Learning Conformation Rules

Abstract

We define a hypergraph representation of a protein which captures its tertiary structure in a loose way. By using the notions of hypergraphs, we define a conformation rule as-a kind of hypergraph rewriting. With a conformation rule, a procedure of conformation from sequences is described. Then we discuss a method of learning a conformation rule from a collection of hypergraph representations of proteins. A polynomial-time PAClearning algorithm is shown for a class of conformations. This algorithm is now being implemented with Common Lisp for experiments.

Learnable Hypergraph Laplacian for Hypergraph Learning

“…Consequently, a new research area aiming at establishing convolutional networks on hypergraphs attracts a surge of attention recently. Hypergraph is a generalization of the regular graph, whose edge could join any number of vertices, and thus possess a more powerful capability of modeling complex relationship preserved in the real-world data [7][8][9]. For example, in a co-citation relationship [10], papers act as hypernodes, and citation relationships become hyperedges.…”