1
|
Nie F, Cai G, Li J, Li X. Auto-Weighted Multi-View Learning for Image Clustering and Semi-Supervised Classification. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2018; 27:1501-1511. [PMID: 28945592 DOI: 10.1109/tip.2017.2754939] [Citation(s) in RCA: 129] [Impact Index Per Article: 21.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/07/2023]
Abstract
Due to the efficiency of learning relationships and complex structures hidden in data, graph-oriented methods have been widely investigated and achieve promising performance. Generally, in the field of multi-view learning, these algorithms construct informative graph for each view, on which the following clustering or classification procedure are based. However, in many real-world data sets, original data always contain noises and outlying entries that result in unreliable and inaccurate graphs, which cannot be ameliorated in the previous methods. In this paper, we propose a novel multi-view learning model which performs clustering/semi-supervised classification and local structure learning simultaneously. The obtained optimal graph can be partitioned into specific clusters directly. Moreover, our model can allocate ideal weight for each view automatically without explicit weight definition and penalty parameters. An efficient algorithm is proposed to optimize this model. Extensive experimental results on different real-world data sets show that the proposed model outperforms other state-of-the-art multi-view algorithms.
Collapse
|
2
|
Liu Q, Sun Y, Wang C, Liu T, Tao D. Elastic Net Hypergraph Learning for Image Clustering and Semi-Supervised Classification. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2017; 26:452-463. [PMID: 28113763 DOI: 10.1109/tip.2016.2621671] [Citation(s) in RCA: 14] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
Graph model is emerging as a very effective tool for learning the complex structures and relationships hidden in data. In general, the critical purpose of graph-oriented learning algorithms is to construct an informative graph for image clustering and classification tasks. In addition to the classical K-nearest-neighbor and r-neighborhood methods for graph construction, l1-graph and its variants are emerging methods for finding the neighboring samples of a center datum, where the corresponding ingoing edge weights are simultaneously derived by the sparse reconstruction coefficients of the remaining samples. However, the pairwise links of l1-graph are not capable of capturing the high-order relationships between the center datum and its prominent data in sparse reconstruction. Meanwhile, from the perspective of variable selection, the l1 norm sparse constraint, regarded as a LASSO model, tends to select only one datum from a group of data that are highly correlated and ignore the others. To simultaneously cope with these drawbacks, we propose a new elastic net hypergraph learning model, which consists of two steps. In the first step, the robust matrix elastic net model is constructed to find the canonically related samples in a somewhat greedy way, achieving the grouping effect by adding the l2 penalty to the l1 constraint. In the second step, hypergraph is used to represent the high order relationships between each datum and its prominent samples by regarding them as a hyperedge. Subsequently, hypergraph Laplacian matrix is constructed for further analysis. New hypergraph learning algorithms, including unsupervised clustering and multi-class semi-supervised classification, are then derived. Extensive experiments on face and handwriting databases demonstrate the effectiveness of the proposed method.
Collapse
|
4
|
Bellmunt J, Selvarajah S, Rodig S, Salido M, de Muga S, Costa I, Bellosillo B, Werner L, Mullane S, Fay AP, O'Brien R, Barretina J, Minoche AE, Signoretti S, Montagut C, Himmelbauer H, Berman DM, Kantoff P, Choueiri TK, Rosenberg JE. Identification of ALK gene alterations in urothelial carcinoma. PLoS One 2014; 9:e103325. [PMID: 25083769 PMCID: PMC4118868 DOI: 10.1371/journal.pone.0103325] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2014] [Accepted: 06/26/2014] [Indexed: 12/18/2022] Open
Abstract
Background Anaplastic lymphoma kinase (ALK) genomic alterations have emerged as a potent predictor of benefit from treatment with ALK inhibitors in several cancers. Currently, there is no information about ALK gene alterations in urothelial carcinoma (UC) and its correlation with clinical or pathologic features and outcome. Methods Samples from patients with advanced UC and correlative clinical data were collected. Genomic imbalances were investigated by array comparative genomic hybridization (aCGH). ALK gene status was evaluated by fluorescence in situ hybridization (FISH). ALK expression was assessed by immunohistochemistry (IHC) and high-throughput mutation analysis with Oncomap 3 platform. Next generation sequencing was performed using Illumina Genome Analyzer IIx, and Illumina HiSeq 2000 in the FISH positive case. Results 70 of 96 patients had tissue available for all the tests performed. Arm level copy number gains at chromosome 2 were identified in 17 (24%) patients. Minor copy number alterations (CNAs) in the proximity of ALK locus were found in 3 patients by aCGH. By FISH analysis, one of these samples had a deletion of the 5′ALK. Whole genome next generation sequencing was inconclusive to confirm the deletion at the level of the ALK gene at the coverage level used. We did not observe an association between ALK CNA and overall survival, ECOG PS, or development of visceral disease. Conclusions ALK genomic alterations are rare and probably without prognostic implications in UC. The potential for testing ALK inhibitors in UC merits further investigation but might be restricted to the identification of an enriched population.
Collapse
Affiliation(s)
- Joaquim Bellmunt
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
- Hospital del Mar Research Institute-IMIM, Barcelona, Spain
- * E-mail:
| | - Shamini Selvarajah
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Scott Rodig
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Marta Salido
- Department of Pathology, Hospital del Mar Research Institute-IMIM, Barcelona, Spain
| | - Silvia de Muga
- Department of Pathology, Hospital del Mar Research Institute-IMIM, Barcelona, Spain
| | | | - Beatriz Bellosillo
- Department of Pathology, Hospital del Mar Research Institute-IMIM, Barcelona, Spain
| | - Lillian Werner
- Biostatistics and Computational Biology, Harvard Medical School, Dana-Farber Cancer Institute, Boston, Massachusetts, United States of America
| | - Stephanie Mullane
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - André P. Fay
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Robert O'Brien
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Jordi Barretina
- Broad Institute, Cambridge, Massachusetts, United States of America
| | - André E. Minoche
- Max Planck Institute for Molecular Genetics, Berlin, Germany
- Centre for Genomic Regulation (CRG), Barcelona, Spain
- Universitat Pompeu Fabra, Barcelona, Spain
| | - Sabina Signoretti
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Clara Montagut
- Hospital del Mar Research Institute-IMIM, Barcelona, Spain
| | - Heinz Himmelbauer
- Centre for Genomic Regulation (CRG), Barcelona, Spain
- Universitat Pompeu Fabra, Barcelona, Spain
| | - David M. Berman
- Department of Pathology, Johns Hopkins University, Baltimore, Maryland, United States of America
| | - Philip Kantoff
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Toni K. Choueiri
- Bladder Cancer Center, Dana-Farber Cancer Institute/Harvard Medical School, Boston, Massachusetts, United States of America
| | - Jonathan E. Rosenberg
- Department of Medicine, Memorial Sloan-Kettering Cancer Center, New York, New York, United States of America
| |
Collapse
|