Protein ligands Binding Affinity Prediction model
The protein–ligand interactions assume a continuum of binding strength values, also called binding affinity and we are predicting this value using deep learning architectures.Furthermore, a regression-based model brings in the advantage of predicting an approximate value for the strength of the interaction between the drug and target which in turn would be significantly beneficial for limiting the large compound search-space in drug discovery studies.
We implemented 2 Deep learning model name:Deep DTA and WideDTA to predict binding affinity. : Prediction of the interaction affinity between proteins and compounds is a major challenge in the drug discovery process.
Deep DTA-Using Deep learning architecture in identification of drug-target interactions (DTI) strength (binding affinity) using character-based sequence representation approach.
WideDTA is a deep-learning based prediction model that employs chemical and biological textual sequence information-word-based sequence representation to predict binding affinity.
We evaluated our model on the KIBA data set (kinase inhibitors bioactive data).We used the filtered version of the KIBA dataset, in which each protein and ligand has at least ten interactions. KIBA set contains ligands-2111, and proteins-229.For more details refer Blog post.