PCA-Based Representations of Graphs for Prediction in QSAR Studies

Cardin, Riccardo; Michielan, Lisa; Moro, Stefano; Sperduti, Alessandro

doi:10.1007/978-3-642-04277-5_11

Cited by 1 publication

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…support vector machine and artificial neural networks) [12][13][14][15][16] . Modellers also sometimes employ principal component analysis (PCA) to aid the process of designing (Q)SARs 17,18 e.g. for searching for structural similarity patterns and thus predefining new categorises of the studied chemicals.…”

Section: Introductionmentioning

confidence: 99%

Nano(Q)SAR: Challenges, pitfalls and perspectives

et al. 2014

View full text Add to dashboard Cite

Regulation for nanomaterial is urgently needed and the drive to adopt an intelligent testing strategy is evident. The intelligent testing strategy will not only be beneficial from a cost reduction point of view but will also mean the reduction of the moral and ethical concerns related to animal research. In the chemical and legislative world, such an approach is promoted by REACH and in particular the use of (Q)SAR as a tool for the purpose of categorisation. In addition to traditional compounds, (Q)SAR has also been applied to nanomaterials i.e. nano(Q)SAR, useful to correlate toxicological endpoints with physicochemical properties.Although (Q)SAR in chemicals is well established, nano(Q)SAR is still at an early stage of its development and its successful uptake is far from reality. The purpose of this paper is to identify some of the pitfalls and challenges associated with nano-(Q)SARs, in relation for its use to categorise nanomaterials. Our findings show clear gaps in the research framework that must be addressed if we are to have reliable predications from the use of such models. Three major types of barriers were identified: a) the need to improve quality of experimental data in which the models are being developed from in the first place, b) the need to have practical guidelines for the development of the nano(Q)SAR models, c) the need to standardise and harmonise activities for the purpose of regulation. Out of the three barriers, immediate attention is needed for a) as this underpins activities associated in b) and c). It should be noted that the usefulness of data in the context of nano-(Q)SAR modelling is not only about the quantity of data but also about the quality, consistency and accessibility of those data.

show abstract