Effective drug–target interaction prediction with mutual interaction neural network

Drug-drug interaction Drug target Interaction network
DOI: 10.1093/bioinformatics/btac377 Publication Date: 2022-06-02T13:36:21Z
ABSTRACT
Accurately predicting drug-target interaction (DTI) is a crucial step to drug discovery. Recently, deep learning techniques have been widely used for DTI prediction and achieved significant performance improvement. One challenge in building models how appropriately represent drugs targets. Target distance map molecular graph are low dimensional informative representations, which however not jointly prediction. Another effectively model the mutual impact between Though attention mechanism has capture one-way of targets on or vice versa, yet explored, very important their interactions.Therefore, this article we propose MINN-DTI, new MINN-DTI combines an interacting-transformer module (called Interformer) with improved Communicative Message Passing Neural Network (CMPNN) Inter-CMPNN) better two-way targets, represented by map, respectively. The proposed method obtains than state-of-the-art methods three benchmark datasets: DUD-E, human BindingDB. also provides good interpretability assigning larger weights amino acids atoms that contribute more interactions targets.The data code study available at https://github.com/admislf/MINN-DTI.
SUPPLEMENTAL MATERIAL
Coming soon ....
REFERENCES (41)
CITATIONS (57)
EXTERNAL LINKS
PlumX Metrics
RECOMMENDATIONS
FAIR ASSESSMENT
Coming soon ....
JUPYTER LAB
Coming soon ....