Impact of Orthogonal Signal Correction (OSC) on the predictive
ability of CoMFA models for the ciliate toxicity of
nitrobenzenes

J 2002

Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes

BOHÁČ, Michal; Bjorn LOEPRECHT; Jiří DAMBORSKÝ a Gerrit SCHUURMANN

Základní údaje

Originální název

Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes

Autoři

BOHÁČ, Michal; Bjorn LOEPRECHT; Jiří DAMBORSKÝ a Gerrit SCHUURMANN

Vydání

Quantitative Structure-Activity Relationships, 2002, 0931-8771

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10600 1.6 Biological sciences

Stát vydavatele

Německo

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 1.558

Kód RIV

RIV/00216224:14310/02:00006265

Organizační jednotka

Přírodovědecká fakulta

UT WoS

000176149600001

Klíčová slova anglicky

QSAR; VALIDATION; COMFA; GOLPE; VARIABLE SELECTION

Štítky

COMFA, GOLPE, QSAR, validation, VARIABLE SELECTION

Změněno: 19. 3. 2010 10:54, prof. Mgr. Jiří Damborský, Dr.

Anotace

V originále

The impact of orthogonal signal correction (OSC) on the prediction power of CoMFA models was studied using a data set of 47 nitrobenzenes with toxicities (log 1/IC50) towards the aquatic ciliates Tetrahymena pyriformis. Comparative analyses of different data pre-treatments shows that block unscaled weighting (BUW) results in significantly better PLS models than no scaling, centering or autoscaling for OSC. One OSC component is optimal for the signal correction and reduces the X variance by about 40%. While OSC yields improved calibration and cross-validation statistics, standard CoMFA is superior with respect to the external prediction power as evaluated by models built from complementary subsets. Moreover, external prediction reveals some cases of severe OSC overfitting, which needs attention in future investigations.

Návaznosti

ME 276, projekt VaV

Název: Racionální re-design mikrobiálních enzymů podílejících se na degradaci toxických organických polutantů

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Racionální re-design mikrobiálních enzymů podílejících se na degradaci toxických organických polutantů

MSM 143100005, záměr

Název: Strukturně-funkční vztahy biomolekul a jejich role v metabolismu

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, Strukturně-funkční vztahy biomolekul a jejich role v metabolismu

Citovat

BOHÁČ, Michal; Bjorn LOEPRECHT; Jiří DAMBORSKÝ a Gerrit SCHUURMANN. Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes. Quantitative Structure-Activity Relationships. 2002, roč. 21, č. 1, s. 3-11. ISSN 0931-8771.

@article{404592,
   author = {Boháč, Michal and Loeprecht, Bjorn and Damborský, Jiří and Schuurmann, Gerrit},
   article_number = {1},
   keywords = {QSAR; VALIDATION; COMFA; GOLPE; VARIABLE SELECTION},
   language = {eng},
   issn = {0931-8771},
   journal = {Quantitative Structure-Activity Relationships},
   title = {Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes},
   url = {http://ncbr.chemi.muni.cz/~jiri/ABSTRACTS/qsarj02.html},
   volume = {21},
   year = {2002}
}

TY  - JOUR
ID  - 404592
AU  - Boháč, Michal - Loeprecht, Bjorn - Damborský, Jiří - Schuurmann, Gerrit
PY  - 2002
TI  - Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes
JF  - Quantitative Structure-Activity Relationships
VL  - 21
IS  - 1
SP  - 3
EP  - 3
SN  - 09318771
KW  - QSAR
KW  - VALIDATION
KW  - COMFA
KW  - GOLPE
KW  - VARIABLE SELECTION
UR  - http://ncbr.chemi.muni.cz/~jiri/ABSTRACTS/qsarj02.html
N2  - The impact of orthogonal signal correction (OSC) on the prediction power of CoMFA models was studied using a data set of 47 nitrobenzenes with toxicities (log 1/IC50) towards the aquatic ciliates Tetrahymena pyriformis. Comparative analyses of different data pre-treatments shows that block unscaled weighting (BUW) results in significantly better PLS models than no scaling, centering or autoscaling for OSC. One OSC component is optimal for the signal correction and reduces the X variance by about 40%. While OSC yields improved calibration and cross-validation statistics, standard CoMFA is superior with respect to the external prediction power as evaluated by models built from complementary subsets. Moreover, external prediction reveals some cases of severe OSC overfitting, which needs attention in future investigations.
ER  -

BOHÁČ, Michal; Bjorn LOEPRECHT; Jiří DAMBORSKÝ a Gerrit SCHUURMANN. Impact of Orthogonal Signal Correction (OSC) on the predictive ability of CoMFA models for the ciliate toxicity of nitrobenzenes. \textit{Quantitative Structure-Activity Relationships}. 2002, roč.~21, č.~1, s.~3-11. ISSN~0931-8771.

Přehled o publikaci