HitPick: a web server for hit identification and target prediction of chemical screenings

Liu, Xueping; Vogt, Ingo; Haque, Tanzeem; Campillos, Mónica

doi:10.1093/bioinformatics/btt303

Cited by 107 publications

(82 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To gain deeper insights into the molecular basis of these assay combinations, we extracted molecular information of the chemical hits shared by these pairs by annotating predicted human drug targets of the compounds. For that, we applied the HitPick target prediction method (Liu et al , 2013) to predict the molecular targets of hits with high confidence (precision > 50%). Interestingly, we found the same predicted drug targets related to several assay pairs.…”

Section: Resultsmentioning

confidence: 99%

“…This is particularly relevant for the hits of phenotypic assays, for which the underlying molecular targets responsible for their activity is unknown. To determine the protein targets of the chemical hits of these assays, in silico target prediction methods (Keiser et al , 2007; Liu et al , 2013; Wang et al , 2012) are arising as an efficient approach to obtain insights into the compound mode of action. For instance, Young et al have shown recently that the predicted molecular targets of hits are able to explain complex readouts of high-content screening assays (Young et al , 2008).…”

Section: Introductionmentioning

confidence: 99%

“…Subsequently, to understand the molecular mechanism linking pairs of phenotypic assays sharing chemical hits, we annotated the molecular targets of the shared hits. To that aim, we used HitPick (Liu et al , 2013), a recently developed in silico target prediction method to predict the molecular targets of compounds. We found that the known biological role of the predicted targets of common chemical hits confirms the biological processes relationships between the phenotypic assay pairs and provides mechanistic understanding of the relationships.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Unveiling new biological relationships using shared hits of chemical screening assay pairs

Liu

Campillos

2014

Bioinformatics

View full text Add to dashboard Cite

Motivation: Although the integration and analysis of the activity of small molecules across multiple chemical screens is a common approach to determine the specificity and toxicity of hits, the suitability of these approaches to reveal novel biological information is less explored. Here, we test the hypothesis that assays sharing selective hits are biologically related.Results: We annotated the biological activities (i.e. biological processes or molecular activities) measured in assays and constructed chemical hit profiles with sets of compounds differing on their selectivity level for 1640 assays of ChemBank repository. We compared the similarity of chemical hit profiles of pairs of assays with their biological relationships and observed that assay pairs sharing non-promiscuous chemical hits tend to be biologically related. A detailed analysis of a network containing assay pairs with the highest hit similarity confirmed biological meaningful relationships. Furthermore, the biological roles of predicted molecular targets of the shared hits reinforced the biological associations between assay pairs.Contact: monica.campillos@helmholtz-muenchen.deSupplementary information: Supplementary data are available at Bioinformatics online.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unveiling new biological relationships using shared hits of chemical screening assay pairs

Liu

Campillos

2014

Bioinformatics

View full text Add to dashboard Cite

show abstract

“…It is usually assumed that the use of multiple models can increase the prediction accuracy as compared to the use of a single model and help to manage high-dimensional and complex data sets. Similarly to our approach, several other studies have proven that merging a naïve Bayes classifier with a similarity-based approach such as k-nearest neighbors can result in highly predictive models for various applications including the prediction of molecular targets (Ferdousy et al, 2013;Liu et al, 2013). Future investigations could focus on the evaluation of other classification methods (logistic regression, random forests, etc.)…”

Section: Combination Of Features and Algorithmsmentioning

confidence: 90%

Molecular similarity-based predictions of the Tox21 screening outcome

Drwal

Siramshetty

Banerjee

et al. 2015

Front. Environ. Sci.

View full text Add to dashboard Cite

Citation:Drwal MN, Siramshetty VB, Banerjee P, Goede A, Preissner R and Dunkel M (2015) To assess the toxicity of new chemicals and drugs, regulatory agencies require in vivo testing for many toxic endpoints, resulting in millions of animal experiments conducted each year. However, following the Replace, Reduce, Refine (3R) principle, the development and optimization of alternative methods, in particular in silico methods, has been put into focus in the recent years. It is generally acknowledged that the more complex a toxic endpoint, the more difficult it is to model. Therefore, computational toxicology is shifting from modeling general and complex endpoints to the investigation and modeling of pathways of toxicity and the underlying molecular effects. The U.S. Toxicology in the twenty-first century (Tox21) initiative has screened a large library of compounds, including approximately 10K environmental chemicals and drugs, for different mechanisms responsible for eliciting toxic effects, and made the results publicly available. Through the Tox21 Data Challenge, the consortium has established a platform for computational toxicologists to develop and validate their predictive models. Here, we present a fast and successful method for the prediction of different outcomes of the nuclear receptor and stress response pathway screening from the Tox21 Data Challenge 2014. The method is based on the combination of molecular similarity calculations and a naïve Bayes machine learning algorithm and has been implemented as a KNIME pipeline. Molecules are represented as binary vectors consisting of a concatenation of common two-dimensional molecular fingerprint types with topological compound properties. The prediction method has been optimized individually for each modeled target and evaluated in a cross-validation as well as with the independent Tox21 validation set. Our results show that the method can achieve good prediction accuracies and rank among the top algorithms submitted to the prediction challenge, indicating its broad applicability in toxicity prediction.

show abstract

“…For example, prediction models have been developed based on the structural similarity of drugs to infer common targets [11,12]. A different approach, not relying on the structural similarity of drugs, predicts drug-target interactions based on the semantic similarity using drug side effects as data source [13].…”

Section: Introductionmentioning

confidence: 99%

Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies

et al. 2018

View full text Add to dashboard Cite

Aims: We propose a novel machine learning approach to expand the knowledge about drug-target interactions. Our method may help to develop effective, less harmful treatment strategies and to enable the detection of novel indications for existing drugs. Methods: We developed a novel machine learning strategy to predict drug-target interactions based on drug side effects and traits from genome-wide association studies. We integrated data from the databases SIDER and GWASdb and utilized them in a unique way by a neural network approach. Results: We validate our method using drug-target interactions from the STITCH database. In addition, we compare the chemical similarity of the predicted target to known targets of the drug under consideration and present literature-based evidence for predicted interactions. We find drug combination warnings for drugs we predict to target the same protein, hinting to synergistic effects aggravating harmful events. This substantiates the translational value of our approach, because we are able to detect drugs that should be taken together with care due to common mechanisms of action. Conclusion: Taken together, we conclude that our approach is able to generate a novel and clinically applicable insight into the molecular determinants of drug action.

show abstract

HitPick: a web server for hit identification and target prediction of chemical screenings

Cited by 107 publications

References 16 publications

Unveiling new biological relationships using shared hits of chemical screening assay pairs

Unveiling new biological relationships using shared hits of chemical screening assay pairs

Molecular similarity-based predictions of the Tox21 screening outcome

Novel Neural Network Approach to Predict Drug-Target Interactions Based on Drug Side Effects and Genome-Wide Association Studies

Contact Info

Product

Resources

About