Integration of various protein similarities using random forest technique to infer augmented drug-protein matrix for enhancing drug-disease association prediction

Abstract

Identifying new therapeutic indications for existing drugs is a major challenge in drug repositioning. Most computational drug repositioning methods focus on known targets. Analyzing multiple aspects of various protein associations provides an opportunity to discover underlying drug-associated proteins that can be used to improve the performance of the drug repositioning approaches. In this study, machine learning models were developed based on the similarities of diversified biological features, including protein interaction, topological network, sequence alignment, and biological function to predict protein pairs associating with the same drugs. The crucial set of features was identified, and the high performances of protein pair predictions were achieved with an area under the curve (AUC) value of more than 93%. Based on drug chemical structures, the drug similarity levels of the promising protein pairs were used to quantify the inferred drug-associated proteins. Furthermore, these proteins were employed to establish an augmented drug-protein matrix to enhance the efficiency of three existing drug repositioning techniques: a similarity constrained matrix factorization for the drug-disease associations (SCMFDD), an ensemble meta-paths and singular value decomposition (EMP-SVD) model, and a topology similarity and singular value decomposition (TS-SVD) technique. The results showed that the augmented matrix helped to improve the performance up to 4% more in comparison to the original matrix for SCMFDD and EMP-SVD, and about 1% more for TS-SVD. In summary, inferring new protein pairs related to the same drugs increase the opportunity to reveal missing drug-associated proteins that are important for drug development via the drug repositioning technique.

Tumor relapse-free survival prognosis related consistency between cancer tissue and adjacent normal tissue in drug repurposing for solid tumor via connectivity map

“…This innovative approach seeks to identify new indications for investigational or approved drugs, extending beyond their original medical scope, thereby offering a promising avenue to overcome the aforementioned obstacles[4–6]. Common methodologies for computational drug repurposing include machine learning-based approaches[7–9], network-based approaches[10–13], text mining-based approaches[14–16], semantics inference-based approaches[17, 18], sequence-based approaches[19], structure-based approaches[20–22], and signature-based drug repurposing approaches[3, 4]. Among these methods, signature-based approaches have rapidly evolved with the accumulation of big data in life sciences, such as the growing availability of gene expression data[3, 4].…”

“…Common methodologies for computational drug repurposing include machine learning-based approaches [7][8][9] , network-based approaches [10][11][12][13] , text mining-based approaches [14][15][16] , semantics inference-based approaches [17,18] , sequence-based approaches [19] , structure-based approaches [20][21][22] , and signature-based drug repurposing approaches [3,4] . Among these methods, signature-based approaches have rapidly evolved with the accumulation of big data in life sciences, such as the growing availability of gene expression data [3,4] .…”

“…The subsequent iteration, the next-generation version, Cmap2 or Library of Integrated Network-Based Cellular Signatures L1000 (LINCS-L1000), was developed by the same team in 2014 [28] . It was completed in 2017 and generated 1,319,138 L100 expression profiles from 42,080 perturbagens, including 19,811 small molecule compounds, 18,493 shRNAs, 3,462 cDNAs, and 314 biologics [26] .…”

Tumor relapse-free survival prognosis related consistency between cancer tissue and adjacent normal tissue in drug repurposing for solid tumor via connectivity map

“…Compared to signatures based on DEGs, PCS-based signatures exhibit superior performance, identifying more drugs with higher prediction accuracy, as con rmed by DrugBank annotations. Notably, a signi cant proportion of predicted drugs without corresponding indications were subsequently validated in the ClinicalTrials database.Additionally, PCS-based signatures demonstrate elevated disease speci city and association with Drug Related Gene (DRG).Common methodologies for computational drug repurposing include machine learning-based approaches [7][8][9] , network-based approaches [10][11][12][13] , text mining-based approaches [14][15][16] , semantics inference-based approaches [17,18] , sequence-based approaches [19] , structure-based approaches [20][21][22] , and signature-based drug repurposing approaches [3,4] . Among these methods, signature-based approaches have rapidly evolved with the accumulation of big data in life sciences, such as the growing availability of gene expression data [3,4] .…”