Detection of Drug-Drug Interactions by Modeling Interaction Profile Fingerprints

Drug-drug interactions (DDIs) constitute an important problem in postmarketing pharmacovigilance and in the development of new drugs. The effectiveness or toxicity of a medication could be affected by the co-administration of other drugs that share pharmacokinetic or pharmacodynamic pathways. For this reason, a great effort is being made to develop new methodologies to detect and assess DDIs. In this article, we present a novel method based on drug interaction profile fingerprints (IPFs) with successful application to DDI detection. IPFs were generated based on the DrugBank database, which provided 9,454 well-established DDIs as a primary source of interaction data. The model uses IPFs to measure the similarity of pairs of drugs and generates new putative DDIs from the non-intersecting interactions of a pair. We described as part of our analysis the pharmacological and biological effects associated with the putative interactions; for example, the interaction between haloperidol and dicyclomine can cause increased risk of psychosis and tardive dyskinesia. First, we evaluated the method through hold-out validation and then by using four independent test sets that did not overlap with DrugBank. Precision for the test sets ranged from 0.4–0.5 with more than two fold enrichment factor enhancement. In conclusion, we demonstrated the usefulness of the method in pharmacovigilance as a DDI predictor, and created a dataset of potential DDIs, highlighting the etiology or pharmacological effect of the DDI, and providing an exploratory tool to facilitate decision support in DDI detection and patient safety.     

Translating clinical findings into knowledge in drug safety evaluation--drug induced liver injury prediction system (DILIps)

Drug-induced liver injury (DILI) is a significant concern in drug development due to the poor concordance between preclinical and clinical findings of liver toxicity. We hypothesized that the DILI types (hepatotoxic side effects) seen in the clinic can be translated into the development of predictive in silico models for use in the drug discovery phase. We identified 13 hepatotoxic side effects with high accuracy for classifying marketed drugs for their DILI potential. We then developed in silico predictive models for each of these 13 side effects, which were further combined to construct a DILI prediction system (DILIps). The DILIps yielded 60-70% prediction accuracy for three independent validation sets. To enhance the confidence for identification of drugs that cause severe DILI in humans, the "Rule of Three" was developed in DILIps by using a consensus strategy based on 13 models. This gave high positive predictive value (91%) when applied to an external dataset containing 206 drugs from three independent literature datasets. Using the DILIps, we screened all the drugs in DrugBank and investigated their DILI potential in terms of protein targets and therapeutic categories through network modeling. We demonstrated that two therapeutic categories, anti-infectives for systemic use and musculoskeletal system drugs, were enriched for DILI, which is consistent with current knowledge. We also identified protein targets and pathways that are related to drugs that cause DILI by using pathway analysis and co-occurrence text mining. While marketed drugs were the focus of this study, the DILIps has a potential as an evaluation tool to screen and prioritize new drug candidates or chemicals, such as environmental chemicals, to avoid those that might cause liver toxicity. We expect that the methodology can be also applied to other drug safety endpoints, such as renal or cardiovascular toxicity.     

Adverse Drug Reaction Prediction Using Scores Produced by Large-Scale Drug-Protein Target Docking on High-Performance Computing Machines

Late-stage or post-market identification of adverse drug reactions (ADRs) is a significant public health issue and a source of major economic liability for drug development. Thus, reliable in silico screening of drug candidates for possible ADRs would be advantageous. In this work, we introduce a computational approach that predicts ADRs by combining the results of molecular docking and leverages known ADR information from DrugBank and SIDER. We employed a recently parallelized version of AutoDock Vina (VinaLC) to dock 906 small molecule drugs to a virtual panel of 409 DrugBank protein targets. L1-regularized logistic regression models were trained on the resulting docking scores of a 560 compound subset from the initial 906 compounds to predict 85 side effects, grouped into 10 ADR phenotype groups. Only 21% (87 out of 409) of the drug-protein binding features involve known targets of the drug subset, providing a significant probe of off-target effects. As a control, associations of this drug subset with the 555 annotated targets of these compounds, as reported in DrugBank, were used as features to train a separate group of models. The Vina off-target models and the DrugBank on-target models yielded comparable median area-under-the-receiver-operating-characteristic-curves (AUCs) during 10-fold cross-validation (0.60–0.69 and 0.61–0.74, respectively). Evidence was found in the PubMed literature to support several putative ADR-protein associations identified by our analysis. Among them, several associations between neoplasm-related ADRs and known tumor suppressor and tumor invasiveness marker proteins were found. A dual role for interstitial collagenase in both neoplasms and aneurysm formation was also identified. These associations all involve off-target proteins and could not have been found using available drug/on-target interaction data. This study illustrates a path forward to comprehensive ADR virtual screening that can potentially scale with increasing number of CPUs to tens of thousands of protein targets and millions of potential drug candidates.     

