Network-based methods utilize protein-protein interaction information to identify significantly perturbed subnetworks in cancer and to propose key molecular pathways. Numerous methods have been developed, but to date, a rigorous benchmark analysis to compare the performance of existing approaches is lacking. In this paper, we proposed a novel benchmarking framework using synthetic data and conducted a comprehensive analysis to investigate the ability of existing methods to detect target genes and subnetworks and to control false positives, and how they perform in the presence of topological biases at both gene and subnetwork levels. Our analysis revealed insights into algorithmic performance that were previously unattainable. Based on the results of the benchmark study, we presented a practical guide for users on how to select appropriate detection methods and protein-protein interaction networks for cancer pathway identification, and provided suggestions for future algorithm development.

MOTIVATION: Cancer subtype classification has the potential to significantly improve disease prognosis and develop individualized patient management. Existing methods are limited by their ability to handle extremely high-dimensional data and by the influence of misleading, irrelevant factors, resulting in ambiguous and overlapping subtypes. RESULTS: To address the above issues, we proposed a novel approach to disentangling and eliminating irrelevant factors by leveraging the power of deep learning. Specifically, we designed a deep-learning framework, referred to as DeepType, that performs joint supervised classification, unsupervised clustering and dimensionality reduction to learn cancer-relevant data representation with cluster structure. We applied DeepType to the METABRIC breast cancer dataset and compared its performance to state-of-the-art methods. DeepType significantly outperformed the existing methods, identifying more robust subtypes while using fewer genes. The new approach provides a framework for the derivation of more accurate and robust molecular cancer subtypes by using increasingly complex, multi-source data. AVAILABILITY AND IMPLEMENTATION: An open-source software package for the proposed method is freely available at http://www.acsu.buffalo.edu/~yijunsun/lab/DeepType.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

This letter focuses on a modified complex-valued Markov random field (CMRF) modeling filter to improve the performance in the filtering of the synthetic aperture radar interferometric phase. In the reference CMRF modeling phase map filter, the CMRF model was employed to update residues and their neighbors. By this, the residues were reduced, and phase jumps were preserved simultaneously. However, residue reduction was still insufficient. Furthermore, incorrect model parameter estimation leads to wrong filtering in some blocks. To solve the two aforementioned problems, we propose a modified CMRF modeling filter, where the original interferogram is divided into overlapped blocks. In addition, the adaptive weighted neighbor values are used to estimate the CMRF model parameters. Both simulated and real data experiments are performed to validate this method.

In this paper, an adaptive patch-based filter for Synthetic aperture Radar (SAR) Interferometric phase in the Fourier transform complex domain is proposed. The proposed filter fully utilizes the properties of locally planar terrain phase noise model so that the noise can be suppressed according to the local level of noise. Moreover, the denoising performance of the proposed filter is further improved by an adaptive selection strategy for patch size. The experimental results show that the proposed method delivers state-of-the-art denoising performance in terms of objective criteria.

Both in quality-guide phase unwrapping algorithms and weighted minimum-norm phase unwrapping algorithms, quality maps play a crucial role in obtaining the absolute phase from the wrapped ones. In this letter, a new technique for generating quality maps based on the gray level co-occurrence matrix (GLCM) is proposed. GLCM is a classical second-order statistics method for analyzing the texture features of images. Through exploring the second-order statistics of GLCM, much useful information in the image can be exploited. According to the characteristics of the interferogram, the second-order statistic of GLCM called “difference of entropy” is used to generate the quality maps. Besides, we modified the definition of “difference of entropy” to make the statistic more suitable for the problem. Finally, the new algorithm is compared with other conventional algorithms both in the simulated and real data experiments and the results show its better performance.

In this letter, we propose an approach for multichannel spaceborne/stationary synthetic aperture radar (SAR) interferometry based on maximum a posteriori (MAP). Spaceborne/stationary SAR is a typical bistatic SAR configuration. In order to solve the phase disconnection problem while working with a low signal-to-noise ratio and a limited number of baselines as well as having large look angle variations, we use the height estimation results derived from iterative multibaseline unwrapping as the initial heights for the MAP estimation. The method presented here is highly experimental. An experiment is carried out to verify the effectiveness of the proposed approach. In this experiment, TerraSAR-X, working in the high-resolution spotlight mode with a 300-MHz bandwidth, acts as the transmitter. The receivers with three echo channels are placed on the ground to receive the reflected waveform. As proof of concept, we demonstrate the height estimation of several buildings.

