GECCO 2005 Human Competitive Competition S Patel (1) Publications List: 1) Publication 1 (refereed journal) J Comput Aided Mol Des. 1998 Nov;12(6):543-56 Patenting computer-designed peptides. Patel S, Stott IP, Bhakoo M, Elliott P. Unilever Research, Port Sunlight Laboratory, Wirral, U.K. 2) Publication 2 (Book chapter) Shail Patel, Ian Stott, Manmohan Bhakoo, Peter Elliott. Patenting Evolved Bacterial Peptides in Peter J. Bentley, David W. Corne, editors. Creative Evolutionary Systems. Morgan Kaufmann. 2002 3) Publication 3 (presentation) S Patel - GECCO 04 Industrial Applications of Genetic Algorithms part of presentation on industrical applications at the Industrial track of GECCO 2004 (2) Patel, Shail Shail.patel@unilever.com Shail Patel Programme Leader Mathematical & Psychological Sciences Unilever Corporate Research Colworth House Sharnbrook, Bedford, UK MK44 1LQ tel: +44 (0) 1234 22 2176 mob: +44 (0) 7720 275 716 fax: +44 (0) 1234 22 2161 Elliott, Peter, +44 151 641 3832, Peter.elliott@unilever.com Stott, Ian, +44 151 641 3660 ian.stott@unilever.com Bhakoo, Mohan, +44 151 641 3526, mohan.bhakoo@unilever.com All at: Unilever Research Port Sunlight Lab Quarry Rd East Bebington, Wirral CH63 3JW UK (3) Corresponding author: Shail Patel (4) Abstract: The problem of designing new peptides that possess specific properties, such as bactericidal activity, is of wide interest. Recently, attention has focused on the use of Computer-Aided Molecular Design techniques in parallel with more traditional "synthesise and test" methods. These techniques may typically use Genetic Algorithms to optimise molecules based on Neural Network models that predict activity. In this paper we describe a successful application of this Molecular Design methodology that has resulted in novel bactericidal peptides of real value. A key issue for commercial utilisation of such results is the ability to protect the intellectual property rights associated with the discovery of new molecules. Typically peptide patents use structural templates of amino acid hydrophibicity-hydrophilicity that define highly regular peptide patent spaces. In an extension of established patenting practice we describe a patent application that uses a Neural Net predictive model to define the regions of peptide space that we claim within the patent. This formalism makes no a priori assumptions about the regularity of the patent space. A preliminary comparative investigation of the shape and size of this and other bactericidal peptide patent spaces is conducted. (5) A, C, D (6) (A) The result is part of a granted patent: AU 199648316 B2 downloadable from: http://apa.hpa.com.au:8080/ipapa/view?hit=1&page=1 front page attached as .pdf full text attached as .txt and .doc files Note that the patent has two parts: a. the peptides MC_nn which were generated by machine methods (GA) are patented alongside those designed by an expert molecular biologist MB_nn b. the neural network evalution functions are used with the GA as a rule to find any number of new peptides, i.e. the patent claims all peptides that are defined by the evaluation function - this is described in more detail in the paper. (C,D) The results, ie the peptides designed by GA, are part of the database of bactericidal peptides available in the public domain, cf references & links in: http://www.drug-redesign.de/paper/jcamd.pdf http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?dopt=DocSum&cmd=Search&db=PubMed&orig_db=PubMed&term=loftextKluwer%5Bfilter%5D+AND+0920-654X%5Bta%5D+AND+1998%5Bdp%5D http://www.foresight.gov.uk/Intelligent_Infrastructure_Systems/martinincepaperoncomplexi.pdf (7) in 1