GSA: a GPU-accelerated structure similarity algorithm and its application in progressive virtual screening

Yan, Xin; Gu, Qiong; Lu, F.; Li, Jiabo; Xu, Jing

doi:10.1007/s11030-012-9403-0

Cited by 16 publications

(18 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, virtual screening tools were developed in our lab based on atom center fragments (ACFs) approach [36]–[40]. A program (called ACFs_NB), which can classify compounds into actives and non-actives based on ACFs and Bayesian rules, has been implemented in our lab.…”

Section: Resultsmentioning

confidence: 99%

Predicting mTOR Inhibitors with a Classifier Using Recursive Partitioning and Naïve Bayesian Approaches

et al. 2014

Self Cite

View full text Add to dashboard Cite

BackgroundMammalian target of rapamycin (mTOR) is a central controller of cell growth, proliferation, metabolism, and angiogenesis. Thus, there is a great deal of interest in developing clinical drugs based on mTOR. In this paper, in silico models based on multi-scaffolds were developed to predict mTOR inhibitors or non-inhibitors.MethodsFirst 1,264 diverse compounds were collected and categorized as mTOR inhibitors and non-inhibitors. Two methods, recursive partitioning (RP) and naïve Bayesian (NB), were used to build combinatorial classification models of mTOR inhibitors versus non-inhibitors using physicochemical descriptors, fingerprints, and atom center fragments (ACFs).ResultsA total of 253 models were constructed and the overall predictive accuracies of the best models were more than 90% for both the training set of 964 and the external test set of 300 diverse compounds. The scaffold hopping abilities of the best models were successfully evaluated through predicting 37 new recently published mTOR inhibitors. Compared with the best RP and Bayesian models, the classifier based on ACFs and Bayesian shows comparable or slightly better in performance and scaffold hopping abilities. A web server was developed based on the ACFs and Bayesian method (http://rcdd.sysu.edu.cn/mtor/). This web server can be used to predict whether a compound is an mTOR inhibitor or non-inhibitor online.Conclusion In silico models were constructed to predict mTOR inhibitors using recursive partitioning and naïve Bayesian methods, and a web server (mTOR Predictor) was also developed based on the best model results. Compound prediction or virtual screening can be carried out through our web server. Moreover, the favorable and unfavorable fragments for mTOR inhibitors obtained from Bayesian classifiers will be helpful for lead optimization or the design of new mTOR inhibitors.

show abstract

Section: Resultsmentioning

confidence: 99%

Predicting mTOR Inhibitors with a Classifier Using Recursive Partitioning and Naïve Bayesian Approaches

et al. 2014

Self Cite

View full text Add to dashboard Cite

show abstract

“…Polyene (13) is isolated from the network; it is not commonly combined with other chemoyls. Flavones ( 1 ), steroids ( 7 ), alkaloids ( 14 ) and terpenes ( 15 ) are most frequently (indicated by darker lines) present in natural products simultaneously, so as to exhibit more bioactivities.…”

Section: Resultsmentioning

confidence: 99%

“…Based upon the rules of chemoyl combination and related bioactivities, quasi-natural product libraries can be constructed from a set of biochemoyls for specified bioactivities and virtual screening can be performed against drug targets using a number of computational tools (15)(16)(17)(18)(19). A consequent challenge is to develop feasible synthetic technologies to make the libraries.…”

Section: Discussionmentioning

confidence: 99%

Drug Discovery Inspired by Mother Nature: Seeking Natural Biochemotypes and the Natural Assembly Rules of the Biochemome

Yan

2013

J Pharm Pharm Sci

Self Cite

View full text Add to dashboard Cite

Purpose. The Human Genome Project is producing a new biological ‘periodic table’, which defines all genes for making macromolecules (proteins, DNA, RNA, etc) and the relations between genes and their biological functions. We now need to consider whether to initiate a biochemome project aimed at discovering biochemistry’s ‘periodic table’, which would define all molecular parts for making small molecules (natural products) and the relations between the parts and their functions to regulate genes. By understanding the Biochemome, we might be able to design biofunctional molecules based upon a set of molecular parts for drug innovation. Methods. A number of algorithms for processing chemical structures are used to systematically derive chemoyls (natural building blocks) from a database of compounds identified in Traditional Chinese Medicine (TCM). The rules to combine chemoyls for biological activities are then deduced by mining an annotated TCM structure-activity database (ATCMD). Based upon the rules and the basic chemoyls, a chemical library can be biochemically profiled, virtual synthetic routes can be planned, and lead compounds can be identified for a specific drug target. Conclusions. The Biochemome is the complete set of molecular components (chemoyls) in an organism and Biochemomics studies the rules governing their assembly and their evolution, together with the relations between the Biochemome and drug targets. This approach provides a new paradigm for drug discovery that is based on a comprehensive knowledge of the synthetic origins of biochemical diversity, and helps to direct biomimetic syntheses aimed at assembling quasi-natural product libraries for drug screening. This article is open to POST-PUBLICATION REVIEW. Registered readers (see “For Readers”) may comment by clicking on ABSTRACT on the issue’s contents page.

show abstract

“…Each component in the descriptor vector is the count of a designated substructure that appeared in the compound. The designated substructures for the vector can be empirical (such as MDL 166 search keys or 960 extended search keys 32 , Daylight fingerprints 38 , or atom center fragments 13 , 39 ). In this work, we select the designated substructures for the vector based upon statistics.…”

Section: Methodsmentioning

confidence: 99%

A de novo substructure generation algorithm for identifying the privileged chemical fragments of liver X receptorβ agonists

Peng

Liu

Yan

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

Liver X receptorβ (LXRβ) is a promising therapeutic target for lipid disorders, atherosclerosis, chronic inflammation, autoimmunity, cancer and neurodegenerative diseases. Druggable LXRβ agonists have been explored over the past decades. However, the pocket of LXRβ ligand-binding domain (LBD) is too large to predict LXRβ agonists with novel scaffolds based on either receptor or agonist structures. In this paper, we report a de novo algorithm which drives privileged LXRβ agonist fragments by starting with individual chemical bonds (de novo) from every molecule in a LXRβ agonist library, growing the bonds into substructures based on the agonist structures with isomorphic and homomorphic restrictions, and electing the privileged fragments from the substructures with a popularity threshold and background chemical and biological knowledge. Using these privileged fragments as queries, we were able to figure out the rules to reconstruct LXRβ agonist molecules from the fragments. The privileged fragments were validated by building regularized logistic regression (RLR) and supporting vector machine (SVM) models as descriptors to predict a LXRβ agonist activities.

show abstract

GSA: a GPU-accelerated structure similarity algorithm and its application in progressive virtual screening

Cited by 16 publications

References 37 publications

Predicting mTOR Inhibitors with a Classifier Using Recursive Partitioning and Naïve Bayesian Approaches

Predicting mTOR Inhibitors with a Classifier Using Recursive Partitioning and Naïve Bayesian Approaches

Drug Discovery Inspired by Mother Nature: Seeking Natural Biochemotypes and the Natural Assembly Rules of the Biochemome

A de novo substructure generation algorithm for identifying the privileged chemical fragments of liver X receptorβ agonists

Contact Info

Product

Resources

About