NRBdMF: A recommendation algorithm for predicting drug effects considering directionality

@article{Azuma2022NRBdMFAR,
  title={NRBdMF: A recommendation algorithm for predicting drug effects considering directionality},
  author={Iori Azuma and Tadahaya Mizuno and Hiroyuki Kusuhara},
  journal={Journal of chemical information and modeling},
  year={2022}
}
Predicting the novel effects of drugs based on information about approved drugs can be regarded as a recommendation system. Matrix factorization is one of the most used recommendation systems, and various algorithms have been devised for it. A literature survey and summary of existing algorithms for predicting drug effects demonstrated that most such methods, including neighborhood regularized logistic matrix factorization, which was the best performer in benchmark tests, used a binary matrix… 
View on PubMed
arxiv.org

Figures and Tables from this paper

References

SHOWING 1-10 OF 47 REFERENCES

Neighborhood Regularized Logistic Matrix Factorization for Drug-Target Interaction Prediction

The proposed NRLMF method focuses on modeling the probability that a drug would interact with a target by logistic matrix factorization, where the properties of drugs and targets are represented by drug-specific and target-specific latent vectors, respectively.

A Novel Triple Matrix Factorization Method for Detecting Drug-Side Effect Association Based on Kernel Target Alignment

To predict potential associations between drugs and side effects, a novel method called the Triple Matrix Factorization- (TMF-) based model is proposed, built by the biprojection matrix and latent feature of kernels, which is based on Low Rank Approximation (LRA).

A unified solution for different scenarios of predicting drug-target interactions via triple matrix factorization

A Triple Matrix Factorization-based model (TMF) is proposed, which provides a unified framework of DTI prediction for all the screening scenarios and presents a new insight for the underlying mechanism of DTIs by indicating dominant features, which play important roles in the forming ofDTI.

Drug-Target Interaction Prediction via Dual Laplacian Graph Regularized Logistic Matrix Factorization

This study establishes a novel dual Laplacian graph regularized logistic matrix factorization model for drug-target interaction prediction, referred to as DLGrLMF briefly, and designs a gradient descent algorithm to solve the resultant optimization problem.

Manifold regularized matrix factorization for drug-drug interaction prediction

Predicting drug-target interactions by dual-network integrated logistic matrix factorization

The DNILMF algorithm outperforms the previously reported approaches in terms of AUPR and AUC based on the 5 trials of 10-fold cross-validation and the performance improvement depends on not only the proposed objective function, but also the used nonlinear diffusion technique.

A unified drug–target interaction prediction framework based on knowledge graph and recommendation system

KGE_NFM is developed, a unified framework for DTI prediction by combining knowledge graph (KG) and recommendation system and achieves accurate and robust predictions on four benchmark datasets, especially in the scenario of the cold start for proteins.

Collaborative matrix factorization with multiple similarities for predicting drug-target interactions

A factor model, named Multiple Similarities Collaborative Matrix Factorization (MSCMF), is proposed, which projects drugs and targets into a common low-rank feature space, which is further consistent with weighted similarity matrices over drugs and those over targets.

NMTF-DTI: A Nonnegative Matrix Tri-factorization Approach With Multiple Kernel Fusion for Drug-Target Interaction Prediction

Prediction of drug-target interactions (DTIs) plays a significant role in drug development and drug discovery. Although this task requires a large investment in terms of time and cost, especially…

Predicting the frequencies of drug side effects

A machine learning framework for computationally predicting frequencies of drug side effects and shows that the model is informative of the biology underlying drug activity: individual components of the drug signatures are related to the distinct anatomical categories of the drugs and to the specific drug routes of administration.