Extension of pQSAR: Ensemble Model Generated by Random Forest and Partial Least Squares Regressions

Abstract

Quantitative structure-activity relationship (QSAR) regression models are mathematical ones which relate the structural properties of chemicals to the potencies of the biological activities of the chemicals. In QSAR models, the physical and chemical information of the molecules is encoded into quantitative numbers called descriptors. Recently, experimental test results (profiles) have been used as descriptors of chemicals. Profile QSAR 2.0 (pQSAR) model suggested by Martin et. al, is a multitask, two step machine learning prediction method with a combination of random forest regressions (RFRs) and partial least squares regression (PLSR). In pQSAR model, one fills the profile table's missing values with RFRs and then builds PLSR using the profile predictions. Note that in the second step of the pQSAR method, PLSR's predictor variables are profiles; so activity values, and the response variables are also activity values. Thus we can use the PLSRs to update the profile table and then repeat the second step. In this work, we propose an extended model of pQSAR generated by RFRs and PLSRs. Experiment of updating the given full initially predicted profile table by two kinds of prediction models, RFRs and PLSRs, has been conducted iteratively for the PKIS and ChEMBL data sets. Even though prediction performance of individual combination of RFRs and PLSRs varies, the average of the all possible predicted profile tables for given iteration shows better performance. This ensemble model has better prediction performance in sense of Pearson's R 2 compared to that of the pQSAR model.

Evaluation of Variability Across Rat Acute Oral Systemic Toxicity Studies

“…The original data compilation, prior to the manual curation efforts undertaken here, served as the basis for several predictive modeling efforts, including the Collaborative Acute Toxicity Modeling Suite (CATMoS) collaboration ( Mansouri et al , 2021 ), in which an appropriate representative LD 50 value was calculated for each compound and data were used to develop a consensus model for predicting rat acute oral LD 50 ( Bercu et al , 2021 ; Borba et al , 2020 ; Helman et al , 2019 ; Kim et al , 2020 ; Lunghini et al , 2019 ). However, for the purpose of evaluating variability among replicate study results, additional data curation was conducted to increase confidence and fidelity in subsequent analyses.…”

Collaborative Profile-QSAR: A Natural Platform for Building Collaborative Models among Competing Companies

“…Stacked models can iteratively add more levels. Yoon et al have extended pQSAR to up to nine iterations, expanding each level combinatorically by training both random forest regression (RFR) and partial least-squares (PLS) models on the output of each model at each level …”

“…Yoon et al have extended pQSAR to up to nine iterations, expanding each level combinatorically by training both random forest regression (RFR) and partial least-squares (PLS) models on the output of each model at each level. 17 Figure 1 illustrates the pQSAR procedure for assay "A1". For level 1, conventional single-assay random forest regression (RFR) models are trained on the available negative log of concentration for 50% inhibition (pIC 50 ) or similar continuous data for each individual assay.…”