Use of a microcomputer for the definition of multivariate confidence regions in medical diagnosis based on clinical laboratory profiles

Coomans, Danny; Broeckaert, I.; Derde, Marie-Paule; Tassin, Aude; Massart, D.L.; Wold, Svante

doi:10.1016/0010-4809(84)90002-8

Cited by 73 publications

(45 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4 Coomans' plots of distance to model for Class 1 and GAT1 inhibitors. Coomans' plots (Coomans et al 1984) illustrate two selected models (e.g. Class A and Class B) and plot the distance to each of the selected models along with the critical distance.…”

Section: Discussionmentioning

confidence: 99%

“…Next, we were interested to discover objectively whether the GAT1 inhibitor metabolic profiles were truly similar to those from Class 1 GABA receptors. This was done by use of a Coomans' plot (Coomans et al 1984) which plots the class distances of two models against each other in a scatter plot. The distance to model (DModX) of an observation is the same as the residual standard deviation of the observation.…”

Section: Analysis Of Similar Metabolic Outcomesmentioning

confidence: 99%

See 1 more Smart Citation

A metabonomic study of inhibition of GABA uptake in the cerebral cortex

2009

View full text Add to dashboard Cite

GABAergic activity is regulated by rapid, high affinity uptake of GABA from the synapse. Perturbation of GABA reuptake has been implicated in neurological disease and inhibitors of GABA transporters (GAT) have been used therapeutically but little detail is known about the ramifications of GAT inhibition on brain neurochemistry. Here, we incubated Guinea pig cortical tissue slices with [3-13 C]pyruvate and major, currently available GABA uptake inhibitors. Metabolic fingerprints were generated from these experiments using 13 C/ 1 H NMR spectroscopy. These fingerprints were analyzed using multivariate statistical approaches and compared with an existing library of fingerprints of activity at GABA receptors. This approach identified five distinct clusters of metabolic activity induced by blocking GABA uptake. Inhibition of GABA uptake via GAT1 produced patterns similar to activity at mainstream GABAergic synapses in particular those containing a1-subunits but still statistically separable. This indicated that inhibition of GABA uptake, an indirect method of activating GABA receptors, produces different effects to direct receptor activation or to exogenous GABA. The mechanism of inhibitor function also produced different outcomes, with the channel blocker SKF 89976A yielding a unique metabolic response. Blocking GAT1 and GAT3 simultaneously induces a large metabolic response consistent with induction of tonic inhibition via high affinity GABA receptors. Blocking BGT produces patterns similar to activity at less common receptors such as those containing a5 subunits. This approach is useful for determining where in the spectrum of GABAergic responses a particular GABA transport inhibitor is effective.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Analysis Of Similar Metabolic Outcomesmentioning

confidence: 99%

A metabonomic study of inhibition of GABA uptake in the cerebral cortex

2009

View full text Add to dashboard Cite

show abstract

“…Cooman's plots 44 were used for the discrimination of classes and S o was calculated according Eq. (6) for evaluate the class compaction in each model.…”

Section: B) Pattern Recognition Methodsmentioning

confidence: 99%

Supervised Pattern Recognition Techniques for Classification of Eucalyptus Species From Leaves Nir Spectra

Castillo

Contreras

Freer

et al. 2008

J. Chil. Chem. Soc.

View full text Add to dashboard Cite

Three supervised pattern recognition methods (SPRM) were evaluated to discriminate between Eucalyptus globulus and Eucalyptus nitens species applying near infrared (NIR) spectroscopy on leaves. The methods used were k-nearest neighbor (KNN), soft modeling class analogy (SIMCA) and discriminant partial least squares (PLS-DA). First and second derivatives were used as transform techniques and mean-center (MC) and autoscaling (AS) as preprocessing techniques. The training set was constitued by 288 samples and 20 samples were used as validation set. A significant difference between the assayed methods was not observed, however best results for separation of classes and prediction rate were obtained when first derivative and MC were used for all the recognition pattern methods. Use of leaves and NIR spectroscopy avoids the destructive usual wood analysis in forest industries and facilities the fast classification of these species for forest applications.

show abstract

“…SIMCA uses PCA to generate significance limits for the classes in the scores and the residual direction. The SIMCA output can be visualized with the Coomans plot [34], which highlights class distances against each other for two classes at a time. We calculated one separate PCA for each MOA class and the number of significant PCs for each modeled MOA class was determined according to the cross-validation procedure adopted by the SIMCA À P þ package [24].…”

Section: Comparison Of Classification Performance With Simcamentioning

confidence: 99%

ChemGPS‐NP Mapping of Chemical Compounds for Prediction of Anticancer Mode of Action

et al. 2009

View full text Add to dashboard Cite

A combined graph describing the growth inhibition values from a number of human cancer cell lines represents an activity profile for a compound. The fact that compounds with similar activity profiles often show similar Mode of Action (MOA) has frequently been used in prediction of MOA. Obtaining the profiles is demanding with respect to both time and resources. Therefore, as a work and time efficient alternative, we explore the central premise of medicinal chemistry that structurally similar molecules often have similar biological activity. In this study we investigate correlations between chemical structure and MOA, and subsequently use this as a complementing basis for prediction. The correlations between MOA and activity profile on one hand and between MOA and chemical structure on the other were analyzed for anticancer agents, classified with regard to MOA, using Principal Component Analysis (PCA), chemographic mapping with ChemGPS-NP, and Orthogonal Partial Least Squares Discriminant Analysis (OPLS-DA). The compounds clustered according to MOA both based on chemical structures and activity profiles. The subsequent validation with external test sets showed that initial PCA scores prediction or chemographic mapping followed by OPLS-DA could be used for the prediction of MOA as well as identification of novel MOAs in a highly accurate way. An efficient and straight forward procedure for the prediction of MOA of anticancer agents is suggested. With todays resistance problems in cancer therapy, there is a need for new anticancer agents and mechanisms. We believe that the fast initial virtual guidance this procedure implies, especially the novel step using ChemGPS-NP, could be of general use in early stages of cancer research.

show abstract

Use of a microcomputer for the definition of multivariate confidence regions in medical diagnosis based on clinical laboratory profiles

Cited by 73 publications

References 13 publications

A metabonomic study of inhibition of GABA uptake in the cerebral cortex

A metabonomic study of inhibition of GABA uptake in the cerebral cortex

Supervised Pattern Recognition Techniques for Classification of Eucalyptus Species From Leaves Nir Spectra

ChemGPS‐NP Mapping of Chemical Compounds for Prediction of Anticancer Mode of Action

Contact Info

Product

Resources

About