Abstract
Predicting the protein structure from an amino acid sequence is computationally very intensive. In order to speed up protein sequence matching and processing, we present a novel coprocessor architecture for fast protein structure prediction. The architecture consists of systolic arrays to speed up the data intensive sequence alignment and structure prediction steps, and finite state machines for the control dominated steps. The architecture has been synthesized using Synopsys DC Compiler in 0.18 micron CMOS technology and details of its area and timing performance have been provided. A procedure to develop architectures with area-time trade-offs has also been presented.
Original language | English (US) |
---|---|
Pages (from-to) | 2494-2505 |
Number of pages | 12 |
Journal | Pattern Recognition |
Volume | 39 |
Issue number | 12 |
DOIs | |
State | Published - Dec 2006 |
Keywords
- Neural network
- PSI BLAST
- PSIPRED
- Protein structure prediction
- VLSI architecture
ASJC Scopus subject areas
- Software
- Signal Processing
- Computer Vision and Pattern Recognition
- Artificial Intelligence