A Bi-Recursive Neural Network Architecture for the Prediction of Protein Coarse Contact Maps

Authors:
Alessandro Vullo;Paolo Frasconi
Affiliations:
-;-
Venue:
CSB '02 Proceedings of the IEEE Computer Society Conference on Bioinformatics
Year:
2002

Citing 3
Cited 1

Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Mining Residue Contacts in Proteins Using Local Structure Predictions

BIBE '00 Proceedings of the 1st IEEE International Symposium on Bioinformatics and Biomedical Engineering
A general framework for adaptive processing of data structures

IEEE Transactions on Neural Networks

A New Protein Representation Based on Fragment Contacts: Towards an Improvement of Contact Maps Predictions

Computational Intelligence Methods for Bioinformatics and Biostatistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Prediction of contact maps may be seen as a strategic step towards the solution of fundamental open problems in structural genomics. In this paper we focus on coarse grained maps that describe the spatial neighborhood relation between secondary structure elements (helices, strands, and coils) of a protein. We introduce a new machine learning approach for scoring candidate contact maps. The method combines a specialized noncausal recursive connectionist architecture and a heuristic graph search algorithm. The network is trained using candidate graphs generated during search. We show how the process of selectingand generating training examples is important for tuning the precision of the predictor.