These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
Molecular_generation_from_images_ChemRXiv _v1.pdf (470.76 kB)

Cell Morphology-Guided De Novo Hit Design by Conditioning Generative Adversarial Networks on Phenotypic Image Features

submitted on 13.01.2020, 20:18 and posted on 17.01.2020, 16:52 by Oscar Méndez-Lucio, Paula Andrea Marin Zapata, Joerg Wichard, David Rouquié, Djork-Arné Clevert
Developing new small molecules that are bioactive is time-consuming, costly and rarely successful. As a mitigation strategy, we apply, for the first time, generative adversarial networks to de novo design of small molecules using a phenotype-based drug discovery approach. We trained our model on a set of 30,000 compounds and their respective morphological profiles extracted from high content images; no target information was used to train the model. Using this approach, we were able to automatically design agonist-like compounds of different molecular targets.


Email Address of Submitting Author


Bayer CropScience



ORCID For Submitting Author


Declaration of Conflict of Interest

All authors are or were employees of Bayer AG or Bayer SAS