Identification of concealed structural alerts using QSTR modeling for Pseudokirchneriella subcapitata

Document Type

Article

Publication Date

Fall 10-1-2021

Abstract

In the present work, QSTR modeling was conducted for microalga Pseudokirchneriella subcapitata using a data set of 271 molecules belonging to different types of chemical classes for the prediction of EC50 for 72 hr based assays. The balanced QSTR model encompasses seven easily interpretable molecular descriptors and possesses statistical robustness with high predictive ability. This Genetic Algorithm Multi-linear regression (GA-MLR) model was subjected to internal validation, Y-randomization test, applicability domain analysis, and external validation as per the recommended OECD guidelines. The newly developed model fulfilled the threshold values for more than 20 recommended validation parameters including R2 = 0.72, Q2LOO = 0.70, etc. The developed QSTR model was successful in identifying the type of hybridization or specific type of atoms of previously reported and newer structural alerts. Thus, the model could be useful for data gap filling and expanding mechanistic interpretation of toxicity for different chemicals.

Comments

A GA-MLR–based QSTR model was developed using 271 compounds and seven interpretable molecular descriptors, demonstrating strong statistical robustness and predictive performance.
The model satisfied OECD-recommended validation criteria, achieving high validation metrics (e.g., R2=0.72R^2 = 0.72R2=0.72, QLOO2=0.70Q^2_{LOO} = 0.70QLOO2=0.70) and successfully passing internal, external, and Y-randomization tests.

Link to Full Text

Share

COinS