Artemyriantholides A-K, guaiane-type sesquiterpenoid dimers from Artemisia myriantha var. pleiocephala and their antihepatoma activity.

Artemyriantholides A-K (1-11) as well as 14 known compounds (12-25) were isolated from Artemisia myriantha var. pleiocephala (Asteraceae). The structures and absolute configuration of compounds 2 and 8-9 were confirmed by the single crystal X-ray diffraction analyses, and the others were elucidated by MS, NMR spectral data and electronic circular dichroism calculations. All compounds were chemically characterized as guaiane-type sesquiterpenoid dimers (GSDs). Compound 1 was the first example of the GSD fused via C-3/C-11' and C-5/C-13' linkages, and compounds 2 and 5 were rare GSDs containing chlorine atoms. Eleven compounds showed obvious inhibitory activity in HepG2, Huh7 and SK-Hep-1 cell lines by antihepatoma assay to provide the IC50 values ranging from 7.9 to 67.1 µM. Importantly, compounds 5 and 8 exhibited the best inhibitory activity with IC50 values of 14.2 and 18.8 (HepG2), 9.0 and 11.5 (Huh7), and 8.8 and 11.3 µM (SK-Hep-1), respectively. The target of compound 5 was predicted to be MAP2K2 by a computational prediction model. The interaction between compound 5 and MAP2K2 was conducted to give docking score of -9.0 kcal/mol by molecular docking and provide KD value of 43.7 µM by Surface Plasmon Resonance assay.

Design, synthesis, and biological evaluation of artemyrianolide H derivatives as potential antihepatoma agents.

Artemyrianolide H (AH) is a germacrene-type sesquiterpenolid isolated from Artemisia myriantha, and showed potent cytotoxicity against three human hepatocellular carcinoma cell lines HepG2, Huh7, and SK-Hep-1 with IC50 values of 10.9, 7.2, and 11.9 µM, respectively. To reveal structure-activity relationship, 51 artemyrianolide H derivatives including 19 dimeric analogs were designed, synthesized, and assayed for their cytotoxicity against three human hepatoma cell lines. Among them, 34 compounds were more active than artemyrianolide H and sorafenib on the three cell lines. Especially, compound 25 exhibited the most promising activity with IC50 values of 0.7 (HepG2), 0.6 (Huh7), and 1.3 µM (SK-Hep-1), which were 15.5, 12.0, and 9.2-fold higher than that of AH and 16.4, 16.3 and 17.5-fold higher than that of sorafenib. Cytotoxicity evaluation on normal human liver cell lines (THLE-2) demonstrated good safety profile of compound 25 with SI of 1.9 (HepG2), 2.2 (Huh 7) and 1.0 (SK-Hep1). Further studies revealed that compound 25 dose-dependently arrested cells at G2/M phase which was correlated with the up-regulation of both cyclin B1 and p-CDK1, and induced apoptosis through the activation of mitochondrial pathways in HepG2 cells. In addition, the migratory and invasive abilities in HepG2 cells after treatment with 1.5 µM of compound 25 were decreased by 89% and 86% with the increase of E-cadherin expression accompanied by the decrease of N-cadherin, vimentin expression. Bioinformatics analysis based on machine learning predicted that PDGFRA and MAP2K2 might be acting targets of compound 25, and SPR assays demonstrated compound 25 were bound with PDGFRA and MAP2K2 with KD value of 0.168 nM, and 8.49 µM, respectively. This investigation proposed that compound 25 might be considered as a promising lead compound for the development of antihepatoma candidate.

Computational probing protein-protein interactions targeting small molecules.

MOTIVATION: With the booming of interactome studies, a lot of interactions can be measured in a high throughput way and large scale datasets are available. It is becoming apparent that many different types of interactions can be potential drug targets. Compared with inhibition of a single protein, inhibition of protein-protein interaction (PPI) is promising to improve the specificity with fewer adverse side-effects. Also it greatly broadens the drug target search space, which makes the drug target discovery difficult. Computational methods are highly desired to efficiently provide candidates for further experiments and hold the promise to greatly accelerate the discovery of novel drug targets. RESULTS: Here, we propose a machine learning method to predict PPI targets in a genomic-wide scale. Specifically, we develop a computational method, named as PrePPItar, to Predict PPIs as drug targets by uncovering the potential associations between drugs and PPIs. First, we survey the databases and manually construct a gold-standard positive dataset for drug and PPI interactions. This effort leads to a dataset with 227 associations among 63 PPIs and 113 FDA-approved drugs and allows us to build models to learn the association rules from the data. Second, we characterize drugs by profiling in chemical structure, drug ATC-code annotation, and side-effect space and represent PPI similarity by a symmetrical S-kernel based on protein amino acid sequence. Then the drugs and PPIs are correlated by Kronecker product kernel. Finally, a support vector machine (SVM), is trained to predict novel associations between drugs and PPIs. We validate our PrePPItar method on the well-established gold-standard dataset by cross-validation. We find that all chemical structure, drug ATC-code, and side-effect information are predictive for PPI target. Moreover, we can increase the PPI target prediction coverage by integrating multiple data sources. Follow-up database search and pathway analysis indicate that our new predictions are worthy of future experimental validation. CONCLUSION: In conclusion, PrePPItar can serve as a useful tool for PPI target discovery and provides a general heterogeneous data integrative framework. AVAILABILITY AND IMPLEMENTATION: PrePPItar is available at http://doc.aporc.org/wiki/PrePPItar. CONTACT: ycwang@nwipb.cas.cn or ywang@amss.ac.cn SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Network predicting drug's anatomical therapeutic chemical code.

