From Regression to Dose–Response: Predicting GPCR Activity and EC50 via Concentration-Conditional Modelling

ML models have revolutionised drug discovery, yet they still struggle with modelling the molecule-induced response of G-protein coupled receptors (GPCRs) — cellular membrane "sensors" that account for nearly $30$% targets of approved drugs. The central challenge in GPCRs lies in predicting activity and potency (i.e., half maximal effective concentration, EC50). To estimate these properties, we propose a unified learning framework inspired by *in vitro* dose-response assays that models concentration-conditional activation. Specifically, for each training protein-molecule pair $(s,m)$, we uniformly sample concentrations $c$ and generate labels that are deterministic far from the EC50 and soft in the transition region. We then train a concentration-conditional model that learns the probability $P(active|s,m,c)$ at any $c$. Finally, querying the model across concentrations enables fitting a Hill curve from which both activity (upper asymptote) and EC50 (inflection point in $\log c$) are derived. On the challenging M2OR dataset, our approach achieves an EC50 estimation error of $0.683$ log units, an improvement of $0.399$ log units compared to drug–target affinity baselines, $0.205$ log units compared to censored regression, and $0.433$ log units compared to the Boltz-2 affinity module, while achieving comparable performance in activity classification to the SOTA baselines (MCC $0.665$ in the i.i.d. case).