| Literature DB >> 28988138 |
Dimitra-Danai Varsou1, Georgia Melagraki2, Haralambos Sarimveis3, Antreas Afantitis4.
Abstract
Advances in the drug discovery research substantially depend on in silico methods and techniques that capitalize on experimental data to enable the accurate property/activity assessment by employing a variety of computational techniques. These in silico tools can significantly reduce expensive and time consuming experimental procedures required and are strongly recommended to avoid animal testing, especially as far as toxicity evaluation and risk assessment is concerned. In this context, in the present work we aim to develop a predictive model for the cytotoxic effects of a wide range of compounds based solely on calculated molecular descriptors that account for their topological, geometric and structural characteristics. The developed model was fully validated and was released online via Enalos Cloud platform accessible through http://enalos.insilicotox.com/MouseTox/. This ready-to-use web service offers, through a user-friendly interface, free access to the model results and therefore can act as a toxicity prediction tool for the risk assessment of novel compounds, without any special requirements or prior programming skills.Entities:
Keywords: Cytotoxicity; Enalos cloud platform; Enalos+ KNIME nodes; KNIME workflow; Predictive model; Random forest
Mesh:
Substances:
Year: 2017 PMID: 28988138 DOI: 10.1016/j.fct.2017.09.058
Source DB: PubMed Journal: Food Chem Toxicol ISSN: 0278-6915 Impact factor: 6.023