Ligand-Target Prediction by Structural Network Biology Using nAnnoLyze

Target identification is essential for drug design, drug-drug interaction prediction, dosage adjustment and side effect anticipation. Specifically, the knowledge of structural details is essential for understanding the mode of action of a compound on a target protein. Here, we present nAnnoLyze, a method for target identification that relies on the hypothesis that structurally similar binding sites bind similar ligands. nAnnoLyze integrates structural information into a bipartite network of interactions and similarities to predict structurally detailed compound-protein interactions at proteome scale. The method was benchmarked on a dataset of 6,282 pairs of known interacting ligand-target pairs reaching a 0.96 of area under the Receiver Operating Characteristic curve (AUC) when using the drug names as an input feature for the classifier, and a 0.70 of AUC for “anonymous” compounds or compounds not present in the training set. nAnnoLyze resulted in higher accuracies than its predecessor, AnnoLyze. We applied the method to predict interactions for all the compounds in the DrugBank database with each human protein structure and provide examples of target identification for known drugs against human diseases. The accuracy and applicability of our method to any compound indicate that a comparative docking approach such as nAnnoLyze enables large-scale annotation and analysis of compound–protein interactions and thus may benefit drug development.     

Genetic networks and soft computing

The analysis of gene regulatory networks provides enormous information on various fundamental cellular processes involving growth, development, hormone secretion, and cellular communication. Their extraction from available gene expression profiles is a challenging problem. Such reverse engineering of genetic networks offers insight into cellular activity toward prediction of adverse effects of new drugs or possible identification of new drug targets. Tasks such as classification, clustering, and feature selection enable efficient mining of knowledge about gene interactions in the form of networks. It is known that biological data is prone to different kinds of noise and ambiguity. Soft computing tools, such as fuzzy sets, evolutionary strategies, and neurocomputing, have been found to be helpful in providing low-cost, acceptable solutions in the presence of various types of uncertainties. In this paper, we survey the role of these soft methodologies and their hybridizations, for the purpose of generating genetic networks.     

MScanner: a classifier for retrieving Medline citations

Background  

Keyword searching through PubMed and other systems is the standard means of retrieving information from Medline. However, ad-hoc retrieval systems do not meet all of the needs of databases that curate information from literature, or of text miners developing a corpus on a topic that has many terms indicative of relevance. Several databases have developed supervised learning methods that operate on a filtered subset of Medline, to classify Medline records so that fewer articles have to be manually reviewed for relevance. A few studies have considered generalisation of Medline classification to operate on the entire Medline database in a non-domain-specific manner, but existing applications lack speed, available implementations, or a means to measure performance in new domains.     

Multi-dimensional classification of biomedical text: toward automated, practical provision of high-utility text to diverse users

