A New Weighted Imputed Neighborhood-Regularized Tri-Factorization One-Class Collaborative Filtering Algorithm: Application to Target Gene Prediction of Transcription Factors

Abstract

Identifying target genes of transcription factors (TFs) is crucial to understand transcriptional regulation. However, our understanding of genome-wide TF targeting profile is limited due to the cost of large-scale experiments and intrinsic complexity of gene regulation. Thus, computational prediction methods are useful to predict unobserved TF-gene associations. Here, we develop a new Weighted Imputed Neighborhood-regularized Tri-Factorization one-class collaborative filtering algorithm, WINTF. It predicts unobserved target genes for TFs using known but noisy, incomplete, and biased TF-gene associations and protein-protein interaction networks. Our benchmark study shows that WINTF significantly outperforms its counterpart matrix factorization-based algorithms and tri-factorization methods that do not include weight, imputation, and neighbor-regularization, for TF-gene association prediction. When evaluated by independent datasets, accuracy is 37.8 percent on the top 495 predicted associations, an enrichment factor of 4.19 compared with random guess. Furthermore, many predicted novel associations are supported by literature evidence. Although we only use canonical TF-gene interaction data, WINTF can directly be applied to tissue-specific data when available. Thus, WINTF provides a potentially useful framework to integrate multiple omics data for further improvement of TF-gene prediction and applications to other sparse and noisy biological data. The benchmark dataset and source code are freely available at https://github.com/XieResearchGroup/WINTF.

SeEn: Sequential enriched datasets for sequence-aware recommendations

“…An investigator studying the effect of chemical compounds in the creation of new drugs would be more than glad if a system recommended the next best match to their studies preferences. Several recent studies support this claim [1][2][3][4][5] . The goal of most of these studies is to obtain a recommendation for the response a drug will have in the patients, for example, realizing studies with patients' cell cultures [1][2][3][4] .…”

“…Several recent studies support this claim [1][2][3][4][5] . The goal of most of these studies is to obtain a recommendation for the response a drug will have in the patients, for example, realizing studies with patients' cell cultures [1][2][3][4] . A different approach was followed by 5 , in which the recommendations are based on sentiment analyses of the patient's reviews about drugs.…”

Design of Personalized Recommendation and Sharing Management System for Science and Technology Achievements based on WEBSOCKET Technology

“…In e-commerce, social networking, music, and other industries, CFRA, or a Personalised Recommendation Algorithm (PRA), is frequently utilised. When evaluated using independent datasets, Lim H et [11]. A recommendation framework that integrates local differential privacy (LDP) www.ijacsa.thesai.org with collaborative filtering has been developed by Bao T et al to address the problem of dishonest server behavior or user privacy disclosure in case of failure.…”

Collaborative Filtering Algorithm based on Hybrid Machine Learning Optimization

“…We reorganize all the scored items of a single user, and then according to the above method, all users will get their corresponding user vectors, which will be combined into a user matrix. Find out K items similar to the products evaluated by a user, and form a recommended item matrix for users [17][18].…”