Gene-based Collaborative Filtering using recommender system. (January 2018)

• Record Type: Journal Article
• Authors: Hu, Jinyu; Sharma, Sugam; Gao, Zhiwei; Chang, Victor
• Is Part Of: Computers & electrical engineering. Volume 65(2018)
• Page Start: 332
• Page End: 341
• Publication Date: 2018-01
• Subjects: Big Data -- GeneCF -- GPC -- HCC -- Recommender systems -- Collaborative filtering; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2017.04.010
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The recommender system, widely used in the e-commerce sites like Amazon, was used to help find target genes. The relationship of genes was an idea, inspired from the social network site, Facebook. The TOP-N Gene-based Collaborative Filtering (GeneCF) model was proposed in this paper, can recommend personalized genes as biomarkers for each patient. The RNA expression and cancer staining were used to verify the recommended genes by GeneCF algorithm. Abstract: The recommender system (RS) has achieved substantial evolution in this information age of the twenty-first century, with no exception to biological domain. While RS has been effectively exploited in analysis of biological data for gene prediction, it has raised interesting research challenges such as how to explore the gene interest (Gi) and recommend the genes for individual patients. To meet these research challenges, we propose a novel TOP-N Gene-based Collaborative Filtering (GeneCF) algorithm based on Gi of patients. The GeneCF algorithm is aimed for matching more accurate recommendations about genes to the patients, with exceptional precision and coverage achieved. The GeneCF algorithm has been tested and evaluated on a hepatocellular carcinoma (HCC) gene expression database. We found that six genes could be the cause of liver cancer: AMP, SAA1, S100P, SPP1 and CY2A7 and AFP. The GeneCF algorithm contributes to help doctors provide smarter, customized care for cancer patients.