Self-organizing neural network for modeling 3D QSAR of colchicinoids.

Polański, Jarosław

doi:10.18388/abp.2000_4060

Cited by 11 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of SOMs has been reported in the chemical and QSAR literature. [10][11][12][13][14][15] For instance, Zupan and Gasteiger designed a scheme for the application of the SOM algorithm for the projection of the molecular surface properties into two-dimensional feature maps, 16 and Polanski and Bek used a similar scheme for the comparison of molecules represented by atomic coordinates and superimposed by moments of inertia. 17 Prior to our original study, sSOMs had, to our knowledge, not been used to predict biological endpoints via classification of unknowns.…”

Section: Introductionmentioning

confidence: 99%

Supervised Self-Organizing Maps in Drug Discovery. 1. Robust Behavior with Overdetermined Data Sets

Xiao

Clauset

Harris

et al. 2005

J. Chem. Inf. Model.

View full text Add to dashboard Cite

The utility of the supervised Kohonen self-organizing map was assessed and compared to several statistical methods used in QSAR analysis. The self-organizing map (SOM) describes a family of nonlinear, topology preserving mapping methods with attributes of both vector quantization and clustering that provides visualization options unavailable with other nonlinear methods. In contrast to most chemometric methods, the supervised SOM (sSOM) is shown to be relatively insensitive to noise and feature redundancy. Additionally, sSOMs can make use of descriptors having only nominal linear correlation with the target property. Results herein are contrasted to partial least squares, stepwise multiple linear regression, the genetic functional algorithm, and genetic partial least squares, collectively referred to throughout as the "standard methods". The k-nearest neighbor (kNN) classification method was also performed to provide a direct comparison with a different classification method. The widely studied dihydrofolate reductase (DHFR) inhibition data set of Hansch and Silipo is used to evaluate the ability of sSOMs to classify unknowns as a function of increasing class resolution. The contribution of the sSOM neighborhood kernel to its predictive ability is assessed in two experiments: (1) training with the k-means clustering limit, where the neighborhood radius is zero throughout the training regimen, and (2) training the sSOM until the neighborhood radius is reduced to zero. Results demonstrate that sSOMs provide more accurate predictions than standard linear QSAR methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Supervised Self-Organizing Maps in Drug Discovery. 1. Robust Behavior with Overdetermined Data Sets

Xiao

Clauset

Harris

et al. 2005

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…First, there is considerable use of GAs and NNs on design problems. Looking more closely at these applications, a third of these applications are about drug design and involve quantifying structure-activity relationships (e.g., (Kovesdi et al 1999;Polanski et al 2002;Polanski et al 2000;So and Karplus 1997;Terfloth and Gasteiger 2001). A further 20% are applications in Engineering design such as design of concrete structures (Adeli and Park 1995;Cladera and Mari 2004;Deng et al 2003;Dias and Pooliyadda 2001;Hadi 2003), design of cold-form steel (Adeli and Park 1995;El-Kassas et al 2001;El-Kassas et al 2002;Karim and Adeli 1999) and the design of polymers (Zhang and Friedrich 2003).…”

Section: Analysis Current Trends and Discussionmentioning

confidence: 99%

“…Drug design represents more than a third of the neural network applications in design. Many of these focus on using the predicative power of the backpropagation algorithm to help quantify structure-activity relationships (Kovesdi et al 1999;Polanski et al 2002;Polanski et al 2000;So and Karplus 1997;Terfloth and Gasteiger 2001). Other uses include optimising release of drugs such as aspirin (Ibricacute et al 2003;Sun et al 2003;Wei et al 2001) and the pursuit of therapies for AIDS (Cai et al 1998;Sardari and Sardari 2002).…”

Section: Neural Network and Designmentioning

confidence: 99%

AI and OR in management of operations: history and trends

Kobbacy

Vadera

Rasmy

2007

Journal of the Operational Research Society

View full text Add to dashboard Cite

The last decade has seen a considerable growth in the use of AI for operations management with the aim of finding solutions to problems that are increasing in complexity and scale. This paper begins by setting the context for the survey through a historical perspective of OR and AI. An extensive survey of applications of AI techniques for operations management, covering a total of over 1200 papers published from 1995 to 2004 is then presented. The papers are categorised into four areas of operations management: (a) design, (b) scheduling, (c) process planning and control and (d) quality, maintenance and fault diagnosis. Each of the four areas is categorised in terms of the AI techniques used: genetic algorithms, case based reasoning, knowledge based systems, fuzzy logic and hybrid techniques. The trends over the last decade are identified, discussed with respect to expected trends and directions for future work suggested.

show abstract

“…A regression-based method for model self-organization is the group method of data handling (GMDH). 32,33,44,56 The GMDH combines the principles of statistics and ANNs under the framework of the principle of induction. The GMDH creates models adaptively guided by this cybernetic principle from data in the form of networks of optimized transfer functions (active neurons).…”

Section: Self-organizing Modelsmentioning

confidence: 99%

Predictive Modeling Techniques in Prostate Cancer

Tewari

Porter²,

Peabody³

et al. 2001

Molecular Urology

View full text Add to dashboard Cite

A number of new predictive modeling techniques have emerged in the past several years. These methods can be used independently or in combination with traditional modeling techniques to produce useful tools for the management of prostate cancer. Investigators should be aware of these techniques and avail themselves of their potentially useful properties. This review outlines selected predictive methods that can be used to develop models that may be useful to patients and clinicians for prostate cancer management.

show abstract

Self-organizing neural network for modeling 3D QSAR of colchicinoids.

Cited by 11 publications

References 34 publications

Supervised Self-Organizing Maps in Drug Discovery. 1. Robust Behavior with Overdetermined Data Sets

Supervised Self-Organizing Maps in Drug Discovery. 1. Robust Behavior with Overdetermined Data Sets

AI and OR in management of operations: history and trends

Predictive Modeling Techniques in Prostate Cancer

Contact Info

Product

Resources

About