INFERRING A CHEMICAL STRUCTURE FROM A FEATURE VECTOR BASED ON FREQUENCY OF LABELED PATHS AND SMALL FRAGMENTS

摘要: This paper proposes algorithms for inferring a chemical structure from feature vector based on frequency of labeled paths and small fragments, where this inference problem has potential application to drug design. In paper, structures are modeled as trees or tree-like structures. It is shown that the problems these kinds can be solved in polynomial time using dynamic programming-based algorithms. Since not practical, branchand-bound type algorithm also proposed. The result computational experiment suggests solve few few-tens seconds moderate size compounds.