David M. Reif

Tox21mer is a transformer model trained on Tox21 concentration-response curves to predict compound activity and AC50, achieving high accuracy in outcome prediction and log10(AC50) estimation.

An audit of 38 PFAS non-targeted studies from 2023 found confidence levels often missing or misapplied; a five-level, sublevel-free checklist with predefined platform tolerances is proposed for ion mobility workflows.

The paper introduces an aggregated molecular phenotype (AMP) scoring system to visualize and classify molecular changes in mass spectrometry imaging data with high accuracy.

The paper uses a conditional GAN and toxicity data to predict chemical toxicity, achieving higher sensitivity than a regression model but lower specificity.