Summary of a workshop on regulatory acceptance of (Q)SARs for human health and environmental endpoints.

Abstract

The "Workshop on Regulatory Use of (Q)SARs for Human Health and Environmental Endpoints," organized by the European Chemical Industry Council and the International Council of Chemical Associations, gathered more than 60 human health and environmental experts from industry, academia, and regulatory agencies from around the world. They agreed, especially industry and regulatory authorities, that the workshop initiated great potential for the further development and use of predictive models, that is, quantitative structure-activity relationships [(Q)SARs], for chemicals management in a much broader scope than is currently the case. To increase confidence in (Q)SAR predictions and minimization of their misuse, the workshop aimed to develop proposals for guidance and acceptability criteria. The workshop also described the broad outline of a system that would apply that guidance and acceptability criteria to a (Q)SAR when used for chemical management purposes, including priority setting, risk assessment, and classification and labeling.

Guidance Document on the Validation of (Quantitative) Structure-Activity Relationship [(Q)SAR] Models

“…A set of principles for assessing the validity of (Q)SARs (Setubal principles) were proposed at an international workshop on the "Regulatory Acceptance of QSARs for Human Health and Environment Endpoints", organised by the International Council of Chemical Associations (ICCA) and the European Chemical Industry Council (CEFIC), and held in Setubal, Portugal, on 4-6 March, 2002 (Jaworska et al, 2003;Cronin et al, 2003aCronin et al, , 2003b.…”

Assessment of Machine Learning Reliability Methods for Quantifying the Applicability Domain of QSAR Regression Models

“…The conceptual definition of the AD states that a chemical structure is within the AD if it is predicted with "a given reliability". 2 Notice that this definition of the applicability domain is binary: predictions are either reliable or not. Each of the scoring techniques we use in this paper computes a degree of reliability, hence quantifying the degree to which a compound falls within the AD.…”

“…2 Hence, the applicability domain is quantified by reliability methods that estimate the error of prediction. Recently, a set of such approaches was proposed within the machine learning community, 12 and we here study their utility within QSAR.…”

“…Though there is no scientific consensus on the exact definition of the AD, the Setubal workshop report from 2003 conceptually defined it as "the response and chemical structure space in which the model makes predictions with a given reliability". 2 The emphasis on the importance of the AD in QSAR modeling 3,4 originates from the notion of the vastness of chemical space and the relatively small coverage by data sets with ADMET annotations. It is generally perceived that chemical compounds "similar" to those used in the development of predictive models (e.g., the training set compounds) fall within the AD, while predictions of dissimilar compounds should not be considered reliable.…”

Peer Reviewed: Meeting the Scientific Needs of Ecological Risk Assessment in a Regulatory Context

“…Over the past 25 years, many OECD member countries have established QSAR tools to provide exposure and effects inputs in ranking and prioritization schemes for in vivo screening and testing programs (37)(38)(39)(40)(41)(42)(43)(44). Because of today's computing capabilities, thousands of chemicals can be processed readily in near real time to estimate properties associated with 3-D structures.…”