Results 151 to 160 of about 2,166 (199)

HLN-DDI: hierarchical molecular representation learning with co-attention mechanism for drug-drug interaction prediction. [PDF]

BMC Bioinformatics
Luo Y, Deng L, Huang Z.
europepmc   +1 more source

Multi-Modal Fusion Frameworks of Subgraph-Optimized Graph Autoencoder for Molecular Property Prediction. [PDF]

J Chem Inf Model
Zhang K, Han C, Zhang F, Lin C, Li Q, Zang T, Zhao Y.   +6 more
europepmc   +1 more source

Prediction of circRNA-Disease Associations via Graph Isomorphism Transformer and Dual-Stream Neural Predictor. [PDF]

Biomolecules
Li H, Qian Y, Sun Z, Zhu H.
europepmc   +1 more source

Structure-Aware Compound-Protein Affinity Prediction via Graph Neural Networks with Group Lasso Regularization. [PDF]

Comput Struct Biotechnol J
Shi Z, Wang Y, Weerawarna PM, Richardson TI, Zhang J, Wang Y, Huang K.   +6 more
europepmc   +1 more source

Dual-channel graph learning reveals similarity and complementarity in protein-protein interaction networks. [PDF]

PLoS Comput Biol
Tang T, Shen T, Li W, Chen Y, Yuan S, Liu Y, Yang X, Luo X.   +7 more
europepmc   +1 more source

TF-DWGNet: a directed weighted graph neural network with tensor fusion for multi-omics cancer subtype classification. [PDF]

NAR Genom Bioinform
Yang T, Chen Z.
europepmc   +1 more source

Evaluating topological and graph-theoretical approaches to extract complex multimodal brain connectivity patterns in multiple sclerosis. [PDF]

Health Inf Sci Syst
Lozano-Bagén T, Martinez-Heras E, Pontillo G, Solana E, Vivó F, Petracca M, Calvi A, Garrido-Romero S, Solé-Ribalta A, Llufriu S, Prados F, Casas-Roma J.   +11 more
europepmc   +1 more source

Proteome-wide prediction of the mode of inheritance and molecular mechanisms underlying genetic diseases using structural interactomics. [PDF]

iScience
Saadat A, Fellay J.
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Solving inexact graph isomorphism problems using neural networks

Neurocomputing, 2005
We present a neural network approach to solve exact and inexact graph isomorphism problems for weighted graphs. In contrast to other neural heuristics or related methods this approach is based on a neural refinement procedure to reduce the search space followed by an energy-minimizing matching process. Experiments on random weighted graphs in the range
Brijnesh J Jain, Fritz Wysotzki
exaly   +2 more sources