scholarly journals SkipGNN: predicting molecular interactions with skip-graph networks

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Kexin Huang ◽  
Cao Xiao ◽  
Lucas M. Glass ◽  
Marinka Zitnik ◽  
Jimeng Sun
Keyword(s):  
Neural Network ◽  
Molecular Interactions ◽  
Biological Networks ◽  
Interaction Network ◽  
Interaction Networks ◽  
Original Graph ◽  
Neural Network Approach ◽  
Molecular Interaction Networks ◽  
Current Graph ◽  
Fusion Scheme

AbstractMolecular interaction networks are powerful resources for molecular discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep learning on graphs has dramatically advanced the prediction prowess, current graph neural network (GNN) methods are mainly optimized for prediction on the basis of direct similarity between interacting nodes. In biological networks, however, similarity between nodes that do not directly interact has proved incredibly useful in the last decade across a variety of interaction networks. Here, we present SkipGNN, a graph neural network approach for the prediction of molecular interactions. SkipGNN predicts molecular interactions by not only aggregating information from direct interactions but also from second-order interactions, which we call skip similarity. In contrast to existing GNNs, SkipGNN receives neural messages from two-hop neighbors as well as immediate neighbors in the interaction network and non-linearly transforms the messages to obtain useful information for prediction. To inject skip similarity into a GNN, we construct a modified version of the original network, called the skip graph. We then develop an iterative fusion scheme that optimizes a GNN using both the skip graph and the original graph. Experiments on four interaction networks, including drug–drug, drug–target, protein–protein, and gene–disease interactions, show that SkipGNN achieves superior and robust performance. Furthermore, we show that unlike popular GNNs, SkipGNN learns biologically meaningful embeddings and performs especially well on noisy, incomplete interaction networks.

scholarly journals CSGNN: Contrastive Self-Supervised Graph Neural Network for Molecular Interaction Prediction

2021 ◽  
Author(s):  
Chengshuai Zhao ◽  
Shuai Liu ◽  
Feng Huang ◽  
Shichao Liu ◽  
Wen Zhang
Keyword(s):  
Neural Network ◽  
Molecular Interactions ◽  
Molecular Interaction ◽  
Learning Task ◽  
Interaction Networks ◽  
Molecular Networks ◽  
Specific Domain ◽  
Interaction Prediction ◽  
Molecular Interaction Networks ◽  
Systems Identification

Molecular interactions are significant resources for analyzing sophisticated biological systems. Identification of multifarious molecular interactions attracts increasing attention in biomedicine, bioinformatics, and human healthcare communities. Recently, a plethora of methods have been proposed to reveal molecular interactions in one specific domain. However, existing methods heavily rely on features or structures involving molecules, which limits the capacity of transferring the models to other tasks. Therefore, generalized models for the multifarious molecular interaction prediction (MIP) are in demand. In this paper, we propose a contrastive self-supervised graph neural network (CSGNN) to predict molecular interactions. CSGNN injects a mix-hop neighborhood aggregator into a graph neural network (GNN) to capture high-order dependency in the molecular interaction networks and leverages a contrastive self-supervised learning task as a regularizer within a multi-task learning paradigm to enhance the generalization ability. Experiments on seven molecular interaction networks show that CSGNN outperforms classic and state-of-the-art models. Comprehensive experiments indicate that the mix-hop aggregator and the self-supervised regularizer can effectively facilitate the link inference in multifarious molecular networks.

scholarly journals A Graph Feature Auto-Encoder for the prediction of unobserved node features on biological networks

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Ramin Hasibi ◽  
Tom Michoel
Keyword(s):  
Gene Expression ◽  
Neural Networks ◽  
Gene Expression Data ◽  
Biological Networks ◽  
Molecular Interaction ◽  
Interaction Networks ◽  
Omics Data ◽  
Expression Data ◽  
Molecular Interaction Networks ◽  
Graph Neural Networks

Abstract Background Molecular interaction networks summarize complex biological processes as graphs, whose structure is informative of biological function at multiple scales. Simultaneously, omics technologies measure the variation or activity of genes, proteins, or metabolites across individuals or experimental conditions. Integrating the complementary viewpoints of biological networks and omics data is an important task in bioinformatics, but existing methods treat networks as discrete structures, which are intrinsically difficult to integrate with continuous node features or activity measures. Graph neural networks map graph nodes into a low-dimensional vector space representation, and can be trained to preserve both the local graph structure and the similarity between node features. Results We studied the representation of transcriptional, protein–protein and genetic interaction networks in E. coli and mouse using graph neural networks. We found that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further proposed a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and showed that it performs better at predicting unobserved node features than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the Graph Feature Auto-Encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach. Conclusion Our proposed Graph Feature Auto-Encoder framework is a powerful approach for integrating and exploiting the close relation between molecular interaction networks and functional genomics data.

scholarly journals Computational Intractability Law Molds the Topology of Biological Networks

