Le-Le Hu

Predicting drug-target interaction networks based on functional groups and biological features.

Background Study of drug-target interaction networks is an important topic for drug development. It is both time-consuming and costly to determine compound-protein interactions or potential drug-target interactions by experiments alone. As a complement, the in silico prediction methods can provide us with very useful information in a timely manner. Methods/Principal Findings To realize this, drug compounds are encoded with functional groups and proteins encoded by biological features including biochemical and physicochemical properties. The optimal feature selection procedures are adopted by means of the mRMR (Maximum Relevance Minimum Redundancy) method. Instead of classifying the proteins as a whole family, target proteins are divided into four groups: enzymes, ion channels, G-protein- coupled receptors and nuclear receptors. Thus, four independent predictors are established using the Nearest Neighbor algorithm as their operation engine, with each to predict the interactions between drugs and one of the four protein groups. As a result, the overall success rates by the jackknife cross-validation tests achieved with the four predictors are 85.48%, 80.78%, 78.49%, and 85.66%, respectively. Conclusion/Significance Our results indicate that the network prediction system thus established is quite promising and encouraging.

Analysis and Prediction of the Metabolic Stability of Proteins Based on Their Sequential Features, Subcellular Locations and Interaction Networks

The metabolic stability is a very important idiosyncracy of proteins that is related to their global flexibility, intramolecular fluctuations, various internal dynamic processes, as well as many marvelous biological functions. Determination of proteins metabolic stability would provide us with useful information for in-depth understanding of the dynamic action mechanisms of proteins. Although several experimental methods have been developed to measure proteins metabolic stability, they are time-consuming and more expensive. Reported in this paper is a computational method, which is featured by (1) integrating various properties of proteins, such as biochemical and physicochemical properties, subcellular locations, network properties and protein complex property, (2) using the mRMR (Maximum Relevance & Minimum Redundancy) principle and the IFS (Incremental Feature Selection) procedure to optimize the prediction engine, and (3) being able to identify proteins among the four types: “short”, “medium”, “long”, and “extra-long” half-life spans. It was revealed through our analysis that the following seven characters played major roles in determining the stability of proteins: (1) KEGG enrichment scores of the protein and its neighbors in network, (2) subcellular locations, (3) polarity, (4) amino acids composition, (5) hydrophobicity, (6) secondary structure propensity, and (7) the number of protein complexes the protein involved. It was observed that there was an intriguing correlation between the predicted metabolic stability of some proteins and the real half-life of the drugs designed to target them. These findings might provide useful insights for designing protein-stability-relevant drugs. The computational method can also be used as a large-scale tool for annotating the metabolic stability for the avalanche of protein sequences generated in the post-genomic age.

Predicting Functions of Proteins in Mouse Based on Weighted Protein-Protein Interaction Network and Protein Hybrid Properties

Background With the huge amount of uncharacterized protein sequences generated in the post-genomic age, it is highly desirable to develop effective computational methods for quickly and accurately predicting their functions. The information thus obtained would be very useful for both basic research and drug development in a timely manner. Methodology/Principal Findings Although many efforts have been made in this regard, most of them were based on either sequence similarity or protein-protein interaction (PPI) information. However, the former often fails to work if a query protein has no or very little sequence similarity to any function-known proteins, while the latter had similar problem if the relevant PPI information is not available. In view of this, a new approach is proposed by hybridizing the PPI information and the biochemical/physicochemical features of protein sequences. The overall first-order success rates by the new predictor for the functions of mouse proteins on training set and test set were 69.1% and 70.2%, respectively, and the success rate covered by the results of the top-4 order from a total of 24 orders was 65.2%. Conclusions/Significance The results indicate that the new approach is quite promising that may open a new avenue or direction for addressing the difficult and complicated problem.

