No abstract

Recent studies on face attribute transfer have achieved great success. A lot of models are able to transfer face attributes with an input image. However, they suffer from three limitations: (1) incapability of generating image by exemplars; (2) being unable to transfer multiple face attributes simultaneously; (3) low quality of generated images, such as low-resolution or artifacts. To address these limitations, we propose a novel model which receives two images of opposite attributes as inputs. Our model can transfer exactly the same type of attributes from one image to another by exchanging certain part of their encodings. All the attributes are encoded in a disentangled manner in the latent space, which enables us to manipulate several attributes simultaneously. Besides, our model learns the residual images so as to facilitate training on higher resolution images. With the help of multi-scale discriminators for adversarial training, it can even generate high-quality images with finer details and less artifacts. We demonstrate the effectiveness of our model on overcoming the above three limitations by comparing with other methods on the CelebA face database. A pytorch implementation is available at https://github.com/Prinsphield/ELEGANT.

Motivation: Currently there are no curative anticancer drugs, and drug resistance is often acquired after drug treatment. One of the reasons is that cancers are complex diseases, regulated by multiple signaling pathways and cross talks among the pathways. It is expected that drug combinations can reduce drug resistance and improve patients’ outcomes. In clinical practice, the ideal and feasible drug combinations are combinations of existing Food and Drug Administration-approved drugs or bioactive compounds that are already used on patients or have entered clinical trials and passed safety tests. These drug combinations could directly be used on patients with less concern of toxic effects. However, there is so far no effective computational approach to search effective drug combinations from the enormous number of possibilities.Results: In this study, we propose a novel systematic computational tool DrugComboRanker to prioritize synergistic drug combinations and uncover their mechanisms of action. We first build a drug functional network based on their genomic profiles, and partition the network into numerous drug network communities by using a Bayesian non-negative matrix factorization approach. As drugs within overlapping community share common mechanisms of action, we next uncover potential targets of drugs by applying a recommendation system on drug communities. We meanwhile build disease-specific signaling networks based on patients’ genomic profiles and interactome data. We then identify drug combinations by searching drugs whose targets are enriched in the complementary signaling modules of the disease signaling network. The novel method was evaluated on lung adenocarcinoma and endocrine receptor positive breast cancer, and compared with other drug combination approaches. These case studies discovered a set of effective drug combinations top ranked in our prediction list, and mapped the drug targets on the disease signaling network to highlight the mechanisms of action of the drug combinations.Availability and implementation: The program is available on request.Contact: stwong@tmhs.org

The Library of Integrated Network-based Cellular Signatures (LINCS) L1000 big data provide gene expression profiles induced by over 10,000 compounds, shRNAs, and kinase inhibitors using the L1000 platform. We developed csNMF, a systematic compound signature discovery pipeline covering from raw L1000 data processing to drug screening and mechanism generation. The csNMF pipeline demonstrated better performance than the original L1000 pipeline. The discovered compound signatures of breast cancer were consistent with the LINCS KINOMEscan data and were clinically relevant. The csNMF pipeline provided a novel and complete tool to expedite signature-based drug discovery leveraging the LINCS L1000 resources.

Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep learning technologies. Recently, graph convolution network (GCN) is leveraged to boost the performance of multi-label recognition. However, what is the best way for label correlation modeling and how feature learning can be improved with label system awareness are still unclear. In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects. Firstly, we model the label correlations by superimposing label graph built from statistical co-occurrence information into the graph constructed from knowledge priors of labels, and then multi-layer graph convolutions are applied on the final superimposed graph for label embedding abstraction. Secondly, we propose to leverage embedding of the whole label system for better representation learning. In detail, lateral connections between GCN and CNN are added at shallow, middle and deep layers to inject information of label system into backbone CNN for label-awareness in the feature learning process. Extensive experiments are carried out on MS-COCO and Charades datasets, showing that our proposed solution can greatly improve the recognition performance and achieves new state-of-the-art recognition performance.

Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics. Through investigating this general optimization dynamics, we analyze the behavior of SGD on escaping from minima and its regularization effects. A novel indicator is derived to characterize the efficiency of escaping from minima through measuring the alignment of noise covariance and the curvature of loss function. Based on this indicator, two conditions are established to show which type of noise structure is superior to isotropic noise in term of escaping efficiency. We further show that the anisotropic noise in SGD satisfies the two conditions, and thus helps to escape from sharp and poor minima effectively, towards more stable and flat minima that typically generalize well. We systematically design various experiments to verify the benefits of the anisotropic noise, compared with full gradient descent plus isotropic diffusion (i.e. Langevin dynamics).

No abstract

The morphology of TiO2 nanotubes with nanowires directly formed on top (designed as TiO2 NTWs) would be a promising nanostructure in fabricating photoelectrochemical solar cells for its advantages in charge separation, electronic transport, and light harvesting. In this study, a TiO2 NTWs array film was prepared by a simple anodization method. The formation of CdS, CdSe, and ZnS quantum dots (QDs) sensitized TiO2 NTWs photoelectrode was carried out by successive ionic layer adsorption. The as-prepared materials were characterized by scanning electron microscopy, high-resolution transmission electron microscopy, and X-ray diffraction. Our results indicate that the nanocrystals have effectively covered both inner and outer surfaces of TiO2 NTWs array. The interfacial structure of QDs/TiO2 was also investigated for the first time in our experiment, and the growth interface when annealed to 300 °C was verified. Under AM 1.5G illumination, we found the photoelectrodes have an optimum short-circuit photocurrent density of 4.30 mA/cm2 and corresponding energy conversation efficiency of 2.408%, which is 28 times higher than that of a bare TiO2 NTWs array. The excellent photoelectrochemical properties of our photoanodes suggest that the TiO2 NTWs array films (2.6–2.8 μm) cosensitized by CdS, CdSe, and ZnS nanoclusters have potential applications in solar cells.