Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

Search 250 million research papers

Read the abstract, see who wrote it and who cites it, and get the citation in APA, MLA, Chicago or Harvard.

About 10,000 papers for “multi-network integration”

Multi-variable integration with a neural network

D. Maître, R. Santos-Mateos · Journal of High Energy Physics · 2023

A bstract In this article we present a method for automatic integration of parametric integrals over the unit hypercube using a neural network. The method fits a neural network to the primitive of the integrand using a loss function designed to minimize the difference between multiple derivatives of the network and the function to be integrated. We apply this method to two example integrals resulting from the sector decomposition of a one-loop and two-loop scalar integrals. Our method can achieve per-mil and percent accuracy for these integrals over a range of invariant values. Once the neural network is fitted, the evaluation of the integral is between 40 and 125 times faster than the usual numerical integration method for our examples, and we expect the speed gain to increase with the complexity of the integrand.

Cited by 17Open access

Multi-variable Integration with a Neural Network

D. Maître, Roi Santos-Mateos · arXiv (Cornell University) · 2022

In this article we present a method for automatic integration of parametric integrals over the unit hypercube using a neural network. The method fits a neural network to the primitive of the integrand using a loss function designed to minimize the difference between multiple derivatives of the network and the function to be integrated. We apply this method to two example integrals resulting from the sector decomposition of a one-loop and two-loop scalar integrals. Our method can achieve per-mil and percent accuracy for these integrals over a range of invariant values. Once the neural network is fitted, the evaluation of the integral is between 40 and 125 times faster than the usual numerical integration method for our examples, and we expect the speed gain to increase with the complexity of the integrand.

Cited by 6Open access

Optimizing Network Propagation for Multi-Omics Data Integration

Konstantina Charmpi, Manopriya Chokkalingam, Ronja Johnen et al. · bioRxiv (Cold Spring Harbor Laboratory) · 2021

ABSTRACT Network propagation refers to a class of algorithms that integrate information from input data across connected nodes in a given network. These algorithms have wide applications in systems biology, protein function prediction, inferring condition-specifically altered sub-networks, and prioritizing disease genes. Despite the popularity of network propagation, there is a lack of comparative analyses of different algorithms on real data and little guidance on how to select and parameterize the various algorithms. Here, we address this problem by analyzing different combinations of network normalization and propagation methods and by demonstrating schemes for the identification of optimal parameter settings on real proteome and transcriptome data. Our work highlights the risk of a ‘topology bias’ caused by the incorrect use of network normalization approaches. Capitalizing on the fact that network propagation is a regularization approach, we show that minimizing the bias-variance tradeoff can be utilized for selecting optimal parameters. The application to real multi-omics data demonstrated that optimal parameters could also be obtained by either maximizing the agreement between different omics layers (e.g. proteome and transcriptome) or by maximizing the consistency between biological replicates. Furthermore, we exemplified the utility and robustness of network propagation on multi-omics datasets for identifying ageing-associated genes in brain and liver tissues of rats and for elucidating molecular mechanisms underlying prostate cancer progression. Overall, this work compares different network propagation approaches and it presents strategies for how to use network propagation algorithms to optimally address a specific research question at hand.

Cited by 3Open access

Multi-level integration model of supply chain network

Qiu Zhong Zhou, Quanyi Fan · 2010

To deepen the production and operation management needs, achieve the integration of manufacturing enterprises internal and external supply chain management, an ideas of multi-level supply chain network integration model was proposed. Through the detailed analysis of the material flow relationship between enterprise level, workshop level, station level, process-level organizational unit of production network in the product manufacturing process, supply chain network diagrams at all levels of production units were drawed, and a complete multi-level supply chain network integration information model was given. The model reflects not only the hierarchy of manufacturing supply chain network, and also reflects the cross-flow of materials between different layers supply chain network unit. In addition, by analyzing the applications of this model in the digital product development process, production planning, production preparation and other enterprise management, the wide application base of this model in promoting enterprise digital construction was confirmed.

