Sample-distance partial least squares: PLS optimized for many variables, with application to CoMFA

Bush, Bruce L.; Nachbar, Robert B.

doi:10.1007/bf00124364

Cited by 405 publications

(259 citation statements)

References 32 publications

Supporting

Mentioning

258

Contrasting

Unclassified

Order By: Relevance

“…Then, a partial least squares technique (PLS) was employed to derive a CoMFA model expressing the correlation between the steric and electrostatic properties and the biological activities [26,27]. The orthogonal latent variables were extracted by the NIPALS algorithm and subjected to full crossvalidation with the Leave-One-Out method (LOO) [28,29].…”

Section: Methods Of Comfa Studymentioning

confidence: 99%

Particular interaction between pyrimethamine derivatives and quadruple mutant type dihydrofolate reductase of Plasmodium falciparum: CoMFA and quantum chemical calculations studies

Maitarad

Saparpakorn

Hannongbua

et al. 2008

Journal of Enzyme Inhibition and Medicinal Chemistry

View full text Add to dashboard Cite

Comparative molecular field analysis (CoMFA) was performed on twenty-three pyrimethamine (pyr) derivatives active against quadruple mutant type (Asn51Ile, Cys59Arg, Ser108Asn, Ile164Leu) dihydrofolate reductase of Plasmodium falcipaarum (Pf DHFR). The represented CoMFA models were evaluated based on the various three different probe atoms, C sp3 (þ1), O sp3 (21) and H (þ1), resulting in the best model with combined three types of probe atoms. The statistical results were r 2 cv ¼ 0.702, S press ¼ 0.608, r 2 nv ¼ 0.980, s ¼ 0.156, and r 2 test2set ¼ 0.698 which can explain steric contribution of about 50%. In addition, an understanding of particular interaction energy between inhibitor and surrounding residues in the binding pocket was performed by using MP2/6-31G(d,p) quantum chemical calculations. The obtained results clearly demonstrate that Asn108 is the cause of pyr resistance with the highest repulsive interaction energy. Therefore, CoMFA and particular interaction energy analyses can be useful for identifying the structural features of potent pyr derivatives active against quadruple mutant type Pf DHFR.

show abstract

Section: Methods Of Comfa Studymentioning

confidence: 99%

Particular interaction between pyrimethamine derivatives and quadruple mutant type dihydrofolate reductase of Plasmodium falciparum: CoMFA and quantum chemical calculations studies

Maitarad

Saparpakorn

Hannongbua

et al. 2008

Journal of Enzyme Inhibition and Medicinal Chemistry

View full text Add to dashboard Cite

show abstract

“…13 Subsequently, the final 3D-QSAR models were derived from the non-cross-validated calculations. The CoMSIA results were graphically interpreted by the field contribution maps using the field type "stdev*coeff".…”

Section: Methodsmentioning

confidence: 99%

Three-Dimensional Quantitative Structure−Activity Relationship Analysis of the New Potent Sulfonylureas Using Comparative Molecular Similarity Indices Analysis

Hou

Li²,

Liu³

et al. 2000

J. Chem. Inf. Comput. Sci.

View full text Add to dashboard Cite

The present study describes the implementation of a new three-dimensional quantitative structure-activity relationship (3D-QSAR) technique: comparative molecular similarity indices analysis (CoMSIA) to a set of novel herbicidal sulfonylureas targeted acetolactate synthase. Field expressions in terms of similarity indices in CoMSIA were applied instead of the usually used Lennard-Jones and Coulomb-type potentials in CoMFA. Two different kinds of alignment techniques including field-fit alignment and atom-by-atom fits were used to produce the molecular aggregate. The results indicated that those two alignment rules generated comparative 3D-QSAR models with similar statistical significance. However, from the predictive ability of the test set, the models from the alignment after maximal steric and electrostatic optimization were slightly better than those from the simple atom-by-atom fits. Moreover, systematic variations of some parameters in CoMSIA were performed to search the best 3D-QSAR model. A significant cross-validated q 2 was obtained, indicating the predictive potential of the model for the untested compounds; meanwhile the predicted biological activities of the five compounds in the test set were in good agreement with the experimental values. The CoMSIA coefficient contour plots identified several key features explaining the wide range of activities, which were very valuable for us in tracing the properties that really matter and getting insight into the potential mechanisms of the intermolecular interactions between inhibitor and receptor, especially with respect to the design of new compounds.

show abstract

“…Both LOO and LNO CV have been implemented the advantages and disadvantages of these two approaches are discussed below. The SAMPLS algorithm [13] provides a highly efficient implementation of PLS-1 and, for univariate Y only, gives identical results to the classical NIPALS [5] and SIMPLS [14] algorithms.…”

Section: Searching For An Optimal Solution (V Opt ) Eva_gamentioning

confidence: 99%

Untitled

Turner

Willett

2000

Journal of Computer-Aided Molecular Design

View full text Add to dashboard Cite

SummaryThe EVA structural descriptor, based upon calculated fundamental molecular vibrational frequencies, has proved to be an effective descriptor for both QSAR and database similarity calculations. The descriptor is sensitive to 3D structure but has an advantage over fieldbased 3D-QSAR methods inasmuch as structural superposition is not required. The original technique involves a standardisation method wherein uniform Gaussians of fixed standard deviation (σ) are used to smear out frequencies projected onto a linear scale. This smearing function permits the overlap of proximal frequencies and thence the extraction of a fixed dimensional descriptor regardless of the number and precise values of the frequencies. It is proposed here that there exist optimal localised values of σ in different spectral regions; that is, the overlap of frequencies using uniform Gaussians may, at certain points in the spectrum, either be insufficient to pick up relationships where they exist or mix up information to such an extent that significant correlations are obscured by noise. A genetic algorithm is used to search for optimal localised σ values using crossvalidated PLS regression scores as the fitness score to be optimised. The resultant models are then validated against a previously unseen test set of compounds. The performance of EVA_GA is compared to that of EVA and analogous CoMFA studies.

show abstract

Sample-distance partial least squares: PLS optimized for many variables, with application to CoMFA

Cited by 405 publications

References 32 publications

Particular interaction between pyrimethamine derivatives and quadruple mutant type dihydrofolate reductase of Plasmodium falciparum: CoMFA and quantum chemical calculations studies

Particular interaction between pyrimethamine derivatives and quadruple mutant type dihydrofolate reductase of Plasmodium falciparum: CoMFA and quantum chemical calculations studies

Three-Dimensional Quantitative Structure−Activity Relationship Analysis of the New Potent Sulfonylureas Using Comparative Molecular Similarity Indices Analysis

Untitled

Contact Info

Product

Resources

About