Hashing-based approximate nearest neighbor (ANN) search in huge databases has become popular due to its computational and memory efficiency. The popular hashing methods, e.g., Locality Sensitive Hashing and Spectral Hashing, construct hash functions based on random or principal projections. The resulting hashes are either not very accurate or are inefficient. Moreover, these methods are designed for a given metric similarity. On the contrary, semantic similarity is usually given in terms of pairwise labels of samples. There exist supervised hashing methods that can handle such semantic similarity, but they are prone to overfitting when labeled data are small or noisy. In this work, we propose a semi-supervised hashing (SSH) framework that minimizes empirical error over the labeled set and an information theoretic regularizer over both labeled and unlabeled sets. Based on this framework, we present three different semi-supervised hashing methods, including orthogonal hashing, nonorthogonal hashing, and sequential hashing. Particularly, the sequential hashing method generates robust codes in which each hash function is designed to correct the errors made by the previous ones. We further show that the sequential learning paradigm can be extended to unsupervised domains where no labeled pairs are available. Extensive experiments on four large datasets (up to 80 million samples) demonstrate the superior performance of the proposed SSH methods over state-of-the-art supervised and unsupervised hashing techniques.

Long non-coding RNAs (lncRNAs) play crucial roles in complex disease diagnosis, prognosis, prevention, and treatment, but only a small portion of lncRNA-disease associations have been experimentally verified. Various computational models have been proposed to identify lncRNA-disease associations by integrating heterogeneous data sources. However, existing models generally ignore the intrinsic structure of data sources or treat them as equally relevant, while they may not be. To accurately identify lncRNA-disease associations, we propose a Matrix Factorization based LncRNA-Disease Association prediction model (MFLDA in short). MFLDA decomposes data matrices of heterogeneous data sources into low-rank matrices via matrix tri-factorization to explore and exploit their intrinsic and shared structure. MFLDA can select and integrate the data sources by assigning different weights to them. An iterative solution is further introduced to simultaneously optimize the weights and low-rank matrices. Next, MFLDA uses the optimized low-rank matrices to reconstruct the lncRNA-disease association matrix and thus to identify potential associations. In five-fold cross validation experiments to identify verified lncRNA-disease associations, MFLDA achieves an Area Under the receiver operating characteristic Curve (AUC) of 0.7408, at least 3% higher than those given by state-of-the-art data fusion based computational models. An empirical study on identifying masked lncRNA-disease associations again shows that MFLDA can identify potential associations more accurately than competing models. A case study on identifying lncRNAs associated with breast, lung, and stomach cancers show that 38 out of 45 (84%) associations predicted by MFLDA are supported by recent biomedical literature and further proves the capability of MFLDA in identifying novel lncRNA-disease associations. MFLDA is a general data fusion framework, and as such it can be adopted to predict associations between other biological entities. The source code for MFLDA is available at: http://mlda.swu.edu.cn/codes.php?name=MFLDA. gxyu@swu.edu.cn Supplementary data are available at Bioinformatics online.

Extracting road networks from very-high-resolution (VHR) aerial and satellite imagery has been a long-standing problem. In this article, a neural-dynamic tracking framework is proposed to extract road networks based on deep convolutional neural networks (DNN) and a finite state machine (FSM). Inspired by autonomous mobile systems, the authors train a DNN to recognize the pattern of input data, which is an image patch extracted in a detection window centred at the current location of the tracker. The pattern is predefined according to the environment and associated with the states in the FSM. A vector-guided sampling method is proposed to generate the training data set for the DNN, which extracts massive image-direction pairs from the imagery and existing vector road maps. In the tracking procedure, the size of the detection window is determined by a fusion strategy and the extracted image patches represent the orientation features of the road (local environment) that can be recognized by the trained DNN. The reactive unit in FSM associates states with behaviours of the tracker while continually modifying the orientation to follow the road and generating a sequence of states and locations. In this way, our framework combines the DNN and FSM. DNN acts as a key component to recognize patterns from a complex and changing environment; FSM translates the recognized patterns to states and controls the behaviour of the tracker. The results illustrate that our approach is more accurate and efficient than the traditional ones.