Filters








2,125 Hits in 5.7 sec

Detecting recurrent gene mutation in interaction network context using multi-scale graph diffusion

Sepideh Babaei, Marc Hulsman, Marcel Reinders, Jeroen de Ridder
2013 BMC Bioinformatics  
Results: We identify densely connected components of known and putatively novel cancer genes and demonstrate that they are strongly enriched for cancer related pathways across the diffusion scales.  ...  To this end, we introduce a multi-scale diffusion kernel and apply it to a large collection of murine retroviral insertional mutagenesis data.  ...  The diffusion kernel is applied to the complete PPI graph N for a range of scales by varying β in the range [ 0, 0.03].  ... 
doi:10.1186/1471-2105-14-29 pmid:23343428 pmcid:PMC3626877 fatcat:iioqaeqkcjgz3clevuglngz5su

On the Effect of Semantically Enriched Context Models on Software Modularization

Amir Saeidi, Jurriaan Hage, Ravi Khadka, Slinger Jansen
2017 The Art, Science, and Engineering of Programming  
The second notion of context is defined based on the flow of data between identifiers to represent a module as a dependency graph where the nodes correspond to identifiers and the edges represent the data  ...  We try to overcome this problem by introducing context models for source code identifiers to obtain a semantic kernel, which can be used for both deriving the topics that run through the system as well  ...  Di usion Kernels A class of graph-based kernel functions are the diffusion kernels, originally introduced by Kondor and Lafferty [ ].  ... 
doi:10.22152/programming-journal.org/2018/2/2 fatcat:bjuu7tf7sre6pjlzohj5254xwe

Knowledge-driven graph similarity for text classification

Niloofer Shanavas, Hui Wang, Zhiwei Lin, Glenn Hawe
2020 International Journal of Machine Learning and Cybernetics  
In this paper, we present a graph kernel-based text classification framework which utilises the structural information in text effectively through the weighting and enrichment of a graph-based representation  ...  The similarity between enriched graphs, knowledge-driven graph similarity, is calculated using a graph kernel.  ...  A sprinkled diffusion kernel that uses both co-occurrence information and class information for word sense disambiguation is presented in [36] .  ... 
doi:10.1007/s13042-020-01221-4 fatcat:wfzom7w3xjc5pfq4vxdwi6t2em

Finding friends and enemies in an enemies-only network: A graph diffusion kernel for predicting novel genetic interactions and co-complex membership from yeast genetic interactions

Y. Qi, Y. Suhail, Y.-y. Lin, J. D. Boeke, J. S. Bader
2008 Genome Research  
We have developed a graph diffusion kernel as a unified framework for inferring complex/pathway membership analogous to "friends" and genetic interactions analogous to "enemies" from the genetic interaction  ...  The kernels show significant improvement over previous best methods for predicting genetic interactions and protein co-complex membership from genetic interaction data.  ...  Conclusion Graphs are a useful abstraction for biological networks, and diffusion kernels have been effective for inferring similarities between nodes in a graph.  ... 
doi:10.1101/gr.077693.108 pmid:18832443 pmcid:PMC2593582 fatcat:sxqpczut3bgidit7v6y5inboiy

A Methodology for Mining Document-Enriched Heterogeneous Information Networks [chapter]

Miha Grčar, Nada Lavrač
2011 Lecture Notes in Computer Science  
The methodology presented in this paper is based on decomposing a heterogeneous network into (homogeneous) graphs, computing feature vectors with Personalized PageRank [14] , and constructing a common  ...  For short, such networks are called heterogeneous information networks [6] .  ...  The authors would also like to thank Center for Knowledge Transfer at Jožef Stefan Institute and Viidea Ltd. for providing the dataset and use case presented in the paper.  ... 
doi:10.1007/978-3-642-24477-3_11 fatcat:vn4cq4p44zbynpcurhp6feespq

A Methodology for Mining Document-Enriched Heterogeneous Information Networks

M. Grcar, N. Trdin, N. Lavrac
2012 Computer journal  
The methodology presented in this paper is based on decomposing a heterogeneous network into (homogeneous) graphs, computing feature vectors with Personalized PageRank [14] , and constructing a common  ...  For short, such networks are called heterogeneous information networks [6] .  ...  The authors would also like to thank Center for Knowledge Transfer at Jožef Stefan Institute and Viidea Ltd. for providing the dataset and use case presented in the paper.  ... 
doi:10.1093/comjnl/bxs058 fatcat:tvsnxcems5fzfgdz4yc4p76ojq

Identifying influential nodes in a wound healing-related network of biological processes using mean first-passage time

Tomasz Arodz, Danail Bonchev
2015 New Journal of Physics  
The MFPT-based scores correctly reflected the pattern of the healing process dynamics to be highly concentrated around several processes between day 0 and day 3, and becoming more diffuse at day 7.  ...  The information from these networks is used to build a network of the most enriched processes with undirected links weighted proportionally to the count of shared genes between the pair of processes, and  ...  The influence has been defined in terms of a diffusion kernel [18] , diffusion with loss [19] or a heat kernel [20] .  ... 
doi:10.1088/1367-2630/17/2/025002 fatcat:e6h5nzcy3rdlrlj4ejhulaxjiy

Scale-space measures for graph topology link protein network architecture to function

Marc Hulsman, Christos Dimitrakopoulos, Jeroen de Ridder
2014 Computer applications in the biosciences : CABIOS  
Results: In this work, we derive generalized scale-aware versions of known graph topological measures based on diffusion kernels.  ...  Moreover, we demonstrate that graph topological scale spaces capture biologically meaningful features that provide new insights into the link between function and protein network architecture.  ...  ACKNOWLEDGEMENT The authors thank Laurens van der Maaten for a tailored implementation of the t-SNE algorithm.  ... 
doi:10.1093/bioinformatics/btu283 pmid:24931989 pmcid:PMC4058939 fatcat:x4swybudtnep5hihshh4c4fk4q

