Modified FPred-Apriori: improving function prediction of target proteins from essential neighbours by finding their association with relevant functional groups using Apriori algorithm
by Sovan Saha; Abhimanyu Prasad; Piyali Chatterjee; Subhadip Basu; Mita Nasipuri
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 19, No. 1, 2021

Abstract: Drug assistance to various harmful diseases is still not discoverable since functions of proteins responsible for the cause of these diseases are still unannotated. By the use of high throughput techniques, huge amount of protein sequence can be annotated rapidly using computational technique to formulate biological hypothesis rather than using costly, time consuming, low throughput wet lab experiments. Here we propose a novel prediction method, modified FPred-Apriori, which aims to annotate proteins by selecting active target proteins efficiently at three levels of threshold and considerably by pruning nonessential neighbours and investigate functional association of level-1 and level-2 neighbours to mine out frequently occurred relevant functional groups for annotation using Apriori algorithm. Modified FPred-Apriori is improved modified version of FPred-Apriori, which achieves an overall precision, recall and F-score of 0.887, 0.708 and 0.787 respectively. The comprehensive comparison demonstrates that the proposed method outperforms the other competing methods.

Online publication date: Wed, 28-Apr-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email