ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?

Mostapha Benhenda (1)

1 LAGA - Laboratoire Analyse, Géométrie et Applications

Generating molecules with desired chemical properties is important for drug discovery. The use of generative neural networks is promising for this task. However, from visual inspection, it often appears that generated samples lack diversity. In this paper, we quantify this internal chemical diversity, and we raise the following challenge: can a nontrivial AI model reproduce natural chemical diversity for desired molecules? To illustrate this question, we consider two generative models: a Reinforcement Learning model and the recently introduced ORGAN. Both fail at this challenge. We hope this challenge will stimulate research in this direction.

Mots clés: Neural networks; Chemoinformatics; organic chemistry; drug discovery; machine learning

Domaines: Autres [stat.ML]; Apprentissage [cs.LG]; Intelligence artificielle [cs.AI]

Mostapha Benhenda. ChemGAN challenge for drug discovery: can AI reproduce natural chemical diversity?. 2017. ⟨hal-01577696v3⟩