MOTIVATION: Much current research in biomedical text mining is concerned with serving biologists by extracting certain information from scientific text. We note that there is no 'average biologist' client; different users have distinct needs. For instance, as noted in past evaluation efforts (BioCreative, TREC, KDD) database curators are often interested in sentences showing experimental evidence and methods. Conversely, lab scientists searching for known information about a protein may seek facts, typically stated with high confidence. Text-mining systems can target specific end-users and become more effective, if the system can first identify text regions rich in the type of scientific content that is of interest to the user, retrieve documents that have many such regions, and focus on fact extraction from these regions. Here, we study the ability to characterize and classify such text automatically. We have recently introduced a multi-dimensional categorization and annotation scheme, developed to be applicable to a wide variety of biomedical documents and scientific statements, while intended to support specific biomedical retrieval and extraction tasks. RESULTS: The annotation scheme was applied to a large corpus in a controlled effort by eight independent annotators, where three individual annotators independently tagged each sentence. We then trained and tested machine learning classifiers to automatically categorize sentence fragments based on the annotation. We discuss here the issues involved in this task, and present an overview of the results. The latter strongly suggest that automatic annotation along most of the dimensions is highly feasible, and that this new framework for scientific sentence categorization is applicable in practice.     

Text processing through Web services: calling Whatizit

MOTIVATION: Text-mining (TM) solutions are developing into efficient services to researchers in the biomedical research community. Such solutions have to scale with the growing number and size of resources (e.g. available controlled vocabularies), with the amount of literature to be processed (e.g. about 17 million documents in PubMed) and with the demands of the user community (e.g. different methods for fact extraction). These demands motivated the development of a server-based solution for literature analysis. Whatizit is a suite of modules that analyse text for contained information, e.g. any scientific publication or Medline abstracts. Special modules identify terms and then link them to the corresponding entries in bioinformatics databases such as UniProtKb/Swiss-Prot data entries and gene ontology concepts. Other modules identify a set of selected annotation types like the set produced by the EBIMed analysis pipeline for proteins. In the case of Medline abstracts, Whatizit offers access to EBI's in-house installation via PMID or term query. For large quantities of the user's own text, the server can be operated in a streaming mode (http://www.ebi.ac.uk/webservices/whatizit).     

Clustering of PubMed abstracts using nearer terms of the domain

Literature search is a process in which external developers provide alternative representations for efficient data mining of biomedical literature such as ranking search results, displaying summarized knowledge of semantics and clustering results into topics. In clustering search results, prominent vocabularies, such as GO (Gene Ontology), MeSH(Medical Subject Headings) and frequent terms extracted from retrieved PubMed abstracts have been used as topics for grouping. In this study, we have proposed FNeTD (Frequent Nearer Terms of the Domain) method for PubMed abstracts clustering. This is achieved through a two-step process viz; i) identifying frequent words or phrases in the abstracts through the frequent multi-word extraction algorithm and ii) identifying nearer terms of the domain from the extracted frequent phrases using the nearest neighbors search. The efficiency of the clustering of PubMed abstracts using nearer terms of the domain was measured using F-score. The present study suggests that nearer terms of the domain can be used for clustering the search results.     

A Comprehensive Benchmark of Kernel Methods to Extract Protein–Protein Interactions from Literature

The most important way of conveying new findings in biomedical research is scientific publication. Extraction of protein–protein interactions (PPIs) reported in scientific publications is one of the core topics of text mining in the life sciences. Recently, a new class of such methods has been proposed - convolution kernels that identify PPIs using deep parses of sentences. However, comparing published results of different PPI extraction methods is impossible due to the use of different evaluation corpora, different evaluation metrics, different tuning procedures, etc. In this paper, we study whether the reported performance metrics are robust across different corpora and learning settings and whether the use of deep parsing actually leads to an increase in extraction quality. Our ultimate goal is to identify the one method that performs best in real-life scenarios, where information extraction is performed on unseen text and not on specifically prepared evaluation data. We performed a comprehensive benchmarking of nine different methods for PPI extraction that use convolution kernels on rich linguistic information. Methods were evaluated on five different public corpora using cross-validation, cross-learning, and cross-corpus evaluation. Our study confirms that kernels using dependency trees generally outperform kernels based on syntax trees. However, our study also shows that only the best kernel methods can compete with a simple rule-based approach when the evaluation prevents information leakage between training and test corpora. Our results further reveal that the F-score of many approaches drops significantly if no corpus-specific parameter optimization is applied and that methods reaching a good AUC score often perform much worse in terms of F-score. We conclude that for most kernels no sensible estimation of PPI extraction performance on new text is possible, given the current heterogeneity in evaluation data. Nevertheless, our study shows that three kernels are clearly superior to the other methods.     

