[PDF] Combining Drug and Gene Similarity Measures for Drug-Target Elucidation | Semantic Scholar (2024)

The results showed that MDADTI can effectively identify unknown DTIs and validated the predictions of the MDAD TI in six drug-target interactions reference databases, and the results indicated thatMDADTI is superior to the other four baseline methods.

In spite of many improvements for pharmacology applications by learning-based methods, there are many over simplification settings in construction of predictive models that may lead to over-optimistic results on drug–target interaction prediction.

Heterogeneous network propagation with the forward similarity integration (FSI) algorithm is proposed, which systematically selects the optimal integration of multiple similarity measures of drugs and target proteins to create an optimal heterogeneous network model.

A simple procedure called neighbor-based interaction-profile inferring (NII) is presented and integrated into the existing BLM method to handle the new candidate problem and demonstrates the effectiveness of the NII strategy and shows the great potential of BLM-NII for prediction of compound-protein interactions.

The proposed DT2Vec method was able to integrate and map chemical and genomic space into low-dimensional dense vectors and showed promising results in predicting novel DTIs.

This study extracts four drug features and two disease features to find the semantic relations between drugs and diseases, and utilizes deep learning to extract an efficient representation for each feature, to introduce a pipeline for drug repositioning.

DASPfind is a computational method for finding reliable new interactions between drugs and proteins that significantly outperforms other state-of-the-art methods when the single top-ranked predictions are considered, or when a drug with no known targets or with few known targets is considered.

The experimental results demonstrate that the proposed approach DTI-CDF achieves a significantly higher performance than that of the traditional ensemble learning-based methods such as random forest and XGBoost, deep neural network, and the state-of-the-art methods, such as DDR.

BANDIT is developed, a novel paradigm that integrates multiple data types within a Bayesian machine-learning framework to predict the targets and mechanisms for small molecules with unprecedented accuracy and versatility that can be used as a resource to accelerate drug discovery and direct the clinical application of small molecule therapeutics with improved precision.

A method that uses probabilistic matrix factorization (PMF) for this purpose, which is particularly useful for analyzing large interaction networks, outperforms those recently introduced in quantitative analysis of known drug–target interactions.

...

...

A sequence-based drug target prediction method based solely on protein sequence information without the knowledge of family/domain annotation, or the protein 3D structure that can be applied in novel drug target identification and validation, as well as genome scale drug target predictions.

A drug similarity network starting from a public reference dataset containing genome-wide gene expression profiles (GEPs) following treatments with more than a thousand compounds is built and it is shown that, despite the complexity and the variety of the experimental conditions, the approach is able to identify similarities in drug mode of action from GEPs.

A one-stop data warehouse that integrates drug-related information about medical indication areas, adverse drug effects, drug metabolization, pathways and Gene Ontology terms of the target proteins and provides tools for 2D drug screening and sequence comparison of the targets.

This article characterize four classes of drug–target interaction networks in humans involving enzymes, ion channels, G-protein-coupled receptors (GPCRs) and nuclear receptors, and reveal significant correlations between drug structure similarity, target sequence similarity and the drug– target interaction network topology.

Applied to 746 marketed drugs, a network of 1018 side effect–driven drug-drug relations became apparent, 261 of which are formed by chemically dissimilar drugs from different therapeutic indications, hinting at new uses of marketed drugs.

The latest version of DrugBank (release 2.0) has been expanded significantly over the previous release and contains 60% more FDA-approved small molecule and biotech drugs including 10% more ‘experimental’ drugs.

A method that ranks 12,460 genes in the human genome on the basis of their potential relevance to a specific query drug and its putative indications, using known gene–drug interactions, networks of gene–gene interactions, and available measures of drug–drug similarity is developed.

A novel supervised inference method, known as bipartite local models to first predict target proteins of a given drug, then to predict drugs targeting a given protein, which gives two independent predictions for each putative drug–target interaction, which can be combined to give a definitive prediction for each interaction.

Compared 3,665 US Food and Drug Administration (FDA)-approved and investigational drugs against hundreds of targets, defining each target by its ligands, chemical similarities between drugs and ligand sets predicted thousands of unanticipated associations.

DrugBank is a unique bioinformatics/cheminformatics resource that combines detailed drug data with comprehensive drug target information and is fully searchable supporting extensive text, sequence, chemical structure and relational query searches.

...

...