Proteomics," ed. by Lisa Neuhold.

• A resource for constructing customized test suites for molecular biology entity identification systems with K. Bretonnel Cohen, Lorraine Tanabe, and Shuhei Kinoshita. BioLINK 2004: Linking biological literature, ontologies, and databases: tools for users, 2004, pp. 1-8.
   
• The Compositional Structure of Gene Ontology Terms with P.V. Ogren, K.B. Cohen, G.K. Acquaah-Mensah, and J. Eberlein. Pacific Symposium on Biocomputing 2004 9:214-225
   
• Gene Expression in Human Cerebral Vascular Malformations with Robert Shenkar, J.P. Elliott, K. Diener, J. Gault, L.J. Hu, R.J. Cohrs, T. Phang, R.E. Breeze, and I.A. Awad. Neurosurgery, 2003, Jul;3(7):1335-44.
   
• Trajectory Clustering: A Non-Parametric Method for Grouping Gene Expression Time Courses, With Applications to Mammary Development with Tzu Phang, Michael Rudolph and Margaret Neville. Pacific Symposium on Biocomputing 2003 8:351-62
   
• Ontologies for Programs, Not People Genome Biology 2002, 3(6):interactions1002.1-1002.2
   
• Contrast and variability in gene names with Kevin Cohen, Andy Dolbey and George Acquaah-Mensah Proceedings of the Workshop on Natural Language Processing in the Biomedical Domain, Philadelphia, July 2002, pp. 14-20 Association for Computational Linguistics.
   
• A Bioinformatics Tool to Mine Sequences for Microarray Studies of Mouse Models of Oncogenesis with Mary Edgerton, Ron Taylor, Jon Powell, Rich Simon, and Ed Liu, Bioinformatics, 2002, 18(5):774-775
   
• GEST: a gene expression search tool based on a novel Bayesian similarity metric with Ron Taylor, Sonia Leach and Richard Simon. Bioinformatics. 2001 Jun;17 Suppl 1:S115-S122.
   
• Visual Management of Large Scale Data Mining Projects with Imran Shah. Pacific Symposium on Biocomputing, 5:275-287, 2000
   
• Edgar: Extraction of Drugs, Genes and Relations from the Biomedical Literature with Thomas C. Rindflesch, Lorraine Tanabe,and John N. Weinstein, Pacific Symposium on Biocomputing, 5:514-525, 2000
   
• MedMiner: An Internet Tool for Filtering and Organizing Biomedical Information with Lorraine Tanabe and John N. Weinstein. Biotechniques, 27(6):1210-7, Dec 1999.
   

Lectures
 
I recently gave the Engelmore Prize lecture at the Innovative Applications of Artificial Intelligence conference. I have an a clinically oriented bioinformatics overview lecture for medical residents and a pharmacologically oriented one for pharmacology graduate students. If you are interested in more detail, see the BioI 7711 class notes.
 

Software

I have written a variety of software packages that may be of use to you. The main packages are:

• Statistics for Common Lisp with documentation and Copyright notices. Or download the whole tarball.
   
• CoEv is a system for the synergistic integration of multiple automated induction methods. Think of it as a kind of multistrategy constructive induction. It was patented by NIH in 1998, and I can no longer distribute it. The US patent number 6,449,603 and you can contact Pat Lake at the NIH Tech Transfer office (301) 496-0477 for licensing information. One licensee who is using it effectively is Medical Scientists.
   
• acldoc.el is an emacs package that manages access to the Franz Allegro Common Lisp documentation. It's only useful to people who use emacs and Franz ACL.
   
• BioLisp is a repository of bioinformatics relevant software written in Common Lisp to which I have contributed. Check it out.
   

Books

My 1993 book, Artificial Intelligence and Molecular Biology is now available for free on the web. Some of the chapters, particularly the introduction to molecular biology for the computer scientist, may still be of interest.

I am under contract with MIT Press to write an introduction to molecular biology for computer scientists and others coming to the field. I'm behind, but I continue to work on it.
 
BACK TO TOP

 
Teaching and Learning

We are very proud of our Bioinformatics Ph.D. program at UC Denver. Note that it requires are masters degree or equivalent in compuer science to enter.

I can also advise graduate students in the Ph.D. program in computer science at CU Boulder, the UC Denver Pharmacology PH.D. program (which has a bioinformatics track now) and in several other bioscience degree programs at UC Denver. The Center for Computational Biology has a good list of other bioinformatics training options at CU. You may also be interested in a recent Sloan Foundation report on bioinformatics training programs and the associated job market.

I am teaching BIOI 7710/7711 Introduction to Bioinformatics in the fall semester. You can contact me if you are interested in arranging an independent study or readings course.

Previously, I have taught:

• BIOI 7713 Topics in Bioinformatics
• Biology 5099 (UC Denver) Molecular Biology for Computer Scientists, Mathematicians and Engineers
• A non-credit class in lisp for programmers
• PHCL 7610 Statistical Methods in Pharmacology

I am always willing to consider taking on additional well qualified students and post-docs. Please feel free to contact me if you are interested in studying in my lab.

I wrote An introduction to machine learning for statisticians which some local statisticians have found useful. It's still in progress, and I welcome feedback on it.
 

Resources for learning about computer science

I am often asked by bioinformatics students what computer science they need to know. Here's my answer:

• Software engineering. Read the free, online version of The Structure and Interpretation of Computer Programs. This is the textbook on software engineering. Even better, you can take the free ArsDigita course, include the lectures for the course on RealVideo.
   
• Data structures and Algorithms. The best introductory textbook I've seen so far is J. Glenn Brookshear's Computer Science: An Overview, 6th edition. For a reference book, Cormen, Leiserson & Rivest's Introduction to Algorithms is unbeatable.
   
• Machine Learning. If you want a gentle introduction, try Tom Mitchell's Machine Learning. If you want more substance, try Duda, Hart & Stork's recently revised Pattern Classification. An alternative to that book is Hastie, Tibshirani and Friedman's Elements of Statistical Learning A nice introduction to Support Vector Machines just came out: Nello Cristianini and John Shawe-Taylor's An Introduction to Support Vector Machines: And Other Kernel-Based Learning Methods

Sorry all these books are so expensive, but in my opinion, they're worth it.
 

Conferences

I founded three annual conferences in computational biology: The Pacific Symposium on Biocomputing, the conference on Intelligent Systems for Molecular Biology and the relatively new Rocky Mountain Regional Meeting on Bioinformatics. I generally attend these meetings, as well as sometimes RECOMB and ECCB. These meetings are the best way to find out about what is going on in computational biology, and to meet the practitioners in the field. Try one!
 
BACK TO TOP

 
Recruiting

 
Contact Information