DeepGO: predicting protein functions from sequence and interactions using a deep ontology-aware classifier.

Motivation: A large number of protein sequences are becoming available through the application of novel high-throughput sequencing technologies. Experimental functional characterization of these proteins is time-consuming and expensive, and is often only done rigorously for few selected model organisms. Computational function prediction approaches have been suggested to fill this gap. The functions of proteins are classified using the Gene Ontology (GO), which contains over 40 000 classes. Additionally, proteins have multiple functions, making function prediction a large-scale, multi-class, multi-label problem. Results: We have developed a novel method to predict protein function from sequence. We use deep learning to learn features from protein sequences as well as a cross-species protein-protein interaction network. Our approach specifically outputs information in the structure of the GO and utilizes the dependencies between GO classes as background information to construct a deep learning model. We evaluate our method using the standards established by the Computational Assessment of Function Annotation (CAFA) and demonstrate a significant improvement over baseline methods such as BLAST, in particular for predicting cellular locations. Availability and implementation: Web server: http://deepgo.bio2vec.net, Source code: https://github.com/bio-ontology-research-group/deepgo. Contact: robert.hoehndorf@kaust.edu.sa. Supplementary information: Supplementary data are available at Bioinformatics online.

Commercial and Plant Extract Denture Cleansers in Prevention of Candida albicans Growth on Soft Denture Reliner: In Vitro Study.

OBJECTIVE: To evaluate and compare the efficacy of two plant extracts and two commercially available denture cleansers against candida albicans adherent to soft denture reline material. MATERIALS AND METHODS: In this study 60 specimens of soft denture reliner material specimens were fabricated with dimensions 10x10x2 mm. The sterile specimens were inoculated by immersion in Sabourand broth containing Candida albicans for 16 hours at 37°C in an incubator. Then the specimens were washed and immersed in denture cleansers which were divided into group five groups from Group I-V for CD Clean(®), Nigella sativa, thyme essential oil, Fittydent(®) and distilled water respectively, for 8 hours at room temperature. Then they were washed, fixed with methanol and stained with crystal violet. Candida cells adherent to the specimens were counted under microscope. The number of cells adherent to test samples were compared with that adherent to control. RESULTS: The effectiveness of Fittydent(®) was more than CD Clean(®) in reducing the adherent candida albicans and the difference was statically significant (p = <0.001). Both thyme essential oil and nigella sativa were almost same in effectiveness against candida albicans but the difference was not statically significant (p= 0.79). Post-hoc Tukey's test was performed which indicated that Fittydent® was the most effective amongst the denture cleansers tested in this study, followed by thyme essential oil, nigella sativa and CD Clean(®). CONCLUSION: The results of the study showed that all denture cleansers used in the study were significantly effective. The study indicated that Fittydent is more effective amongst the denture cleansers because of its mechanism of action; however the plant extracts used in this study were also significantly effective against candida albicans.