Cited by 0

Physical Network Models and Multi-source Data Integration

Chen-Hsiang Yeang And, Chen-hsiang Yeang, Tommi Jaakkola · 2003

We develop a new framework for inferring models of transcriptional regulation. The models in this approach, which we call physical models, are constructed on the basis of verifiable molecular attributes of the underlying biological system. The attributes include, for example, the existence of protein-protein and protein-DNA interactions in gene regulatory processes, the directionality of signal transduction in protein-protein interactions, as well as the signs of the immediate e#ects of these interactions (e.g., whether an upstream gen activates or represses the downstream genes). Each attribute is included as a variable in the model, and the variables define a collection of annotated random graphs. Possible configurations of these variables (realizations of the underlying biological system) are constrained by the available data sources. Some of the data sources such as factor-binding data (location data) involve measurements that are directly tied to the variables in the model. Other sources such as gene knock-outs are functional in nature and provide only indirect evidence about the (physical) variables. We associate each knock-out e#ect in the deletion mutant data with a set of causal paths (molecular cascades) that could in principle explain the e#ect, resulting in aggregate constraints about the physical variables in the model. The most likely setting of all the variables is found by the max-product algorithm.

Cited by 0

Multi-network integration of location-aware and services

Zhongliang Deng, Jun Mo, Jichao Jiao et al. · 2015

With the rapid development of wireless networks, people demand more and more location services. Demand for location services and the indoor and outdoor positioning urgent problems, combined with a variety of available ubiquitous wireless signals in the urban environment, the new positioning method named Time & Code Division-Orthogonal Frequency Division Multiplexing (TC-OFDM) based on the integration of mobile broadcast networks, communication networks and BeiDou Navigation Satellite System (BDS) is proposed, also positioning technologies based on mobile communications network are discussed. Especially for the urban environmental characteristics, we made a preliminary test for the TC-OFDM system, it has given a prototype framework to meet the indoor and outdoor high-precision location services.

Cited by 0

Multi-omics Data Integration by Generative Adversarial Network

Khandakar Tanvir Ahmed, Jiao Sun, Sze Cheng et al. · bioRxiv (Cold Spring Harbor Laboratory) · 2021

Accurate disease phenotype prediction plays an important role in the treatment of heterogeneous diseases like cancer in the era of precision medicine. With the advent of high throughput technologies, more comprehensive multi-omics data is now available that can effectively link the genotype to phenotype. However, the interactive relation of multi-omics datasets makes it particularly challenging to incorporate different biological layers to discover the coherent biological signatures and predict phenotypic outcomes. In this study, we introduce omicsGAN, a generative adversarial network (GAN) model to integrate two omics data and their interaction network. The model captures information from the interaction network as well as the two omics datasets and fuse them to generate synthetic data with better predictive signals. Large-scale experiments on The Cancer Genome Atlas (TCGA) breast cancer, lung cancer, and ovarian cancer datasets validate that (1) the model can effectively integrate two omics data (e.g., mRNA and microRNA expression data) and their interaction network (e.g., microRNA-mRNA interaction network). The synthetic omics data generated by the proposed model has a better performance on cancer outcome classification and patients survival prediction compared to original omics datasets. (2) The integrity of the interaction network plays a vital role in the generation of synthetic data with higher predictive quality. Using a random interaction network does not allow the framework to learn meaningful information from the omics datasets; therefore, results in synthetic data with weaker predictive signals.

Cited by 6Open access

Optimizing network propagation for multi-omics data integration

Konstantina Charmpi, Manopriya Chokkalingam, Ronja Johnen et al. · PLoS Computational Biology · 2021

Network propagation refers to a class of algorithms that integrate information from input data across connected nodes in a given network. These algorithms have wide applications in systems biology, protein function prediction, inferring condition-specifically altered sub-networks, and prioritizing disease genes. Despite the popularity of network propagation, there is a lack of comparative analyses of different algorithms on real data and little guidance on how to select and parameterize the various algorithms. Here, we address this problem by analyzing different combinations of network normalization and propagation methods and by demonstrating schemes for the identification of optimal parameter settings on real proteome and transcriptome data. Our work highlights the risk of a 'topology bias' caused by the incorrect use of network normalization approaches. Capitalizing on the fact that network propagation is a regularization approach, we show that minimizing the bias-variance tradeoff can be utilized for selecting optimal parameters. The application to real multi-omics data demonstrated that optimal parameters could also be obtained by either maximizing the agreement between different omics layers (e.g. proteome and transcriptome) or by maximizing the consistency between biological replicates. Furthermore, we exemplified the utility and robustness of network propagation on multi-omics datasets for identifying ageing-associated genes in brain and liver tissues of rats and for elucidating molecular mechanisms underlying prostate cancer progression. Overall, this work compares different network propagation approaches and it presents strategies for how to use network propagation algorithms to optimally address a specific research question at hand.

