Zhiguo Yu

Learn More
Based on the principle of one-against-one support vector machines (SVMs) multi-class classification algorithm, this paper proposes an extended SVMs method which couples adaptive resonance theory (ART) network to reconstruct a multi-class classifier. Different coupling strategies to reconstruct a multi-class classifier from binary SVM classifiers are(More)
Natural products remain the best sources of drugs and drug leads and serve as outstanding small-molecule probes to dissect fundamental biological processes. A great challenge for the natural product community is to discover novel natural products efficiently and cost effectively. Here we report the development of a practical method to survey biosynthetic(More)
We have recently isolated tirandamycin (TAM) B from Streptomyces sp. 17944 as a Brugia malayi AsnRS (BmAsnRS) inhibitor that efficiently kills the adult B. malayi parasites and does not exhibit general cytotoxicity to human hepatic cells. We now report (i) the comparison of metabolite profiles of S. sp. 17944 in six different media, (ii) identification of a(More)
Lymphatic filariasis is caused by the Brugia malayi parasite. Three new congeners of the depsipeptide WS9326A (1), WS9326C (2), WS9326D (3), and WS9326E (4), were isolated from Streptomyces sp. 9078 by using a B. malayi asparaginyl-tRNA synthetase (BmAsnRS) inhibition assay. WS9326D specifically inhibits the BmAsnRS, kills the adult B. malayi parasite, and(More)
Platensimycin (PTM) and platencin (PTN) are potent and selective inhibitors of bacterial and mammalian fatty acid synthases and have emerged as promising drug leads for both antibacterial and antidiabetic therapies. We have previously cloned and sequenced the PTM-PTN dual biosynthetic gene cluster from Streptomyces platensis MA7327 and the PTN biosynthetic(More)
In this work, a new strategy for achieving efficient p-type doping in high bandgap nitride semiconductors to overcome the fundamental issue of high activation energy has been proposed and investigated theoretically, and demonstrated experimentally. Specifically, in an AlxGa(1-x)N/GaN superlattice structure, by modulation doping of Mg in the AlxGa(1-x)N(More)
OBJECTIVE To evaluate whether vector representations encoding latent topic proportions that capture similarities to MeSH terms can improve performance on biomedical document retrieval and classification tasks, compared to using MeSH terms. MATERIALS AND METHODS We developed the TopicalMeSH representation, which exploits the 'correspondence' between topics(More)
Estimation of the semantic relatedness between biomedical concepts has utility for many informatics applications. Automated methods fall into two broad categories: methods based on distributional statistics drawn from text corpora, and methods based on the structure of existing knowledge resources. In the former case, taxonomic structure is disregarded. In(More)
—Given that unstructured data is increasing exponentially everyday, extracting and understanding the information , themes, and relationships from large collections of documents is increasingly important to researchers in many disciplines including biomedicine. Latent Dirichlet Allocation (LDA) is an unsupervised topic modeling technique based on the "(More)