TY  - JOUR
TI  - Construction of Protein-Protein Interaction Network Using Community Molecular Detection
AU  - J. Monika
AU  -  K. Srinivas
JO  - International Journal of Scientific Research in Computer Science, Engineering and Information Technology
PB  - Technoscience Academy
DA  - 2018/04/30
PY  - 2018
DO  - https://doi.org/10.32628/IJSRCSEIT
UR  - https://ijsrcseit.com/CSEIT21833753
VL  - 3
IS  - 3
SP  - 2101	
EP  - 2112
AB  - The number of proteins continues grow. Machine learning is a subfield of computer science that includes the study of systems that can learn from data, rather than follow only explicitly programmed instructions. Some of the most common techniques used for machine learning are Support Vector Machine, Artificial Neural Networks, k-Nearest Neighbor and Decision Tree. Machine learning techniques are widely used techniques in bioinformatics to solve different type of problems. In the year of 2014, the genome project was completed. Some of the proteins have an individual functionality. But there is no accurate information about function for remaining proteins and its network. In general, by using the In-Vitro and In-Vivo techniques are predict the functionality of proteins and its network. But the experimental investigation is costly and time consuming. To overcome this problem, In-silico technique was used such as molecular modeling, etc., but some limitation here is low accuracy. So here to construct Protein-Protein Interaction network for target protein. 

In this frame work, a novel technique is applied called Community Molecular Detection (CMD). Collect the dataset from “yeastExpData” package called litG. The CMD algorithm operates in two steps, first step is connected components, and second step is community prediction. The first step of CMD, find the connected components by using degree distribution. The second steps, molecular community prediction, takes the output of connected components graph and then find communities.