Analysis of the benefits of imputation models over traditional QSAR models for toxicity prediction

Autor:	Moritz Walter, Luke Neil Allen, Antonio de la Vega de León, Samuel Jonathan Webb, Valerie Jane Gillet
Rok vydání:	2022
Předmět:	Library and Information Sciences Physical and Theoretical Chemistry Computer Graphics and Computer-Aided Design Computer Science Applications
Zdroj:	Journal of cheminformatics. 14(1)
ISSN:	1758-2946
Popis:	Recently, imputation techniques have been adapted to predict activity values among sparse bioactivity matrices, showing improvements in predictive performance over traditional QSAR models. These models are able to use experimental activity values for auxiliary assays when predicting the activity of a test compound on a specific assay. In this study, we tested three different multi-task imputation techniques on three classification-based toxicity datasets: two of small scale (12 assays each) and one large scale with 417 assays. Moreover, we analyzed in detail the improvements shown by the imputation models. We found that test compounds that were dissimilar to training compounds, as well as test compounds with a large number of experimental values for other assays, showed the largest improvements. We also investigated the impact of sparsity on the improvements seen as well as the relatedness of the assays being considered. Our results show that even a small amount of additional information can provide imputation methods with a strong boost in predictive performance over traditional single task and multi-task predictive models.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7c2bc8688c9dcbd2de98879e84e90288 https://pubmed.ncbi.nlm.nih.gov/35672779 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.