Background: Although targeted drugs have contributed to impressive advances in the treatment of cancer patients, their clinical benefits on tumor therapies are greatly limited due to intrinsic and acquired resistance of cancer cells against such drugs. Drug combinations synergistically interfere with protein networks to inhibit the activity level of carcinogenic genes more effectively, and therefore play an increasingly important role in the treatment of complex disease. Results: In this paper, we combined the drug similarity network, protein similarity network and known drug-protein associations into a drug-protein heterogenous network. Next, we ran random walk with restart (RWR) on the heterogenous network using the combinatorial drug targets as the initial probability, and obtained the converged probability distribution as the feature vector of each drug combination. Taking these feature vectors as input, we trained a gradient tree boosting (GTB) classifier to predict new drug combinations. We conducted performance evaluation on the widely used drug combination data set derived from the DCDB database. The experimental results show that our method outperforms seven typical classifiers and traditional boosting algorithms. Conclusions: The heterogeneous network-derived features introduced in our method are more informative and enriching compared to the primary ontology features, which results in better performance. In addition, from the perspective of network pharmacology, our method effectively exploits the topological attributes and interactions of drug targets in the overall biological network, which proves to be a systematic and reliable approach for drug discovery.

The ability to perceive and regulate emotion is a key component of cognition that is often disrupted by disease. Current neuroimaging studies regarding emotion regulation have implicated a number of cortical regions and identified several EEG features of interest, including the late positive potential and frontal asymmetry. Unfortunately, currently applied methods generally lack in the resolution necessary to capture focal cortical activity and explore the causal interactions between brain regions. In this paper, electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) data were simultaneously recorded from 20 subjects undergoing emotion processing and regulation tasks. Cortical activity with high-spatiotemporal resolution and accuracy was reconstructed using a novel multimodal EEG/fMRI integration method. A detailed causal brain network associated with emotion processing and regulation was then identified, and the network changes that facilitate different emotion conditions were investigated. The cortical activity of the ventrolateral prefrontal (VLPFC) and posterior parietal cortices depicted conditionally-sensitive spike and wave patterns evidenced in inter-regional communication. The VLPFC was found to behave as a main network source, with conditionally-specific interactions supporting emotional shifts. The results provide unique insight into the cortical activity that supports emotional perception and regulation, the origins of known EEG phenomena, and the manner in which brain regions coordinate to affect behavior.

In order to detect hearing loss more efficiently and accurately, this study proposed a new method based on fractional Fourier transform (FRFT). Three-dimensional volumetric magnetic resonance images were obtained from 15 patients with left-sided hearing loss (LHL), 20 healthy controls (HC), and 14 patients with right-sided hearing loss (RHL). Twenty-five FRFT spectrums were reduced by principal component analysis with thresholds of 90%, 95%, and 98%, respectively. The classifier is the single-hidden-layer feed-forward neural network (SFN) trained by the Levenberg–Marquardt algorithm. The results showed that the accuracies of all three classes are higher than 95%. In all, our method is promising and may raise interest from other researchers.

Stereo vision is an important branch of the research area in computer vision. Among the techniques of stereo vision, binocular stereo vision which is based on processing two images remains a research hotspot. Binocular stereo vision directly simulates the manner of human eyes observing one scene from two different viewpoints. By using the principle of triangulation, the disparities of a number of 3D points mapped to pixels in two images are computed. Then the visual information of depth is also recovered. The object surface shape can be acquired using these disparities. In this paper, a pair of common web cameras is used to collect images. Based on OpenCV, the calibration algorithm of stereo vision is achieved. Stereo rectify and stereo matching algorithm are also rapidly and efficiently implemented. Finally, the depth information of object is obtained.