Prediction of Antimicrobial Peptides Based on Sequence Alignment and Feature Selection Methods

Antimicrobial peptides (AMPs) represent a class of natural peptides that form a part of the innate immune system, and this kind of ‘natures antibiotics’ is quite promising for solving the problem of increasing antibiotic resistance. In view of this, it is highly desired to develop an effective computational method for accurately predicting novel AMPs because it can provide us with more candidates and useful insights for drug design. In this study, a new method for predicting AMPs was implemented by integrating the sequence alignment method and the feature selection method. It was observed that, the overall jackknife success rate by the new predictor on a newly constructed benchmark dataset was over 80.23%, and the Mathews correlation coefficient is 0.73, indicating a good prediction. Moreover, it is indicated by an in-depth feature analysis that the results are quite consistent with the previously known knowledge that some amino acids are preferential in AMPs and that these amino acids do play an important role for the antimicrobial activity. For the convenience of most experimental scientists who want to use the prediction method without the interest to follow the mathematical details, a user-friendly web-server is provided at http://amp.biosino.org/.

Prediction of Pharmacological and Xenobiotic Responses to Drugs Based on Time Course Gene Expression Profiles

More and more people are concerned by the risk of unexpected side effects observed in the later steps of the development of new drugs, either in late clinical development or after marketing approval. In order to reduce the risk of the side effects, it is important to look out for the possible xenobiotic responses at an early stage. We attempt such an effort through a prediction by assuming that similarities in microarray profiles indicate shared mechanisms of action and/or toxicological responses among the chemicals being compared. A large time course microarray database derived from livers of compound-treated rats with thirty-four distinct pharmacological and toxicological responses were studied. The mRMR (Minimum-Redundancy-Maximum-Relevance) method and IFS (Incremental Feature Selection) were used to select a compact feature set (141 features) for the reduction of feature dimension and improvement of prediction performance. With these 141 features, the Leave-one-out cross-validation prediction accuracy of first order response using NNA (Nearest Neighbor Algorithm) was 63.9%. Our method can be used for pharmacological and xenobiotic responses prediction of new compounds and accelerate drug development.

Prediction of protein domain with mRMR feature selection and analysis.

The domains are the structural and functional units of proteins. With the avalanche of protein sequences generated in the postgenomic age, it is highly desired to develop effective methods for predicting the protein domains according to the sequences information alone, so as to facilitate the structure prediction of proteins and speed up their functional annotation. However, although many efforts have been made in this regard, prediction of protein domains from the sequence information still remains a challenging and elusive problem. Here, a new method was developed by combing the techniques of RF (random forest), mRMR (maximum relevance minimum redundancy), and IFS (incremental feature selection), as well as by incorporating the features of physicochemical and biochemical properties, sequence conservation, residual disorder, secondary structure, and solvent accessibility. The overall success rate achieved by the new method on an independent dataset was around 73%, which was about 28–40% higher than those by the existing method on the same benchmark dataset. Furthermore, it was revealed by an in-depth analysis that the features of evolution, codon diversity, electrostatic charge, and disorder played more important roles than the others in predicting protein domains, quite consistent with experimental observations. It is anticipated that the new method may become a high-throughput tool in annotating protein domains, or may, at the very least, play a complementary role to the existing domain prediction methods, and that the findings about the key features with high impacts to the domain prediction might provide useful insights or clues for further experimental investigations in this area. Finally, it has not escaped our notice that the current approach can also be utilized to study protein signal peptides, B-cell epitopes, HIV protease cleavage sites, among many other important topics in protein science and biomedicine.

Prediction of deleterious non-synonymous SNPs based on protein interaction network and hybrid properties.

Non-synonymous SNPs (nsSNPs), also known as Single Amino acid Polymorphisms (SAPs) account for the majority of human inherited diseases. It is important to distinguish the deleterious SAPs from neutral ones. Most traditional computational methods to classify SAPs are based on sequential or structural features. However, these features cannot fully explain the association between a SAP and the observed pathophysiological phenotype. We believe the better rationale for deleterious SAP prediction should be: If a SAP lies in the protein with important functions and it can change the protein sequence and structure severely, it is more likely related to disease. So we established a method to predict deleterious SAPs based on both protein interaction network and traditional hybrid properties. Each SAP is represented by 472 features that include sequential features, structural features and network features. Maximum Relevance Minimum Redundancy (mRMR) method and Incremental Feature Selection (IFS) were applied to obtain the optimal feature set and the prediction model was Nearest Neighbor Algorithm (NNA). In jackknife cross-validation, 83.27% of SAPs were correctly predicted when the optimized 263 features were used. The optimized predictor with 263 features was also tested in an independent dataset and the accuracy was still 80.00%. In contrast, SIFT, a widely used predictor of deleterious SAPs based on sequential features, has a prediction accuracy of 71.05% on the same dataset. In our study, network features were found to be most important for accurate prediction and can significantly improve the prediction performance. Our results suggest that the protein interaction context could provide important clues to help better illustrate SAPs functional association. This research will facilitate the post genome-wide association studies.

