Two recent articles (Pucci et al., 2018; Usmanova et al., 2018) proposed two ad hoc datasets and evaluation procedures to quantify an important bias in the predictors of protein stability changes (ΔΔG) upon single-point variations. Current datasets are dominated by destabilizing variations. Thus predictors (trained on those datasets) tend to perform better on destabilizing rather than on stabilizing variations. However, as highlighted before (Capriotti et al., 2008; Christensen and Kepp 2012; Pucci et al., 2015, 2018; Thiltgen and Goldstein 2012; Usmanova et al., 2018), there must be an intrinsic anti-symmetric property in the Physics of the ΔΔG.
On the biases in predictions of protein stability changes upon variations: the INPS test case / Montanucci, Ludovica; Savojardo, Castrense; Martelli, Pier Luigi; Casadio, Rita; Fariselli, Piero. - In: BIOINFORMATICS. - ISSN 1367-4803. - ELETTRONICO. - 35:14(2019), pp. 2525-2527. [10.1093/bioinformatics/bty979]
On the biases in predictions of protein stability changes upon variations: the INPS test case
Savojardo, Castrense;Martelli, Pier Luigi;Casadio, Rita;
2019
Abstract
Two recent articles (Pucci et al., 2018; Usmanova et al., 2018) proposed two ad hoc datasets and evaluation procedures to quantify an important bias in the predictors of protein stability changes (ΔΔG) upon single-point variations. Current datasets are dominated by destabilizing variations. Thus predictors (trained on those datasets) tend to perform better on destabilizing rather than on stabilizing variations. However, as highlighted before (Capriotti et al., 2008; Christensen and Kepp 2012; Pucci et al., 2015, 2018; Thiltgen and Goldstein 2012; Usmanova et al., 2018), there must be an intrinsic anti-symmetric property in the Physics of the ΔΔG.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
