Similarity network fusion for aggregating data types on a genomic scale

Wang, Bo; Mezlini, Aziz M.; Demir, Feyyaz; Fiume, Marc; Tu, Zhuowen; Brudno, Michael; Haibe‐Kains, Benjamin; Goldenberg, Anna

doi:10.1038/nmeth.2810

Cited by 1,615 publications

(1,803 citation statements)

References 21 publications

Supporting

Mentioning

1,792

Contrasting

Unclassified

Order By: Relevance

“…Namely, instead of processing large-scale matrices constructed over a large number of genes, SNF method fuses much smaller matrices representing networks constructed over patients (i.e., samples), which makes the convergence faster. SNF is shown to be robust to noise and when applied on five different cancer types from TCGA database, it was shown to be effective in prediction of patient survival outcomes [131]. Proteomics This article is protected by copyright.…”

Section: The First Methods That Deals With Detection Of Contradictory mentioning

confidence: 99%

See 1 more Smart Citation

Integrative methods for analyzing big data in precision medicine

2016

View full text Add to dashboard Cite

We provide an overview of recent developments in big data analyses in the context of precision medicine and health informatics. With the advance in technologies capturing molecular and medical data, we entered the area of Big Data in biology and medicine. These data offer many opportunities to advance precision medicine.We outline key challenges in precision medicine and present recent advances in data integrationbased methods to uncover personalized information from big data produced by various omics studies. We survey recent integrative methods for disease subtyping, bio-markers discovery and drug repurposing, and list the tools that are available to domain scientists. Given the ever-growing nature of these big data, we highlight key issues that big data integration methods will face.

show abstract

Section: The First Methods That Deals With Detection Of Contradictory mentioning

confidence: 99%

“…Matrix Factorization unsupervised JIVE [130] Cancer patient stratification by integrating mRNA expression and miRNA expression data. Network-based unsupervised SNF [131] Patient subtyping by integrating patient similarity networks constructed from mRNA expression, DNA methylation and miRNA expression data.…”

Section: Databasementioning

confidence: 99%

Integrative methods for analyzing big data in precision medicine

2016

View full text Add to dashboard Cite

show abstract

“…Although some studies have and will continue to work successfully on a single omic level, recent decades have seen an ever-increasing body of work where several distinct omics datasets, including also other biological or clinical levels, are analysed conjointly using multiscale integrative methods such as SNF (similarity network fusion) [69]. This combination of levels has the potential to provide researchers with simultaneous information from several compartments of the biological system of interest, thus facilitating the modelling of the dynamic nonlinear relationships that characterise emergent properties ( phenotypes) and complex diseases.…”

Section: Multilevel Analysis: the True Revolutionmentioning

confidence: 99%

From systems biology to P4 medicine: applications in respiratory medicine

2018

View full text Add to dashboard Cite

Human health and disease are emergent properties of a complex, nonlinear, dynamic multilevel biological system: the human body. Systems biology is a comprehensive research strategy that has the potential to understand these emergent properties holistically. It stems from advancements in medical diagnostics, "omics" data and bioinformatic computing power. It paves the way forward towards "P4 medicine" ( predictive, preventive, personalised and participatory), which seeks to better intervene preventively to preserve health or therapeutically to cure diseases. In this review, we: 1) discuss the principles of systems biology; 2) elaborate on how P4 medicine has the potential to shift healthcare from reactive medicine (treatment of illness) to predict and prevent illness, in a revolution that will be personalised in nature, probabilistic in essence and participatory driven; 3) review the current state of the art of network (systems) medicine in three prevalent respiratory diseases (chronic obstructive pulmonary disease, asthma and lung cancer); and 4) outline current challenges and future goals in the field.

show abstract

“…Collaborative affinity metric fusion originates from the self-smoothing operator [27], which can robustly measure the affinity by propagating the similarities among auxiliary images when only one type of feature is utilized and is fully proposed in [19] for natural image retrieval by fusing multiple metrics. Afterwards, collaborative affinity metric fusion is utilized in genome-wide data aggregation [28] and multi-cue fusion for salient object detection [29]. In this paper, we utilize collaborative affinity metric fusion to fully incorporate the merit of multiple features introduced in Section 2 for content-based high-resolution remote sensing image retrieval (CB-HRRS-IR).…”

Section: Collaborative Affinity Metric Fusionmentioning

confidence: 99%

Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion

Zhang

Tao

et al. 2016

Remote Sensing

View full text Add to dashboard Cite

Abstract:With the urgent demand for automatic management of large numbers of high-resolution remote sensing images, content-based high-resolution remote sensing image retrieval (CB-HRRS-IR) has attracted much research interest. Accordingly, this paper proposes a novel high-resolution remote sensing image retrieval approach via multiple feature representation and collaborative affinity metric fusion (IRMFRCAMF). In IRMFRCAMF, we design four unsupervised convolutional neural networks with different layers to generate four types of unsupervised features from the fine level to the coarse level. In addition to these four types of unsupervised features, we also implement four traditional feature descriptors, including local binary pattern (LBP), gray level co-occurrence (GLCM), maximal response 8 (MR8), and scale-invariant feature transform (SIFT). In order to fully incorporate the complementary information among multiple features of one image and the mutual information across auxiliary images in the image dataset, this paper advocates collaborative affinity metric fusion to measure the similarity between images. The performance evaluation of high-resolution remote sensing image retrieval is implemented on two public datasets, the UC Merced (UCM) dataset and the Wuhan University (WH) dataset. Large numbers of experiments show that our proposed IRMFRCAMF can significantly outperform the state-of-the-art approaches.Keywords: high-resolution remote sensing image management; content-based high-resolution remote sensing image retrieval (CB-HRRS-IR); unsupervised feature learning; collaborative affinity metric fusion

show abstract

Similarity network fusion for aggregating data types on a genomic scale

Cited by 1,615 publications

References 21 publications

Integrative methods for analyzing big data in precision medicine

Integrative methods for analyzing big data in precision medicine

From systems biology to P4 medicine: applications in respiratory medicine

Content-Based High-Resolution Remote Sensing Image Retrieval via Unsupervised Feature Learning and Collaborative Affinity Metric Fusion

Contact Info

Product

Resources

About