Neural network design
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
The Applicability of Recurrent Neural Networks for Biological Sequence Analysis
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
FPGA Implementations of Neural Networks
FPGA Implementations of Neural Networks
Establishing a statistic model for recognition of steroid hormone response elements
Computational Biology and Chemistry
Data mining coupled conceptual spaces for intelligent agents in data-rich environments
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV
An analog VLSI recurrent neural network learning a continuous-time trajectory
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
A two-phase ANN method for genome-wide detection of hormone response elements
PRIB'07 Proceedings of the 2nd IAPR international conference on Pattern recognition in bioinformatics
An FPGA-based fast classifier with high generalization property
ACM SIGARCH Computer Architecture News
An optimal implementation on FPGA of a hopfield neural network
Advances in Artificial Neural Systems
Hi-index | 0.00 |
Some specialized transcription factors recognize specific DNA sequences arranged in inverted and direct repeats with a short nucleotide spacer in between. Identification of these motifs has been challenging due to their high divergence. In this paper, we describe a novel computational approach that can greatly improve the efficiency and accuracy in prediction of these DNA binding sites. A Hopfield neural classifier was designed with the flexibility of internal structure being adapted recurrently for the target motif structure. An FPGA implementation of this recurrent neural network is presented. It contains 60 neurons, and is described by the Verilog HDL modules. The circuitry was mapped onto an Alpha Data Virtex-4LX160 FPGA board. A set of 600 experimentally verified steroid hormone binding sites was used as the training set, and the developed Hopfield neural classifier has been used to identify and classify actual Hormone Response Elements. The program has been proven to be an effective tool in studying hormone-regulated gene networks.