PIR: a new resource for bioinformatics

SUMMARY: The Protein Information Resource (PIR) has greatly expanded its Web site and developed a set of interactive search and analysis tools to facilitate the analysis, annotation, and functional identification of proteins. New search engines have been implemented to combine sequence similarity search results with database annotation information. The new PIR search systems have proved very useful in providing enriched functional annotation of protein sequences, determining protein superfamily-domain relationships, and detecting annotation errors in genomic database archives. AVAILABILITY: http://pir.georgetown.edu/. CONTACT: mcgarvey@nbrf.georgetown.edu     

Identification and characterization of ErbB4 kinase inhibitors for effective breast cancer therapy

The overexpression of ErbB4 is associated with aggressive disease biology and reduced the survival of breast cancer patients. We have used ErbB4 receptor as a novel drug target to spearhead the rational drug design. The present study is divided into two parts. In the first part, we have exploited the hidden information inside ErbB4 kinase receptor both at sequence and structural level. PSI-BLAST algorithm is used to search similar sequences against ErbB4 kinase sequence. Top 15 sequences with high identity were selected for finding conserved and variable regions among sequences using multiple sequence alignment. In the second part, available 3?D structure of ErbB4 kinase is curated using loop modeling, and anomalies in the modeled structure is improved by energy minimization. The resultant structure is validated by analyzing dihedral angles by Ramachandran plot analysis. Furthermore, the potential binding sites were detected by using DoGSite and CASTp server. The similarity-search criterion is used for the preparation of our in-house database of drugs from DrugBank database. In total, 409 drugs yet to be tested against ErbB4 kinase is used for screening purpose. Virtual screening results in identification of 11 compounds with better binding affinity than lapatinib and canertinib. Study of protein–ligand interactions reveals information about amino acid residues; Lys726, Thr771, Met774, Cys778, Arg822, Thr835, Asp836 and Phe837 at the binding pocket. The physicochemical properties and bioactivity score calculation of selected compounds suggest them as biological active. This study presents a rich array that assist in expediting new drug discovery for breast cancer.     

A Systematic In Silico Search for Target Similarity Identifies Several Approved Drugs with Potential Activity against the Plasmodium falciparum Apicoplast

Most of the drugs in use against Plasmodium falciparum share similar modes of action and, consequently, there is a need to identify alternative potential drug targets. Here, we focus on the apicoplast, a malarial plastid-like organelle of algal source which evolved through secondary endosymbiosis. We undertake a systematic in silico target-based identification approach for detecting drugs already approved for clinical use in humans that may be able to interfere with the P. falciparum apicoplast. The P. falciparum genome database GeneDB was used to compile a list of ≈600 proteins containing apicoplast signal peptides. Each of these proteins was treated as a potential drug target and its predicted sequence was used to interrogate three different freely available databases (Therapeutic Target Database, DrugBank and STITCH3.1) that provide synoptic data on drugs and their primary or putative drug targets. We were able to identify several drugs that are expected to interact with forty-seven (47) peptides predicted to be involved in the biology of the P. falciparum apicoplast. Fifteen (15) of these putative targets are predicted to have affinity to drugs that are already approved for clinical use but have never been evaluated against malaria parasites. We suggest that some of these drugs should be experimentally tested and/or serve as leads for engineering new antimalarials.     

Extracting Drug-Drug Interaction from the Biomedical Literature Using a Stacked Generalization-Based Approach

Drug-drug interaction (DDI) detection is particularly important for patient safety. However, the amount of biomedical literature regarding drug interactions is increasing rapidly. Therefore, there is a need to develop an effective approach for the automatic extraction of DDI information from the biomedical literature. In this paper, we present a Stacked Generalization-based approach for automatic DDI extraction. The approach combines the feature-based, graph and tree kernels and, therefore, reduces the risk of missing important features. In addition, it introduces some domain knowledge based features (the keyword, semantic type, and DrugBank features) into the feature-based kernel, which contribute to the performance improvement. More specifically, the approach applies Stacked generalization to automatically learn the weights from the training data and assign them to three individual kernels to achieve a much better performance than each individual kernel. The experimental results show that our approach can achieve a better performance of 69.24% in F-score compared with other systems in the DDI Extraction 2011 challenge task.     

