Targeting Chemical Inputs and Optimising HTS for Agrochemical Discovery

Insecticide discovery-"Chance favors the prepared mind"

New options for pest insect control, including new insecticides, are needed to ensure a plentiful food supply for an expanding global population. Any new insecticides must meet the increasingly stringent regulatory requirements for mammalian and environmental safety, and also address the need for new chemistries and modes of action to deal with resistance to available insecticides. As underscored by a paraphrase of a quote from Louis Pasteur "Chance favors the prepared mind", the agrochemical industry uses a variety of approaches that attempt to improve on "chance" for the discovery of new insecticides. Although there are a number of approaches to the discovery of new insecticidal active ingredients (AIs), historically most insecticides are based on a pre-existing molecule or product either from a competitor or from an internal company source. As such the first examples of a new insecticide representing a new type or class of AI (First-in-Class: FIC) are important as prototypes for other AIs stimulating further spectrum, efficacy, physicochemical, and environmental safety refinements. FIC insecticides also represent a measure of innovation. Understanding the origins of these FIC compounds and the approaches used in their discovery can provide insights into successful strategies for future new classes of insecticides. This perspective will focus on an analysis of the approaches that have been used for discovery of FIC insecticides highlighting those approaches that have been the most successful and providing a reference point for current and future directions.

Big data in chemical toxicity research: the use of high-throughput screening assays to identify potential toxicants

High-throughput screening (HTS) assays that measure the in vitro toxicity of environmental compounds have been widely applied as an alternative to in vivo animal tests of chemical toxicity. Current HTS studies provide the community with rich toxicology information that has the potential to be integrated into toxicity research. The available in vitro toxicity data is updated daily in structured formats (e.g., deposited into PubChem and other data-sharing web portals) or in an unstructured way (papers, laboratory reports, toxicity Web site updates, etc.). The information derived from the current toxicity data is so large and complex that it becomes difficult to process using available database management tools or traditional data processing applications. For this reason, it is necessary to develop a big data approach when conducting modern chemical toxicity research. In vitro data for a compound, obtained from meaningful bioassays, can be viewed as a response profile that gives detailed information about the compound's ability to affect relevant biological proteins/receptors. This information is critical for the evaluation of complex bioactivities (e.g., animal toxicities) and grows rapidly as big data in toxicology communities. This review focuses mainly on the existing structured in vitro data (e.g., PubChem data sets) as response profiles for compounds of environmental interest (e.g., potential human/animal toxicants). Potential modeling and mining tools to use the current big data pool in chemical toxicity research are also described.

A comparison of machine learning algorithms for chemical toxicity classification using a simulated multi-scale data model

BACKGROUND

Bioactivity profiling using high-throughput in vitro assays can reduce the cost and time required for toxicological screening of environmental chemicals and can also reduce the need for animal testing. Several public efforts are aimed at discovering patterns or classifiers in high-dimensional bioactivity space that predict tissue, organ or whole animal toxicological endpoints. Supervised machine learning is a powerful approach to discover combinatorial relationships in complex in vitro/in vivo datasets. We present a novel model to simulate complex chemical-toxicology data sets and use this model to evaluate the relative performance of different machine learning (ML) methods.

RESULTS

The classification performance of Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), Recursive Partitioning and Regression Trees (RPART), and Support Vector Machines (SVM) in the presence and absence of filter-based feature selection was analyzed using K-way cross-validation testing and independent validation on simulated in vitro assay data sets with varying levels of model complexity, number of irrelevant features and measurement noise. While the prediction accuracy of all ML methods decreased as non-causal (irrelevant) features were added, some ML methods performed better than others. In the limit of using a large number of features, ANN and SVM were always in the top performing set of methods while RPART and KNN (k = 5) were always in the poorest performing set. The addition of measurement noise and irrelevant features decreased the classification accuracy of all ML methods, with LDA suffering the greatest performance degradation. LDA performance is especially sensitive to the use of feature selection. Filter-based feature selection generally improved performance, most strikingly for LDA.

CONCLUSION

We have developed a novel simulation model to evaluate machine learning methods for the analysis of data sets in which in vitro bioassay data is being used to predict in vivo chemical toxicology. From our analysis, we can recommend that several ML methods, most notably SVM and ANN, are good candidates for use in real world applications in this area.

The ToxCast program for prioritizing toxicity testing of environmental chemicals

The U.S. Environmental Protection Agency (EPA) is developing methods for utilizing computational chemistry, high-throughput screening (HTS), and various toxicogenomic technologies to predict potential for toxicity and prioritize limited testing resources toward chemicals that likely represent the greatest hazard to human health and the environment. This chemical prioritization research program, entitled "ToxCast," is being initiated with the purpose of developing the ability to forecast toxicity based on bioactivity profiling. The proof-of-concept phase of ToxCast will focus upon chemicals with an existing, rich toxicological database in order to provide an interpretive context for the ToxCast data. This set of several hundred reference chemicals will represent numerous structural classes and phenotypic outcomes, including tumorigens, developmental and reproductive toxicants, neurotoxicants, and immunotoxicants. The ToxCast program will evaluate chemical properties and bioactivity profiles across a broad spectrum of data domains: physical-chemical, predicted biological activities based on existing structure-activity models, biochemical properties based on HTS assays, cell-based phenotypic assays, and genomic and metabolomic analyses of cells. These data will be generated through a series of external contracts, along with collaborations across EPA, with the National Toxicology Program, and with the National Institutes of Health Chemical Genomics Center. The resulting multidimensional data set provides an informatics challenge requiring appropriate computational methods for integrating various chemical, biological, and toxicological data into profiles and models predicting toxicity.