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 TRANSFACê 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 MATCHTM. The results show that our method has the potential to attain very high classification accuracy.

[1]  Gang Li,et al.  Discovering multiple realistic TFBS motifs based on a generalized model , 2009, BMC Bioinformatics.

[2]  Larry J. Eshelman,et al.  The CHC Adaptive Search Algorithm: How to Have Safe Search When Engaging in Nontraditional Genetic Recombination , 1990, FOGA.

[3]  Gary D. Stormo,et al.  DNA binding sites: representation and discovery , 2000, Bioinform..

[4]  J. David Schaffer,et al.  A series of failed and partially successful fitness functions for evolving spiking neural networks , 2009, GECCO '09.

[5]  Keith E. Mathias,et al.  The Effect of Incest Prevention on Genetic Drift , 1998, FOGA.

[6]  J. David Schaffer,et al.  SSNNS -: a suite of tools to explore spiking neural networks , 2008, GECCO '08.

[7]  G. Church,et al.  Nucleotides of transcription factor binding sites exert interdependent effects on the binding affinities of transcription factors. , 2002, Nucleic acids research.

[8]  Olaf Booij,et al.  Temporal Pattern Classification using Spiking Neural Networks , 2004 .

[9]  Heike Sichtig.  The SGE framework: Discovering spatio-temporal patterns in biological systems with spiking neural ne , 2009 .

[10]  G. Stormo,et al.  Additivity in protein-DNA interactions: how good an approximation is it? , 2002, Nucleic acids research.

[11]  John Hawkins,et al.  Assessing phylogenetic motif models for predicting transcription factor binding sites , 2009, Bioinform..

[12]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[13]  Edgar Wingender,et al.  The TRANSFAC project as an example of framework technology that supports the analysis of genomic regulation , 2008, Briefings Bioinform..

[14]  Victor G. Levitsky,et al.  Effective transcription factor binding site prediction using a combination of optimization, a genetic algorithm and discriminant analysis to capture distant interactions , 2007, BMC Bioinformatics.

[15]  Daniel E. Newburger,et al.  Diversity and Complexity in DNA Recognition by Transcription Factors , 2009, Science.

[16]  Kwong-Sak Leung,et al.  TFBS identification based on genetic algorithm with combined representations and adaptive post-processing , 2008, Bioinform..

[17]  Alberto Riva,et al.  MAPPER: a search engine for the computational identification of putative transcription factor binding sites in multiple genomes , 2005, BMC Bioinformatics.

[18]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .