http://hdl.handle.net/10967/211 Liverpool John Moores University (England), Chemoinformatics Research Group Tue, 07 Apr 2026 09:49:14 GMT 2026-04-07T09:49:14Z https://qsardb.org:443/repository/bitstream/id/53de748f-0776-47f6-8893-fe7ed6c082c1/ http://hdl.handle.net/10967/211 http://hdl.handle.net/10967/264 Recent years have seen a substantial growth in the adoption of machine learning approaches for the purposes of quantitative structure-activity relationship (QSAR) development. Such a trend has coincided with desire to see a shifting in the focus of methodology employed within chemical safety assessment: away from traditional reliance upon animalintensive in vivo protocols, and towards increased application of in silico (or computational) predictive toxicology. With QSAR central amongst techniques applied in this area, the emergence of algorithms trained through machine learning with the objective of toxicity estimation has, quite naturally, arisen. On account of the pattern-recognition capabilities of the underlying methods, the statistical power of the ensuing models is potentially considerable– appropriate for the handling even of vast, heterogeneous datasets. However, such potency comes at a price: this manifesting as the general practical deficits observed with respect to the reproducibility, interpretability and generalisability of the resulting tools. Unsurprisingly, these elements have served to hinder broader uptake (most notably within a regulatory setting). Areas of uncertainty liable to accompany (and hence detract from applicability of) toxicological QSAR have previously been highlighted, accompanied by the forwarding of suggestions for “best practice” aimed at mitigation of their influence. However, the scope of such exercises has remained limited to “classical” QSAR–that conducted through use of linear regression and related techniques, with the adoption of comparatively few features or descriptors. Accordingly, the intention of this study has been to extend the remit of best practice guidance, so as to address concerns specific to employment of machine learning within the field. In doing so, the impact of strategies aimed at enhancing the transparency (feature importance, feature reduction), generalisability (cross-validation) and predictive power (hyperparameter optimisation) of algorithms, trained upon real toxicity data through six common learning approaches, is evaluated. Mon, 21 Oct 2024 11:48:57 GMT http://hdl.handle.net/10967/264 2024-10-21T11:48:57Z http://hdl.handle.net/10967/260 The replacement of animal testing for endpoints such as reproductive toxicity is a long-term goal. This study describes the possibilities of using simple (quantitative) structure-activity relationships ((Q)SARs) to predict whether a molecule may cross the placental membrane. The concept is straightforward, if a molecule is not able to cross the placental barrier, then it will not be a reproductive toxicant. Such a model could be placed at the start of any integrated testing strategy. To develop these models the literature was reviewed to obtain data relating to the transfer of molecules across the placenta. A reasonable number of data were obtained and are suitable for the modelling of the ability of a molecule to cross the placenta. Clearance or transfer indices data were sought due to their ability to eliminate inter-placental variation by standardising drug clearance to the reference compound antipyrine. Modelling of the permeability data indicates that (Q)SARs with reasonable statistical fit can be developed for the ability of molecules to cross the placental barrier membrane. Analysis of the models indicates that molecular size, hydrophobicity and hydrogen-bonding ability are molecular properties that may govern the ability of a molecule to cross the placental barrier. Thu, 07 Mar 2024 14:20:55 GMT http://hdl.handle.net/10967/260 2024-03-07T14:20:55Z http://hdl.handle.net/10967/221 All compounds are considered to act by polar narcosis. This is well established for non-reactive compounds. Acute lethality is brought about by accumulation in cellular membranes causing their disruption and ultimately death of the organism. The ability of the compound to accumulate in a cellular membrane is thought to be related to its intrinsic hydrophobicity. Hydrophobicity of these compounds is modelled by log P. Fri, 13 Mar 2020 10:09:05 GMT http://hdl.handle.net/10967/221 2020-03-13T10:09:05Z http://hdl.handle.net/10967/220 All compounds are considered to act by non-polar narcosis. This is well established for non-reactive compounds. Acute lethality is brought about by accumulation in cellular membranes causing their disruption and ultimately death of the organism. The ability of the compound to accumulate in a cellular membrane is thought to be related to its intrinsic hydrophobicity. Hydrophobicity of these compounds is modelled by log P. Thu, 12 Mar 2020 13:40:17 GMT http://hdl.handle.net/10967/220 2020-03-12T13:40:17Z