MOTIVATION: Discovering drug's Anatomical Therapeutic Chemical (ATC) classification rules at molecular level is of vital importance to understand a vast majority of drugs action. However, few studies attempt to annotate drug's potential ATC-codes by computational approaches. RESULTS: Here, we introduce drug-target network to computationally predict drug's ATC-codes and propose a novel method named NetPredATC. Starting from the assumption that drugs with similar chemical structures or target proteins share common ATC-codes, our method, NetPredATC, aims to assign drug's potential ATC-codes by integrating chemical structures and target proteins. Specifically, we first construct a gold-standard positive dataset from drugs' ATC-code annotation databases. Then we characterize ATC-code and drug by their similarity profiles and define kernel function to correlate them. Finally, we use a kernel method, support vector machine, to automatically predict drug's ATC-codes. Our method was validated on four drug datasets with various target proteins, including enzymes, ion channels, G-protein couple receptors and nuclear receptors. We found that both drug's chemical structure and target protein are predictive, and target protein information has better accuracy. Further integrating these two data sources revealed more experimentally validated ATC-codes for drugs. We extensively compared our NetPredATC with SuperPred, which is a chemical similarity-only based method. Experimental results showed that our NetPredATC outperforms SuperPred not only in predictive coverage but also in accuracy. In addition, database search and functional annotation analysis support that our novel predictions are worthy of future experimental validation. CONCLUSION: In conclusion, our new method, NetPredATC, can predict drug's ATC-codes more accurately by incorporating drug-target network and integrating data, which will promote drug mechanism understanding and drug repositioning and discovery. AVAILABILITY: NetPredATC is available at http://doc.aporc.org/wiki/NetPredATC. CONTACT: ycwang@nwipb.cas.cn or ywang@amss.ac.cn SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Kernel-based data fusion improves the drug-protein interaction prediction.

Proteins are involved in almost every action of every organism by interacting with other small molecules including drugs. Computationally predicting the drug-protein interactions is particularly important in speeding up the process of developing novel drugs. To borrow the information from existing drug-protein interactions, we need to define the similarity among proteins and the similarity among drugs. Usually these similarities are defined based on one single data source and many methods have been proposed. However, the availability of many genomic and chemogenomic data sources allows us to integrate these useful data sources to improve the predictions. Thus a great challenge is how to integrate these heterogeneous data sources. Here, we propose a kernel-based method to predict drug-protein interactions by integrating multiple types of data. Specially, we collect drug pharmacological and therapeutic effects, drug chemical structures, and protein genomic information to characterize the drug-target interactions, then integrate them by a kernel function within a support vector machine (SVM)-based predictor. With this data fusion technology, we establish the drug-protein interactions from a collections of data sources. Our new method is validated on four classes of drug target proteins, including enzymes, ion channels (ICs), G-protein couple receptors (GPCRs), and nuclear receptors (NRs). We find that every single data source is predictive and integration of different data sources allows the improvement of accuracy, i.e., data integration can uncover more experimentally observed drug-target interactions upon the same levels of false positive rate than single data source based methods. The functional annotation analysis indicates that our new predictions are worthy of future experimental validation. In conclusion, our new method can efficiently integrate diverse data sources, and will promote the further research in drug discovery.

Improving accuracy of protein-protein interaction prediction by considering the converse problem for sequence representation.