A Network of Networks Approach for Modeling Interconnected Brain Tissue-Specific Networks [article]

Hideko Kawakubo, Yusuke Matsui, Itaru Kushima, Norio Ozaki, Teppei Shimamura
2018 bioRxiv   pre-print
We demonstrate on simulated data that GOSPEL outperforms existing kernel-based algorithms in terms of F-measure.  ...  Several state-of-the art network-based analyses have been proposed for mechanical understanding of genetic variants in neurogenetic disorders.  ...  Acknowledgements We would like to thank Makoto Yamada for helpful discussions. Funding This research was supported by AMED under grant No. JP18dm0107087.  ... 
doi:10.1101/349969 fatcat:44hv4dafn5gypebcj5aq5yhxki

Graphlet Laplacians: graphlet-based neighbourhoods highlight topology-function and topology-disease relationships [article]

Sam F. L. Windels, Noël Malod-Dognin, Nataša Pržulj
2018 bioRxiv   pre-print
Currently available graphlet-based methods do not consider whether nodes are in the same network neighbourhood.ContributionTo combine graphlet-based topological information and membership of nodes to the  ...  Local wiring patterns are typically quantified by counting how often a node touches different graphlets (small, connected, induced sub-graphs).  ...  The diffusion kernel is often called the 'heat kernel', as it can be viewed as describing the flow of heat originating from the nodes across the edges of a graph with time.  ... 
doi:10.1101/460964 fatcat:fcgfxaoiufgvrj3pft63bpwwtq

Graphlet Laplacians for topology-function and topology-disease relationships

2019 Bioinformatics  
Local wiring patterns are typically quantified by counting how often a node touches different graphlets (small, connected, induced sub-graphs).  ...  Finally, diffusing pan-cancer gene mutation scores based on different Graphlet Laplacians, we find complementary sets of cancer-related genes.  ...  Here, we will focus on generalizing the diffusion kernel to graphlet based diffusion kernel.  ... 
doi:10.1093/bioinformatics/btz455 pmid:31192358 fatcat:v6tf6dueonf33a2fa5kvtxplye

Kernel-Based Models for Influence Maximization on Graphs based on Gaussian Process Variance Minimization [article]

Salvatore Cuomo and Wolfgang Erb and Gabriele Santin
2021 arXiv   pre-print
In this work, we introduce and investigate a novel model for influence maximization (IM) on graphs using ideas from kernel-based approximation, Gaussian process regression, and the minimization of a corresponding  ...  Compared to stochastic models in this field that rely on costly Monte-Carlo simulations, our model allows for a simple and cost-efficient update strategy to compute optimal influencing nodes on a graph  ...  In this work, we focus on the analysis of kernel-based models for the problem of Influence Maximization (IM) on graphs.  ... 
arXiv:2103.01575v1 fatcat:5h3l5bjtvvf25p4pnizm56xyua

Angiogenesis-Associated Crosstalk Between Collagens, CXC Chemokines, and Thrombospondin Domain-Containing Proteins

Corban G. Rivera, Joel S. Bader, Aleksander S. Popel
2011 Annals of Biomedical Engineering  
Compounds that inhibit angiogenesis represent potential therapeutics for many diseases.  ...  We built on a graph theoretic approach to identify proteins that may represent conduits of crosstalk between protein families.  ...  The authors would like to thank Emmanouil Karagiannis for helpful discussions at the initial stage of the project.  ... 
doi:10.1007/s10439-011-0325-2 pmid:21590489 pmcid:PMC3150481 fatcat:pnv3bvqjwfcytplq4ounjqph6u

Network Traffic Prediction based on Diffusion Convolutional Recurrent Neural Networks

Davide Andreoletti, Sebastian Troia, Francesco Musumeci, Silvia Giordano, Guido Maier, Massimo Tornatore
2019 IEEE INFOCOM 2019 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)  
In this paper, we employ a recently-proposed graph-based ML algorithm, the Diffusion Convolutional Recurrent Neural Network (DCRNN), to forecast traffic load on the links of a real backbone network.  ...  The main novelty of these techniques relies on their ability to learn a representation of each node of the graph considering both its properties (e.g., features) and the structure of the network (e.g.,  ...  At a high-level, these methods are based on filtering operations designed to be suitable for graphs.  ... 
doi:10.1109/infcomw.2019.8845132 dblp:conf/infocom/AndreolettiT0GM19 fatcat:6gh4xg2rjvhu7gxmcvtagjj2b4

Network Infusion to Infer Information Sources in Networks

Soheil Feizi, Muriel Medard, Gerald Quon, Manolis Kellis, Ken Duffy
2018 IEEE Transactions on Network Science and Engineering  
Here, we propose a path-based network diffusion kernel which considers edge-disjoint shortest paths among pairs of nodes in the network and can be computed efficiently for both homogeneous and heterogeneous  ...  We apply NI to several synthetic networks and compare its performance to centrality-based and distance-based methods for Erdös-Rényi graphs, power-law networks, symmetric and asymmetric grids.  ...  (b) Likelihood scores based on the SI diffusion model. (c) A graph considered in Remark 2. (d) Likelihood scores based on the path-based network diffusion kernel.  ... 
doi:10.1109/tnse.2018.2854218 fatcat:2quwhmi2lja6tn6cwmrr6vwoe4
« Previous Showing results 1 — 15 out of 2,125 results