Tiejun Cheng

Structure-Based Virtual Screening for Drug Discovery: a Problem-Centric Review

Structure-based virtual screening (SBVS) has been widely applied in early-stage drug discovery. From a problem-centric perspective, we reviewed the recent advances and applications in SBVS with a special focus on docking-based virtual screening. We emphasized the researchers’ practical efforts in real projects by understanding the ligand-target binding interactions as a premise. We also highlighted the recent progress in developing target-biased scoring functions by optimizing current generic scoring functions toward certain target classes, as well as in developing novel ones by means of machine learning techniques.

PubChem as a public resource for drug discovery

PubChem is a public repository of small molecules and their biological properties. Currently, it contains more than 25 million unique chemical structures and 90 million bioactivity outcomes associated with several thousand macromolecular targets. To address the potential utility of this public resource for drug discovery, we systematically summarized the protein targets in PubChem by function, 3D structure and biological pathway. Moreover, we analyzed the potency, selectivity and promiscuity of the bioactive compounds identified for these biological targets, including the chemical probes generated by the NIH Molecular Libraries Program. As a public resource, PubChem lowers the barrier for researchers to advance the development of chemical tools for modulating biological processes and drug candidates for disease treatments.

PubChem BioAssay: 2014 update

PubChem’s BioAssay database (http://pubchem.ncbi.nlm.nih.gov) is a public repository for archiving biological tests of small molecules generated through high-throughput screening experiments, medicinal chemistry studies, chemical biology research and drug discovery programs. In addition, the BioAssay database contains data from high-throughput RNA interference screening aimed at identifying critical genes responsible for a biological process or disease condition. The mission of PubChem is to serve the community by providing free and easy access to all deposited data. To this end, PubChem BioAssay is integrated into the National Center for Biotechnology Information retrieval system, making them searchable by Entrez queries and cross-linked to other biomedical information archived at National Center for Biotechnology Information. Moreover, PubChem BioAssay provides web-based and programmatic tools allowing users to search, access and analyze bioassay test results and metadata. In this work, we provide an update for the PubChem BioAssay resource, such as information content growth, new developments supporting data integration and search, and the recently deployed PubChem Upload to streamline chemical structure and bioassay submissions.

Identifying Compound-Target Associations by Combining Bioactivity Profile Similarity Search and Public Databases Mining

Molecular target identification is of central importance to drug discovery. Here, we developed a computational approach, named bioactivity profile similarity search (BASS), for associating targets to small molecules by using the known target annotations of related compounds from public databases. To evaluate BASS, a bioactivity profile database was constructed using 4296 compounds that were commonly tested in the US National Cancer Institute 60 human tumor cell line anticancer drug screen (NCI-60). Each compound was used as a query to search against the entire bioactivity profile database, and reference compounds with similar bioactivity profiles above a threshold of 0.75 were considered as neighbor compounds of the query. Potential targets were subsequently linked to the identified neighbor compounds by using the known targets of the query compound. About 45% of the predicted compound-target associations were successfully verified retrospectively, suggesting the possible application of BASS in identifying the targets of uncharacterized compounds and thus providing insight into the study of promiscuity and polypharmacology. Furthermore, BASS identified a significant fraction of structurally diverse compounds with similar bioactivities, indicating its feasibility of “scaffold hopping” in searching novel molecules against the target of interest.

Binary classification of aqueous solubility using support vector machines with reduction and recombination feature selection.

Aqueous solubility is recognized as a critical parameter in both the early- and late-stage drug discovery. Therefore, in silico modeling of solubility has attracted extensive interests in recent years. Most previous studies have been limited in using relatively small data sets with limited diversity, which in turn limits the predictability of derived models. In this work, we present a support vector machines model for the binary classification of solubility by taking advantage of the largest known public data set that contains over 46 000 compounds with experimental solubility. Our model was optimized in combination with a reduction and recombination feature selection strategy. The best model demonstrated robust performance in both cross-validation and prediction of two independent test sets, indicating it could be a practical tool to select soluble compounds for screening, purchasing, and synthesizing. Moreover, our work may be used for comparative evaluation of solubility classification studies ascribe to the use of completely public resources.

Pathway analysis for drug repositioning based on public database mining.

Sixteen FDA-approved drugs were investigated to elucidate their mechanisms of action (MOAs) and clinical functions by pathway analysis based on retrieved drug targets interacting with or affected by the investigated drugs. Protein and gene targets and associated pathways were obtained by data-mining of public databases including the MMDB, PubChem BioAssay, GEO DataSets, and the BioSystems databases. Entrez E-Utilities were applied, and in-house Ruby scripts were developed for data retrieval and pathway analysis to identify and evaluate relevant pathways common to the retrieved drug targets. Pathways pertinent to clinical uses or MOAs were obtained for most drugs. Interestingly, some drugs identified pathways responsible for other diseases than their current therapeutic uses, and these pathways were verified retrospectively by in vitro tests, in vivo tests, or clinical trials. The pathway enrichment analysis based on drug target information from public databases could provide a novel approach for elucidating drug MOAs and repositioning, therefore benefiting the discovery of new therapeutic treatments for diseases.

