A statistical-heuristic method for automated selection of drugs for screening

Hodes, Louis; Hazard, George F.; Geran, R. I.; Richman, Sidney

doi:10.1021/jm00214a002

Cited by 58 publications

(30 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A score is then computed for a test-set molecule by summing (or otherwise combining) the weights of those bits that are set in its fingerprint, this sum representing the overall probability of activity for that molecule given that it contains a particular pattern of bits. Substructural analysis was studied in considerable detail by workers at the National Institutes of Health in an extended programme to develop novel anti-cancer agents [47][48][49], and also by workers at Lederle [29] and Sheffield [50][51][52]. However, it is only in the last few years that this general approach has become widely used [53][54][55][56][57][58][59][60][61][62].…”

Section: Substructural Analysis Naive Bayesian Classifiers and Groupmentioning

confidence: 99%

Evaluation of machine-learning methods for ligand-based virtual screening

Chen

Harrison

Papadatos

et al. 2007

J Comput Aided Mol Des

115

View full text Add to dashboard Cite

Abstract. Machine-learning methods can be used for virtual screening by analysing the structural characteristics of molecules of known (in)activity, and we here discuss the use of kernel discrimination and naive Bayesian classifier methods for this purpose. We report a kernel method that allows the processing of molecules represented by binary, integer and real-valued descriptors, and show that it is little different in screening performance from a previously described kernel that had been developed specifically for the analysis of binary fingerprint representations of molecular structure. We then evaluate the performance of a naive Bayesian classifier when the training-set contains only a very few active molecules. In such cases, a simpler approach based on group fusion would appear to provide superior screening performance, especially when structurally heterogeneous datasets are to be processed.

show abstract

Section: Substructural Analysis Naive Bayesian Classifiers and Groupmentioning

confidence: 99%

Evaluation of machine-learning methods for ligand-based virtual screening

Chen

Harrison

Papadatos

et al. 2007

J Comput Aided Mol Des

115

View full text Add to dashboard Cite

show abstract

“…A similar approach has already been applied in earlier computer-aided methods (21)(22)(23) for predicting different biological activities (antiarthritic-immunoregulatory effects and antineoplastic effects). In these earlier works, not all the possible fragments within a given range of nonhydrogen atoms were generated, but only a limited subset of fragments, such as augmented atoms, heteropaths, and ring fragments.…”

Section: Methods Software Featuresmentioning

confidence: 99%

Relationship between Molecular Connectivity and Carcinogenic Activity: A Confirmation with a New Software Program Based on Graph Theory

Malacarne¹,

Pesenti²,

Paolucci³

et al. 1993

Environmental Health Perspectives

View full text Add to dashboard Cite

“…A score is then obtained for a molecule of unknown activity by summing the weights for its constituent fragments. The resulting score represents the molecule's probability of activity, and untested molecules can hence be prioritised for screening in order of decreasing probability of activity; the anticancer screening programme that was carried out during the Eighties by the National Cancer Institute [133] is an important example of such an approach. Substructural analysis is important not just in its own right but also as the first example of machine learning being used on a large scale in chemoinformatics since, although not realised at the time [134], substructural analysis is an example of a naive Bayesian classifier, a machine-learning technique that is now widely used for the analysis of biological screening data [135].…”

Section: Quantitative Structure-activity Relationships and Molecular mentioning

confidence: 99%

From chemical documentation to chemoinformatics: 50 years of chemical information science

Willett

2008

Journal of Information Science

View full text Add to dashboard Cite

This paper summarises the historical development of the discipline that is now called 'chemoinformatics'. It shows how this has evolved, principally as a result of technological developments in chemistry and biology during the past decade, from long-established techniques for the modelling and searching of chemical molecules. A total of 30 papers, the earliest dating back to 1957, are briefly summarised to highlight some of the key publications and to show the development of the discipline.Keywords: Chemical documentation; Chemical structures; Chemoinformatics; Drug discovery; History; Informatics; Molecules; Pharmaceutical research IntroductionChemistry is, and has been for many years, one of the most information-rich academic disciplines. The very first journal devoted to chemistry was Chemisches Journal, which was published 1778-1784 and then, under the name of Chemische Annalen, till 1803 [1]. The growth in the chemical literature during the 19 th century led to a recognition of the need for comprehensive abstracting and indexing services for the chemical sciences. The principal such service is Chemical Abstracts Service (CAS), which was established in 1907 and which acts as the central repository for the world's published chemical (and, increasingly, life-sciences) information. The size of this repository is impressive: at the end of its first year of operations, the CAS database contained ca. 12K abstracts; by the end of 2006, this had grown to ca. 25M abstracts with ca. 1M being added each year. Most chemical publications will refer to one or more chemical substances. The structures of these substances form a vitally important part of the chemical literature, and one that distinguishes chemistry from many other disciplines. The CAS Registry System was started in 1965 to provide access to substance information, initially registering just small organic and inorganic molecules but now also registering biological sequences [2]. At the end of 1965 there 1 Correspondence to: Prof. Peter Willett, Department of Information Studies, University of Sheffield, 211 Portobello Street, Sheffield S1 4DP, UK; p.willett@sheffield.ac.uk. Journal of Information Science, XX (X) 2007, pp. 1-24 © CILIP, DOI: 10.1177/0165551506nnnnnn 1 Peter Willettwere ca. 222K substances in the System; by the end of 2006 this had grown to ca. 89M substances, of which ca. one-third were small molecules and the remainder biological sequences, with ca. 1.5M being added each year. There are also many additional molecular structures in public databases such as the Beilstein Database [3], and corporate files, in particular those of the major pharmaceutical, agrochemical and biotechnology companies.The presence of chemical structures requires very different computational techniques from those used for processing conventional textual information. These specialised techniques -now referred to by the name of chemoinformatics as discussed further below -have developed steadily over the fifty years that have passed since the founding of the I...

show abstract

A statistical-heuristic method for automated selection of drugs for screening

Cited by 58 publications

References 2 publications

Evaluation of machine-learning methods for ligand-based virtual screening

Evaluation of machine-learning methods for ligand-based virtual screening

Relationship between Molecular Connectivity and Carcinogenic Activity: A Confirmation with a New Software Program Based on Graph Theory

From chemical documentation to chemoinformatics: 50 years of chemical information science

Contact Info

Product

Resources

About