How to Predict Future Upcoming Harmful Agents: Array Type Meta-Predictor Based Classification

Abstract Molecular insights into chemical safety are very important for sustainable development as well as risk assessment. This study considers how to manage future upcoming harmful agents, especially potentially cholinergic chemical warfare agents (CWAs). For this purpose, structures of known cholinergic agents were encoded by molecular descriptors. And then each drug target interaction (DTI) was learned from the encoded structures and their cholinergic activities to build DTI classification models for five cholinergic targets with reliable statistical validation (ensemble-AUC: up to 0.790, MCC: up to 0.991, accuracy: up to 0.995). The collected classifiers were transformed to 2D or 3D array type meta-predictors for multi-tasking: (1) cholinergic prediction and (2) CWA detection. The detection ability of the array classifiers was verified under the imbalanced dataset between CWAs and none CWAs (area under the precision-recall curve: up to 0.997, MCC: up to 0.638, F1-sore of none CWAs: up to 0.991, F1-sore of CWAs: up to 0.585).