Here we propose MeTDDI—a deep learning framework with local–global self-attention and co-attention to learn motif-based graphs for DDI prediction. MeTDDI achieved competitive performance compared with state-of-the-art models. Regarding interpretability, we conducted extensive assessments on 73 drugs...
This paper introduces a generalization of Convolutional Neural Networks (CNNs) to graphs with irregular linkage structures, especially heterogeneous graphs with typed nodes and schemas. We propose a novel spatial convolution operation to model the key properties of local connectivity and translation invaria...
Deep learning on graphs and in particular, graph convolutional neural networks, have recently attracted significant attention in the machine learning community. Many of such techniques explore the analogy between the graph Laplacian eigenvectors and the classical Fourier basis, allowing to formulate the co...
Graphs Documentation for theMotifClusterpackage is available onthe web. Performance Theperformancedirectory contains scripts and plots relating to timing the construction of motif adjacency matrices, in R, Python and Julia. Sticker A high-resolution hexagonal sticker is available in thestickerdirectory. ...
Building genome variation graphs (VGs) with GRAFIMO GRAFIMO allows also to build a genome variation graph from user data. To construct the VG are required a genome reference (in FASTA format) VCF file containing the genomic variants to enrich the reference sequence. ...
orderinteractionsbetweennodeswork,weproposemoti-basedgraphattentionmodel,calledMotiConvolutionalNetworks,whichgeneralizespastapproachesusingweightedmulti-hopmotiadjacencymatricescapturehigher-orderneighborhoods.Anovelattentionmechanismisusedalloweachindividualnodemostrelevantneighborhoodapplyitsflter.Weevaluateourapproachgraphsrom...
Network science has widely studied the properties of brain networks. Recent work has observed a global back-to-front pattern of information flow for higher frequency bands in magnetoencephalography data. However, the effective connectivity at a local lev
In addition, Table1and Table2describe the results of VINE (Huang et al. [20]) and sMCL-WMR (Boucher and King [23], sMCL for short) in order to compare these sample-driven algorithms, which extract cliques fromN-partite graphs, to our work.′∗′indicates that no result was available...
The bar graphs represent the percent number of colonies formed, normalized to untreated control cells. The white bars represent cells transfected with control vehicles (control siRNA or empty pcDNA3.1 vector). The error bars indicate the standard error of the mean of 3 replicates. (I) Same as ...
Sentence description of objects are utilized in the model. The description is transformable into graphs. Fast shape coding is accomplished by an operator t... Zbigniew M. Wójcik - 《Pattern Recognition》 被引量: 32发表: 1985年 加载更多研究...