Objective: Multi Electrodes Arrays (MEAs) combined with cardiomy-ocytes derived from human induced pluripotent stem cells (hiPSC-CMs) can enable high-or medium-throughput drug screening in safety pharma-cology. This technology has recently attracted a lot of attention, in particular from an international initiative named CiPA. But it is currently limited by the difficulty to analyze the measured signals. We propose a strategy to analyze the signals acquired by the MEA and to automatically deduce the channels affected by the drug. Methods: Our method is based on the bidomain equations, a model for the MEA electrodes, and an inverse problem strategy. Results: In silico MEA signals are obtained for two commercial devices and an example of Early After Depolarization (EAD) is presented. Then, by processing real signals obtained for four different compounds, our algorithm was able to provide dose-response curves for potassium, sodium and calcium channels. For ivabradine and moxifloxacin, the IC50 and dose-response curves are in very good agreement with known values. Significance: The proposed strategy offers a possible answer to a major question raised by the community of safety pharmacology. By allowing a more automated analysis of the signals, our approach could contribute to promote the technology based on MEA and hiPSC-CMs, and therefore improve reliability and efficiency of drug screening.