Dataset Information

Comparison of various methods for validity evaluation of QSAR models.

ABSTRACT:

Background

Quantitative structure-activity relationship (QSAR) modeling is one of the most important computational tools employed in drug discovery and development. The external validation of QSAR models is the main point to check the reliability of developed models for the prediction activity of not yet synthesized compounds. It was performed by different criteria in the literature.

Methods

In this study, 44 reported QSAR models for biologically active compounds reported in scientific papers were collected. Various statistical parameters of external validation of a QSAR model were calculated, and the results were discussed.

Results

The findings revealed that employing the coefficient of determination (r²) alone could not indicate the validity of a QSAR model. The established criteria for external validation have some advantages and disadvantages which should be considered in QSAR studies.

Conclusion

This study showed that these methods alone are not only enough to indicate the validity/invalidity of a QSAR model.

SUBMITTER: Shayanfar S

PROVIDER: S-EPMC9396839 | biostudies-literature | 2022 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparison of various methods for validity evaluation of QSAR models.

Shayanfar Shadi S Shayanfar Ali A

BMC chemistry 20220823 1

<h4>Background</h4>Quantitative structure-activity relationship (QSAR) modeling is one of the most important computational tools employed in drug discovery and development. The external validation of QSAR models is the main point to check the reliability of developed models for the prediction activity of not yet synthesized compounds. It was performed by different criteria in the literature.<h4>Methods</h4>In this study, 44 reported QSAR models for biologically active compounds reported in scien ...[more]

PMID: 35999611

Similar Datasets

Project description:Due to their multiple beneficial effects, antioxidant peptides have attracted increasing interest. Currently, the screening and identification of bioactive peptides, including antioxidative peptides based on wet-chemistry methods are time-consuming and highly rely on many advanced instruments and trained personnel. Quantitative structure-activity relationship (QSAR) analysis as an in silico method can be more efficient and cost-effective. However, model performance of QSAR studies on antioxidant peptides was still poor due to limited attempts in model development approaches. The objective of this study was to compare popular machine learning methods for antioxidant activity modeling and screening of tripeptides and identify the critical amino acid features that determine the antioxidant activity. 533 numerical indices of amino acids were adopted to characterize 130 tripeptides with known antioxidant activity from the published literature, and then 7 feature selection strategies plus pairwise correlation were used to screen the most important indices for antioxidant activity and model building. 14 machine learning methods were used to build models based on the feature selection strategies, respectively. Among the 98 models, non-linear regression methods tended to perform better, and the best model with an R 2 Test of 0.847 and RMSETest of 0.627 for tripeptide antioxidants was obtained by combining random forest for feature selection and tree-based extreme gradient boost regression for model development. Based on the predicted antioxidant values of 7870 unknown tripeptides, potentially high antioxidant activity tripeptides all have a tyrosine, tryptophan, or cysteine residue at the C-terminal position. Furthermore, the predicted antioxidant activity of six synthesized tripeptides was confirmed through experimental determination, and for the first time, the cysteine or tyrosine residue at the C-terminal was found to be critical to the antioxidant activity based on both QSAR models and experimental observations.

Project description:The advantages of intraoral model scanning have yielded recent developments. However, few studies have explored the orthodontic clinical use of this technique particularly among young patients. This study aimed to evaluate the reliability, reproducibility and validity of the orthodontic measurements: tooth width, arch length and arch length discrepancy in each digital model obtained by model scanner and intraoral scanner, relative to a plaster model. Arch length measured using two methods: curved arch length (CAL) measured automatically by digital program and sum of sectional liner arch length (SLAL) measured sum of anterior and posterior liner arch lengths. Arch length discrepancy calculated each arch length measurement methods: curved arch length discrepancy (CALD) and sum of sectional liner arch length discrepancy (SLALD). Forty young patients were eligible for the study. A plaster model (P), model-scanned digital model (MSD) and intraoral scanned digital model (ISD) were acquired from each patient. The reliability of the measurements was evaluated using Pearson's correlation coefficient, while the reproducibility was evaluated using the intraclass correlation coefficient. The validity was assessed by a paired t-test. All measurements measured in P, MSD and ISD exhibited good reliability and reproducibility. Most orthodontic measurements despite of CAL in MSD exhibited high validity. Only the SLAL and SLALD in ISD group differed significantly, despite the good validity of the tooth width, CAL and CALD. The measurements based on the digital program appeared high reliability, reproducibility and accurate than conventional measurement. However, SLAL and SLALD in ISD group appeared shorter because of distortion during intraoral scanning. However, this could be compensated by using digital programed curved arch. Although the validity of SLAL and SLALD in the ISD group differed statistically, the difference is not considered clinically significant. Although MSD and ISD are acceptable for a clinical space analysis, clinicians should be aware of digital model-induced errors.

Dataset Information

Comparison of various methods for validity evaluation of QSAR models.

Background

Methods

Results

Conclusion

Publications

Comparison of various methods for validity evaluation of QSAR models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets