Computational methods for predicting drug-target interactions

  • What are feature based methods for drug-target interaction prediction?

    The feature based methods represent the drug target pair with a vector of descriptors.
    The various properties of drugs, as well as the proteins, are encoded as corresponding features.
    The feature based methods predict the interactions between these drug target pairs by discovering features that are more discriminative..

  • What is predicting drug-target interactions?

    In order to predict DTI, a similarity model is proposed, in 2021 that uses two-dimensional CNN in the external products between column vectors corresponding to two similarity matrices in drugs and targets28.
    There are also various machine learning methods for this prediction..

  • What techniques are used in drug-target identification?

    Target identification uses methods such as genetic associations such as connecting genes with a disease and data mining methods for searching through literature and databases.
    A target may be identified for further investigation, from both clinical and academic research as well as from the commercial setting as well..

  • Why is drug-target interaction prediction important?

    Prediction of drug–target interactions (DTIs) is one of the most important steps in the genomic drug discovery pipeline and drug repurposing (Knowles and Gromo, 2003; Yildirim et al., 2007), the purpose is to discover putative new drugs and new uses of existing drugs..

  • Chem-bioinformatic approach for drug discovery
    Ideally, the target must be associated with a disease and it must have a suitable binding-pocket/active site into which a drug or drug-like molecule can bind.
    Generally, proteins are good targets but sometimes RNA can also serve the purpose.
  • In order to predict DTI, a similarity model is proposed, in 2021 that uses two-dimensional CNN in the external products between column vectors corresponding to two similarity matrices in drugs and targets28.
    There are also various machine learning methods for this prediction.
  • The feature based methods represent the drug target pair with a vector of descriptors.
    The various properties of drugs, as well as the proteins, are encoded as corresponding features.
    The feature based methods predict the interactions between these drug target pairs by discovering features that are more discriminative.
Molecular docking and the aforementioned receptor-centric pharmacophore modeling are the two existing computational approaches for target-based (structure-based) DTI prediction, and are generally used in conjunction.
Computational DTI prediction speeds up as well as reduce the cost of the rather expensive drug discovery and development process.
These methods can be classified as two categories: the ligand-based virtual screening approach and docking simulation. The first method compares the similarity of a given protein based on chemical structure with a classical SAR framework to predict DTIs [13].

Categories

Tailored computational methods
Computational methods in biology
Méthode delphi
Computational methods in aerospace engineering
Computational methods in potential aerodynamics
Advanced computational methods for aeronautics
Computational methods for single-cell multi-omics integration and alignment
Computational methods for single-cell rna sequencing
Computational design practices
Computational design approach
Computational methods for drug design
Computational methods for engineering design
Computational protein design methods
Computational methods in electrical engineering
Computational methods for fluid dynamics ferziger
Computational methods in german
Theoretical and computational methods helsinki
Computational experiments with heuristic methods
Computational methods for least squares approximation
International journal of computational methods letpub