Publication: Prediction of protein structural class using a fpga-based hardware accelerator
Loading...
Date
2012-06-01
Authors
Yee, Chau Jinn
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In order to understand protein folding patterns and its function, adequate knowledge of protein structural class is an element that should not be ignored. Thus, it is important that effective meth ods for protein structural class prediction are developed. For the past three decades, many algo rithms had been proposed but only few of them performed well in terms of accuracy. The most significant one was the nearest neighbour complexity distance measure (NN-CDM) method. How ever, this approach suffered from high computational load due to utilization of complete aminoacid sequence in prediction. To this end, a new effort is presented: prediction of protein structural class using a Field-Programmable Gate Array (FPGA) based hardware accelerator, hopingto improve prediction of protein structural class in terms of its speed. It is a nearest neighbourclassifier with complexity-based distance measure. Distance between pair of protein sequences isevaluated by a complexity based measure of raw symbol sequences rather than extracting featuresfrom them. And as predictive engine, nearest neighbour classifier is adopted and is implementedinto Altera Cyclone II FPGA (EP2C35) using verilog hardware description language (HDL). Results obtained from simulation, software approach and hardware implementation proved that thisapproach can function as a protein structural class predictor and it is 40 times faster compared to software approach, without any hardware accelerated.