Investigating the correlations among the chemical structures, bioactivity profiles and molecular targets of small molecules

Motivation: Most of the previous data mining studies based on the NCI-60 dataset, due to its intrinsic cell-based nature, can hardly provide insights into the molecular targets for screened compounds. On the other hand, the abundant information of the compound–target associations in PubChem can offer extensive experimental evidence of molecular targets for tested compounds. Therefore, by taking advantages of the data from both public repositories, one may investigate the correlations between the bioactivity profiles of small molecules from the NCI-60 dataset (cellular level) and their patterns of interactions with relevant protein targets from PubChem (molecular level) simultaneously. Results: We investigated a set of 37 small molecules by providing links among their bioactivity profiles, protein targets and chemical structures. Hierarchical clustering of compounds was carried out based on their bioactivity profiles. We found that compounds were clustered into groups with similar mode of actions, which strongly correlated with chemical structures. Furthermore, we observed that compounds similar in bioactivity profiles also shared similar patterns of interactions with relevant protein targets, especially when chemical structures were related. The current work presents a new strategy for combining and data mining the NCI-60 dataset and PubChem. This analysis shows that bioactivity profile comparison can provide insights into the mode of actions at the molecular level, thus will facilitate the knowledge-based discovery of novel compounds with desired pharmacological properties. Availability: The bioactivity profiling data and the target annotation information are publicly available in the PubChem BioAssay database (ftp://ftp.ncbi.nlm.nih.gov/pubchem/Bioassay/). Contact: ywang@ncbi.nlm.nih.gov; bryant@ncbi.nlm.nih.gov Supplementary information: Supplementary data are available at Bioinformatics online.

PubChem applications in drug discovery: a bibliometric analysis

A bibliometric analysis of PubChem applications is presented by reviewing 1132 research articles. The massive volume of chemical structure and bioactivity data in PubChem and its online services have been used globally in various fields including chemical biology, medicinal chemistry and informatics research. PubChem supports drug discovery in many aspects such as lead identification and optimization, compound-target profiling, polypharmacology studies and unknown chemical identity elucidation. PubChem has also become a valuable resource for developing secondary databases, informatics tools and web services. The growing PubChem resource with its public availability offers support and great opportunities for the interrogation of pharmacological mechanisms and the genetic basis of diseases, which are vital for drug innovation and repurposing.

FSelector: a Ruby gem for feature selection

SUMMARY The FSelector package contains a comprehensive list of feature selection algorithms for supporting bioinformatics and machine learning research. FSelector primarily collects and implements the filter type of feature selection techniques, which are computationally efficient for mining large datasets. In particular, FSelector allows ensemble feature selection that takes advantage of multiple feature selection algorithms to yield more robust results. FSelector also provides many useful auxiliary tools, including normalization, discretization and missing data imputation. AVAILABILITY FSelector, written in the Ruby programming language, is free and open-source software that runs on all Ruby supporting platforms, including Windows, Linux and Mac OS X. FSelector is available from https://rubygems.org/gems/fselector and can be installed like a breeze via the command gem install fselector. The source code is available (https://github.com/need47/fselector) and is fully documented (http://rubydoc.info/gems/fselector/frames).

Predicting drug–drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge

Drug–drug interactions (DDIs) may lead to adverse effects and potentially result in drug withdrawal from the market. Predicting DDIs during drug development would help reduce development costs and time by rigorous evaluation of drug candidates. The primary mechanisms of DDIs are based on pharmacokinetics (PK) and pharmacodynamics (PD). This study examines the effects of 2D structural similarities of drugs on DDI prediction through interaction networks including both PD and PK knowledge. Our assumption was that a query drug (Dq) and a drug to be examined (De) likely have DDI if the drugs in the interaction network of De are structurally similar to Dq. A network of De describes the associations between the drugs and the proteins relating to PK and PD for De. These include target proteins, proteins interacting with target proteins, enzymes, and transporters for De. We constructed logistic regression models for DDI prediction using only 2D structural similarities between each Dq and the drugs in the network of De. The results indicated that our models could effectively predict DDIs. It was found that integrating structural similarity scores of the drugs relating to both PK and PD of De was crucial for model performance. In particular, the combination of the target- and enzyme-related scores provided the largest increase of the predictive power.Graphical abstract.