基于多结构深度学习的蛋白质模型细化方法

为了进一步改善AlphaFold2蛋白质结构模型的质量,本文提出了一种基于深度学习捕捉多结构之间互补信息的蛋白质模型细化方法MSDRefine.首先,MSDRefine从初始结构出发,搜索多序列比对信息并提取位置特异性打分矩阵和协方差矩阵;同时从多个结构中提取残基的LDDT、USR、结构谱等特征.其次,设计了一个深度残差神经网络,学习多个结构间的互补信息来预测蛋白质残基间的距离分布.最后,将距离分布转化为势能函数用于能量极小化的模型细化.在150个测试蛋白上,MSDRefine在不依赖于多结构信息的条件下,细化模型的TM-score相比于DeepRefiner和GNNRefine分别提升了8.8%和5.7%.在47个CAMEO蛋白上,MSDRefine融合了AlphaFold2和RoseTTAFold的结构信息,大幅度提升了初始结构的精度,并优于AlphaFold2模型.

Structural damage detection method based on information fusion technique

Multi-source information fusion （MSIF） is imported into structural damage diagnosis methods to improve the validity of damage detection. After the introduction of the basic theory, the function model, classifications and mathematical methods of MSIF, a structural damage detection method based on MSIF is presented, which is to fuse two or more damage character vectors from different structural damage diagnosis methods on the character-level. In an experiment of concrete plates, modal information is measured and analyzed. The structural damage detection method based on MSIF is taken to localize cracks of concrete plates and it is proved to be effective. Results of damage detection by the method based on MSIF are compared with those from the modal strain energy method and the flexibility method. Damage, which can hardly be detected by using the single damage identification method, can be diagnosed by the damage detection method based on the character-level MSIF technique. Meanwhile multi-location damage can be identified by the method based on MSIF. This method is sensitive to structural damage and different mathematical methods for MSIF have different preconditions and applicabilities for diversified structures. How to choose mathematical methods for MSIF should be discussed in detail in health monitoring systems of actual structures.

Multi-broker architecture for large-scale dynamic heterogeneous information integration

In order to realize interoperability to a large number of autonomous and heterogeneous information sources with high efficiency, an agent-based multi-broker architecture （AMA）-HustEven, is constructed. A group of broker agents are designed to provide brokering services in a peer-to-peer （P2P） manner for the non- broker agents （user agents, resource agents, query agents）. Thus, the scalability and robustness of the system are enhanced. Ontology is also used by the broker agents for facilitating interoperability among all the agents in HustEven. Unlike any other AMAs, an interdomain ontology is built in this system to represent the relationships among the common concepts in the innerdomain ontologies. Therefore, a broker forwards the queries only to the other related brokers according to the interdomain ontology and the communication overhead among the brokers is reduced. Obviously, the application of the interdomain ontology enables a broker to fully take advantage of the multi-broker architecture. The experimental results show that the HustEven performs more efficiently than any other existing systems.

Towards a multilingual, multimedia and multimodal digital library platform

The China-US Million Book Digital Library Project （Million Book Project） is an intemational cooperation program between China and the US. However, one million digitized books are considered not to be the ultimate goal of the project, but a first step towards universal access to human knowledge. In particular, there are four challenges about the new way to analyze, process, operate, visualize and interact with digital media resource in this library. To tackle these challenges, North China Centre of Million Book Project （in Chinese Academy of Sciences） has initiated several innovative research projects in areas such as multimedia content analysis and retrieval, bilingual services, multimodal information presentation, and knowledge-based organization and services. In this keynote speech, we simply review our work in these areas, and argue that by technological cooperation with these innovation research topics, the project will develop a top-level digital library platform for the million book library.

Development of 57 Novel Polymorphic Microsatellite Markers in Half-Smooth Tongue Sole(Cynoglossus semilaevis)

Half-smooth tongue sole (Cynoglossus semilaevis) is a promising species for aquaculture in China.The wild population of C. semilaevis is under threat from environmental factors. Microsatellite markers are very suitable for assessing genetic diversity. Four microsatellite-enriched libraries of half smooth tongue sole (Cynoglossus semilaevis) were constructed,from which 57 polymorphic microsatellites were isolated and characterized.The polymorphism of these microsatellites was assessed by genotyping in 30 individual fish.The number of alleles ranged from 2 to 11, with an average of 4.614 alleles per locus.The values of observed and expected heterozygosities ranged from 0.1000 to 1.0000 and from 0.0966 to 0.8847 respectively. Polymorphism information content (PIC) ranged from 0.0905 to 0.862.These markers would be useful for population structure assessment,genetic linkage map construction and parentage analysis for this species.