| RESEARCH ASSOCIATE POSITION AT DEPARTMENT OF COMPUTER SCIENCE,
UNIVERSITY OF YORK
Mining knowledge of protein topology - application of inductive logic
programming to discover structural principles
Research Assistant
This post requires a post-doctoral researcher with a background in either
Machine Learning, Logic Programming or Molecular Modelling.
The project will be carried out jointly with Dr. M. Sternberg, Head of
the iomolecular Modelling Laboratory at Imperial Cancer Research Fund,
and will be supported under the BBSRC/EPSRC
Bio-informatics initiative. The project will involve using Inductive
Logic Programming to derive new knowledge about protein structure.
The appointment is for a period of two years and is available
immediately. Starting salary within Grade IA (16,286 GBP - 24,479 GBP)
of the scales for research staff.
Informal enquiries may be made to: Prof. Stephen Muggleton
([email protected], Tel: +44 1904 434750) and more information
about Inductive Logic Programming and its application to deriving
knowledge about protein structure can be found at
and .
Further information on how to apply can be obtained from
http://www.york.ac.uk/admin/persnl/jobs/ .
CLOSING DATE FOR APPLICATIONS IS 15TH NOVEMBER 1999.
Further particulars
~~~~~~~~~~~~~~~~~~
Project: BBSRC/EPSRC bioinformatics initiative project involving
Imperial Cancer Research Fund (ICRF), Oxford University Computing
Laboratory (OUCL), Glaxo-Wellcome (GW) and SmithKline Beecham (SB).
Start date: 1/1/97.
Value: 118,599 pounds.
Investigators: Dr. M. Sternberg, Imperial Cancer Research Fund
Dr. S. Muggleton, York
Dr. A. Lyall, Glaxo Wellcome,
Dr. C. Rawlings, SmithKline Beecham
Title: Mining knowledge of protein topology - application of inductive
logic
programming to discover structural principles.
Overview:
The objective is to apply and thereby challenge one approach for
deriving new knowledge about protein structure. Specifically we propose
to 1) establish a database of protein topology and function encoded
in Prolog; 2) apply the inductive logic programming system Progol
to obtain new structural principles; 3) identify required improvements
in Progol; 4) evaluate the utility of the learnt rules for understanding
and predicting protein architecture; 5) disseminate the results via the
Web to the biological and computer science communities.
There are now more than 300 known protein domain folds and the number
is doubling every two years. The extraction of the principles
governing these folds is important for several reasons, namely
i) for the fundamental understanding of principles governing protein
architecture (what are the common building blocks and construction
rules?),
ii) to identify possible relationships governing the function of a
protein
and its conformation - particularly important as increasingly genes
are being sequenced and protein structures predicted without information
about the biological role of the molecule, iii) as a key component
to translate protein sequence into structure following the strategy
of secondary structure prediction and subsequent identification of
a common tertiary fold by threading.
Department
The Department of Computer Science has a record of high achievement in
research and teaching. It was rated Grade 5* (i.e. attainable levels of
international excellence in a majority of sub-areas of activity and to
attainable levels of national excellence in all others) in the 1996
Research Assessment Exercise, and Excellent (i.e. demonstrably very high
levels of achievement and best practice) in the 1994 Teaching Quality
Assessment Exercise. The University won the 1996 Queen's Anniversary
Prize for Higher and Further Education for the work of the Department of
Computer Science, and a recent ranking of UK Computer Science
departments placed the department equal first in a ranking of 83
institutions.
Research Group
The new group in Machine Learning, led by Professor Stephen Muggleton,
was
formed within the Department in October 1997. The group currently has
four lecturers, two Research Associates and four DPhil students.
The group is well known internationally for its develoment of the
theory, implementations and applications of machine learning.
Stephen Muggleton has a had a series of highly productive collaborative
projects with Mike Sternberg's group at Imperial Cancer Research
Fund since the late 1980s. The research on the new project is expected
to be internationally leading in the area bio-informatic analysis.
|