Cited by 16Open access

METABOLIC-INFORMED NEURAL NETWORK FOR MULTI-OMICS DATA INTEGRATION

Tazza, Gabriele, Moro, Francesco; id_orcid 0000-0003-3683-187X · VU Research Portal · 2024

Understanding cellular behavior requires knowledge of both metabolism and its regulation. While omics data provides clues about cellular activity, integrating it with traditional models (GEMs) can be challenging. Conversely, machine learning (ML) models learn directly from data but lack a mechanistic foundation. Recently, a new framework to embed a GEM in a neural network has been proposed, opening the door for developing of hybrid models that combine the strengths of mechanistic and data-driven approaches. In this work, we present a novel Metabolic-Informed Neural Network (MINN) that integrates also multi-omics data as inputs. We apply this MINN to predict metabolic fluxes in Escherichia coli under different growth rates and gene knockouts. We demonstrate that, while the measured fluxes lie outside the feasible space of the GEM, incorporating this information helps prevent over-fitting, a common challenge in ML with limited data.

Cited by 1

An Approach to Multi-Protocol Integration of Home Network

Ping Chen · 2007

The competition of a number of home network protocols emerge as obstacle to development of home network. This paper introduces an approach to multi-protocol integration, and discusses its reasonable trade-off between interoperability and viability. This approach adopts UPnP as core network protocol, and wraps other home network protocols into UPnP devices respectively. Based on such an approach, a reference home gateway design, which connects SJ/T 11314-2005 wireless protocol to the UPnP core network, is also presented in this paper.

Cited by 0

Study on Security Protection Technology of Multi-Network Integration

Sheng Jin, Jie Liu, Lei Wang et al. · 2020

With the wide application of information technology, the network architecture presents heterogeneous characteristic. As different security requirements, how to realize connection and security management of heterogeneous networks has become an inevitable challenge. Accordingly, it is important to study information security technology in the situation of multi-network integration. Based on the technologies of security supervision, physical dependence and network virtualization, this paper discusses the methods of security protection for multi-network integration. Furthermore, strict management regulations are established to improve the multi-network security performance. The above-mentioned methods were expounded and have been applied to a certain multi-network structure. The result indicates that the security protection scheme presented in this paper is effective and feasible.

Cited by 1

Multi-Affinity Network integration based on multi-omics data for tumor Stratification

Zhensheng Sun, Feng Li, Shengjun Li et al. · Research Square · 2022

Abstract Tumor stratification facilitates clinical applications such as diagnosis and targeted treatment of patients. Sufficient multi-omics data have facilitated the study of tumor stratification, and many omics fusion methods have been proposed. However, most methods require that the omics data must contain the same samples. In this study, we propose a Multi-Affinity Network integration based on multi-omics data for tumor Stratification, call MANS. MANS addresses the limitation that omics data fusion must contain identical samples. Another novelty is that the subdivision of a single cancer type into a corresponding cancer subtype is unsupervised. Firstly, MANS constructs affinity networks based on the calculated similarity matrices between genes. Then we integrate multi-omics information by performing biased random walks in multiple affinity networks to obtain the neighborhood relationships of genes. Finally, the patient feature is constructed by using the somatic mutation profile. We classify the pan-cancer by lightGBM algorithm with an AUC value of approximately 0.94. The cancer is further subdivided into subtypes by unsupervised clustering algorithm. Among the 12 cancer types, MANS identifies significant differences in patient survival for subtypes of 10 cancer types. In conclusion, MANS is a potent precision oncology tool.

Cited by 0Open access