Koutroumpa Nikoletta-Maria, Antoniou Maria, Varsou Dimitra-Danai, Papavasileiou Konstantinos D, Sidiropoulos Nikolaos K, Kyprianou Christoforos, Tsoumanis Andreas, Sarimveis Haralambos, Lynch Iseult, Melagraki Georgia, Afantitis Antreas
NovaMechanics Ltd, 1070, Nicosia, Cyprus.
School of Chemical Engineering, National Technical University of Athens, 157 80, Athens, Greece.
Mol Divers. 2025 Apr 23. doi: 10.1007/s11030-025-11196-5.
Advances in drug discovery and material design rely heavily on in silico analysis of extensive compound datasets and accurate assessment of their properties and activities through computational methods. Efficient and reliable prediction of molecular properties is crucial for rational compound design in the chemical industry. To address this need, we have developed predictive models for nine key properties, including the octanol/water partition coefficient, water solubility, experimental hydration free energy in water, vapor pressure, boiling point, cytotoxicity, mutagenicity, blood-brain barrier permeability, and bioconcentration factor. These models have demonstrated high predictive accuracy and have undergone thorough validation in accordance with OECD test guidelines. The models are seamlessly integrated into the Enalos Cloud Platform through Titania ( https://enaloscloud.novamechanics.com/EnalosWebApps/titania/ ), a comprehensive web-based application designed to democratize access to advanced computational tools. Titania features an intuitive, user-friendly interface, allowing researchers, regardless of computational expertise, to easily employ models for property prediction of novel compounds. The platform enables informed decision-making and supports innovation in drug discovery and material design. We aspire for this tool to become a valuable resource for the scientific community, enhancing both the efficiency and accuracy of property and toxicity predictions.
药物发现和材料设计的进展在很大程度上依赖于对大量化合物数据集的计算机模拟分析,以及通过计算方法对其性质和活性进行准确评估。高效且可靠地预测分子性质对于化学工业中的合理化合物设计至关重要。为满足这一需求,我们针对九个关键性质开发了预测模型,包括正辛醇/水分配系数、水溶性、水中实验性水合自由能、蒸气压、沸点、细胞毒性、致突变性、血脑屏障通透性和生物富集因子。这些模型已证明具有较高的预测准确性,并已根据经合组织测试指南进行了全面验证。这些模型通过Titania(https://enaloscloud.novamechanics.com/EnalosWebApps/titania/)无缝集成到Enalos云平台中,Titania是一个基于网络的综合应用程序,旨在使先进计算工具的使用更加普及。Titania具有直观、用户友好的界面,使研究人员无论计算专业知识如何,都能轻松使用模型来预测新型化合物的性质。该平台有助于做出明智的决策,并支持药物发现和材料设计中的创新。我们期望这个工具能成为科学界的宝贵资源,提高性质和毒性预测的效率和准确性。