14940

13446

كارشناسي ارشد

نرم‌افزار

اصفهان : دانشگاه صنعتي اصفهان

1398

دوازده، 71ص. : مصور، جدول، نمودار

ناصر قديري مدرس

زينب مالكي

عبدالرضا ميرزايي، حسين فلسفين

1398/05/27

كتابنامه

مهندسي كاميپيوتر

مهندسي برق و كامپيوتر

1398/05/27

2552975

Protein Protein Interaction PPI network clustering based on multi layer graph Amir Hossein Atashkar a atashkar@ec iut ac ir May 2019 Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan 84156 83111 Iran Degree M Sc Language Farsi Supervisor Prof Naser Ghadiri Modarres nghadiri@cc iut ac ir Advisor Prof Zeinab Maleki zmaleki@cc iut ac ir Abstract The Bioinformatics Research Field is a new science that seeks to address biological issues in cellular and molecularfields using computers and bioinformatics databases One of the areas of bioinformatics research is the identification anddetection of protein clusters Protein clusters are a group of proteins that with each other s interaction carry out a specificactivity in living creatures As a result the design and implementation of an algorithm that can carry out this high precisionclustering on proteins is considered by researchers in this field So far most of the proposed algorithms for clusteringdetect and extract protein clusters from a single source of information Since the Protein Protein Interaction PPI networkshave a large error the approach of integrating different data sources makes the identified clusters more accurate So someclustering methods of PPI networks use the approach of integrating different data sources Most of these algorithms firstintegrate the data sources together and then run existing clustering algorithms for single layer networks on the integratednetwork Although this approach makes clustering more accurate than the use of only one data source the loss of someimportant information during data integration does not result in good clustering One way to use different data sources is touse multi layer graphs Unfortunately the citation method for the clustering of PPI networks based on multi layer graphshas not been introduced In this research a method is presented that uses multi layer graph theory to cluster PPI networks with higher accuracy In this way different data sources each of which is a layer of a multi layer graph All layers are initially integrated anda single layer graph is created Then in the next step and in the next clustering process in addition to the single layerintegrated graph the information from each layer is also used separately to reduce the amount of information that is lost In the proposed method the multi layer graph is made of three PPI networks Also the results obtained from the clusteringalgorithm are compared with the clusters of the four gold standard data sets Comparison results show that in the proposedmethod the value of F measure is higher than other methods Also in the Precision and Recall value the results areimproved Key Words Clustering Protein complexes Protein protein interaction networks Graph theory Multi layer graphs

ناصر قديري مدرس

زينب مالكي

عبدالرضا ميرزايي، حسين فلسفين