It is expensive and time-consuming to measure oral bioavailability using traditional methods,and existing machine learning methods show lower accuracy.To solve the problems,a classification method of human oral bioavailability based on stacked autoencoder(SAE) was presented.Filtered features of molecular are combined with the model of SAE to classify human oral bioavailability.Experimental results show that the deep network can study more essential features of molecules comparing with other shallow learning models like support vector machine and artificial neural network,and the combination of screened 2D and 3D molecular features achieves better classification effect of oral bioavailability,with a average accuracy value of 83%,a sensitivity(SE) value of 94% and a specificity(SP) value of 49%.

Bioinformatics visualization is an important approach to exploit the information behind the massive biological data.In view of the challenges like massive data size,accurate visualization effect and diversified visualization requirements,we presented a bioinformatics visualization software based on SVG,called SBV (SVG for Bioinformatics Visuali-zation).SBV takes advantages of scalability of SVG and customizable performance form of DOM and CSS to draw a variety of bioinformatics maps.It is a maneuverable integrative bioinformatics visualization platform supporting most of existing bioinformatics visualization requirements.The software has been open source in Github,which provides good foundation for the further development.

Since the Linked Data project arises,abundant open linked data have been published on the semantic Web,which contain plentiful biological pathway datasets.To make these data be utilized effectively for the biological scientists,this paper conducted the research on heterogeneous biological pathway data visualization system based on Linked Data,proposed a biological pathway visualization model,and then designed visualization layout strategies.After that,this paper utilized the dynamic mapping of identifiers to implement the browsing of heterogeneous biological pathway data,and finally developed a biological pathway visualization system called BioPW+.Primarily,BioPW+ retrieves the essential information with respect to the biological pathway by means of the semantic Web technologies and SPARQL queries.Then,through the Open PHACTS platform,it acquires the detailed information of the pathway.Finally,it illustrates the biological pathway on the Web page by employing the force-directed layout and Sankey layout,and furnishes various interoperable functions.Not like the existing tools that only retrieve data from single data source,BioPW+ is based on the Linked Data,and can elaborate the biological pathways with their relevant biochemical information from multiple datasets,saving large amounts of time and improving the data integrity.

The essential protein is the most important material basis for the maintenance of all life activities in the living body.With the development of high throughput technology,how to identify the essential proteins from the protein interaction network has become a hot research topic in proteomics.For most of the existing methods are only based on the information of network topology for recognition as well as high false positive of protein-protein interaction data,this paper presented the improved particle swarm algorithm to identify the essential proteins.We considered the network topology characteristics and multi-source biological attribute information to construct the high quality of the weighted networks.We also considered node links between protein to measure the essentiality of protein,and expanded the local network topology to the second-order neighbor,improving the accuracy greatly.We proposed a measure of the overall top-pindex,which reduces the computational complexity.The experimental results on standard data sets show that our algorithm is superior to other algorithms in comparison with other classical algorithms,which can identify more proteins with higher accuracy.

Proteins are the essential molecules to accomplish important biological activities.It will greatly promote the advance of life science research and application to accurately grasp their functions.A tremendous amount of protein sequences has been generated with the development of high-throughput techniques.Thus,prediction of large-scale protein functions with computation technology has become one of the key tasks in bioinformatics today.Currently,the prediction method based on protein-protein interaction network,which is a research hotspot of protein function prediction,still has shortcomings at such aspects as reducing the impact of data noise,making full use of network topology characteristics,integrating multi-source data,and so on.In this paper,the Bi-Weighted Vote(BIWV) algorithm was proposed to predict protein functions,which combines the global topological similarity produced by Random Walk with Resistance (RWS) and the semantic similarity between terms.In addition,the Bi-Weighted Vote algorithm with pathway (BiWV-P) was presented by integrating the information of biological pathway.By using the data sets of saccharomyces cerevi-siae and homo sapiens,experiments were performed to compare TMC,UBiRW,ProHG,BiWV and BiWV-P.The experimental results indicate that BiWV algorithm and BiWV-P algorithm can predict protein functions effectively,and achieve higher micro-accuracy and micro-F1 than other algorithms in many data sets.

Protein complexes play significant roles in biological processes.The detection of protein complexes from available protein-protein interaction (PPI) networks is one of the most challenging tasks in the post-genome era.Seed expansion method is an effective clustering technique for overlapping protein complexes detection from PPI networks.However,existing methods are usually faced with two problems.One is that they only consider link density between direct neighbors of nodes in a network in the step of seed selection,which is not enough to indicate the importance of nodes in local subgraphs consisting of their neighborhoods.The other is that candidate nodes are assumed to be independent from each other,ignoring the impact of candidate nodes’ order on clustering in the process of cluster extension.To solve the problems,this paper proposed an overlapping protein complexes detection algorithm based on assortativity,which considers 2-order neighborhood of nodes in the process of seed selection,and multiple candidate nodes are added into clusters based on assortativity in networks in the process of cluster expansion.In order to evaluate overlapping results,a new evaluation index named F-overlap was presented.Experiment results on PPI networks show that the proposed algorithm can effectively identify overlapping protein complexes.