Predicting endocrine disruption using conformal prediction – a prioritisation strategy to identify hazardous chemicals with confidence

Receptor-mediated molecular initiating events (MIEs) and their relevance in endocrine activity (EA) have been highlighted in literature. More than 15 receptors have been associated with neurodevelopmental adversity and metabolic disruption. MIEs describe chemical interactions with defined biological outcomes, a relationship that could be described with quantitative structure–activity relationship (QSAR) models. QSAR uncertainty can be assessed using Conformal Prediction (CP) framework, which provides similarity (i.e. non-conformity) scores relative to the defined classes per prediction. CP calibration can indirectly mitigate data imbalance during model development, and the non-conformity scores serve as intrinsic measures of chemical applicability domain assessment during screening. The focus of this work was to propose an in silico predictive strategy for EA. First, 23 QSAR models for MIEs associated with EA were developed using high-throughput data for 14 receptors. To handle data imbalance, five protocols were compared, and CP provided the most balanced class definition. Second, the developed QSAR models were applied to a large dataset (~55,000 chemicals), comprising chemicals representative of potential risk for human exposure. Using CP, it was possible to assess uncertainty of the screening results, identify model strengths and out of domain chemicals. Last, two clustering methods, t-distributed stochastic neighbour embedding (t-SNE) and Tanimoto similarity, were used to identify compounds with potential EA using as reference known endocrine disruptors. The cluster overlap between methods brought forward 23 chemicals with suspected or demonstrated EA potential. The presented models could be utilized for first-tier screening and identification of compounds with potential biological activity across he studied MIEs.

Manuscript DOI: 10.1021/acs.chemrestox.2c00267

Supplementary Information 2: Python code for Conformal Prediction implementation for all 23 developed models. 

Contents: CP python code, readme, licence file and example input file