2019 ◽  
Author(s):  
Ali A Atiia ◽  
Corbin Hopper ◽  
Katsumi Inoue ◽  
Silvia Vidal ◽  
Jérôme Waldispühl
Keyword(s):  
Biological Networks ◽  
Molecular Interaction ◽  
Necessary Conditions ◽  
Fitness Function ◽  
Interaction Networks ◽  
Software Adaptation ◽  
Computational Optimization ◽  
Molecular Interaction Networks ◽  
The Cost ◽  
Computational Intractability

AbstractVirtually all molecular interaction networks (MINs), irrespective of organism or physiological context, have a majority of loosely-connected ‘leaf’ genes interacting with at most 1-3 genes, and a minority of highly-connected ‘hub’ genes interacting with at least 10 or more other genes. Previous reports proposed adaptive and non-adaptive hypotheses describing sufficient but not necessary conditions for the origin of this majority-leaves minority-hubs (mLmH) topology. We modeled the evolution of MINs as a computational optimization problem which describes the cost of conserving, deleting or mutating existing genes so as to maximize (minimize) the overall number of beneficial (damaging) interactions network-wide. The model 1) provides sufficient and, assuming , necessary conditions for the emergence of mLmH as a software adaptation to circumvent computational intractability, 2) predicts the percentage number of genes having d interacting partners, and 3) when employed as a fitness function in an evolutionary algorithm, produces mLmH-possessing synthetic networks whose degree distributions match those of equal-size MINs.SummaryOur results indicate that the topology of molecular interaction networks is a selected-for software adaptation that minimizes the evolutionary cost of re-wiring the network in response to an evolutionary pressure to conserve, delete or mutate existing genes and interactions.

A fuzzy neural network approach for modeling the growth kinetics of FeB and Fe2B layers during the boronizing process

2018 ◽  
Vol 106 (6) ◽  
pp. 603 ◽  
Author(s):  
Bendaoud Mebarek ◽  
Mourad Keddam
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Fuzzy Neural Network ◽  
Treatment Time ◽  
Calculation Model ◽  
Average Error ◽  
Network Approach ◽  
Neural Network Approach ◽  
Fuzzy Neural ◽  
Kinetics Of

In this paper, we develop a boronizing process simulation model based on fuzzy neural network (FNN) approach for estimating the thickness of the FeB and Fe2B layers. The model represents a synthesis of two artificial intelligence techniques; the fuzzy logic and the neural network. Characteristics of the fuzzy neural network approach for the modelling of boronizing process are presented in this study. In order to validate the results of our calculation model, we have used the learning base of experimental data of the powder-pack boronizing of Fe-15Cr alloy in the temperature range from 800 to 1050 °C and for a treatment time ranging from 0.5 to 12 h. The obtained results show that it is possible to estimate the influence of different process parameters. Comparing the results obtained by the artificial neural network to experimental data, the average error generated from the fuzzy neural network was 3% for the FeB layer and 3.5% for the Fe2B layer. The results obtained from the fuzzy neural network approach are in agreement with the experimental data. Finally, the utilization of fuzzy neural network approach is well adapted for the boronizing kinetics of Fe-15Cr alloy.

Assessment of Self-Heating Susceptibility of Indian Coal Seams – A Neural Network Approach

2014 ◽  
Vol 59 (4) ◽  
pp. 1061-1076 ◽  
Author(s):  
D.C. Panigrahi ◽  
S.K. Ray
Keyword(s):  
Neural Network ◽  
Spontaneous Combustion ◽  
Potential Method ◽  
Oxidation Potential ◽  
Wet Oxidation ◽  
Experimental Conditions ◽  
Neural Network Approach ◽  
Indian Coal ◽  
Petrographic Analyses ◽  
Artificial Neural Network Ann

Abstract The paper addresses an electro-chemical method called wet oxidation potential technique for determining the susceptibility of coal to spontaneous combustion. Altogether 78 coal samples collected from thirteen different mining companies spreading over most of the Indian Coalfields have been used for this experimental investigation and 936 experiments have been carried out by varying different experimental conditions to standardize this method for wider application. Thus for a particular sample 12 experiments of wet oxidation potential method were carried out. The results of wet oxidation potential (WOP) method have been correlated with the intrinsic properties of coal by carrying out proximate, ultimate and petrographic analyses of the coal samples. Correlation studies have been carried out with Design Expert 7.0.0 software. Further, artificial neural network (ANN) analysis was performed to ensure best combination of experimental conditions to be used for obtaining optimum results in this method. All the above mentioned analysis clearly spelt out that the experimental conditions should be 0.2 N KMnO4 solution with 1 N KOH at 45°C to achieve optimum results for finding out the susceptibility of coal to spontaneous combustion. The results have been validated with Crossing Point Temperature (CPT) data which is widely used in Indian mining scenario.

A neural network approach to anomaly detection in spectra

1997 ◽  
Author(s):  
Daniel Benzing ◽  
Kevin Whitaker ◽  
Dedra Moore ◽  
Daniel Benzing ◽  
Kevin Whitaker ◽  
...  
Keyword(s):  
Neural Network ◽  
Anomaly Detection ◽  
Network Approach ◽  
Neural Network Approach
Sign in / Sign up

Export Citation Format

Share Document