Overview of the protein-protein interaction annotation extraction task of BioCreative II

Background:

The biomedical literature is the primary information source for manual protein-protein interaction annotations. Text-mining systems have been implemented to extract binary protein interactions from articles, but a comprehensive comparison between the different techniques as well as with manual curation was missing.

Results:

We designed a community challenge, the BioCreative II protein-protein interaction (PPI) task, based on the main steps of a manual protein interaction annotation workflow. It was structured into four distinct subtasks related to: (a) detection of protein interaction-relevant articles; (b) extraction and normalization of protein interaction pairs; (c) retrieval of the interaction detection methods used; and (d) retrieval of actual text passages that provide evidence for protein interactions. A total of 26 teams submitted runs for at least one of the proposed subtasks. In the interaction article detection subtask, the top scoring team reached an F-score of 0.78. In the interaction pair extraction and mapping to SwissProt, a precision of 0.37 (with recall of 0.33) was obtained. For associating articles with an experimental interaction detection method, an F-score of 0.65 was achieved. As for the retrieval of the PPI passages best summarizing a given protein interaction in full-text articles, 19% of the submissions returned by one of the runs corresponded to curator-selected sentences. Curators extracted only the passages that best summarized a given interaction, implying that many of the automatically extracted ones could contain interaction information but did not correspond to the most informative sentences.

Conclusion:

The BioCreative II PPI task is the first attempt to compare the performance of text-mining tools specific for each of the basic steps of the PPI extraction pipeline. The challenges identified range from problems in full-text format conversion of articles to difficulties in detecting interactor protein pairs and then linking them to their database records. Some limitations were also encountered when using a single (and possibly incomplete) reference database for protein normalization or when limiting search for interactor proteins to co-occurrence within a single sentence, when a mention might span neighboring sentences. Finally, distinguishing between novel, experimentally verified interactions (annotation relevant) and previously known interactions adds additional complexity to these tasks.

     

The Protein Information Resource

The Protein Information Resource (PIR) is an integrated public resource of protein informatics that supports genomic and proteomic research and scientific discovery. PIR maintains the Protein Sequence Database (PSD), an annotated protein database containing over 283 000 sequences covering the entire taxonomic range. Family classification is used for sensitive identification, consistent annotation, and detection of annotation errors. The superfamily curation defines signature domain architecture and categorizes memberships to improve automated classification. To increase the amount of experimental annotation, the PIR has developed a bibliography system for literature searching, mapping, and user submission, and has conducted retrospective attribution of citations for experimental features. PIR also maintains NREF, a non-redundant reference database, and iProClass, an integrated database of protein family, function, and structure information. PIR-NREF provides a timely and comprehensive collection of protein sequences, currently consisting of more than 1 000 000 entries from PIR-PSD, SWISS-PROT, TrEMBL, RefSeq, GenPept, and PDB. The PIR web site (http://pir.georgetown.edu) connects data analysis tools to underlying databases for information retrieval and knowledge discovery, with functionalities for interactive queries, combinations of sequence and text searches, and sorting and visual exploration of search results. The FTP site provides free download for PSD and NREF biweekly releases and auxiliary databases and files.     

Annotating eukaryote genomes

The Genome Annotation Assessment Project tested current methods of gene identification, including a critical assessment of the accuracy of different methods. Two new databases have provided new resources for gene annotation: these are the InterPro database of protein domains and motifs, and the Gene Ontology database for terms that describe the molecular functions and biological roles of gene products. Efforts in genome annotation are most often based upon advances in computer systems that are specifically designed to deal with the tremendous amounts of data being generated by current sequencing projects. These efforts in analysis are being linked to new ways of visualizing computationally annotated genomes.