drugs target interaction prediction binary classification series

[MohammedFCIS]

where
the drug-target pairs are treated as instances, and the
chemical structures of drugs and the amino acid subsequences
of targets are treated as features. Then, classical
classification methods can be used, e.g., support vector
machines (SVM) and regularized least square (RLS). Liu
et al. [33] have developed PyDTI package which mainly
focuses on neighborhood regularized logistic matrix
factorization (NRLMF). NRLMF uses logistic matrix factorization
and neighbouhood regularization to prediction
drug target pairs.
NetLapRLS,BLM-NII,KBMF-2k,CMF implemented in a
single package. Bajic [17] have developed DDR package
which combines multiple different similarity measures
in the drug space and protein target space and optimizes
using average entropy measures. Peska [12] developed
bayesian ranking approach for drug target prediction.
The novelty of the approach comes from “per-drug ranking”
optimization criteria, while projecting drugs and
targets to a shared latent space. Most of these methods
are command line based and they need to have prior
programming expertise to start the analysis. Netpredictor
solves this problem by building an intuitive UI
and giving users an easy way to interaction and peform
prediction based on their data. The main advantages of
network-based methods are:
• They use label information and as well as unlabeled
data as input in the form of vectors.
• Once can use multiple classes inside the network
structure.
• It uses multitude of paths to compute associations.
• Network based methods mostly use transductive
learning strategy,in which the test set is unlabelled
but while computation