BACKGROUND: With the development of genome-sequencing technologies, protein sequences are readily obtained by translating the measured mRNAs. Therefore predicting protein-protein interactions from the sequences is of great demand. The reason lies in the fact that identifying protein-protein interactions is becoming a bottleneck for eventually understanding the functions of proteins, especially for those organisms barely characterized. Although a few methods have been proposed, the converse problem, if the features used extract sufficient and unbiased information from protein sequences, is almost untouched. RESULTS: In this study, we interrogate this problem theoretically by an optimization scheme. Motivated by the theoretical investigation, we find novel encoding methods for both protein sequences and protein pairs. Our new methods exploit sufficiently the information of protein sequences and reduce artificial bias and computational cost. Thus, it significantly outperforms the available methods regarding sensitivity, specificity, precision, and recall with cross-validation evaluation and reaches ~80% and ~90% accuracy in Escherichia coli and Saccharomyces cerevisiae respectively. Our findings here hold important implication for other sequence-based prediction tasks because representation of biological sequence is always the first step in computational biology. CONCLUSIONS: By considering the converse problem, we propose new representation methods for both protein sequences and protein pairs. The results show that our method significantly improves the accuracy of protein-protein interaction predictions.

Support vector machine prediction of enzyme function with conjoint triad feature and hierarchical context.

BACKGROUND: Enzymes are known as the largest class of proteins and their functions are usually annotated by the Enzyme Commission (EC), which uses a hierarchy structure, i.e., four numbers separated by periods, to classify the function of enzymes. Automatically categorizing enzyme into the EC hierarchy is crucial to understand its specific molecular mechanism. RESULTS: In this paper, we introduce two key improvements in predicting enzyme function within the machine learning framework. One is to introduce the efficient sequence encoding methods for representing given proteins. The second one is to develop a structure-based prediction method with low computational complexity. In particular, we propose to use the conjoint triad feature (CTF) to represent the given protein sequences by considering not only the composition of amino acids but also the neighbor relationships in the sequence. Then we develop a support vector machine (SVM)-based method, named as SVMHL (SVM for hierarchy labels), to output enzyme function by fully considering the hierarchical structure of EC. The experimental results show that our SVMHL with the CTF outperforms SVMHL with the amino acid composition (AAC) feature both in predictive accuracy and Matthew's correlation coefficient (MCC). In addition, SVMHL with the CTF obtains the accuracy and MCC ranging from 81% to 98% and 0.82 to 0.98 when predicting the first three EC digits on a low-homologous enzyme dataset. We further demonstrate that our method outperforms the methods which do not take account of hierarchical relationship among enzyme categories and alternative methods which incorporate prior knowledge about inter-class relationships. CONCLUSIONS: Our structure-based prediction model, SVMHL with the CTF, reduces the computational complexity and outperforms the alternative approaches in enzyme function prediction. Therefore our new method will be a useful tool for enzyme function prediction community.

Prediction of enzyme subfamily class via pseudo amino acid composition by incorporating the conjoint triad feature.

Predicting enzyme subfamily class is an imbalance multi-class classification problem due to the fact that the number of proteins in each subfamily makes a great difference. In this paper, we focus on developing the computational methods specially designed for the imbalance multi-class classification problem to predict enzyme subfamily class. We compare two support vector machine (SVM)-based methods for the imbalance problem, AdaBoost algorithm with RBFSVM (SVM with RBF kernel) and SVM with arithmetic mean (AM) offset (AM-SVM) in enzyme subfamily classification. As input features for our predictive model, we use the conjoint triad feature (CTF). We validate two methods on an enzyme benchmark dataset, which contains six enzyme main families with a total of thirty-four subfamily classes, and those proteins have less than 40% sequence identity to any other in a same functional class. In predicting oxidoreductases subfamilies, AM-SVM obtains the over 0.92 Matthew's correlation coefficient (MCC) and over 93% accuracy, and in predicting lyases, isomerases and ligases subfamilies, it obtains over 0.73 MCC and over 82% accuracy. The improvement in the predictive performance suggests the AM-SVM might play a complementary role to the existing function annotation methods.

Prediction of palmitoylation sites using the composition of k-spaced amino acid pairs.

Palmitoylation is an important hydrophobic protein modification activity that participates many cellular processes, including signaling, neuronal transmission, membrane trafficking and so on. So it is an important problem to identify palmitoylated proteins and the corresponding sites. Comparing with the expensive and time-consuming biochemical experiments, the computational methods have attracted much attention due to their good performances in predicting palmitoylation sites. In this paper, we develop a novel automated computational method to perform this work. For a sequence segment in a given protein, the encoding scheme based on the composition of k-spaced amino acid pairs (CKSAAP) is introduced, and then the support vector machine is used as the predictor. The proposed prediction model CKSAAP-Palm outperforms the existing method CSS-Palm2.0 on both cross-validation experiments and some independent testing data sets. These results imply that our CKSAAP-Palm is able to predict more potential palmitoylation sites and increases research productivity in palmitoylation sites discovery. The corresponding software can be freely downloaded from http://www.aporc.org/doc/wiki/CKSAAP-Palm.