Evolving Spiking Neural Networks for Predicting Transcription Factor Binding Sites

Interdisciplinary problem solving in computational biology requires a fundamental understanding of complex biological adaptive systems, from cellular to molecular level in order to tackle challenging problems such as neurodegenerative diseases. In this work we present a description and an initial evaluation of a Spiking Neural Network-Genetic Algorithm (SNN-GA) system we are developing for the computational prediction of transcription factor binding sites (TFBS). The SNN-GA approach is based on modeling information processing of biological neurons through evolutionary processes. The goal of our work is to reduce the number of false positives in the predicted TFBSs, through a more precise modeling of information contained in the alignments in the training data. We show an evaluation of four proposed network topologies that represent TFBS data. We use real TFBS data from the TRANSFAC (R) database and appropriately generated negative samples. We evaluated the network topologies one three well-known models for transcription factors: RSRFC4, ZID and p53. Benchmark performances for these models are given using MAPPER and MATCH (TM). The results show that our method has the potential to attain very high classification accuracy.