Prediction of lysine ubiquitination with mRMR feature selection and analysis

Ubiquitination, one of the most important post-translational modifications of proteins, occurs when ubiquitin (a small 76-amino acid protein) is attached to lysine on a target protein. It often commits the labeled protein to degradation and plays important roles in regulating many cellular processes implicated in a variety of diseases. Since ubiquitination is rapid and reversible, it is time-consuming and labor-intensive to identify ubiquitination sites using conventional experimental approaches. To efficiently discover lysine-ubiquitination sites, a sequence-based predictor of ubiquitination site was developed based on nearest neighbor algorithm. We used the maximum relevance and minimum redundancy principle to identify the key features and the incremental feature selection procedure to optimize the prediction engine. PSSM conservation scores, amino acid factors and disorder scores of the surrounding sequence formed the optimized 456 features. The Mathew’s correlation coefficient (MCC) of our ubiquitination site predictor achieved 0.142 by jackknife cross-validation test on a large benchmark dataset. In independent test, the MCC of our method was 0.139, higher than the existing ubiquitination site predictor UbiPred and UbPred. The MCCs of UbiPred and UbPred on the same test set were 0.135 and 0.117, respectively. Our analysis shows that the conservation of amino acids at and around lysine plays an important role in ubiquitination site prediction. What’s more, disorder and ubiquitination have a strong relevance. These findings might provide useful insights for studying the mechanisms of ubiquitination and modulating the ubiquitination pathway, potentially leading to potential therapeutic strategies in the future.

Predict and analyze S-nitrosylation modification sites with the mRMR and IFS approaches.

S-nitrosylation (SNO) is one of the most important and universal post-translational modifications (PTMs) which regulates various cellular functions and signaling events. Identification of the exact S-nitrosylation sites in proteins may facilitate the understanding of the molecular mechanisms and biological function of S-nitrosylation. Unfortunately, traditional experimental approaches used for detecting S-nitrosylation sites are often laborious and time-consuming. However, computational methods could overcome this demerit. In this work, we developed a novel predictor based on nearest neighbor algorithm (NNA) with the maximum relevance minimum redundancy (mRMR) method followed by incremental feature selection (IFS). The features of physicochemical/biochemical properties, sequence conservation, residual disorder, amino acid occurrence frequency, second structure and the solvent accessibility were utilized to represent the peptides concerned. Feature analysis showed that the features except residual disorder affected identification of the S-nitrosylation sites. It was also shown via the site-specific feature analysis that the features of sites away from the central cysteine might contribute to the S-nitrosylation site determination through a subtle manner. It is anticipated that our prediction method may become a useful tool for identifying the protein S-nitrosylation sites and that the features analysis described in this paper may provide useful insights for in-depth investigation into the mechanism of S-nitrosylation.

Deciphering the effects of gene deletion on yeast longevity using network and machine learning approaches

Longevity is one of the most basic and one of the most essential properties of all living organisms. Identification of genes that regulate longevity would increase understanding of the mechanisms of aging, so as to help facilitate anti-aging intervention and extend the life span. In this study, based on the network features and the biochemical/physicochemical features of the deletion network and deletion genes, as well as their functional features, a two-layer model was developed for predicting the deletion effects on yeast longevity. The first stage of our prediction approach was to identify whether the deletion of one gene would change the life span of yeast; if it did, the second stage of our procedure would automatically proceed to predict whether the deletion of one gene would increase or decrease the life span. It was observed by analyzing the predicted results that the functional features (such as mitochondrial function and chromatin silencing), the network features (such as the edge density and edge weight density of the deletion network), and the local centrality of deletion gene, would have important impact for predicting the deletion effects on longevity. It is anticipated that our model may become a useful tool for studying longevity from the angle of genes and networks. Moreover, it has not escaped our notice that, after some modification, the current model can also be used to study many other phenotype prediction problems from the angle of systems biology.