Drug development has a high attrition rate, with poor pharmacokinetic and safety properties a significant hurdle. Computational approaches may help minimize these risks. We have developed a novel approach (pkCSM) which uses graph-based signatures to develop predictive models of central ADMET properties for drug development. pkCSM performs as well or better than current methods. A freely accessible web server (http://structure.bioc.cam.ac.uk/pkcsm), which retains no information submitted to it, provides an integrated platform to rapidly evaluate pharmacokinetic and toxicity properties.

/pdf/pkcsm-predicting-small-molecule-pharmacokinetic-and-toxicity-2czy0d4m61.pdf

pkCSM: Predicting Small-Molecule Pharmacokinetic and Toxicity Properties Using Graph-Based Signatures

Despite a changing world in terms of data sharing, availability, and transparency, there are still major resource issues associated with collating datasets that will satisfy the requirements of comprehensive pesticide risk assessments, especially those undertaken at a regional or national scale. In 1996, a long-term project was initiated to begin collating and formatting pesticide data to eventually create a free-to-all repository of data that would provide a comprehensive transparent, harmonized, and managed extensive dataset for all types of pesticide risk assessments. Over the last 20 years, this database has been keeping pace with improving risk assessments, their associated data requirements, and the needs and expectations of database end users. In 2007, the Pesticide Properties DataBase (PPDB) was launched as a free-to-access website. Currently, the PPDB holds data for almost 2300 pesticide active substances and over 700 metabolites. For each substance around 300 parameters are stored, cover...

/pdf/an-international-database-for-pesticide-risk-assessments-and-3hhcvcpuyp.pdf

An international database for pesticide risk assessments and management

Artificial intelligence (AI), and, in particular, deep learning as a subcategory of AI, provides opportunities for the discovery and development of innovative drugs. Various machine learning approaches have recently (re)emerged, some of which may be considered instances of domain-specific AI which have been successfully employed for drug discovery and design. This review provides a comprehensive portrayal of these machine learning techniques and of their applications in medicinal chemistry. After introducing the basic principles, alongside some application notes, of the various machine learning algorithms, the current state-of-the art of AI-assisted pharmaceutical discovery is discussed, including applications in structure- and ligand-based virtual screening, de novo drug design, physicochemical and pharmacokinetic property prediction, drug repurposing, and related aspects. Finally, several challenges and limitations of the current methods are summarized, with a view to potential future directions for AI-assisted drug discovery and design.

Concepts of Artificial Intelligence for Computer-Assisted Drug Discovery

The threshold of toxicological concern (TTC) is a pragmatic risk assessment tool that is based on the principle of establishing a human exposure threshold value for all chemicals, below which there is a very low probability of an appreciable risk to human health. The concept that there are levels of exposure that do not cause adverse effects is inherent in setting acceptable daily intakes (ADIs) for chemicals with known toxicological profiles. The TTC principle extends this concept by proposing that a de minimis value can be identified for many chemicals, in the absence of a full toxicity database, based on their chemical structures and the known toxicity of chemicals which share similar structural characteristics. The establishment and application of widely accepted TTC values would benefit consumers, industry and regulators. By avoiding unnecessary toxicity testing and safety evaluations when human intakes are below such a threshold, application of the TTC approach would focus limited resources of time, cost, animal use and expertise on the testing and evaluation of substances with the greatest potential to pose risks to human health and thereby contribute to a reduction in the use of animals. An Expert Group of the European branch of the International Life Sciences Institute-ILSI Europe-has examined the TTC principle for its wider applicability in food safety evaluation. The Expert Group examined metabolism and accumulation, structural alerts, endocrine disrupting chemicals and specific endpoints, such as neurotoxicity, teratogenicity, developmental toxicity, allergenicity and immunotoxicity, and determined whether such properties or endpoints had to be taken into consideration specifically in a step-wise approach. The Expert Group concluded that the TTC principle can be applied for low concentrations in food of chemicals that lack toxicity data, provided that there is a sound intake estimate. The use of a decision tree to apply the TTC principle is proposed, and this paper describes the step-wise process in detail. Proteins, heavy metals and polyhalogenated-dibenzodioxins and related compounds were excluded from this approach. When assessing a chemical, a review of prior knowledge and context of use should always precede the use of the TTC decision tree. The initial step is the identification and evaluation of possible genotoxic and/or high potency carcinogens. Following this step, non-genotoxic substances are evaluated in a sequence of steps related to the concerns that would be associated with increasing intakes. For organophosphates a TTC of 18microg per person per day (0.3 microg/kg bw/day) is proposed, and when the compound is not an OP, the TTC values for the Cramer structural classes III, II and I, with their respective TTC levels (e.g. 1800, 540 and 90 microg per person per day; or 30, 9 and 1.5 microg/kg bw /day), would be applied sequentially. All other endpoints or properties were shown to have a distribution of no observed effect levels (NOELs) similar to the distribution of NOELs for general toxicity endpoints in Cramer classes I, II and III. The document was discussed with a wider audience during a workshop held in March 2003 (see list of workshop participants).

Structure-Based Thresholds of Toxicological Concern (TTC): Guidance for Application to Substances Present at Low Levels in the Diet

http://fragrancematerialsafetyresource.elsevier.com/sites/default/files/Bhatia-Comparison.pdf

Comparison of Cramer classification between Toxtree, the OECD QSAR Toolbox and expert judgment.

Risk assessment for most human health effects is based on the threshold of a toxicological effect, usually derived from animal experiments. The Threshold of Toxicological Concern (TTC) is a concept that refers to the establishment of a level of exposure for all chemicals below which there would be no appreciable risk to human health. When carefully applied, the TTC concept can provide a means of waiving testing based on knowledge of exposure limits. Two main approaches exist; the first of these is a General Threshold of Toxicological Concern; the second approach is a TTC in relation to structural information and/or toxicological data of chemicals. The structural scheme most routinely used is that of Cramer and co-workers from 1978. Recently this scheme was encoded into a software program called Toxtree, specifically commissioned by the European Chemicals Bureau (ECB). Here we evaluate two published datasets using Toxtree to demonstrate its concordance and highlight potential software modifications. The results were promising with an overall good concordance between the reported classifications and those generated by Toxtree. Further evaluation of these results highlighted a number of inconsistencies which were examined in turn and rationalised as far as possible. Improvements for Toxtree were proposed where appropriate. Notable of these is a necessity to update the lists of common food components and normal body constituents as these accounted for the majority of false classifications observed. Overall Toxtree was found to be a useful tool in facilitating the systematic evaluation of compounds through the Cramer scheme.

R J Safford

Papers

An evaluation of the implementation of the Cramer classification scheme in the Toxtree software