High Throughput Read-Across for Screening a Large Inventory of Related Structures by Balancing Artificial Intelligence/Machine Learning and Human Knowledge

Abstract

Read-across is an in silico method applied in chemical risk assessment for data-poor chemicals. The read-across outcomes for repeated-dose toxicity end points include the no-observed-adverse-effect level (NOAEL) and estimated uncertainty for a particular category of effects. We have previously developed a new paradigm for estimating NOAELs based on chemoinformatics analysis and experimental study qualities from selected analogues, not relying on quantitative structure–activity relationships (QSARs) or rule-based SAR systems, which are not well-suited to end points for which the underpinning data are weakly grounded in specific chemical–biological interactions. The central hypothesis of this approach is that similar compounds have similar toxicity profiles and, hence, similar NOAEL values. Analogue quality (AQ) quantifies the suitability of an analogue candidate for reading across to the target by considering similarity from structure, physicochemical, ADME (absorption, distribution, metabolism, excretion), and biological perspectives. Biological similarity is based on experimental data; assay vectors derived from aggregations of ToxCast/Tox21 data are used to derive machine learning (ML) hybrid rules that serve as biological fingerprints to capture target–analogue similarity relevant to specific effects of interest, for example, hormone receptors (ER/AR/THR). Once one or more analogues have been qualified for read-across, a decision theory approach is used to estimate confidence bounds for the NOAEL of the target. The confidence interval is dramatically narrowed when analogues are constrained to biologically related profiles. Although this read-across process works well for a single target with several analogues, it can become unmanageable when, for example, screening multiple targets (e.g., virtual screening library) or handling a parent compound having numerous metabolites. To this end, we have established a digitalized framework to enable the assessment of a large number of substances, while still allowing for human decisions for filtering and prioritization. This workflow was developed and validated through a use case of a large set of bisphenols and their metabolites.

Next-generation risk assessment read-across case study: application of a 10-step framework to derive a safe concentration of daidzein in a body lotion

“…These predictions were confirmed by reports on clinical studies of genistein in humans (Yang et al, 2012) and in vitro metabolism data (Bursztyka et al, 2008;Pritchett et al, 2008). The use of genistein as a source chemical for daidzein was supported by comparing the quality of different potential analogues using ToxGPS (Version 4) software (Yang et al, 2023). The analogue quality considers chemical similarities using MACCS and ToxPrint Fingerprints, Chemotype profiles, molecular properties, including quantum mechanical parameters, and Skyline profiles.…”

“…The use of genistein as a source chemical for daidzein was supported by comparing the quality of different potential analogues using ToxGPS (Version 4) software ( Yang et al, 2023 ). The analogue quality considers chemical similarities using MACCS and ToxPrint Fingerprints, Chemotype profiles, molecular properties, including quantum mechanical parameters, and Skyline profiles.…”

Introduction to the Special Issue: AI Meets Toxicology

“…The methods described in this special issue cover a wide range of AI methods ranging from expert systems, ,, over similarity measures including read-across methods, − to classical machine learning such as random forests (RF), support vector machines (SVM), and artificial neural networks (ANN) − ,, to deep learning (DL) methods ,,− , including equivariant neural networks, deep generative models, and even large language models . In addition to models relying purely on the chemical structure, there is a notable trend of bringing in additional modalities to improve or inform predictive models. , In the following, we provide an overview of the AI approaches used in the publications contained in the SI.…”

“…One of the challenges in read-across is developing suitable vector representations of chemicals based on their molecular features, physicochemical properties, and bioactivities. Yang et al proposed a strategy to induce hybrid vectors from chemical and bioactivity fingerprints and demonstrated its utility for predicting repeat-dose NOAEL values. They developed a read-across approach based on chemoinformatics and machine learning that was used to estimate NOAELs for data-poor chemicals, demonstrating its effectiveness using a large set of bisphenols and their metabolites.…”

Cheminformatic Read-Across Approach Revealed Ultraviolet Filter Cinoxate as an Obesogenic Peroxisome Proliferator-Activated Receptor γ Agonist

“…The read-across approach has raised great attention in the field of chemical safety prediction because animal experiments are strictly restricted even in chemical toxicity testing these days, although regulatory agencies require more insightful information on potential adverse effects of chemicals. − The read-across method assumes that similar molecules are likely to exhibit comparable biological activities, enabling assessment of potential toxicity of untested compounds. − Read-across involves using relevant information from analogous substances (“source” information) to predict properties for the substances under investigation (“target” information).…”