No abstract available.

A knowledge base and learning system is designed to help biologists predict protein structure and function based on sequence information. The knowledge base contains diverse information about: (a) protein motif sequences and structures, (b) heuristics and programs for identifying protein features, and (c) molecular simulation programs. The learning system selects the most relevant information for a particular prediction task and optimally integrates the information to generate accurate and comprehensible hypotheses. Biologists define the objectives for learning such as accuracy and comprehensibility. To overcome the limitations of existing induction algorithms, techniques are developed for constructing new features based on the existing knowledge base. Optimization algorithms are used for determining the best combination of induction and feature construction strategies for a problem.>

Knowledge-based approaches are being increasingly used in predicting protein structure and motifs. Machine learning techniques such as neural networks and decision-trees have become invaluable tools for these approaches. This paper describes the use of machine learning in predicting sequence-based motifs in antibody fragments. Given the limited number of three dimensional structures and the plethora of sequences, this technique is useful for homology modeling of three dimensional structures of antibody fragments.