AMGDTI: drug–target interaction prediction based on adaptive meta-graph learning in heterogeneous network

Abstract

Prediction of drug–target interactions (DTIs) is essential in medicine field, since it benefits the identification of molecular structures potentially interacting with drugs and facilitates the discovery and reposition of drugs. Recently, much attention has been attracted to network representation learning to learn rich information from heterogeneous data. Although network representation learning algorithms have achieved success in predicting DTI, several manually designed meta-graphs limit the capability of extracting complex semantic information. To address the problem, we introduce an adaptive meta-graph-based method, termed AMGDTI, for DTI prediction. In the proposed AMGDTI, the semantic information is automatically aggregated from a heterogeneous network by training an adaptive meta-graph, thereby achieving efficient information integration without requiring domain knowledge. The effectiveness of the proposed AMGDTI is verified on two benchmark datasets. Experimental results demonstrate that the AMGDTI method overall outperforms eight state-of-the-art methods in predicting DTI and achieves the accurate identification of novel DTIs. It is also verified that the adaptive meta-graph exhibits flexibility and effectively captures complex fine-grained semantic information, enabling the learning of intricate heterogeneous network topology and the inference of potential drug–target relationship.

Large Language Model-Based Natural Language Encoding Could Be All You Need for Drug Biomedical Association Prediction

“…12,24 However, due to the complexity of the graph embedding algorithms, these methods were often limited in terms of information extraction effectiveness. 28,29 Meanwhile, feature representation strategies based on similarity spectra might result in a loss of information. 30,31 As for biomedical molecules such as drugs, their feature representations largely relied on intrinsic molecular constitution and characteristics.…”

“…For pharmacological terminologies such as diseases, side effects, etc., their representations were predominantly premised on expert-curated structurized data . This was typically done by constructing KGs for the high-dimensional graph embedding , and feature encoding via semantic similarity profiles computed from ontologies. , However, due to the complexity of the graph embedding algorithms, these methods were often limited in terms of information extraction effectiveness. , Meanwhile, feature representation strategies based on similarity spectra might result in a loss of information. , As for biomedical molecules such as drugs, their feature representations largely relied on intrinsic molecular constitution and characteristics. , Classic molecular fingerprints, physicochemical descriptors, biochemical language-based embeddings, , etc. were commonly applied to represent such substances.…”