---------------------------------------------------------------- WORKSHOP "ARTIFICIAL INTELLIGENCE and the GENOME" at the International Joint Conference on Artificial Intelligence IJCAI-93 August 29 - September 3, 1993 Chambery, FRANCE -------------------------------------------------------------- There is a great deal of intellectual excitement in molecular biology (MB) right now. There has been an explosion of new knowledge due to the advent of the Human Genome Program. Traditional methods of computational molecular biology can hardly cope with important complexity issues without adapting a heuristic approach. They enable one to explicitate molecular biology knowledge to solve a problem as well as to present the obtained solution in biologically-meaningful terms. The computational size of many important biological problems overwhelms even the fastest hardware by many orders of magnitude. The approximate and heuristic methods of Artificial Intelligence have already made significant progress in these difficult problems. Perhaps one reason is great deal of biological knowledge is symbolic and complex in their organization. Another reason is the good match between biology and machine learning. Increasing amout of biological data and a significant lack of theoretical understanding suggest the use of generalization techniques to discover "similarities" in data and to develop some pieces of theory. On the other hand, molecular biology is a challenging real-world domain for artificial intelligence research, being neither trivial nor equivalent to solving the general problem of intelligence. This workshop is dedicated to support the young AI/MB field of research. TOPICS OF INTEREST INCLUDE (BUT ARE NOT RESTRICTED TO): ------------------------------------------------------- *** Knowledge-based approaches to molecular biology problem solving; Molecular biology knowledge-representation issues, knowledge-based heuristics to guide molecular biology data processing, explanation of MB data processing results in terms of relevant MB knowledge; *** Data/Knowledge bases for molecular biology; Acquisition of molecular biology knowledge, building public genomic knowledge bases, a concept of "different view points" in the MB data processing context; *** Generalization techniques applied to molecular biology problem solving; Machine learning techniques as well as neural network techniques, supervised learning versus non-supervised learning, scaling properties of different generalization techniques applied to MB problems; *** Biological sequence analysis; alignment, comparison of AI-based methods for sequence analysis with the methods of computational biology; *** Prediction of DNA protein coding regions and regulatory sites using AI- methods; Machine learning techniques, neural networks, grammar-based approaches, etc.; *** Predicting protein folding using AI-methods; Predicting secondary, super-secondary, tertiary protein structure, construction protein folding prediction theories by examples; *** Predicting gene/protein functions using AI-methods; Complexity of the function prediction problem, understanding the structure/function relationship in biologically-meaningful examples, structure/functions patterns, attempts toward description of functional space; *** Similarity and homology; Similarity measures for gene/protein class construction, knowledge-based similarity measures, similarity versus homology, inferring evolutionary trees; *** Other perspective approaches to classify and predict properties of MB sequences; Information-theoretic approach, standard non-parametric statistical analysis, Hidden Markov models and statistical physics methods; INVITED TALKS: -------------- L. Hunter, NLM, AI problems in finding genetic sequence motifs J. Shavlik, U. of Wisconsin, Learning important relations in protein structures B. Buchanan, U. of Pittsburgh, to be determined R. Lathrop, MIT, to be determined Y. Kodratoff, U. Paris-Sud, to be determined J.-G. Ganascia, U. Paris-VI, Application of machine learning techniques to the biological investigation viewed as a constructive process SCHEDULE ---------- Papers received: March 1, 1993 Acceptance notification: April 1, 1993 Final papers: June 1, 1993 WORKSHOP FORMAT: ------------------ The format of the workshop will be paper sessions with discussion at the end of each session, and a concluding panel. Prospective particitants should submit papers of five to ten pages in length. Four paper copies are required. Those who would like to attend without a presentation should send a one to two-page description of their relevant research interests. Attendance at the workshop will be limited to 30 or 40 people. Each workshop attendee MUST HAVE REGISTERED FOR THE MAIN CONFERENCE. An additional (low) 300 FF fee for the workshop attendance (about $60) (has registered for the main conference) and being in charge of taking notes during the entire workshop, could be exempted from the additional 300 FF fee. Volunteers are invited. ORGANIZING COMMITTEE -------------------- Buchanan, B. (Univ. of Pittsburgh - USA) Ganascia, J.-G., chairperson (Univ. of Paris-VI - France) Hunter, L. (National Labrary of Medicine - USA) Lathrop, R. (MIT - USA) Kodratoff, Y. (Univ. of Paris-Sud - France) Shavlik, J. W. (Univ. of Wisconsin - USA) PLEASE, SEND SUBMISSIONS TO: --------------------------- Ganascia, J.-G. LAFORIA-CNRS University Paris-VI 4 Place Jussieu 75252 PARIS Cedex 05 France Phone: (33-1)-44-27-47-23 Fax: (33-1)-44-27-70-00 E-mail: ganascia@laforia.ibp.fr