Interferometric phase denoising is a crucial step of interferometric synthetic aperture radar processing flow because it has significant influence on the following steps. Traditional interferometric phase denoising algorithms have a similar drawback that they will wipe off some texture details in phase images while denoising. Nonlocal (NL) means filter, in contrast, can reach a balance between denoising and texture preserving because it utilizes the feature of recursive structures in the whole image. Taking the characteristics of interferometric phase image into consideration, this letter proposes a modified NL means filter algorithm for phase denoising. Moreover, in order to preserve texture to the biggest extent, an iterative algorithm is invented. In the end, experiments on synthetic and real data validate that this algorithm outperforms other traditional denoising methods.

In this letter, a fast backprojection algorithm (FBPA) is proposed for bistatic synthetic aperture radar imaging. For range compression, the signal recorded by the synchronization channel of the receiver on the ground is used as a matched filter to compress the echo signal. This method can reduce the requirements of satellite-orbit measurement and synchronization precision. For azimuth compression, a secondary phase correction is implemented to reduce the effect caused by the approximation involved in the FBPA. The computational complexity of the proposed algorithm is O(N2.5). The proposed algorithm is applied in a graphics processing unit and verified by simulation and real raw data.

In the traditional processing flow of interferometric synthetic aperture radar (SAR) technique, the processing of phase is conducted via two separated and successive steps, i.e., phase denoising and phase unwrapping. That is to say, first, wrapped phases without noise are generated, and then, the true phases without 2π-ambiguities are reconstructed (here and in the rest of this paper, true phase refers to the information-induced unwrapped phase without noise). Such separated steps will inevitably bring in extra estimation error because each step has necessary approximations and presumptions which do not always hold. On the contrary, in this paper, we treat phase denoising and unwrapping as a single problem of true phase recovery from observed ones. Following this methodology, an integrated phase denoising and unwrapping algorithm based upon Markov random fields (MRFs) is proposed. Taking a priori knowledge of interferometric phases into account, MRF is used to model the relationship between the elements in the random variable set including both true phases and their observations. After the model is built up, the energy function of this MRF is defined according to the local-independence property inferred from the MRF structure and then minimized to obtain the estimate of the true phase value. In the end of this paper, experiments on simulated and true phase data are conducted, and the comparison with several commonly used unwrapping methods is proposed to verify the efficiency of the proposed MRF algorithm.

The flexible geometry configuration of the bistatic synthetic aperture radar (SAR) has many advantages. However, it causes serious measurement error in the bistatic SAR system, which degrades the quality of the SAR images and the precision of the digital elevation model (DEM) obtained using stereoscopy bistatic SAR. In this paper, the influence of the scene height estimation error, trigger delay, transmitter position measurement error, receiver position measurement error, and transmission line length measurement error are analyzed. These analyses are very useful in bistatic SAR system design. The scene height estimation error, trigger delay, transmitter position measurement error, and synchronization receiver position measurement error affect both the quality of the images and the precision of the DEM obtained by stereoscopy bistatic SAR slightly. The echo receiver position measurement error and transmission line length measurement error affect the quality of the imaging only slightly, but seriously affect the precision of the DEM obtained by stereoscopy bistatic SAR. Luckily, their measurement precision can be quite satisfactory. Simulations and real bistatic experimental results verify the proposed theoretical analysis.

In the above titled paper (ibid., vol. 51, no. 8, pp. 4518-4543, Aug. 2013), some important details concerning the used data, experimental area, and cooperation partner are missing by accident. The details are presented here.

Interferometric phase denoising is a crucial step of interferometric SAR processing flow. Its performance has great effect on the following steps. Traditional interferometric phase denoising algorithms have a similar drawback that they will wipe off some texture details in the phase image at the same time of filtering noise out. Nonlocal mean filter, in contrast, can find a balance between denoising and texture preserving because it utilizes the recursive structures from the whole image. Taking the features of interferometric phase image into consideration this paper proposes a modified Non-local mean filter algorithm to solve this problem. Moreover, in order to preserve texture to the biggest extend, an iterative algorithm is invented. In the end, experiments on synthetic and real data validate that this algorithm outperforms other traditional denoising methods.

In this paper, a modified fast back projection (FBP) algorithm is proposed for Synthetic Aperture Radar (SAR) imaging. The azimuth compression of the proposed FBP is divided into sub-image process and finial image process. The secondary phase correction is used to reduce the error cause by approximation before the finial image process. The interlace sub-image grid method makes image quality uniform for all the pixel in the finial image. The applicability limitations and the sub-image two dimensions over sample method are presented. The computational complexity of the proposed FBP is O(N2.5). Simulation on GPU is given to verify the proposed method efficacious.