Font Size: a A A

Nuclear Export Signal Recognition Based On Spiking Neural P Systems

Posted on:2018-12-06Degree:MasterType:Thesis
Country:ChinaCandidate:P ZhangFull Text:PDF
GTID:2370330566951588Subject:Pattern Recognition and Intelligent Systems
Abstract/Summary:PDF Full Text Request
Nuclear export signal,NES,is a very important signal to guide substances transporting between nucleus and cytoplasm in the biological cells.In general,the method of biological experiment is used to identify the nuclear export signal and to predict the structure of related sequences.However,the cost of the experimental method is higher and the time is longer,which makes it impossible to detect the nuclear export signal in large scale data.In this paper,we use the method of spiking neural P systems to identify the nuclear export signal,which is a comprehensive research subject of computer science,mathematics and life science.This study belongs to the field of bioinformatics research,aiming to use novel and non experimental methods to efficiently identify the nuclear export signal which plays a decisive role in the transport of macromolecules in the cytoplasm.In this research,a new method of using spiking neural P systems is proposed to identify the nuclear export signal NES.The establishment of the NES recognition system is mainly divided into two parts.The first part is the design of input module,reading the pulse sequence through the input neuron then training the information.In this part,we need to design a reasonable topology and the rules of the neuron so that the information will be stored in the neurons of the input module.Another part is a predict module with a simple Hebbian learning strategy,which can obtain the final model by training the information recorded by the input module.After completing the model design,secondary structure elements of 30 experimentally verified NES are randomly selected for training an spiking neural P systems,and then 1224 amino acid sequences abstracted from 221 NES-containing protein sequences randomly in NESdb are selected to test our method.Experimental results show that our method achieves a precision rate 75.41%,better than NES-REBS 47.2%,Wregex 25.4%,ELM,and NetNES 37.4%.At the last,We designed a software interface to facilitate the use of researchers.
Keywords/Search Tags:nuclear export signals, spiking neural systems, Hebbian learning strategy
PDF Full Text Request
Related items